Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

This paper presents an Internet of Things (IoT)-based concept called "IoT Nudge", which aims to induce continuous healthful behavior changes through interactions between human users and IoT devices, including smart sensors and actuators. More specifically, IoT Nudge systems aim to establish self-reflection loops in which our daily behaviors are reflected in the IoT devices around us. The changes in the presentations of those IoT devices promote self-Awareness and provide us with opportunities to improve our lifestyle habits. To reconfigure poor behavior into good behavior, the IoT Nudge provides three functions: (1) automatic tracking of a user's lifestyle habits using IoT sensors, (2) playfully reframing the user's daily activities into other more healthful representations based on analogies, and (3) delivering real-Time ambient feedback through reframed representations from IoT actuators that encourage self-reflection. Herein, we describe our conceptual model of IoT Nudge and introduce three prototype systems aimed at promoting health improvements: fit2plant, eat2pic, and brush2music.

DOI： 10.1145/3460418.3479280

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.3390/s19204600

Scopus

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.3390/s18113978

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

Engaging in discussions that involve diverse perspectives and exchanging arguments on a controversial issue is a natural way for humans to form opinions. In this process, the way arguments are presented plays a crucial role in determining how engaged users are, whether the interaction takes place solely among humans or within human-agent teams. This is of great importance as user engagement plays a crucial role in determining the success or failure of cooperative argumentative discussions. One main goal is to maintain the user's motivation to participate in a reflective opinion-building process, even when addressing contradicting viewpoints. This work investigates how non-verbal agent behavior, specifically co-speech gestures, influences the user's engagement and interest during an ongoing argumentative interaction. The results of a laboratory study conducted with 56 participants demonstrate that the agent's co-speech gestures have a substantial impact on user engagement and interest and the overall perception of the system. Therefore, this research offers valuable insights for the design of future cooperative argumentative virtual agents.

DOI： 10.1145/3687272.3688315

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

少子高齢化とともに，家族構成の変化や新型コロナウイルスの影響により，高齢者の外出頻度が減少し，社会的な孤立やフレイルの信号が深刻な問題となっている．本研究では，高齢者の外出と社会的交流を促進するために，Bluetooth Low Energy (BLE)信号を活用した行動変容システムを開発した．システムは，周辺施設からのBLE信号を記録するタグと，情報を視覚的に掲示するデジタルサイネージを組み合わせており，これにより高齢者の外出活動を可視化・共有することを目指している．本デモセッションではシステムの設計および実装の概要を紹介し，実際にタグを用いて収集した外出情報を可視化する．

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

In the digital age, prolonged computer use often leads to digital eye strain, negatively impacting productivityand Quality of Life (QoL). This paper introduces EyeWise, a system that leverages nudge theory to encourageregular blinking. Unlike previous solutions, EyeWise provides customizable reminder intervals and employs subtleprompts to guide user behavior. Preliminary testing demonstrated high usability (SUS score: 78.86) and positive userengagement. However, no statistically significant difference in blink rates was found compared to the baseline systemwithout nudges (p > 0.05). While EyeWise may influence blinking patterns in some users, it did not consistentlyimprove blink rates for all participants.

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

災害発生時，避難所への効率的な支援物資供給やボランティア派遣は，被災者支援において極めて重要となる．しかし，既存の支援体制では電話，FAX，インターネットといった通信インフラに依存しており，災害時のインフラ途絶により機能不全に陥る可能性が高い．そのため，本研究では避難所などの人が集まる場所にエッジサーバを設置し，インターネットに接続されていないエッジサーバ間におけるデータ交換を実現するための，Web ブラウザの一時ストレージを活用した DTN（Delay Tolerant Networking）の構築法を提案する.本提案手法は，インターネット接続が断絶された状況下でも，自治体職員，社会福祉協議会職員，防災士，災害ボランティア，一般市民といった人の移動をデータフェリーとして活用することで，低コストかつ距離に依存しない情報伝達を実現する．また，エッジサーバ上に既存の災害支援システムである「未来共生災害救援マップ」を導入することで，避難所内外における円滑な情報共有を可能にする．本稿では，通信断絶時でも利用可能な情報流通システムを提案するとともに，実際の災害現場で利用するための具体的なシステムの実装方法について述べる．

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MYU K.K.  

Disaster preparedness guidelines help citizens protect themselves against disasters. Nonetheless, the general public has been found not to read them. Augmented reality (AR) interfaces are known to improve knowledge transfer in studies of education, industry, and elderly assistance. However, this is achieved this by creating specific interfaces for users, not the general public. To test the performance of these interfaces for general public guidance, we designed and implemented a novel AR-assisted disaster prevention guideline that leverages object detection models to identify targets of disaster preparedness advice. We then had a diverse-age audience compare our design against a real traditional paper-based preparedness guide in a room arranged as a common remote work bedroom. By testing their usability, task load, and capacity to make users aware of their environmental hazards, we gained important insights into the performance of different age groups following media developed for the general public. Regardless of different age groups achieving similar usability scores, we found minors improving their performance scores with our novel interface and adults from 20 to 49 years old seemingly performing better than other age groups. In this study, we highlight the importance of guidance alternatives for the young and the less-technology-aware population, contributing to the under-explored area of AR interfaces for the general public.

DOI： 10.18494/sam5215

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

近年，各テレビ放送局において，個人を特定しない形式で，インターネット接続されたテレビから視聴開始時刻や視聴終了時刻等を含む非特定視聴履歴データを収集し，利活用する取り組みが進められている．しかし，各放送局は自局の非特定視聴履歴データしか利用できないため，膨大なデータを蓄積しているにもかかわらず，有用な知見を得るまでに至っていないのが現状である．さらに，非特定視聴履歴データの収集方式やデータ粒度は，各局各様となっており，各局が蓄積したデータを統合し，利用することもできていない．そこで本論文では，各局が独自の方式で取得している非特定視聴履歴データを放送局間で統合する手法を提案し，評価するためのシミュレータ設計と実装を行い，提案手法の評価を行う．提案手法では，各局の視聴履歴データのうち，共通しているIPアドレス・郵便番号・メーカID・ブラウザメジャーバージョン・ブラウザマイナーバージョンの5項目でテレビ受像機を分離処理する．そして，分離された中でこれらの5項目が一致するテレビのうち，さらにチャンネル遷移時刻が一致するテレビを同一テレビと推定する．また，視聴者行動を再現するシミュレータを設計し，そのシミュレータから合成された視聴履歴データに対して，本手法を適用した結果，生成された250万台分のデータのうち約241万台のテレビIDのマッチングに成功し，再現率96.5%であることを示した．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (other academic)  

researchmap

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (other academic)   Publisher：arXiv  

Making the interaction with embodied conversational agents accessible in a ubiquitous and natural manner is not only a question of the underlying software but also brings challenges in terms of the technical system that is used to display them. To this end, we present our spatial augmented reality system ARCADE, which can be utilized like a conventional monitor for displaying virtual agents as well as additional content. With its optical-see-through display, ARCADE creates the illusion of the agent being in the room similarly to a human. The applicability of our system is demonstrated in two different dialogue scenarios, which are included in the video accompanying this paper at https://youtu.be/9nH4c4Q-ooE

DOI： 10.48550/arXiv.2408.06222

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

In their process of information seeking, human users tend to selectively ignore information that contradicts their pre-existing beliefs or opinions. These so-called “self-imposed filter bubbles” (SFBs) pose a significant challenge for argumentative conversational agents aiming to facilitate critical, unbiased opinion formation on controversial topics. With the ultimate goal of developing a system that helps users break their self-imposed filter bubbles (SFBs), this paper aims to investigate the role of co-speech gestures, specifically examining how these gestures significantly contribute to achieving this objective. This paper extends current research by examining methods to engage users in cooperative discussions with a virtual human-like agent, encouraging a deep reflection on arguments to disrupt SFBs. Specifically, we investigate the agent’s non-verbal behavior in the form of co-speech gestures. We analyze whether co-speech gestures, depending on the conveyed information, enhance motivation, and thus conversational user engagement, thereby encouraging users to consider information that could potentially disrupt their SFBs. The findings of a laboratory study with 56 participants highlight the importance of non-verbal agent behaviors, such as co-speech gestures, in improving users’ perceptions of the interaction and the conveyed content. This effect is particularly notable when the content aims to challenge the user’s SFB. Therefore, this research offers valuable insights into enhancing user engagement in the design of multimodal interactions with future cooperative argumentative virtual agents.

DOI： 10.3390/mti8080071

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Enabling federated learning in opportunistic networks unlocks the potential for machine learning in challenging environments like disaster zones and remote regions. However, the divergent models induced by dynamic node encounters, combined with complete parameter overlap in model-homogeneous training lead to catastrophic interference, which disrupts training progress. Furthermore, when whole models must be transmitted, nodes with shorter contact duration are limited from participating in the training process. To address these challenges, we propose a different approach for training neural networks in opportunistic settings that leverages independent subnetworks and sequential training. We partition the original neural network into non-overlapping subnetworks and assign each to a unique node. These subnetworks are then trained and exchanged repeatedly during node encounters, exposing them further to diverse datasets. As a consequence, we achieve parallel and conflict-free progress while minimizing participation costs. Our experiments demonstrate that continuous training and subnetwork accumulation foster the development of a more robust model. Moreover, by utilizing pre-trained backbones as feature extractors, we achieve a test accuracy of 75.06% on MEDIC’s disaster damage severity assessment task, demonstrating that the approach can be adopted in resource-constrained and dynamic scenarios in the real world.

DOI： 10.1109/smartcomp61445.2024.00044

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Numerical calculations using an abacus (also known as Soroban) require understanding numerical representations through beads, and the manipulation of beads in multiple methods and sequences necessitates long-term repetitive learning to master. Traditional abacus instruction involves checking the correctness of answers and observing learners to identify and address mistakes or difficulties in bead manipulation. However, this depends heavily on human resources and requires considerable effort. Therefore, this study proposes a learning support system for abacus learning using a commercially available abacus and a table-top interface to provide coaching content based on real-time estimation of the abacus input values using a document camera.

DOI： 10.1109/smartcomp61445.2024.00056

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Mental health has a huge impact on humans, affecting both psychological and physical well-being. Excessive stress can lead to depression, reduced productivity, and even suicidal tendencies. Stress also impacts appetite and sleep quality, potentially leading to other health issues. However, stress accumulation often goes unnoticed until it severely impacts health, highlighting the need for daily stress level assessment. This study aims to estimate daily distress levels through natural conversations with a smart speaker. We utilize the audio-visual data of users interacting with a smart speaker on a daily basis, extract features from different modalities through analysis, and predict distress changes in daily life using questionnaire responses as labels. In the experiment, participants interacted with a smart speaker placed in their bedrooms, simulating daily life. Webcam recordings captured facial expressions, voice, and heart rate data, which were preprocessed for analysis. Predictions for happiness, depression, and anxiety levels were made using data from questionnaires filled out after each recording session, with scores ranging from 0 to 18. Results from the 14-day experiment with seven participants, aged 22 to 24, revealed MAEs of 2.04, 2.59, and 2.31 for happiness, depression, and anxiety levels, respectively. The corresponding RMSEs were 2.63, 3.20, and 2.91.

DOI： 10.1109/smartcomp61445.2024.00080

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Regulating human flow is essential to reducing congestion in areas where people gather. A digital twin that realistically simulates human flow helps for this purpose. To realize a realistic human flow simulation mechanism, it is essential to take into account people’s attributes. However, existing simulation methods use only location-specific information to predict people’s behavior, thus do not reflect the routines that appear in people’s actual lives. In this paper, we propose a human flow simulation using synthetic population data that help extract the attributes of people living in a target area. In the proposed method, we simulate the movement of people with each attribute like office workers, students, etc. every 15 minutes using the synthetic population data and the hourly transition probability matrix between PoIs (Points of Interest) by computing the transition probability matrix from hourly PoI-level congestion (people count) in the target area using people trajectory data included in the point-type fluid population data commercially available and applying a Markov chain to the congestion. The proposed simulation mechanism is based on the data assimilation of the actual PoI congestion vector (how many people were staying in each PoI) obtained from the point-type fluid population data and the virtual PoI congestion vector generated from the prediction of people’s movement using the attribute information in the synthetic population data at regular time intervals. The data are assimilated at regular intervals to obtain highly accurate PoI-level congestion forecasts. The results of the mobility simulation for office workers showed that the maximum cosine similarity with the actual PoI congestion was 0.96 after 12 hours even when the actual PoI congestion vector is known only for a part of the area (one mesh).

DOI： 10.1109/smartcomp61445.2024.00027

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

To achieve smart cities, leveraging data from cameras, which are often readily-installed IoT devices, can offer precious insights on the behavior of pedestrians and play a crucial role in designing and maintaining efficient transportation, appropriate infrastructure, or attractive tourism facilities. Such pedestrian flow data collection is often achieved through crosscamera person re-identification. This task is heavily privacyinvasive task by design, benefiting from rich visual data, which thus carries highly sensitive personal details about individuals. We here study how image data can be protected upfront, and introduce a novel image differential privacy mechanism leveraging both pixelization and color quantization for this purpose. Our extensive experiments show that through its random noise additions, our mechanism can obfuscate data more effectively than standard image obfuscation methods while retaining high utility for cross-camera re-identification, preserving reasonable re-identification metrics and demographic information even under low privacy budgets.

DOI： 10.1109/smartcomp61445.2024.00086

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Predicting crowd flow is crucial for decision-making to mitigate various risks. For instance, in social problems such as traffic congestion and over-tourism, countermeasures can be taken by predicting crowd flows in advance. Typically, people visit multiple Points of Interest (PoI) for various purposes. Previous work has proposed methods to incorporate the behavioral characteristics of people in different areas, such as dining areas or office areas, into machine learning models. However, they have not considered the specific behavioral characteristics associated with each PoI, such as when restaurants or train stations experience peak periods. Recently, there has been an increase in the ability to handle large amounts of location information, leading to a growth in the volume of individual trace data. In this study, we propose a crowd flow prediction method that aggregates large-scale individual trace data of movements between PoIs and considers the behavioral characteristics associated with each PoI. We define this information as time series PoI stay counts generated from trace data collected from mobile phones. Using this, we developed a machine learning model to predict the number of people in an area (mesh) over the next several minutes to hours. This prediction is based on the number of people staying at each PoI (category) in neighboring areas (meshes). We applied this approach to densely populated areas in central Tokyo, where congestion is a significant concern, and conducted validation. The results showed that the method utilizing time series PoI stay counts improved prediction accuracy by up to 50% compared to methods that did not use it. Additionally, the Mean Absolute Percentage Error (MAPE) for predicting the number of people staying 1 hour later was only 2.57%.

