Faculty Profiles - Matsuda Yuki

Papers - Matsuda Yuki

Division display 21 - 40 of about 275 ／ All the affair displays >>

スマートフォンのブラウザ記憶領域を用いた災害情報流通システムの実装 Reviewed

筒井巽水, 松田裕貴, 秦恭史, 諏訪博彦, 峯英一郎, 稲場圭信, 安本慶一

第32回マルチメディア通信と分散処理ワークショップ (DPSWS '24) 160 - 167 2024.10

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

Mobile Augmented Reality Interface for Instruction-based Disaster Preparedness Guidelines Reviewed International journal

Sergio De León Aguilar, Yuki Matsuda, Keiichi Yasumoto

Sensors and Materials 36 ( 10 ) 4585 - 4585 2024.10

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

非特定テレビ視聴履歴データの放送局間統合手法 Reviewed

松田裕貴, 榊原太一, 真弓大輝, 松田裕貴, 水本旭洋, 安本慶一

情報処理学会論文誌 65 ( 10 ) 1488 - 1500 2024.10

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

ユーザー参加型BLEスキャニングによる都市空間の混雑度推定に向けた検討

菊池尊勝, 池永拓海, 細川蓮, 松田裕貴, 諏訪博彦, 安本慶一

2024年度情報処理学会関西支部支部大会 1 - 6 2024.9

美術館における鑑賞者の心理状態推定に向けた基礎分析

鳥垣耀平, 諏訪博彦, 安本慶一, 松田裕貴

2024年度情報処理学会関西支部支部大会 1 - 6 2024.9

野生動物の生息域推定精度向上のためのLiDAR点群データによる痕跡分類手法の提案

古城司, 由田翔吾, 坪内孝太, 松田裕貴, 諏訪博彦, 安本慶一

2024年度情報処理学会関西支部支部大会 1 - 6 2024.9

BLEのランダムMACアドレスを用いたODデータ推定に向けた初期検討

吉村太斗, 林虎太朗, 新井イスマイル松田裕貴

2024年度情報処理学会関西支部支部大会 1 - 8 2024.9

複数台のBLEスキャナを用いた都市人流推定に向けた基礎検討

林虎太朗, 吉村太斗, 諏訪博彦, 松田裕貴

2024年度情報処理学会関西支部支部大会 1 - 8 2024.9

サイクリストPoIを自動検出／評価をするための走行ログデータ解析手法の提案

長山和樹, 諏訪博彦, 松田裕貴, 安本慶一

2024年度情報処理学会関西支部支部大会 1 - 7 2024.9

ARCADE: An Augmented Reality Display Environment for Multimodal Interaction with Conversational Agents Reviewed International coauthorship

Carolin Schindler, Daiki Mayumi, Yuki Matsuda, Niklas Rach, Keiichi Yasumoto, Wolfgang Minker

arXiv 2408.06222 1 - 3 2024.8

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

Enhancing Reflective and Conversational User Engagement in Argumentative Dialogues with Virtual Agents Reviewed International coauthorship International journal

Annalena Aicher, Yuki Matsuda, Keichii Yasumoto, Wolfgang Minker, Elisabeth André, Stefan Ultes

Multimodal Technologies and Interaction 8 ( 8:71 ) 1 - 44 2024.8

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

Towards Opportunistic Federated Learning Using Independent Subnetwork Training Reviewed International journal

Victor Romero, Tomokazu Matsui, Yuki Matsuda, Hirohiko Suwa, Keiichi Yasumoto

2024 IEEE International Conference on Smart Computing (SMARTCOMP) 174 - 181 2024.6

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

A Table-Top Interface for Real-Time Coaching in Abacus Learning Reviewed International journal

Yuki Matsuda

2024 IEEE International Conference on Smart Computing (SMARTCOMP) 243 - 245 2024.6

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

A Method for City-Wide PoI-Level Congestion Prediction via Assimilation of Actual and Simulation-Based PoI Congestion Data Reviewed International journal

Haruka Sakagami, Osamu Yamada, Yuki Matsuda, Hirohiko Suwa, Keiichi Yasumoto

2024 IEEE International Conference on Smart Computing (SMARTCOMP) 39 - 46 2024.6

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

Detecting Distress Changes Using Multimodal Data During Interaction with A Smart Speaker Reviewed International journal

Chingyuan Lin, Yuki Matsuda, Hirohiko Suwa, Keiichi Yasumoto

2024 IEEE International Conference on Smart Computing (SMARTCOMP) 350 - 355 2024.6

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

Crowd Flow Prediction from Mobile Traces Through Time Series PoI Stay Counts Reviewed International journal

Osamu Yamada, Yuki Matsuda, Hirohiko Suwa, Keiichi Yasumoto

2024 IEEE International Conference on Smart Computing (SMARTCOMP) 266 - 271 2024.6

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

Protecting Cross-Camera Person Re-Identification Data with Image Differential Privacy Reviewed International journal

Lucas Maris, Yuki Matsuda, Keiichi Yasumoto

2024 IEEE International Conference on Smart Computing (SMARTCOMP) 386 - 391 2024.6

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

未知ゴミ識別のための判定手法の比較と実用化に向けた検討

立花巧樹, 呉健朗, 松田裕貴, 諏訪博彦, 安本慶一

マルチメディア, 分散, 協調とモバイル（DICOMO 2024）シンポジウム論文集 33 - 38 2024.6

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

Aromug: a Mug-type Olfactory Interface to Enhance the Sweetness Perception of Beverages Reviewed

Daiki Mayumi, Yugo Nakamura, Yuki Matsuda, Shinya Misaki, Keiichi Yasumoto

IEEE Access 1 - 13 2024.5

属性情報を考慮した人流シミュレーション機構の構築と評価

阪上遥, 山田理, 松田裕貴, 諏訪博彦, 安本慶一

研究報告マルチメディア通信と分散処理（DPS） 2024-DPS-198 ( 45 ) 1 - 8 2024.3

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

　 PREV - NEXT 　

< Matsuda Yuki >

Papers - Matsuda Yuki