DOI： 10.1109/smartcomp61445.2024.00066

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

ゴミのポイ捨ては野生動物の殺傷に繋がるなど深刻な環境問題に発展している．ポイ捨てを防止する策を講じるために必要な，ポイ捨てゴミの実態やゴミ拾い活動の実績は情報として整理されていない．我々は，カメラ装着型トングを用いて，ゴミを拾うだけで，ゴミの種別・位置情報を網羅的に収集するシステムを提案してきた．しかし，現在のシステムは画像認識モデルのため，学習データに含まれていないゴミが拾われた際に，誤認識が不可避である．この問題を解決するため本稿では，未知のゴミをその他として識別する手法を列挙し，比較検討する．実験結果より，多クラス分類モデルを用いることで，F値77%の精度を達成した．

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

DOI： 10.1109/access.2024.3401392

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

インバウンド観光客の復活に伴い，日本各地で混雑が問題となっている．混雑を解消するためには，人流の最適化が必要であり，人流をリアルにシミュレーション可能なデジタルツインが求められている．本稿では，未来の人流予測に焦点を当て，混雑度センシングと，地域ごとの事情や社会的情勢を考慮可能な人流シミュレーションを組み合わせることで，未来の混雑度の予測および人流のデジタルツインの構築を目指す．より確度の高い人流シミュレーション機構の構築のためには，人々の行動を予測する際に，人の属性情報を考慮することが有効である．しかし，既存のシミュレーションでは，場所に特化した情報から，属性を考慮せずに人の行動を予測しているため，人々の実際の生活に現れるルーティンが反映されていない．この問題を解決するために，その地に住む人々の属性情報を取得可能な合成人口データを用いた人流シミュレーションを提案する．提案手法では，株式会社 Agoop によって提供されている「ポイント型流動人口データ」を用いて求めた時間ごとの PoI 間の遷移確率行列と合成人口データを用い，15 分ごとの移動のシミュレーションを行った．PoI 間の遷移確率行列は，ポイント型流動人口データに含まれるユーザの軌跡データなどを基に，対象地域の全 PoI における，時間ごとの混雑度を算出し，混雑度にマルコフ連鎖を適用することによって求めた．対象地域の合成人口データをもとに会社員・学生・主婦といった属性を定義し，それぞれの移動特性に応じた遷移確率を用いて移動予測を行った．社会人を対象に移動シミュレーションを行った結果，実際の PoI 混雑度とのコサイン類似度は，12 時間後に最大 0.961 となった．

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

Geoparsing is a fundamental technique for analyzing geo-entity information in text, which is useful for geographic applications, e.g., tourist spot recommendation. We focus on document-level geoparsing that considers geographic relatedness among geo-entity mentions and present a Japanese travelogue dataset designed for training and evaluating document-level geoparsing systems. Our dataset comprises 200 travelogue documents with rich geo-entity information: 12,171 mentions, 6,339 coreference clusters, and 2,551 geo-entities linked to geo-database entries.

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：人工知能学会  

バス車内の混雑度や乗降の多い停留所をを把握することは，交通システムの効率化と乗客の快適性の向上に不可欠である．バスの混雑度を推定する既存手法として，乗客の所持する電子機器が発信するBLE信号情報を用いた手法が提案されている．このアプローチでは，乗客のプライバシー保護と導入コスト削減を実現しているが，主に車内人数の推定のみに焦点が当てられている．しかし，交通システムの最適化には，各停留所での乗降者数の情報を把握することも重要である．本研究では，BLE信号情報を利用して，乗客の乗降を表す特徴量を作成し，機械学習モデルを用いて乗降者数推定を行う手法を提案する．本研究の有効性を検証するため，奈良交通株式会社の協力のもと，実際に運行する路線バスにおいてデータ収集実験を行い，機械学習モデルを構築してバス乗客の乗降者数推定を行った結果，平均絶対誤差1.142（乗者数），1.290（降車数）の精度で推定できることを示した．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

エネルギーハーベスティング技術を活用したデバイスは，持続可能なIoTの未来に向けて大きな可能性を秘めている．最近では，日常生活で利用可能な様々な嗅覚インターフェースが開発されており，これらは私たちの生活に新たな次元をもたらす．我々の研究グループでは，飲料の甘さを香りで増幅させることで糖分摂取量を低減させる「Kaolid」という蓋型嗅覚インターフェースを開発した．このインターフェースは，口中香によって香り情報を提示し，味の満足度や甘さを大幅に増幅させる機能を持っている．しかし，これまでの「Kaolid」はバッテリーを電力源として使用しており，日常的な使用には定期的な充電が必要であった．そこで，本論文ではエネルギーハーベスティング技術を応用した充電不要な嗅覚インターフェースを提案する．この新しい設計では，デバイスを利用しない時間に太陽光を活用して必要な電力を蓄えることができる．これにより，システムの利便性が拡張され，日常的な使用がより容易になる．本研究では，異なるコンテキストで利用可能な充電不要な嗅覚インターフェースの開発において重要な一歩を踏み出すものである．

researchmap

Other Link： http://id.nii.ac.jp/1001/00232744/

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

データのアノテーション作業をクラウドソーシングで行うことで，低コストで機械学習のための学習データを収集できる．しかし，コストと引き換えに得られるデータの品質に大きなばらつきがあり，特に対価として報酬を付与すると可能な限り速く回答を行おうとする行動により不良回答が発生する問題がある．そこで，本研究では固有表現アノテーションを対象として不良回答をリアルタイムで検出することを目的とし，作業中の画面操作から得られるカーソル移動量や操作時間などの特徴量を用いた検出手法を提案する．本稿では，クラウドワーカーを対象に検証実験を行うとともに，分類精度の改善を目的に個人差を反映できる特徴量を追加する．機械学習モデルによる分類では，学内学生とクラウドワーカーのデータ両方を用いたデータセットにおいて0.747のAccuracyが得られ，ラベル付与数に関する特徴量が分類において重要であることが分かった．

researchmap

Other Link： http://id.nii.ac.jp/1001/00232748/

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：社会情報学会  

算盤学習者が珠算能力を向上させるためには，学習者の苦手操作や計算ミスを見つけ出し，指導することが必要である．しかしながら，この方法には指導者という人手が必要である．この現状から，学習者の操作をセンシングし，個々の状況に応じた学習支援を提供することで，算盤学習の効率を向上させることが可能だと考えた．著者らはこれまでに，市販の算盤にARマーカを枠に貼り付け書画カメラによって撮影した俯瞰映像を分析することで，算盤の盤面を認識し，認識結果に基づき珠算学習支援に必要な情報をリアルタイムに卓上ディスプレイ上へと提示する手法を提案している．また，珠算学習にゲーム要素を取り入れ，楽しみながら繰り返し学習できるような仕組みを実現することで，苦手操作を効果的に克服するための珠算学習支援システムも提案している．しかしながら，苦手操作の検出および苦手克服のための問題生成に関する具体的な手法については提案されていない．本研究では，珠算学習者の苦手操作を検出する珠算学習支援手法の確立を目指している．本稿では，著者らがこれまでに提案してきたシステムを使用することを前提とする．算盤の盤面の認識結果とディスプレイに表示された計算問題の正誤判定を行い，誤答と判定した場合に認識結果の値と出題された計算問題の正解の値の差分を算出し，差分結果から学習者の苦手操作を検出する手法を提案する．

researchmap

Authorship：Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：社会情報学会  

美術館は美術作品を鑑賞する場として人々に親しまれている．鑑賞者の理解を助けるために，学芸員・ミュージアムエデュケータによる作品ガイダンスも行われている．しかしながら，人手によるガイダンスにおいて，人的資源の限界は避けられない課題である．これに対しICTを活用した音声ガイダンスなどが海外を中心に取り入れられているものの，一方的にガイダンス内容が読み上げられるものが多く，鑑賞者が興味や関心に合わせて作品を鑑賞することが難しいという課題がある．そこで本研究では，鑑賞者の心理状態を推定することによって，鑑賞者の興味や関心に合わせたナビゲーションの提供や，鑑賞体験の向上につなげることができると考えた．本稿では，鑑賞者の心理状態推定手法の構築に向けて，美術館で開催された2つの展示会において展示作品計28点・被験者62名による，ガイダンスシステムを用いた作品鑑賞時における鑑賞者の心理状態のマルチモーダルデータセットを構築した結果について報告する．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：人工知能学会  

災害時には避難所への支援物資の供給やボランティア派遣などを行うために，各機関との連携が不可欠である．連携には電話やFAX，インターネットを利用した通信が一般的だが，災害時には建物の倒壊や停電の影響で通信が断絶する可能性が高い．そのため，本研究では避難所などの人が集まる場所にエッジサーバを設置し，インターネットに接続されていないエッジサーバ間におけるデータ交換を実現するための，Webブラウザの一時ストレージを活用したDTN（Delay Tolerant Networking）の構築法を提案する.本提案手法では，災害時にネットワーク接続が切断された状況下でも，避難所間を移動する自治体職員，社会福祉協議会職員，防災士，災害ボランティアおよび一般市民をデータフェリーとして活用することで，低コストで距離に依存しない通信を実現する．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：日本ソフトウェア科学会  

Over 60% of municipalities implementing measures against vacant houses are facing challenges due to a shortage of personnel and a lack of specialized knowledge for current situation assessment. The Ministry of Internal Affairs and Communications, along with municipalities, has been working on identifying vacant houses by soliciting responses from residents through surveys; however, the low response rate has been a problem. Therefore, this study developed an SNS platform that allows local residents to actively post about land use situations, constructing and operating a system where regional circumstances can be communicated. This paper reports the insights gained from the data collected through the developed system.

researchmap

Authorship：Last author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：日本ソフトウェア科学会  

In contemporary society, a wide range of entertainment has become prevalent, leading to an increasing complexity in viewers' preferences and tendencies. This research proposes a method for clustering television viewers based on different viewing tendencies, utilizing non-specific television viewing data collected from five local television stations. The aim is to grasp individual viewing tendencies, enabling more effective and targeted approaches in areas such as program production, timing for commercial broadcasts, and business utilization. The goal is to enhance understanding and facilitate more tailored strategies in these aspects.

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：日本ソフトウェア科学会  

In recent years, there has been an increasing trend in damage to crops and harm to humans caused by nuisance wildlife. Therefore, we propose a system that utilizes participatory sensing to collect trace information and estimate the habitats of nuisance wildlife based on this data. In this system, the discovery points of nuisance wildlife traces and geographic information are used to appropriately estimate the habitats of these animals, with the aim of supporting more efficient pest control and preventive measures. In particular, this study proposes specific trace collection methods and suggests trace species believed to be effective based on insights obtained through demonstration experiments in the mountainous areas of Fukui Prefecture.

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：人工知能学会  

釣りは人気のレジャースポーツであり，その技術は釣果に大きく影響を与える．しかし，釣りの技術はユーザの経験に左右され，評価が難しいという課題がある．そこで，釣りの技術を定量的に評価することで，技術のマニュアル化やユーザに合わせたアドバイスが可能になると考えられる．本研究では，釣竿を振って仕掛けを飛ばすキャスト動作に着目し，リールと呼ばれる釣具に装着したセンサから得られるデータを利用して，キャストの分類モデルの構築および評価を行った．被験者6名からキャスト動作のデータを収集してデータセットを作成し，LightGBMを用いて分類モデルを構築した．分類モデルの評価のため， Leave-One-Session-Out 交差検証および Leave-One-Person-Out 交差検証を利用した．検証の結果，Leave-One-Session-Out交差検証において正解率98.1%，F値98.1% の精度を，Leave-One-Person-Out交差検証においては正解率86.9%，F値87.3%の精度を確認した．また，ユーザが予め自身のキャスト動作のデータを登録した上で，分類モデルを学習および運用することを想定し， Leave-One-Person-Out交差検証において検証用となるユーザのデータの一部を学習用データに追加して，分類モデルを一から学習して検証を行った．その結果，最大で正解率96.1%，F値96.1%の精度を確認した．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：人工知能学会  

ウォーキングは健康維持に有効である上に認知症などにつながるフレイルの発症を予防できる手段として注目されている．高齢者の安全なウォーキングのために様々な見守りサービスが提供されている．その多くはスマートフォンの所持を前提としているが，高齢者の中には，スマートフォンの利用に消極的な人が一定数存在する．また，ウォーキングの際の持ち物は少ない方が望ましい．我々は，高齢者が小型のデバイスのみを持ち歩くだけで，位置やすれ違った相手を判別し，それをデジタルサイネージにより可視化するシステムを提案している．このシステムの実現には，省電力で小型のデバイスのみで，高齢者の位置を推定する必要がある．そこで我々は，省電力であるBLE（Bluetooth Low Energy）に着目し，周辺施設などから発せられているBLE信号のみをスキャンすることで，そのBLE信号のアドレスと受信強度（RSSI）の組み合わせパターンから，高齢者の位置を推定する屋外位置推定手法を提案する．事前実験の結果，施設や住宅の数によって推定精度に違いはあるものの，大まかな位置推定は可能であるということを明らかにしている．

researchmap

Language：Japanese  

エネルギーハーベスティング技術を活用したデバイスは，持続可能なIoTの未来に向けて大きな可能性を秘めている．最近では，日常生活で利用可能な様々な嗅覚インターフェースが開発されており，これらは私たちの生活に新たな次元をもたらす．我々の研究グループでは，飲料の甘さを香りで増幅させることで糖分摂取量を低減させる「Kaolid」という蓋型嗅覚インターフェースを開発した．このインターフェースは，口中香によって香り情報を提示し，味の満足度や甘さを大幅に増幅させる機能を持っている．しかし，これまでの「Kaolid」はバッテリーを電力源として使用しており，日常的な使用には定期的な充電が必要であった．そこで，本論文ではエネルギーハーベスティング技術を応用した充電不要な嗅覚インターフェースを提案する．この新しい設計では，デバイスを利用しない時間に太陽光を活用して必要な電力を蓄えることができる．これにより，システムの利便性が拡張され，日常的な使用がより容易になる．本研究では，異なるコンテキストで利用可能な充電不要な嗅覚インターフェースの開発において重要な一歩を踏み出すものである．

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In urban planning and optimization of commercial facilities, pedestrian flow analysis is essential. Currently, camera- based pedestrian flow analysis methods are widely adopted, but this solutions suffers of high costs and privacy concerns. As a new approach to address these problems, numerous methods utilizing BLE (Bluetooth Low Energy) and Wi-Fi have been proposed. However, many previous studies have focused on the congestion level of spaces, with insufficient attention given to analyzing the direction of movement. In this study, we propose a pedestrian flow estimation method that considers movement direction (upward, downward) using two BLE sensors. In our proposed method, time-series data obtained from the two sensors is used to create differences between the data and perform clustering. The number of BLE addresses belonging to each cluster serve as features for estimating pedestrian flow. To evaluate the effectiveness of this method, experiments were conducted on streets in Osaka Prefecture, Japan. For one sample of the collected data (5 minutes), the average pedestrian flow was 75.5 people moving upward, 81.8 people moving downward, with a total flow of 157.2 people. Evaluating the proposed method in 5-minute increments showed that using the DTW metric for clustering, the upward, downward, and overall pedestrian flow could be estimated with an average absolute error of 18.6, 16.0, and 21.9, respectively.

DOI： 10.1109/PerComWorkshops59983.2024.10503219

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In recent years, aiming to support residents’ daily lives and activities, research and development activities on indoor activity recognition have become increasingly active. However, existing methods of activity recognition still have challenges in- cluding (i) concerns about privacy infringement, (ii) the necessity of wearing sensors constantly, (iii) the need for regular battery charging, and (iv) the difficulty in recognizing certain activities. Additionally, the methods primarily focused on macro activities like cooking and cleaning. Still, it is believed that a more accurate application to life support requires recognition of more detailed activities known as micro activities, such as handling ingredients in cooking or cutting. In this paper, we propose a method for micro activity recognition using 3D point clouds as a solution to these issues. 3D point clouds represent objects as sets of 3D coordinates and are expected to offer lower privacy risks and higher accuracy compared to video images. The challenges to be addressed in the proposed method include defining the micro activities of interest and recognizing them from 3D point clouds. In the proposed method, micro activities are defined as single actions like ''cutting,'' ''holding,'' or ''placing'' that occur in cooking activities in typical households. We then apply a deep learning model called P4Transformer, which can classify time-series 3D point cloud input data obtained from multiple Azure Kinect devices installed in typical households, allowing for occlusion-tolerant micro activity recognition. We have collected a time-series 3D point cloud data for more than 40 sessions of cooking activities in five typical households, then evaluated the accuracy of the micro activity recognition model using Leave- One-Session-Out cross-validation. The results showed that the proposed method achieves an average recognition accuracy of 74.3%.

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Annotation tasks can be conducted through crowd- sourcing to gather training data for machine learning at a reduced cost. However, the quality of the data collected can vary significantly, with an issue of careless responses from workers who may rush through tasks to maximize their earnings. This study proposes a real-time method to detect such careless re- sponses during annotation tasks. This method leverages features like cursor movement and response times, captured from screen interactions during the task. In this paper, we evaluate the accuracy of the careless response estimation model that employs a machine learning approach and explore the significant features contributing to it. Through an experiment with 61 participants, we confirmed that a proposed method has shown performance with an accuracy of 0.738. We also found that the number of labels used, the average cursor movement, and the number of clicks per label assignment, are crucial features for this classification.

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：電子情報通信学会  

食後高血糖予防のためには，食事をはじめとした環境素因に対する継続的な自己管理が必要不可欠である．これまで，著者らはリアルタイムに血糖値を把握しながら，摂取予定の食事から食後高血糖を事前に予測し，摂取量を減らすべき食品を算出し，その結果をユーザへ提示する食事行動変容フレームワークを提案してきた．しかし，食後高血糖を予防するために，各食品の推薦摂取量の算出において，どのような算出方式を適用したら，食事の満足度を保ちながら血糖値を抑制できるのかが明らかになっていない．提案フレームワークを実現するためには，各食品の推薦摂取量の算出方式や，実際に推薦摂取量を適用した食事の満足度を評価する必要がある．そこで本研究では，複数の推薦摂取量算出方式を設定し，それぞれについて満足度評価実験を行った．実験では，クラウドソーシングを用いて，推薦摂取量を適用する前後の食事画像を提示し，満足度を回答するタスクを実施した．実験の結果，品目数や摂取量を優先した算出方式を好むユーザにおいて，その算出方式を適用した食事の満足度が他の算出方式と比較して最も高くなった．また，食事の摂取量が満足度を構成する要素として重要であるという知見を得た．

researchmap

Other Link： https://ken.ieice.org/ken/paper/20240229AcCy/

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：電子情報通信学会  

近年，新型コロナウイルスの行動制限が緩和され，観光需要は回復傾向を見せている．観光地において観光客はSNSを情報発信としてだけではなく，情報収集として用いる動きが増えており，他者が投稿した情報を参考に観光地において目的地を決める例は少なくない．しかし，これらの位置情報が付与された投稿は既存のデータベースに登録された場所を投稿者が投稿にタグ付けするという形であり，未登録の場所はタグ付けできないという問題や，近年のSNSの傾向としてプライバシー保護のために位置情報が秘匿される傾向にある．観光情報サービスにこれらの投稿を活用するにはPoIの位置を推定する必要がある．本研究ではSNSに投稿された写真・テキストの時系列投稿データに基づくPoI位置推定手法を提案する．本稿では提案する位置推定手法の有効性を調査するための実験とその実験データへの提案手法の適用を行った．富山県立山町にて被験者4名でデータ収集を行い，計285件の画像付き投稿を収集した．提案手法の位置推定手法を用いる重みを変えながら適用したところ，最も誤差が小さいもので正解位置との差が約6.5mとなった．

researchmap

Other Link： https://ken.ieice.org/ken/paper/20240301fcCZ/

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：電子情報通信学会  

Mental health significantly affects people, with excessive stress potentially causing depression, low productivity, and suicidal thoughts. It can also harm physical health, impacting appetite and sleep, and may lead to other diseases. In most cases, individuals do not notice stress buildup until their health severely deteriorates. Thus, daily monitoring of stress levels is essential. In this study, we aim to realize a method to estimate people’s distress levels in everyday life through conversation with a smart speaker. We set up a smart speaker in the bedrooms of participants to simulate a home environment and recorded their interactions with it using a webcam. These recordings allowed us to analyze facial expressions, voice, and heart rate data. We processed these features and predicted levels of Happiness, Depression, and Anxiety. Participants completed questionnaires using the Depression and Anxiety Mood Scale (DAMS) after each session, providing emotion labels with scores from 0 to 18. In a 14-day experiment involving seven participants aged 22-24, the MAE for Happiness, Depression, and Anxiety levels were 2.04, 2.59, and 2.31, respectively, while the RMSE for these distress levels were 2.63, 3.20, and 2.91.

researchmap

Other Link： https://ken.ieice.org/ken/paper/20240229hccA/

Authorship：Lead author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：社会情報システム学研究会  

バスをはじめとする交通機関の情報を正確に推定することは，交通システムの効率化と乗客の快適性の向上に不可欠である．バス車内の情報を推定する既存手法として，乗客の所持するデバイスが発信するBLE信号情報を用いて，車内人数を推定する手法が提案されている． このアプローチでは，主に車内人数の推定のみに焦点を当てているが，同じ車内人数でも乗客が感じる混雑度はそれぞれ異なるため，各停留所間の体感混雑度を推定することは重要である．本研究では，車内人数の推定で効果が確認されているBLE信号情報を利用して，乗客の体感混雑度を推定可能かどうかをを評価する．実験の結果，正解率による評価で0.653（車内人数），0.513（体感混雑度）となり，BLE信号情報で体感混雑度の大まかな傾向を捉えることができるとわかった．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

アノテーション作業をクラウドソーシングで行うことにより，低コストで機械学習のための学習データを収集できる．しかし，得られるデータの品質に大きなばらつきがあり，対価として報酬を付与すると可能な限り速く回答を行おうとする行動によって不良回答が発生する問題がある．そこで，本研究ではアノテーションタスクを対象として不良回答をリアルタイムで検出することを目的とし，作業中の画面操作から得られるカーソル移動量や操作時間などの特徴量を用いた検出手法を提案する．本稿では，適切回答・不良回答の分類を行い，精度を評価するとともに分類において重要な特徴量について分析を行う．機械学習モデルによる分類では，0.738のAccuracyが得られ，ラベル付与数と，ラベル付与毎の平均カーソル移動量・クリック回数が，分類において重要であることが分かった．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

本稿では，食べるという行為を風景画への色塗りタスクへ変換することで，健康的な食習慣を促進する行動変容支援システム「eat2pic」を紹介する.eat2picは，箸型センサと2種類のデジタルキャンバスから構成される.「one-mealeat2pic」という小さなキャンバスは，ユーザの食事の食べ方をリアルタイムで認識し，その良し悪しを色の変化で表現するフィードバックを提供する．「one-weekeat2pic」という大きなキャンバスは，ユーザが1週間で摂取した食品の色の数をカウントし，その色の多様性を反映するフィードバックを提供する.前者は人々がゆっくりと食事をすることを誘引するために，後者は色バランスの良い食事メニューの選択を奨励するために設計されたものである.本発表では，2つのユーザスタディを通じて，eat2picとのインタラクションの経験を探求した結果を紹介する．実験結果は，eat2picが食習慣に対する内省の機会を提供すると共に，食べる速さやバランスに対する意識を高める可能性を示唆するものである．

researchmap

Other Link： https://www.wiss.org/WISS2023Proceedings/data/11.pdf

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

都市計画や商業施設の最適化に際し，人流解析は不可欠である．現在，カメラベースの人流解析手法が広く採用されているが，これに伴う高いコストやプライバシーの問題が浮き彫りになっている．これらの問題を解決する新たなアプローチとして，BLE（Bluetooth Low Energy）を活用した手法が多数提案されている．しかし，多くの先行研究は空間の混雑度に重点を置いており，移動方向の分析は十分に行われていない．本研究では，移動方向を捉えるために２台のBLEセンサを用いた移動方向（上向き，下向き）を考慮した通行量推定手法を提案する．提案手法では，2台のセンサから得られる時系列データを基に，データ間の差分を作成しクラスタリングを行い，各クラスタに所属するBLEアドレス数を特徴量として通行量を推定する．本手法の有効性を評価するため，大阪府の御堂筋で実験を行い，5分単位の通行量の評価を行なった．その結果，クラスタリングを用いた提案手法では，上向き・下向き・全体の通行量に対してそれぞれ平均絶対誤差20.8，16.3，22.9で推定できることを示した．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/BLECE-Street_c_202311_goto_CNWS.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

インバウンド観光客の復活に伴い，日本各地で混雑が問題となっている．混雑を解消するためには，人流の最適化が必要であり，人流をリアルにシミュレーション可能なデジタルツインが求められている．本稿では，人流の最適化の中でも特に，未来の人流予測に焦点を当て，混雑度センシングと，地域ごとの事情や社会的情勢を考慮可能な人流シミュレーションを組み合わせることで，未来の混雑度の予測および人流のデジタルツインの構築を目指す．より確度の高い人流シミュレーション機構の構築のためには，人々の行動を予測する際に，人の属性情報を考慮することが有効である．しかし，既存のシミュレーションでは，場所に特化した情報から，属性を考慮せずに人の行動を予測しているため，人々の実際の生活に現れるルーティンが反映されていない．この問題を解決するために，その地に住む人々の属性情報を取得可能な合成人口データを用いた人流シミュレーションを提案する．提案手法では，株式会社Agoop によって提供されている「ポイント型流動人口データ」を用いて求めた時間ごとのPoI間の遷移確率行列と合成人口データを用い，15分ごとの移動のシミュレーションを行った．PoI間の遷移確率行列は，ポイント型流動人口データに含まれるユーザの軌跡データなどを基に，対象地域の全PoIにおける，時間ごとの混雑度を算出し，混雑度にマルコフ連鎖を適用することによって求めた．対象地域の合成人口データをもとに会社員・学生・主婦といった属性を定義し，それぞれの移動特性に応じた遷移確率を用いて移動予測を行った．社会人を対象に移動シミュレーションを行った結果，実際のPoI混雑度とのコサイン類似度は，6時間後に最大おおよそ0.985となった．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/DigitalTwin_c_202311_sakagami_MBL109.pdf

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

現在の日本では，糖尿病有病者と糖尿病予備軍は2200万人にのぼり，日本人の5人に1人が該当している．食事2時間後の血糖値が下がらない状態である食後高血糖は，II型糖尿病をはじめとする生活習慣病を引き起こす原因となるため，食事をはじめとした環境素因に対する継続的な自己管理が必要不可欠である．著者らはこれまで，摂取予定の食事から食後高血糖を予測し，各食品の推薦摂取量をフィードバックする自己管理システムを提案してきた．しかし，高血糖領域の予測精度が不十分であることや摂食速度や順番といった食べ方の影響が考慮されていないという課題がある．そこで，本稿では，血糖値予測モデルの精度向上と摂食速度・順番の影響の解明に向けたデータ分析を行う．具体的には，精度向上に向けた血糖値予測モデルを構築する実験1と，摂食速度の違いによる血糖値への影響を調査する実験2を行った．実験1では，血糖値に影響があるとされるデータから抽出した特徴量に加え，食事30，60，90分後の予測値を使用した結果，全被験者に対して予測精度が向上した．最も精度の高い被験者でRMSE（二乗平均平方根誤差）が11.26，MAE（平均絶対誤差）が7.98となることを確認した．また，収集したデータおよびモデル精度の分析を行った結果，高GI食品の摂取や身体活動を新たな特徴量として追加することで，更なる予測精度向上の可能性を示した．実験2では，摂食速度と順番を変更して指定した食事を摂取してもらった結果，早い摂食は若年層でも食後高血糖の発生や，一度上昇した血糖値が下がらない傾向を確認した．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/BloodGlucose_c_202310_michiura_DPSWS.pdf

Authorship：Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

算盤の学習において，正確な珠操作を習得することは計算を正しく行う上で必須であるが，珠操作の種類は多様であり，学習過程において「苦手な珠操作」と直面する学習者は少なくない．この苦手な珠操作の克服にには，長期に渡る繰り返し練習を要することが知られているが，苦手な珠操作ばかりを練習することは心理的な負荷が高く，学習者とってストレスとなったり，学習することに対して嫌悪感を抱いてしまったりすることが懸念される．これまでに，市販の算盤にを書画カメラによって撮影した俯瞰映像を分析することで，算盤の盤面を認識する手法，および，珠算学習支援に必要な情報をリアルタイムに卓上ディスプレイ上へと提示する手法が提案されているものの，苦手操作の抽出・問題への反映を考慮したシステムは導入されていない．本研究では，珠算学習にゲーム要素を取り入れ，楽しみながら繰り返し学習ができるような仕組みを実現することで，苦手操作を効果的に克服するための珠算学習支援方法の確立を目指している．本稿では，算盤の盤面認識に基づく算盤の苦手操作の抽出方法および苦手絵操作を克服する問題生成方法について提案するとともに，苦手操作克服を実現するための珠算学習ゲームのシナリオを設計する．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/AbaCaaS_c_202310_taizo_DPSWSdemo.pdf

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

アノテーション作業をクラウドソーシングで行うことにより，低コストで機械学習のための学習データを収集できる．しかし，対価として報酬を付与すると可能な限り速く回答を行おうとする行動が起こり，不良回答が発生する問題がある．そこで，本研究ではアノテーションタスクを対象として不良回答をリアルタイムで検出することを目指し，作業中の画面操作から得られるカーソル移動量や操作時間などの特徴量を用いた検出手法を提案する．本稿では，手法実現のための基礎的な分析として，提案する特徴量と不良回答との関係性を調査した結果，および構築した適切回答・不良回答の分類モデルの評価結果について報告する．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/AnnoTrust_c_202309_fukumitsu_ubi79.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

近年，宅内環境のスマート化に伴い，宅内で生活する人の行動認識に関する研究ならびにシステム開発が盛んに行われている．宅内の生活行動を認識することにより，居住者の生活・行動支援への応用が期待できる．従来の行動認識手法として，動画像を使ったものはプライバシーの侵害が懸念され，ウェアラブルさセンサを使ったものは常に身につける必要性がある上，バッテリーの定期的な充電が必要であり，振動センサを使ったものは，認識できない行動があるといった問題があった．また，従来の行動認識では，料理や入浴といったマクロな行動を対象としており，正確な生活・行動支援への応用には，より詳細な行動であるマイクロ行動（例えば，料理を構成する食材を持つ，切るなど）の認識が必要であると考える．そこで本研究では，これらの問題点を解決する手法として，3 次元点群を用いたマイクロ行動認識手法を提案する．3 次元点群は対象物を 3 次元座標の点の集合で表現したものであり，動画像よりも低プライバシーで高精度な認識が期待される上に，非接触でのセンシングが可能であり，行動の種類に関係ない認識を行うことができると考える．提案手法で解決すべき課題は，対象とするマイクロ行動の定義と 3 次元点群からのマイクロ行動の認識である．本研究では一般家庭の料理行動の中に現れる，“切る” や “持つ”，“置く” といった行動をマイクロ行動として定義する．一般家庭に設置した Azure Kinect によって得られる 3 次元点群に，時系列 3 次元点群を入力データとして分類を行うことが可能な機械学習モデルである P4Transformer を適用することでマイクロ行動認識を行う．実験の結果，Leave-One-Session-Out 交差検証を用いた実験の結果，8 クラスのマイクロ行動を平均 0.743 の精度で分類可能であることが分かった．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/MicroActivity_c_202309_mishima_mbl108.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

近年，地方自治体では自然災害への備えとして，Web ベースの避難所共有サービスである災救マップなどの利用が広がっているが，通信インフラが断絶すると利用できないという問題がある．本研究では，自然災害により通信インフラが断絶された場合でも災救マップの利用を可能とするための，インフラレス避難支援マップの構築を検討する．提案手法では，既存の災救マップのエッジ化を行うことで，避難所内でローカル環境を構築し，通信インフラが断絶しても災救マップの提供を可能とする．さらに，避難所間での情報共有を効率的に行うために，遅延耐性ネットワーク（DTN）の手法を採用する．検証実験では，Raspberry Pi 4 を用いた簡易エッジサーバを構築し，提案手法の実現可能性を確認した．この実験により，通信インフラが断絶した状況でも，避難所間での情報共有が可能であることが示された．今後の展望として，各避難所にエッジ版の災救マップを導入したエッジサーバを設置し，実証実験を進める．さらに，参加型センシングによる街全体の災害情報収集を行うためのシステム検討も行う予定である．

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/DistributedSaikyuMap_c_202309_tsutsui_mbl108.pdf

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/ElderlyBCSS_c_202309_tsuchihashi_ipsjKansai.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/WildAnimal_c_202309_yoshida_ipsjKansai.pdf

Language：English   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/NeedToTalk_c_202309_chouman_ipsjKansai.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：日本建築学会  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/UPoI_c_202309_sawano_ipsjKansai.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/LLMSelfMngmnt_c_202309_suzawa_ipsjKansai.pdf

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

researchmap

Other Link： https://yukimat.jp/data/pdf/paper/SatisficeChat_c_202309_taira_ipsjKansai.pdf

Authorship：Lead author,　Last author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier BV  

Context: Surface electromyography (sEMG) signals contain rich information recorded from muscle movements and therefore reflect the user's intention. sEMG has seen dominant applications in rehabilitation, clinical diagnosis as well as human engineering, etc. However, current feature extraction methods for sEMG signals have been seriously limited by their stochasticity, transiency, and non-stationarity.

Objective: Our objective is to combat the difficulties induced by the aforementioned downsides of sEMG and thereby extract representative features for various downstream movement recognition.

Method: We propose a novel 3-axis view of sEMG features composed of temporal, spatial, and channel-wise summary. We leverage the state-of-the-art architecture Transformer to enforce efficient parallel search and to get rid of limitations imposed by previous work in gesture classification. The transformer model is designed on top of an attention-based module, which allows for the extraction of global contextual relevance among channels and the use of this relevance for sEMG recognition.

Results: We compared the proposed method against existing methods on two Ninapro datasets consisting of data from both healthy people and amputees. Experimental results show the proposed method attains the state-of-the-art (SOTA) accuracy on both datasets. We further show that the proposed method enjoys strong generalization ability: a new SOTA is achieved by pretraining the model on a different dataset followed by fine-tuning it on the target dataset.

DOI： 10.1016/j.ymeth.2023.06.011

researchmap

Language：Japanese   Publishing type：Research paper (international conference proceedings)   Publisher：Springer Nature Switzerland  

DOI： 10.1007/978-3-031-34609-5_17

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

Background: Transthoracic impedance values have not been widely used to measure extravascular pulmonary water content due to accuracy and complexity concerns. Our aim was to develop a foundational model for a novel system aiming to non-invasively estimate the intrathoracic condition of heart failure patients. Methods: We employed multi-frequency bioelectrical impedance analysis to simultaneously measure multiple frequencies, collecting electrical, physical, and hematological data from 63 hospitalized heart failure patients and 82 healthy volunteers. Measurements were taken upon admission and after treatment, and longitudinal analysis was conducted. Results: Using a light gradient boosting machine, and a decision tree-based machine learning method, we developed an intrathoracic estimation model based on electrical measurements and clinical findings. Out of the 286 features collected, the model utilized 16 features. Notably, the developed model demonstrated high accuracy in discriminating patients with pleural effusion, achieving an area under the receiver characteristic curves (AUC) of 0.905 (95% CI: 0.870–0.940, p < 0.0001) in the cross-validation test. The accuracy significantly outperformed the conventional frequency-based method with an AUC of 0.740 (95% CI: 0.688–0.792, and p < 0.0001). Conclusions: Our findings indicate the potential of machine learning and transthoracic impedance measurements for estimating pleural effusion. By incorporating noninvasive and easily obtainable clinical and laboratory findings, this approach offers an effective means of assessing intrathoracic conditions.

DOI： 10.3390/jcdd10070291

researchmap

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

算盤を用いた数値計算は，珠による数値表現の理解，複数の方法・順序での珠操作が求められ，習得には長期に渡る繰り返し学習を要する．一般的な珠算指導は回答の正誤判定に加え，学習者の観察に基づきミスや苦手な珠操作を発見・指導する方法があるが，人手に頼るものとなっており多大な労力が必要となっている．そこで本研究では，市販の算盤を用いる珠算学習を対象とした学習支援システムの実現に向け，書画カメラを用いたリアルタイムな算盤の盤面認識に基づいて指導内容を卓上ディスプレイに提示する手法の確立を目指している．本稿では，珠算学習支援の情報提示を実現するための要件および制約条件を整理するとともに，システム設計を行った結果について報告する．

researchmap

Authorship：Last author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

算盤を用いた数値計算（珠算）は，算盤上の数値の表し方などを理解した上で，正確かつ高速に「珠」を移動させることが求められることから，その能力習得には長期的な繰り返し学習・練習が必要とされる．最も一般的な珠算能力の習得方法である算盤教室における学習では，指導者が学習者に対して実演することで理解を促したり，学習者の珠操作の観察に基づく苦手な操作を発見したりと，誤操作を減らす指導が中心となっており，スムーズに珠操作を行うという観点については重点が置かれていない．そこで本研究では，特に珠操作における「巧緻性」を高めることに着目した算盤学習支援システムを実現することを目指している．本稿では，指導を行うにあたって必要となる算盤学習者の「珠操作」のイベントを取得するために，深度カメラを用いた指の動作の認識手法を提案する．予備実験として，算盤の基本的な操作である「加算」の操作に関するデータセットを作成し，珠操作の認識モデルを構築した．構築したデータセットを用いて提案手法の性能を評価した結果，Leave-one-session-out交差検証では84.4%，Leave-one-person-out交差検証では58.6%の認識精度で算盤の珠操作を認識できることを確認した．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

各地方行政をはじめとした機関による災害対策方針では，家族同士が別々の場所にいる状況に対して，合流する避難所や待ち合わせの場所を予め決めておくことを推奨する場合が多い. しかし，情報技術が発達し，被災者の位置情報の取得，分析がさらに容易になることを考慮すると，より効率的な避難所決定が行える可能性がある. 本研究は，家族世帯の構成員同士が離れている状況を想定し，世帯ごとに対する避難所決定の方針の違いによる避難時間への影響を論じることを目的とする．避難所の決定方法は，「予め定まった避難所を向かう」方針を基にした「自宅基準時間設定」に加え，被災者の分布に応じた「最大避難時間設定」「最小避難時間設定」「平均避難時間設定」の計4つとする. それぞれの設定を評価するために，約30,000人規模の市の避難を想定したマルチエージェントシミュレーションを実施する．結果として，平均避難完了時間は「平均避難時間設定」で約21%減少，全体避難完了時間は「最大避難時間設定」で約22%減少することが確認された. また，世帯を考慮しない避難所決定では，全体避難完了時間は最大避難時間設定と比べ1時間20分以上短いのに対し，複数人の構成員による世帯の合流率は約24%なるという避難時間と世帯合流率のトレードオフの関係が確認された.

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

社会問題に発展しているごみのポイ捨てを未然防止する都市デザイン的アプローチを支援するためには，ごみの種別・位置情報を網羅的に収集することが必要である．その手法として我々は，カメラ搭載型トングを用いて，ごみを拾うだけで，ごみの種別・位置情報を網羅的に収集するシステムを提案してきた．しかし，本研究の利用はイベントのような，利用者がその場限りに集まって使用することを前提としており，ユーザの日常生活中にも本研究を継続的に使用してもらう必要があるが，これを促す仕組みは現在存在しない．この状況を鑑みて，トングでごみを拾うたびに音をフィードバックすることで，ユーザのごみ拾いに対するモチベーションを維持する方法を検討している．本稿では，トングでごみを拾った際に利用するフィードバックの音を複数種類用意し，ユーザがトングを用いてごみ拾いに対するモチベーションが向上させる際に適切な音を明らかにする比較実験を行った．実験の結果，トングでごみを拾った際に，言語フィードバックを行うことで，ユーザのモチベーションが維持しやすくなることが明らかになった．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

安価で高性能なVR（バーチャルリアリティ）装置の登場に伴い，VRゲームやメタバースなどのVRコンテンツが急速に普及しつつある．VR空間では速度や落下といった様々な感覚・刺激を主に視覚情報・聴覚情報としてユーザに提示することができる一方で，人間が知覚する主観的な印象（例えば体感音量）は，ユーザを取り巻くVR空間内の状況によって変化することから，状況に応じた音量調整により，情報提示のクオリティを向上させることが期待される．それに先立って本研究では，視覚刺激が主観的な音量に与える影響を明らかにすることを目指している．本稿では，単純化した視覚刺激として「色」，聴覚刺激として「テストトーン」に焦点を当て，それらをVR空間内で提示する調査実験を行った．結果として，「色」の種類によって体感音量には差が生じることが示され，特に音量が小さくなる場合において寒色系の色について暖色系よりも音量変化が大きく感じられる（音量が小さく感じられる）ことが明らかとなった．

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

Litter has become a social problem. To prevent litter, we consider urban planning, the efficient placement of garbage bins, and interventions with litterers. In order to carry out these actions, we need to comprehensively grasp the types and locations of litter in advance. However, with the existing methods, collecting the types and locations of litter is very costly and has low privacy. In this research, we have proposed the conceptual design to estimate the types and locations of litter using only the sensor data from a smartwatch worn by the user. This system can record the types and locations of litter only when a user raps on the litter and picks it up. Also, we have constructed a sound recognition model to estimate the types of litter by using sound sensor data, and we have carried out experiments. We have confirmed that the model built with other people’s data enabled to estimate the F-measure of 80.2% in a noisy environment through the experiment with 12 participants.

DOI： 10.3390/su151310079

researchmap

Language：English   Publishing type：Research paper (other academic)   Publisher：Cold Spring Harbor Laboratory  

Context: Surface electromyography (sEMG) signals contain rich information recorded from muscle movements and therefore reflect the user’s intention. sEMG has seen dominant applications in reha-bilitation, clinical diagnosis as well as human engineering, etc. However, current feature extraction methods for sEMG signals have been seriously limited by its stochasticity, transiency, non-stationarity.Objective:Our objective is to combat the difficulties induced by the aforementioned downsides of sEMG and thereby extract representative features for various downstream movement recognition.

Method: We propose a novel 3-axis view of sEMG features composed of temporal, spatial, and channel-wise summary. We leverage the state-of-the-art architecture Transformer to enforce efficient parallel search and to get rid of limitations imposed by previous work in gesture classification.

Results: We compared the proposed method against existing methods on two Ninapro datasets consisting of data from both healthy people and amputees. Experimental results show the proposed method attains the state-of-the-art (SOTA) accuracy on both datasets. We further show that the proposed method enjoys strong generalization ability: a new SOTA is achieved by pretraining the model on a different dataset followed by fine-tuning it on the target dataset.

DOI： 10.1101/2023.06.03.543591

researchmap

Language：English   Publishing type：Research paper (other academic)   Publisher：arXiv  

Camera-based person re-identification is a heavily privacy-invading task by design, benefiting from rich visual data to match together person representations across different cameras. This high-dimensional data can then easily be used for other, perhaps less desirable, applications. We here investigate the possibility of protecting such image data against uses outside of the intended re-identification task, and introduce a differential privacy mechanism leveraging both pixelisation and colour quantisation for this purpose. We show its ability to distort images in such a way that adverse task performances are significantly reduced, while retaining high re-identification performances.

DOI： 10.48550/ARXIV.2306.02765

researchmap

Language：English   Publishing type：Research paper (other academic)   Publisher：arXiv  

Geoparsing is a fundamental technique for analyzing geo-entity information in text. We focus on document-level geoparsing, which considers geographic relatedness among geo-entity mentions, and presents a Japanese travelogue dataset designed for evaluating document-level geoparsing systems. Our dataset comprises 200 travelogue documents with rich geo-entity information: 12,171 mentions, 6,339 coreference clusters, and 2,551 geo-entities linked to geo-database entries.

DOI： 10.48550/ARXIV.2305.13844

researchmap

Authorship：Lead author,　Last author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：電子情報通信学会  

算盤（そろばん）を用いた数値計算，すなわち「珠算」は，「珠」を用いた数値表現を理解した上で，複数の方法・順序により「珠」を操作しなければならず，その習得には長期に渡る繰り返し学習を要する．しかしながら，珠算指導は学習者の観察に基づきミスや苦手な珠操作を発見・指導する形式が主となっており，人手に頼るほかないのが現状である．そこで本研究では，一般的な算盤を用いる珠算学習を対象としたICTによる学習支援を実現するため，書画カメラによって取得した画像認識に基づく算盤上の入力値推定手法を提案する．評価実験の結果，算盤上に入力された7桁の数値に対し正解率95.0%での推定が可能であることを確認した．

researchmap

Other Link： http://research.ubi-lab.com/news/3846/

Language：English   Publishing type：Research paper (other academic)   Publisher：arXiv  

We have constructed Arukikata Travelogue Dataset and released it free of charge for academic research. This dataset is a Japanese text dataset with a total of over 31 million words, comprising 4,672 Japanese domestic travelogues and 9,607 overseas travelogues. Before providing our dataset, there was a scarcity of widely available travelogue data for research purposes, and each researcher had to prepare their own data. This hinders the replication of existing studies and fair comparative analysis of experimental results. Our dataset enables any researchers to conduct investigation on the same data and to ensure transparency and reproducibility in research. In this paper, we describe the academic significance, characteristics, and prospects of our dataset.

DOI： 10.48550/ARXIV.2305.11444

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

There are two nasal pathways through which we perceive odors: 'orthonasal smell,' which comes from the tip of the nose, and 'retronasal smell,' which comes from the mouth and exits through the nose. In particular, the retronasal smell is known to be more critical in influencing perceived taste than the orthonasal smell. In this study, we propose a smart lid called Kaolid that changes the taste of beverages by presenting scent information as retronasal smell. Kaolid achieves retronasal smell by equipping a small, lightweight straw- or cup-type olfactory device with a sensor that senses drinking behavior and the amount of water in the cup. The straw-type device injects the scent into the tube through the middle of the straw, delivering the scent to the user's mouth simultaneously as the beverage is being consumed. The cup-type device injects the scent into the cup through the lid and delivers the scent to the user's mouth at the beginning of drinking to achieve in-mouth scenting. The concept of Kaolid is to promote water consumption, considered insipid, by altering the sense of taste through a scent presented when drinking the beverage.

DOI： 10.1109/PerComWorkshops56833.2023.10150412

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

DOI： 10.11517/jsaisigtwo.2023.SAI-046_04

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

DOI： 10.11517/jsaisigtwo.2023.SAI-046_05

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3545947.3573251

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Architectural Institute of Japan  

DOI： 10.3130/aijt.29.132

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Information Processing Society of Japan  

Recently, TV broadcasters have been collecting and utilizing non-personal TV viewing log data, including start and end times of viewing, from TVs connected to the Internet in a format that does not identify individual viewers. However, since each broadcaster can only use its own non-personal TV viewing log data, it has not yet been able to obtain useful knowledge despite the vast amount of data it has accumulated. In addition, the collection methods and data granularity of non-personal TV viewing log data vary from station to station, and the data accumulated by each station cannot be integrated and used. In this paper, we propose a method for matching non-personal TV viewing log data collected by each broadcaster using its own method, and integrate the data. In the proposed method, TVs whose channel transition timing matches five items collected at the time of non-personal TV viewing log data collection (IP address, ZIP code, TV receiver manufacturer ID, browser major version, and browser minor version) are presumed to be the same TV. This method was applied to a “joint technology verification experiment on TV viewing log data linkage” conducted by four broadcasters in Osaka to verify the technical feasibility of linking non-personal TV viewing log data among broadcasters. We confirmed that we were able to match approximately 2.67 million TV sets, which corresponds to 71.0% of the 3.76 million unique TV sets acquired by each broadcaster.

researchmap

Other Link： https://ipsj.ixsq.nii.ac.jp/ej/?action=repository_uri&item_id=223508&file_id=1&file_no=1

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.1109/ACCESS.2023.3242547

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3567445.3571112

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：English   Publisher：IPSJ  

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/gcce56475.2022.10014071

researchmap

Language：Japanese  

我々が感じる香りには，鼻先から香る「鼻先香（Orthonasal smell）」と口の中から鼻を抜ける香り「口中香（Retronasal smell）」の 2 種類が存在する．これまで，様々な嗅覚デバイスの研究開発が活発に行われてきているが，香りを感じる際の鼻腔経路の違いが，知覚する「味」に与える影響については明らかになっていない．本論文では，小型で軽量な嗅覚デバイスの設計を示し，それぞれ鼻先香と口中香を提示可能な嗅覚デバイスとして，コップ型，ストロー型，マスク型という 3 種類のプロトタイプを提示する．そして，香りを提示する際の鼻腔経路の違いが味覚に及ぼす影響を調査する．実験では，3 種類のプロトタイプを用いて，被験者 13 名を対象に，知覚する香りの評価，デバイスの評価，味覚の評価を行った．実験の結果，香り情報提示の違いで味覚への影響に違いが見られ，鼻先で嗅ぐ香りに比べ，口の中から香る香りによって味覚に影響を及ぼすことが示された．

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publisher：IPSJ  

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：Japanese   Publisher：情報処理学会  

動画情報を用いた行動認識手法は，視認性による認識精度の低下に加えプライバシーの問題がある．そこで本研究では，プライバシーを考慮した3Dポイントクラウドによる行動認識を行う．今後は，マイクロ行動のデータセットを収集し，認識モデルの作成を行う．

CiNii Books

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：Japanese   Publisher：情報処理学会  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

Reducing the amount of sugar consumed from daily beverages is essential for well-being. However, since a sudden reduction in intake is mentally painful for those who prefer sweetened beverages, solutions are needed to help them gradually become accustomed to non-sweetened drinks. In this paper, we propose Aromug, a mug-type olfactory interface that amplifies the user's perceived sweetness by providing a sweet scent along with the action of drinking. Through user studies, we investigated the effect of the information presented by Aromug on the taste of iced coffee. The experiment results showed that the sugar-free coffee and chocolate aroma might enhance the perceived sweetness compared to the no-scent case. In addition, it was suggested that there were differences in preference for sweetness depending on age and frequency of coffee drinking.

DOI： 10.1145/3544793.3563402

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI  

There has been a subsequent increase in the number of elderly people living alone, with contribution from advancement in medicine and technology. However, hospitals and nursing homes are crowded, expensive, and uncomfortable, while personal caretakers are expensive and few in number. Home monitoring technologies are therefore on the rise. In this study, we propose an anonymous elderly monitoring system to track potential risks in everyday activities such as sleep, medication, shower, and food intake using a smartphone application. We design and implement an activity visualization and notification strategy method to identify risks easily and quickly. For evaluation, we added risky situations in an activity dataset from a real-life experiment with the elderly and conducted a user study using the proposed method and two other methods varying in visualization and notification techniques. With our proposed method, 75.2% of the risks were successfully identified, while 68.5% and 65.8% were identified with other methods. The average time taken to respond to notification was 176.46 min with the proposed method, compared to 201.42 and 176.9 min with other methods. Moreover, the interface analyzing and reporting time was also lower (28 s) in the proposed method compared to 38 and 54 s in other methods.

DOI： 10.3390/s22186965

Scopus

PubMed

researchmap

Authorship：Lead author,　Corresponding author   Language：Japanese   Publishing type：Research paper (other academic)  

小学校の総合的な学習（探求）の時間の一環として，GIGAスクール端末を活用することで新たな学びの機会を創出することを目的に掲げ，地域の魅力発信アプリを共創することを題材に，児童・小学校教諭・自治体・地域ボランティア・地域団体・大学から構成されるチームで取り組むプロジェクト型のための活動教材「にしょロボくん」を開発した．本稿では，生駒市立生駒南第二小学校における2021年度の全校縦割り活動に開発した教材を導入し，全児童186名を対象に1年間にわたって実践した結果を報告する．実践を通して，児童の高い自己評価が得られたこと，観察にを通じて児童の自発的な行動が確認されたことから，開発した教材が一定の教育効果を有することが示された．

DOI： 10.51094/jxiv.144

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics55523.2022.00034

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/ithings/ithings2022.html#WatanabeMNAI22

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MYU K.K.  

Short stick exercises have been attracting attention from the viewpoint of preventing falls and improving the health of elderly people and are generally performed under the guidance of instructors and nursing staff at nursing homes. However, in situations such as the COVID-19 pandemic, where people should refrain from unnecessary outings, it is advisable that individuals perform short stick exercises at home and record their exercise implementation status. In this paper, we propose an inertial measurement unit (IMU)-sensor-based short stick exercise tracking method that can automatically record the types and amounts of exercises performed using a short stick equipped with an IMU sensor. The proposed method extracts time-domain and frequency-domain features from linear acceleration and quaternion time-series data obtained from the IMU sensor and classifies the type of exercise using an inference model based on machine learning algorithms. To evaluate the proposed method, we collected sensor data from 21 young subjects (in their 20s) and 14 elderly subjects (79-95 years old), where the participants performed three sets (10 times per set) of eight basic types of short stick exercises (five types for elderly people). As a result of evaluating the proposed method using this data set, we confirmed that when LightGBM was used as the learning algorithm, it achieved F values of 90.0 and 86.6% for recognizing the type of exercise for young and elderly people, respectively.

DOI： 10.18494/sam3968

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In many of the world's major cities, commuter trains provide vital transportation support and thus play an essential role in our daily lives. Therefore, it has become necessary to estimate the degree of congestion in each train car, both to improve passenger comfort levels and, more recently, to prevent worsening the COVID-19 pandemic infection rate. However, it is difficult to estimate the degree of congestion within a train without violating passenger privacy. The same issues are true for busses, which is noteworthy because we have previously developed and evaluated a system that can estimate the degree of congestion within a bus while protecting passenger privacy by using Bluetooth Low Energy (BLE) signals. In this paper, we report on our efforts to extend that system to railway use, which were conducted on actual trains in cooperation with Kintetsu Railway Co., Ltd. During this trial, we collected BLE signals and used the data to estimate congestion levels in each car using an ML regression model. The results show that the mean absolute error (MAE) and the mean absolute percentage error (MAPE) could be estimated at accuracy levels of 5.56 and 0.27, respectively.

DOI： 10.1109/di-cps56137.2022.00007

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Stick exercises, which have been attracting attention for improving the health of the elderly, are usually performed in nursing homes under the guidance of nursing staff. However, in the current pandemic in which the elderly are advised to refrain from going out unnecessarily, it is desirable for each individual to be able to perform the stick exercises alone. In this study, we aim to develop a stick exercise support system that can automatically record the number of times an elderly person performs each type of stick exercise and provide feedback to improve the movement for each exercise. As a first step toward the realization of this stick exercise support system, we investigated a method for recognizing exercise movements using inertial measurement unit (IMU) sensors. In the evaluation experiment, 21 subjects performed 3 sets (10 times per set) of eight basic stick exercises. The exercise movements were classified based on the linear acceleration and quaternion data obtained from the IMU. As a result, 90% of F-measure was achieved when using Light GBM as the learning algorithm.

DOI： 10.1109/cphs56133.2022.9804564

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

新型コロナウイルス感染拡大により，実店舗での試食販売の実施が制限され，売れ残った野菜などの生鮮食品の廃棄が問題となっている．本研究では，試食販売の代替案を模索するべく，試食販売時に発生する「香り」に着目し，香りのナッジが購買行動に及ぼす影響を調査する．具体的には，奈良県の伝統野菜である大和丸なすの購買促進を題材として取り上げ，大和丸なすの旬である2021年の6月から7月の2ヶ月間，実店舗での実証実験を行なった．そして，（1）提示なし，（2）紙媒体の提示，（3）紙・動画媒体の提示，(4）紙・動画・香り媒体の提示という４つの条件下における，販売ブースへの訪問回数，滞在時間，売上高を比較した．実験の結果，香りナッジを用いた介入によって消費者の興味を引き，購買の意思決定に正の影響を与える可能性が示唆された．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：日本データベース学会  

オンラインアンケートにおいて，なるべく楽に早くアンケートタスクを完了しようとする「Satisficing（努力の最小限化）」という態度が調査結果の信頼性を低下させる問題がある．この問題に対し，回答時間が明らかに短い回答を除外するなどの措置が考案されてきたが，回答時間だけでは完全に除外することができない．そこで我々は，回答時間だけでなく，回答中の画面操作を観測することで，より高精度にSatisficingが検出可能になるのではないかという仮説を立てた．世界中で利用されているオープンソースアンケートシステムLimeSurveyの拡張機能として，回答中の画面操作ログ（回答操作ログ）を記録できるプラグインを開発し，本システムを用いてクラウドソーシング上でアンケート実験を行った．実験は，回答者は各自のスマートフォンを用いて，リッカート形式と自由記述形式の質問から成るアンケートに回答してもらうものであり，アンケートの途中にはSatisficingを検出するために考案されている既存の質問を挿入した．1000人に対して回答を依頼し，収集した回答内容および回答操作ログから，Satisficingを表現する可能性が考えられる特徴量を生成し，特徴量ごとにSatisficingである群とSatisficingでない群の母平均の差の検定を行った．結果として，既存の特徴量であるテキストの文字数，連続同一回答数，中間回答数に加え，開発したプラグインでのみ取得可能なスクロール速度，選択肢の変更回数，リッカート形式の回答時間などに統計的有意差があることを明らかにした．また，スクロール速度やテキストの変更回数に関しては，絶対値では差がない一方で，回答者ごとのベースラインとの差では有意な差が確認できた．

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

Information on congestion of buses, which are one of the major public transportation modes, can be very useful in light of the current COVID-19 pandemic. Because it is unrealistic to manually monitor the number of riders on all buses in operation, a system that can automatically monitor congestion is necessary. The main goal of this paper’s work is to automatically estimate the congestion level on a bus route with acceptable performance. For practical operation, it is necessary to design a system that does not infringe on the privacy of passengers and ensures the safety of passengers and the installation sites. In this paper, we propose a congestion estimation system that protects passengers’ privacy and reduces the installation cost by using Bluetooth low-energy (BLE) signals as sensing data. The proposed system consists of (1) a sensing mechanism that acquires BLE signals emitted from passengers’ mobile terminals in the bus and (2) a mechanism that estimates the degree of congestion in the bus from the data obtained by the sensing mechanism. To evaluate the effectiveness of the proposed system, we conducted a data collection experiment on an actual bus route in cooperation with Nara Kotsu Co., Ltd. The results showed that the proposed system could estimate the number of passengers with a mean absolute error of 2.49 passengers (error rate of 38.8%).

DOI： 10.3390/s22030881

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Publishing type：Research paper (international conference proceedings)  

Due to the pandemic of COVID-19, product sampling at supermarkets has been restricted, and the disposal of unsold vegetables and other perishable foods has become a problem. To explore alternatives to product sampling, this study focuses on the “aroma” generated during product sampling and explores the effect of aroma nudges on purchasing behavior. Specifically, we focused on the scenario of promoting the purchase of Yamato-maru eggplant, a traditional vegetable of Nara Prefecture in Japan. We conducted an experiment in a supermarket for two months, from June to July of 2021, the season of the Yamato-maru eggplant. We compared the number of visits to the sales booth, the time spent in the booth, and the sales volume under four conditions: (1) no presentation, (2) presentation of paper media, (3) presentation of the paper and video media, and (4) presentation of a paper, video, and olfactory media. The experiment results suggest that the inclusion of aroma nudges has a positive potential to attract consumer interest and positively influence their purchasing decisions.

Scopus

researchmap

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

To realize ubiquitous services based on physiological sensing, it is important to assume that commercially available sensors will be used in daily life. Collecting physiological data from ordinary people for a long period of time in-the-wild is completely different from performing highly accurate physiological sensing using dedicated sensors in a controlled laboratory environment. In this presentation, we will share the various problems we have experienced and clarify the points that need to be considered in order to achieve stable sensing in a real environment.

DOI： 10.11517/pjsai.jsai2022.0_3i3os5a01

researchmap

J-GLOBAL

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：社会情報学会  

スマートツーリズムは，世界的に注目を集めている。その構成要素の一つとして，ユーザの観光履歴や嗜好に基づく推薦システムが多く提案されている。一方で，マーケティングの分野では，近年，パーソナリティや動機などの心理的要素に着目した推薦の研究がなされているが，観光分野では少ない。そこで，本論文では，どのような特性のユーザにどのような推薦をすべきかを明らかにするために，観光客のパーソナリティに着目し観光行動との関係性を分析する。具体的には，「観光客のパーソナリティの違いによって観光行動（観光行動エリア・観光行動カテゴリ）が異なるか」について検証を行う。検証のために，1,000人に京都観光を想定したアンケート調査を実施している。検証の結果，観光客のパーソナリティの違いによって観光行動が異なることを確認している。具体的には，外向性が低い観光客は清水寺などの人気のある観光エリアに行きやすいなど，を明らかにしている。また，その結果に基づいて，外向性が低い観光客に対しては観光スポットの人気度を示したり，他の観光客からのレビューを表示したりするなど，パーソナリティに合わせた観光推薦について考察している。

researchmap

Other Link： http://www.ssi.or.jp/journal/pdf/Vol10No2_2.pdf

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.23919/icmu50196.2021.9638882

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.23919/icmu50196.2021.9638938

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.23919/icmu50196.2021.9638956

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Springer International Publishing  

DOI： 10.1007/978-3-030-94822-1_43

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Springer International Publishing  

DOI： 10.1007/978-3-030-94822-1_50

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Springer International Publishing  

DOI： 10.1007/978-3-030-94822-1_41

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：情報処理学会  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：The Japanese Society for Neuroendovascular Therapy  

DOI： 10.5797/jnet.oa.2021-0053

researchmap

Other Link： https://www.jstage.jst.go.jp/article/jnet/advpub/0/advpub_oa.2021-0053/_article

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3460418.3479284

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

The emergence of various types of commercial cameras (compact, high resolution, high angle of view, high speed, and high dynamic range, etc.) has contributed significantly to the understanding of human activities. By taking advantage of the characteristic of a high angle of view, this paper demonstrates a system that recognizes micro-behaviors and a small group discussion with a single 360 degree camera towards quantified meeting analysis. We propose a method that recognizes speaking and nodding, which have often been overlooked in existing research, from a video stream of face images and a random forest classifier. The proposed approach was evaluated on our three datasets. In order to create the first and the second datasets, we asked participants to meet physically: 16 sets of five minutes data from 21 unique participants and seven sets of 10 min meeting data from 12 unique participants. The experimental results showed that our approach could detect speaking and nodding with a macro average f1-score of 67.9% in a 10-fold random split cross-validation and a macro average f1-score of 62.5% in a leave-one-participant-out cross-validation. By considering the increased demand for an online meeting due to the COVID-19 pandemic, we also record faces on a screen that are captured by web cameras as the third dataset and discussed the potential and challenges of applying our ideas to virtual video conferences.

DOI： 10.3390/s21175719

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Language：English  

The collection of spatiotemporal tourism information is important in smart
tourism and user-generated contents are perceived as reliable information.
Participatory sensing is a useful method for collecting such data, and the
active contribution of users is an important aspect for continuous and
efficient data collection. This study has focused on the impact of task
allocation interface design and individual personality on data collection
efficiency and their contribution in gamified participatory sensing for
tourism. We have designed two types of interfaces: a map-based with active
selection and a chat-based with passive selection. Moreover, different levels
of elaborateness and indirectness have been introduced into the chat-based
interface. We have employed the Gamification User Types Hexad framework to
identify the differences in the contributions and interface preferences of
different user types. The results of our tourism experiment with 108
participants show that the map-based interface collects more data, while the
chat-based interface collects data for spots with higher information demand. We
also found that the contribution to sensing behavior and interface preference
differed depending on the individual user type.

arXiv

researchmap

Other Link： http://arxiv.org/pdf/2105.12032v1

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

DOI： 10.1109/access.2021.3079473

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

In disaster situations, special support for the disaster weak are crucial to keep them safe. Common evacuation strategies guide individuals to the shelters closest to their present locations. If evacuees are unevenly distributed across areas, some shelters will not be able to accommodate all arriving evacuees due to the limited capacity of shelters. To tackle this, the existing method decides the destinations for each evacuee considering congestion in disaster areas. However, this method does not consider the disaster weak and can be burdensome for them. Giving that the priority to the disaster weak for shelter decision would be effective to lessen burdens for them, but not all evacuees follow the guidance. When a shelter accepts arriving evacuees unconditionally, some evacuees are rejected, causing a delay in evacuation. If the disaster weak are rejected, the delay will be increased. In this paper, we propose two evacuation shelter decision methods considering the capacity of shelters, the disaster weak, and evacuees’ selfish behavior to realize quick evacuation for the disaster weak: (1) Fixed-rate Reduction Method (FRM), which reduces the assignment number of evacuees less than the capacity at the same percentage to all shelters. (2) Simulation-based Reduction Method (SRM), which reduces the assignment number to shelters that will be crowded based on simulation of an evacuation scenario. Then, these methods decide the destinations for evacuees, with the priority given to the disaster weak. To evaluate the efficiency of the proposed methods, we conducted multi-agent simulation assuming the scenario of evacuation of 30,000 visitors for the Gion Festival including the disaster weak. Through the simulation, we compared our methods with conventional methods including the nearest shelter selection method and the exiting method. As a result, our methods can reduce evacuation time of the disaster weak compared to conventional methods with sufficient cooperation by evacuees.

DOI： 10.3390/su13095106

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

Some respondents make careless responses due to the 'satisficing,' which is an attempt to complete a questionnaire as quickly and easily as possible. To obtain results that reflect a fact, detecting satisficing and excluding the responses with satisficing from the analysis targets are required. One of the devised methods detects satisficing by adding questions that check violations of instructions and inconsistencies. However, this approach may cause respondents to lose their motivation and prompt them to satisficing. Additionally, a deep learning model that automatically answers these questions was reported. This threatens the reliability of the conventional method. To detect careless responses without inserting such screening questions, machine learning (ML) detection using data obtained from answer results was attempted in a previous study, with a detection rate of 55.6%, which is not sufficient from the viewpoint of practicality. Therefore, we hypothesized that a supervised ML model with a higher detection rate could be constructed by using on-screen answering behavior as features. However, (1) no existing questionnaire system can record on-screen answering behavior and (2) even if the answering behavior can be recorded, it is unclear which answering behavior features are associated with satisficing. We developed an answering behavior recording plug-in for LimeSurvey, an online questionnaire system used all over the world, and collected a large amount of data (from 5,692 people) in Japan. Then, a variety of features were examined and generated from answering behavior, and we constructed ML models to detect careless responses. We call this detection method the ML-ABS (ML-based answering behavior scale). Evaluation by cross-validation demonstrated that the detection rate for careless responses was 85.9%, which is much higher than the previous ML method. Among the various features we proposed, we found that reselecting the Likert scale and scrolling particularly contributed to the detection of careless responses.

DOI： 10.1109/access.2021.3069049

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In recent years, street parking in prohibited areas has become a serious social problem, particularly in metropolitan and tourist areas where there are many on-street parked cars. In addition, because on-street parking can cause traffic congestion and accidents, real-time detection is considered necessary. In previous studies, fixed-point cameras have been mainly used for traffic control; however, a major disadvantage of these systems is their limited detection area. In this study, we developed a system that can detect and visualize on-street parking in real-time using video data captured by dashboard cameras, which have become widely used in recent years. We created a learned model to detect on-street parking and to recognize cars using an edge device. By displaying the location information of on-street parked cars on a map, their location can be visualized. This system could be used to obtain statistical data for crackdowns on on-street parking and to identify areas where on-street parking occurs.

DOI： 10.1109/PerComWorkshops51409.2021.9431076

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)  

In this paper, we introduce a food-tech design as a healthy nudge called eat2pic that encourages people to slow down their eating pace and encourage healthier eating habits. The eat2pic system is composed of a sensor-equipped chopstick (one of a pair) and components that use context-aware digital canvases. The eat2pic system achieves (1) automatic tracking of what and how fast the user consumed each mouthful of food, (2) real-time visual feedback that indicates good or bad eating behavior. The key concept of eat2pic involves extending the relationship between humans and paintings in order to establish a closed-loop in which daily eating behavior is reflected in pictures on the canvas near us and feedback from the canvas leads our lifestyles towards healthier diets. The eat2pic system provides a novel experience in which users can come to see eating as a playful task that involves coloring landscape pictures, and not simply taking nutrition into their bodies.

DOI： 10.1109/PerComWorkshops51409.2021.9431002

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (other academic)  

Rapid proliferation of mobile devices with various sensors have enabled
Participatory Mobile Sensing (PMS). Several PMS platforms provide multiple
functions for various sensing purposes, but they are suffering from the open
issues: limited use of their functions for a specific scenario/case and
requiring technical knowledge for organizers. In this paper, we propose a novel
PMS platform named ParmoSense for easily and flexibly collecting urban
environmental information. To reduce the burden on both organizers and
participants, in ParmoSense, we employ two novel features: modularization of
functions and scenario-based PMS system description. For modularization, we
provide the essential PMS functions as modules which can be easily chosen and
combined for sensing in different scenarios. The scenario-based description
feature allows organizers to easily and quickly set up a new participatory
sensing instance and participants to easily install the corresponding scenario
and participate in the sensing. Moreover, ParmoSense provides GUI tools as well
for creating and distributing PMS system easily, editing and visualizing
collected data quickly. It also provides multiple functions for encouraging
participants' motivation for sustainable operation of the system. Through
performance comparison with existing PMS platforms, we confirmed ParmoSense
shows the best cost-performance in the perspective of the workload for
preparing PMS system and varieties of functions. In addition, to evaluate the
availability and usability of ParmoSense, we conducted 19 case studies, which
have different locations, scales, and purposes, over 4 years with cooperation
from ordinary citizens. Through the case studies and the questionnaire survey
for participants and organizers, we confirmed that ParmoSense can be easily
operated and participated by ordinary citizens including non-technical persons.

arXiv

researchmap

Other Link： http://arxiv.org/pdf/2102.05586v1

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：社会情報システム学研究会  

近年，自然林の激減に伴い，ニホンミツバチの餌場や棲める空洞のある樹木がなくなっている．ニホンミツバチは，植物の花粉を運び受粉させるポリネーター（送粉者）として，古くより日本の森の植生環境を整える重要な役割を果たしている．しかし，このニホンミツバチの生態は解明されていない点が多く，外来種がもたらしたアカリンダニなどの病気や自然林の激減により，年々減少傾向にあるとされている．NPO法人ビーフォレスト・クラブは，ニホンミツバチの減少の解決を目的とし，ニホンミツバチが繁殖可能な住処となる巣箱の開発・設置に取り組んでいる（2020年11月現在，日本全国90拠点に設置）．しかしながら，開発している巣箱は自然に存在する巣環境を完全には再現できておらず，ニホンミツバチが住みづらい環境が存在することから，営巣率（巣箱の数に対して，実際に巣箱に巣を作った割合）をどのように向上するかが課題となっている．巣箱の改善には，温湿度の条件など営巣に必要な環境条件を明らかにする必要があるが，その環境は現在のところ科学的に調査されていないのが実情である．こうした背景から，本研究では，ニホンミツバチが営巣・繁殖しやすい巣環境をセンシングにより明らかにすることを目的とし，ニホンミツバチの巣箱センシングシステムを提案する．本稿では，巣箱センシングシステムの実装について述べ，動作確認実験を行った結果について報告する．動作確認実験の結果，太陽の光が弱い冬場の2日間の太陽光で充電を完了させ，1週間継続して動作可能である事を確認した．さらに，2020年冬季の3週間，実際に自然環境に設置されている巣箱にシステムを取り付け，温湿度の測定を行った結果，実環境での継続的な動作が可能である事が確認された．また，夜間の結露によるノイズの発生といった今後の課題も確認された．

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MYU K.K.  

DOI： 10.18494/sam.2021.2998

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

DOI： 10.1109/access.2021.3051526

researchmap

Authorship：Lead author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：観光情報学会  

理化学研究所AIPセンター観光情報解析チームでは，旅行者の人流ビッグデータを対象にした人流クラスタリング，および，旅行者の観光を最適化するための参加型POI情報収集，ユーザ行動予測，混雑センシング・予測，事前動画キュレーションの研究を進めている．本稿では，時系列深層学習モデルを用いた人流クラスタリング法，センシング情報から深層学習法を用いた説明文自動生成法，スマートフォンアプリによる参加型POI情報収集法，ユーザ行動時の感情測定と推定法，観光の事前プランキュレーション動画作成法，思い出動画の自動作成法，体力・時間・予算を考慮した観光ルート動的推薦法とそれらの効果について述べる．

researchmap

Authorship：Lead author,　Corresponding author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3448891.3448957

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：{MDPI} {AG}  

<jats:p>In recent years, there has been a growing interest in travel applications that provide on-site personalized tourist spot recommendations. While generally helpful, most available options offer choices based solely on static information on places of interest without consideration of such dynamic factors as weather, time of day, and congestion, and with a focus on helping the tourist decide what single spot to visit next. Such limitations may prevent visitors from optimizing the use of their limited resources (i.e., time and money). Some existing studies allow users to calculate a semi-optimal tour visiting multiple spots in advance, but their on-site use is difficult due to the large computation time, no consideration of dynamic factors, etc. To deal with this situation, we formulate a tour score approach with three components: static tourist information on the next spot to visit, dynamic tourist information on the next spot to visit, and an aggregate measure of satisfaction associated with visiting the next spot and the set of subsequent spots to be visited. Determining the tour route that produces the best overall tour score is an NP-hard problem for which we propose three algorithms variations based on the greedy method. To validate the usefulness of the proposed approach, we applied the three algorithms to 20 points of interest in Higashiyama, Kyoto, Japan, and confirmed that the output solution was superior to the model route for Kyoto, with computation times of the three algorithms of 1.9±0.1, 2.0±0.1, and 27.0±1.8 s.</jats:p>

DOI： 10.3390/smartcities3040066

researchmap

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

The Ministry of Health, Labour and Welfare (MHLW) has released the COVID-19 Contact- Confirming Application (COCOA) to prevent the spread of COVID-19. However, it is currently underuti- lized and its effectiveness is questionable. Therefore, we propose the nudge system that promotes people's voluntary installation and aims to increase the utilization of COCOA. The proposed system motivates users to install COCOA by reframing the installation as the acquisition of tickets to experience three attractive events: (1) paint, (2) vote, and (3) fortune slip. In this paper, we propose the nudge system promoting the installation and assume scenarios for the use of the system, taking into account the appropriate environment for each event.

DOI： 10.11517/jsaisigtwo.2020.sai-039_10

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3384419.3430464

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3384419.3430460

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3384419.3430447

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM  

DOI： 10.1145/3384419.3430593

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

日本は，周囲を海に囲まれた島国であることから，魚釣りを趣味とする人は多く，近年では，センサの小型化や機械学習技術の発展から，釣りのセンシングに関する様々な研究が行われている．釣りを行うにあたり，スポットでの過去の釣果や魚種に基づく時間帯や仕掛けや餌の選定など事前に情報収集を行い，綿密な計画を練るが，多くの防波堤釣りにおいて，良好な釣果が上がらないことが多々発生する．それらの一因として，雑誌などの釣り媒体の情報が最新でないことや SNS などの釣果情報が時間帯，地点，魚種などの情報が離散的に保存され，共有されていない事が挙げられる．本研究では，釣果情報共有を目的とし，釣竿に取り付けたセンサにより釣果，時間帯，場所の情報を，手間をかけずに，自動的に収集するシステムを提案する．提案システムを実現するため，本論文では，魚の釣り上げ時の振動データに基づく魚種判別手法を提案する．実験では，2019 年夏季に防波堤 3 カ所（大阪府，福井県，三重県）で釣り上げた，28 匹の魚の振動データに対して，周波数解析およびバンドパスフィルタとピーク検出による魚種判定を行った．その結果，ピーク点ごとの間隔に着目した特徴量を主成分分析で可視化することで，9 つの魚種のうち，尾数の多かった 5 つの種類について魚種のグループ分けを行うことができた．

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

近年，センサの小型化，高性能化や機械学習技術の進歩から，IoT で得られるフィジカル空間の情報とサイバー空間に蓄積された膨大な情報を AI が解析し，その解析結果をフィジカル空間の人間に様々な形でフィードバックする Cyber Physical System の研究開発が進められている．なかでも，スマートスポーツの分野では，競技者の行動や動作をセンシングし，AI を用いて認識する研究が数多く進められている．本研究では，スポーツとしての釣りに着目し，釣り人の行動をリアルタイムで認識し，釣れないときの意思決定支援として，時間・場所に応じた釣果に結びつく過去の有用な行動に関する情報を提供する釣り CPS を提案する．著者らは，釣り竿に取り付けた加速度センサの情報から魚種と大きさを自動認識する研究を既に実施している．本稿では，これに加えて，釣り CPS 実現に向けた位置情報と加速度・ジャイロ情報を取得する IoT デバイスの開発と，リアルタイム行動認識結果を位置・時刻と合わせてアニメーションにより表示する Web システムについて報告する．開発した IoT デバイスと，Web システムについて，実用化の観点から評価を行った．その結果，実際の防波堤環境で，GPS センサ，加速度センサを起動し，UDP 通信でサーバに常時送信する状態で 4 時間 40 分の動作を確認した．

CiNii Article

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

口腔ケアは健康寿命の延伸に重要である．一方で，自身で口腔内の衛生状態を管理するのは難しく，専門の医師の支援が必要である．近年のリモート診療の普及に伴いオンラインでの口腔内診断に関する研究がなされている．これらの研究では，ユーザがスマートフォンで自身の口腔内を撮影した画像から診断を行っている．撮影に慣れていないユーザにとって診断利用可能な画像かを判断することは困難であり撮り直しが多発する．そこで本稿では口腔内画像撮影支援システムについての提案を行う．予備調査として 9 名の被験者に対し支援が無い場合に 5 枚撮影法の各角度の撮り直し回数や，ユーザの主観による撮影困難な角度について調査した．アンケートから最も撮影が困難な角度は上顎咬合面間であり上下咬合面では 4 名の被験者が 5 回以上の撮り直しを行ったとの回答を得た．この結果により本提案システムの必要性が確認された．そこで，本稿では 5 枚撮影法によるスマートフォンでの撮影を想定し，「1. 歯領域の有無判定」，「2. 診断利用の可否判定」，「3. アシスト」の 3 ステップの支援フローからなる提案システムを提案する．

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

In the tourism sector, user-generated information and communication among tourists are perceived to be more effective and reliable contents. In addition, the collection of dynamic tourism information with high spatio-temporal resolution is required to provide comfortable tourism in response to the changing tourism style with the advancement of information technology. Participatory sensing, which can collect various types of information is a useful method by which to collect these contents. However, continuous participation of users is essential in participatory sensing, and it is one of the most important points to stimulate participation motivation. In the tourism situation, we also need to pay attention to the total tourist satisfaction of participants. In this paper, we adopt gamification, i.e., the implementation of game design elements in real-world contexts for non-gaming purposes, for participatory sensing as an incentive mechanism to motivate participants with active participation and collect the necessary information efficiently. Within the framework, where points are given when completing the requested sensing task (=mission), two sensing missions with different burdens; Area Mission and Check-in Mission, and three different types of rewarding mechanisms; Fixed, Variable and Dynamic Variable, are designed as a gamification mechanism. We implemented these elements in the proposed participatory sensing platform application and conducted an experimental case study with 33 participants at an actual tourist spot: Kyoto, Japan. Then, we investigate the effects on tourist behavior and satisfaction by analyzing collected sensor data, mission logs, and post-survey answers. As a result, we can conclude the following: (1) the tourist behavior is changed due to the proposed gamification design and the necessary information was collected efficiently; (2) the participants tend to prioritize Check-in Mission over the sightseeing, which can induce a behavior change but might impact sightseeing enjoyment.

DOI： 10.3390/smartcities3030037

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：European Language Resources Association  

researchmap

Other Link： https://dblp.uni-trier.de/conf/lrec/2020

Language：English   Publishing type：Research paper (international conference proceedings)  

Copyright © 2020 for this paper by its authors. Nowadays, lifestyle diseases have become a global social problem. As a treatment, it is necessary to review people’s life patterns and lead them to a better lifestyle, which is called “Behavior Change.” With the progress of information technology, many pieces of research and developments have been conducted to assist people with their daily life, trying to induce behavior change. The common approach used in the existing systems is altering users’ target behaviors to new behaviors, such as drinking more water and walking further. However, this approach considers less about the timing of proposing and the relevance between users’ target behaviors and new behaviors, which limits the effectiveness of the existing systems in inducing behavior change. To improve users’ experience and effectiveness of the system, in this paper, we propose a new design of behavior change support system which promotes behavior changes by embedding additional behaviors into users’ daily routines, trying to improve users’ awareness of their health condition.

Scopus

researchmap

Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

Recently, due to the drastic increase in foreign tourists coming to Japan, there has been a demand to provide smart tourism services that enable inbound tourists to comfortably enjoy sightseeing. To provide satisfactory experiences for tourists, it is desirable to provide tourist information in a timely manner by considering dynamic information, which is information that changes over time, such as current congestion information in destination spots and travel route information, in addition to static information, such as the preferences and profiles of tourists. However, in many existing systems, serious problems occur, such as (1) a lack of support for on-site use, (2) a lack of consideration of dynamic information, and (3) heavy burden on tourists. In this paper, we propose a novel system that can provide tourism plans for tourism spots in a timely manner. The proposed system consists of the following two key mechanisms: (A) A mechanism for acquiring preference information from tourists (including preference on dynamic information); (B) a curation mechanism for realizing on-site tourism. To demonstrate the effectiveness of the proposed system, we carried out evaluation experiments utilizing real tourism spots and simulations. As a result, we obtained the following primary findings: (1) On-site tourism spot recommendation is effective for tourists who do not make detailed tourism plans before sightseeing; (2) preference information for participants can be reflected in the tourism spot recommendation while massively reducing the burden on participants; (3) it is possible to obtain a higher satisfaction level than is achieved with model courses, which are often used for sightseeing.

DOI： 10.3390/smartcities3020013

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In data collection of the human physiological and psychological conditions for mental healthcare (e.g., work engagement), measurement methods using environment-installed sensors and questionnaire surveys have been often used. However, these approaches are not practical in continuous data collection, due to the large burden for people. Recently, in association with advancing sensing technology with IoTs, sensing by small sensors and wearable devices has become possible easily. In this paper, we aim to establish a simple and general sensing method based on a mobile application for measuring physiological and psychological state of office workers and environmental state. Through the experiment for 2-3 weeks involving 60 office workers of four Japanese companies by using our application, we succeeded to create a dataset of physiological, environment, and mental state. This paper explains the developed mobile application, experimental procedure, and a summary of the data collected in the experiment.

DOI： 10.1109/percomworkshops48775.2020.9156085

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/percomworkshops48775.2020.9156176

researchmap

Language：Japanese  

グループミーティングの評価のための誰がどれだけ喋ったのかを簡単に分析できるシステムが求められている。本研究では360度カメラで測定された動画から口の動きを抽出し、参加者ごとの発話量を計測する手法を検討した。

CiNii Article

CiNii Books

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

© 2019 International Conference on Computers in Education, Proceedings.All right reserved. By the spread of active learning and group work, the ability to collaborate and discuss among the participants becomes more important than before. Although several studies have reported on that micro facial expressions and body movements give psychological effects to others during conversation, most of them are lacking in quantitative evaluation and there are few datasets about group discussion. In this research, we proposed a highly reproducible system that helps to make datasets of group discussions with multiple devices such as an omnidirectional camera (360-degree camera), an eye tracker and a motion sensor. Our system operates those devices in one-stop to realizing synchronized recording. To confirm the feasibility, we built the proposed system with an omnidirectional camera, 4 eye trackers, and 4 motion sensors. Finally, we succeeded to make a dataset by recording 8 times group meeting by using our developed system easily.

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

© 2019 Association for Computing Machinery. This paper is the first trial to create a corpus on human-to-human multi-modal communication among multiple persons in group discussions. Our corpus includes not only video conversations but also the head movement and eye gaze. In addition, it includes detailed labels about the behaviors appeared in the discussion. Since we focused on the micro-behavior, we classified the general behavior into more detailed behaviors based on those meaning. For example, we have four types of smile: response, agree, interesting, sympathy. Because it takes much effort to create such corpus having multiple sensor data and detailed labels, it seems that no one has created it. In this work, we first attempted to create a corpus called “M3B Corpus (Multi-Modal Meeting Behavior Corpus),” which includes 320 minutes discussion among 21 Japanese students in total by developing the recording system that can handle multiple sensors and 360-degree camera simultaneously and synchronously. In this paper, we introduce our developed recording system and report the detail of M3B Corpus.

DOI： 10.1145/3341162.3345588

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

DOI： 10.1109/PERCOMW.2019.8730708

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

© 2019 IEEE. Many interrupt notification methods have been studied, but most of the existing research assumes that, except for the target application, the applications do not control the notification timing. However, if other applications are controlled by the same notification timing, interrupt timing will become concentrated and the effects of notification timing control may not be exerted. In addition, since the installed applications are different for each user, it is necessary to control notification timings while taking into consideration the behaviors of all the applications installed on a user&#039;s smartphone. In this research, we define notification timing control while considering the behaviors of all installed applications as &#039;Adaptive Notification Management&#039; and then conduct diversity surveys of notifications received by users. In this paper, we report on a system that acquires all notification information while excluding privacy data. We also report on experimental results using actual data collected using crowdsourcing and discuss how to realize the application realizing adaptive notification management.

DOI： 10.1109/percomw.2019.8730694

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

© 2019 IEEE. Recent advances in computational and sensing technologies allowed to incorporate different devices into a smart systems, making the ubiquitous or pervasive computing a hot topic for research and commercial projects. One technology, that can help the user to interact with invisible system representing smart environment is spoken dialogue system. Following the success in research on automatic speech recognition and natural language understanding, spoken dialogue systems have significantly improved themselves during the past decade and now bringing the communication between human and machine closer to natural level. Having user as a main subject, both system may benefit from explicit information about his current state and mood, adjusting their behaviour to the certain extent. In this paper we consider the combination of ubiquitous computing, spoken dialogue systems, and emotion recognition technologies, suggest possible ways of information flow, discuss future applications and potential problems. We find, that these technologies can be complementary to each other, increasing their flexibility, robustness and intelligibility when combined. We present the usage of such approach in a smart house environment, continuously tracking the state of the user, interacting with them in real time and reacting to mood changes.

DOI： 10.1109/percomw.2019.8730876

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

© 2019 IEEE. Following the technical progress and growing touristic market, demand on guidance systems is constantly increasing. Current systems are not personalized, they usually provide only a general information on sightseeing spot and do not concern about the tourist&#039;s perception of it. To design more adjustable and context-aware system, we focus on collecting and estimating emotions and satisfaction level, those tourists experience during the sightseeing tour. We reducing changes in their behaviour by collecting two types of information: conscious (short videos with impressions) and unconscious (behavioural pattern recorded with wearable devices) continuously during the whole tour. We have conducted experiments and collected initial data to build the prototype system. For each sight of the tour, participants provided an emotion and satisfaction labels. We use them to train unimodal neural network based models, fuse them together and get the final prediction for each recording. As tourist himself is the only source of labels for such system, we introduce an approach of post-experimental label correction, based on paired comparison. Such system built together allows us to use different modalities or their combination to perform real-time tourist emotion recognition and satisfaction estimation in-the-wild, bringing touristic guidance systems to the new level.

DOI： 10.1109/percomw.2019.8730864

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM Press  

© Copyright held by the owner/author(s). To design more context-aware systems for smart environments, especially smart cities, the psychological user status such as emotion should be considered in addition to environmental information. In this study, we focus on the tourism domain as a typical use case, and propose a multimodal tourist emotion recognition method during the sightseeing. We employ behavioural cues (eye and head/body movements) and audio-visual features to recognise emotion. As a result of real-world experiments with tourists, we achieved up to 0.71 of average recall score in 3-class emotion recognition task with feature level fusion.

DOI： 10.1145/3267305.3267687

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE Computer Society  

© 2018 IEEE. Following the increase in demand for &#039;smart tourism,&#039; various tourist information becomes available. Current tourist guidance systems can provide many possible routes around the city, which are usually based on an optimal distance and time or popularity of the place. To design more enjoyable tourist routes, we should be aware of tourist&#039;s perception of the urban environment. In this paper, we propose the methodology of estimating the tourist emotions and satisfaction level by analysing physiological features, such as head movement and eye gaze. Features derived from raw sensor data have the correlation up to 0.58 with emotion and satisfaction labels. This study also shows the differences in feature/label dependencies between different touristic areas and highlights the challenges of tourist satisfaction estimation.

DOI： 10.1109/SMARTCOMP.2018.00036

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IOS Press  

We have been working on a real-time tourism guidance system to improve the tourist's satisfaction in sightseeing. In this system, participatory sensing is leveraged to collect real-time sightseeing contents or data. The amount and quality of data collected in participatory sensing depend on the user's contribution. Therefore, gamification is generally utilized as an incentive mechanism. Few existing studies addressed the appropriateness of the gamification design or target tourists. In this paper, we design a gamification mechanism consisting of two types of sensing tasks and three types of rewarding methods and implement the mechanism in our participatory sensing platform called ParmoSense. We conducted a sightseeing experiment supposing three different user types. As a result, we confirmed that some type of tourists (participants) can collect sightseeing information while enjoying sightseeing through behavior change.

DOI： 10.3233/978-1-61499-874-7-196

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/intenv/intenv2018w.html#KawanakaMSFAY18

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Lecture Notes in Electrical Engineering  

Following the increase in use of smart devices, various real-time environmental information becomes available everywhere. To provide more context-aware information, we also need to know emotion and a satisfaction level in a viewpoint of users. In this paper, we define it as ''a user satisfaction impact (USI)'' and propose a method to estimate USI by combining dialogue features and physical reaction features. As dialogue features, facial expression and acoustic feature are extracted from multimodal dialogue system on a smartphone. As physical reactions, head motion, eye motion, and heartbeat are collected by wearable devices. We conducted the preliminary experiments in the real-world to confirm the feasibility of this study in the tourism domain. Among various features, we confirmed that eye motion correlates with satisfaction level up to 0.36.

DOI： 10.1007/978-981-13-9443-0_15

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper, we propose a health support system ''WaistonBelt 2,'' which consists of a belt-type wearable device and a smartphone application. Our system aims to support users to obesity (the metabolic syndrome) that may lead to various adult diseases such as arteriosclerosis, heart disease or stroke. Our proposed device can automatically measure a circumference on the belt position when a user wears it by a rotary encoder, and monitor a tension of belt for recognizing posture and overeating. The measured data is transmitted to our application via Bluetooth. Stored values are visualized by graphs, and advices are given through the avatar based on the analyzed data. Through evaluation experiments, we confirmed that our proposed device achieves highly accurate measurement of the circumference on the belt position (average absolute error is 0.73 cm).We also confirmed that it is possible to realize a recognition system of posture and eating action using belt pressure sensing system.

DOI： 10.1109/icmu.2016.7742089

Web of Science

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

CiNii Article

CiNii Books

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ACM Press  

Participatory sensing is attracting the attention as a popular method for sensing the environment or people. However, this method has some problems such as sensing accuracy and sustainability problem, because participants of this sensing method are the general public. Therefore, there is a need to focus on these two essential components: 1) a data correction system which can calibrate sensors and measurement environments, 2) a motivation generating system which prevents users from stopping or lack of motivation for the participation. We propose a "Participatory Mobile Sensing Platform" that project owners can recompose freely these components.

DOI： 10.1145/2938559.2948836

Web of Science

Scopus

researchmap

Authorship：Last author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.2197/ipsjjip.24.31

Scopus

researchmap

Authorship：Lead author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese  

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery, Inc  

Metabolic syndrome becomes a serious problem in our life, because it is one of the reasons of arteriosclerosis, heart disease or stroke. In order to prevent a person from becoming a metabolic syndrome, it is important to know own current actual abdominal circumference, and care by yourself. However, any wearable devices cannot measure abdominal circumference. In this paper, we propose and implement a belt-type wearable device, called "WaistonBelt", and a smartphone application that can keep monitoring an abdominal circumference forever. "WaistonBelt" can measure an abdominal circumference with ordinary action, and can visualize a transition of it. Through an experimental evaluation, we confirm that our system can measure an abdominal circumference with 0.66% error.

DOI： 10.1145/2800835.2800869

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Authorship：Lead author   Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：Japanese  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Authorship：Lead author   Language：Japanese   Publishing type：Research paper (scientific journal)  

防犯意識の向上にともない，夜道の明るさなどの「安心・安全面」に配慮した情報整備が，歩行者向けナビゲーションにおいて重要となってきている．街灯照度に基づき歩道の安全性を可視化する取り組みは，各自治体などによって実施されているが，安全性判定に必要な街灯照度測定にかかるコストや手間などから，網羅性に欠けているのが現状である．そこで本研究では，スマートフォン搭載照度センサを用いて，街灯照度データを収集，集合知を形成することにより，情報整備における「網羅性」問題の解決を検討している．なお，スマートフォンを用いた測定には，端末の保持角度が不定，歩行中に照度が測定されるといった課題があるため，照度センサの特性に基づく街灯位置推定手法および街灯照度推定手法を提案し，検証を行った．検証の結果，街灯位置推定の再現率は，全街灯種について約89%，一般的な生活道路の大多数に用いられている街灯種（水銀・蛍光ランプ）について94.1%となった．また，街灯と推定地点の平均絶対誤差は全街灯種について約1.97mとなった．街灯照度推定の平均誤差率は全街灯種について約31%，事前調査の対象とした街灯種について約17%となった．There is a growing demand for public managing security information such as the brightness of night sidewalks in the field of pedestrian navigation systems. Such security information is collected and visualized by some municipalities, but the coverage of the survey is not sufficient due to measurement equipment costs and labor costs. Therefore, in this study, we address these cost problems by collecting the illuminance of streetlamps with the light sensors of smartphones and applying collective intelligence. However, there is a problem with the randomness of a smartphone&#039;s measurement angle because users measure illuminance while walking down a sidewalk. So, we propose an inferring method regarding each streetlamp&#039;s position and illuminance based on the properties of each light sensor, and we evaluate each method of collection. As a result of the evaluation, the recall of position estimation method was 94.1% (kinds of streetlamps which are generally installed), 89% (in all streetlamps). In addition, the average absolute error between the estimated point and streetlamp was 1.97m (in all streetlamps). The mean error rate of illuminance estimation method was 17% (expected streetlamps), 31% (in all streetlamps).

CiNii Article

CiNii Books

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery, Inc  

Along with the popularization of smartphones, which have various sensors such as accelerometers and GPS, location based services are also growing in popularity. Additionally, with the growth demand of in security awareness, pedestrian navigation systems are required to provide safety information. Thus, we propose and develop an illuminance inferring method utilizing smartphone's light sensors for assessing a safety level of sidewalks at night.

DOI： 10.1145/2638728.2638797

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)   Publisher：一般社団法人電子情報通信学会  

近年,防犯意識の向上に伴い,夜道の明るさなどの「安心・安全面」での情報整備が歩行者向けナビゲーションにおいて重要となってきている.安心・安全|青報については,企業や自治体,警察署などが独自に提供しているものの,情報の「明快さ」や「網羅性」が十分に達成されているとはいえない.本研究では,スマートフォンに搭載されている照度センサを用いて,街灯照度データを収集,集合知を形成することにより,安心・安全情報のうち「夜道の明るさ」を地図に付加するシステムの開発を行っている.本稿では,上記の課題のうち,情報整備の「網羅性」を解決するために,スマートフォン搭載照度センサの特性に基づいた街灯設置地点推定および街灯照度推定を行う手法を提案し,各手法について検証を行った.検証の結果,街灯位置推定手法における再現率は,事前調査の対象とした街灯については100[%],全サンプルの街灯については約89[%]となった.また,街灯と推定点の平均絶対誤差は全サンプルの街灯について約1.97[m]となった.街灯照度推定手法における平均誤差率は事前調査の対象とした街灯については約17[%],全サンプルの街灯については約31[%]となった.

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

近年，防犯意識の向上に伴い，夜道の明るさなどの 「安心・安全面」 での情報整備が歩行者向けナビゲーションにおいて重要となってきている．安心・安全情報については，企業や自治体，警察署などが独自に提供しているものの，情報の 「明快さ」 や 「網羅性」 が十分に達成されているとはいえない．本研究では，スマートフォンに搭載されている照度センサを用いて，街灯照度データを収集，集合知を形成することにより，安心・安全情報のうち 「夜道の明るさ」 を地図に付加するシステムの開発を行っている．本稿では，上記の課題のうち，情報整備の 「網羅性」 を解決するために，スマートフォン搭載照度センサの特性に基づいた街灯設置地点推定および街灯照度推定を行う手法を提案し，各手法について検証を行った．検証の結果，街灯位置推定手法における再現率は，事前調査の対象とした街灯については 100 [%]，全サンプルの街灯については約 89 [%] となった．また，街灯と推定点の平均絶対誤差は全サンプルの街灯について約 1.97 [m] となった．街灯照度推定手法における平均誤差率は事前調査の対象とした街灯については約 17 [%]，全サンプルの街灯については約 31 [%] となった．

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

CiNii Article

researchmap

Authorship：Lead author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)  

DOI： 10.20729/00213186

CiNii Article

CiNii Books

researchmap

Event date： 2020.8.26 - 2020.8.29

Language：English   Presentation type：Oral presentation (general)  

researchmap

Language：Japanese   Presentation type：Oral presentation (invited, special)  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

Venue：グランフロント大阪 ナレッジサロン  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese  

researchmap

Language：Japanese   Presentation type：Oral presentation (general)  

researchmap

Language：Japanese  

researchmap

Language：Japanese   Presentation type：Oral presentation (invited, special)  

researchmap

Language：Japanese   Presentation type：Oral presentation (general)  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

Language：Japanese   Presentation type：Public lecture, seminar, tutorial, course, or other speech  

researchmap

researchmap

Work type：Software  

researchmap

researchmap

researchmap

researchmap

researchmap

Award type：Award from international society, conference, symposium, etc. 

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Award type：Award from Japanese society, conference, symposium, etc.  Country：Japan

researchmap

Award type：Award from Japanese society, conference, symposium, etc.  Country：Japan

researchmap