担当区分：責任著者   記述言語：英語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：筆頭著者,　責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：最終著者,　責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.11309/jssst.40.1_11

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（学術雑誌）  

DOI： 10.3233/idt-220269

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.15439/2022F25

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/fedcsis/fedcsis2022c.html#IkedaNT22

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：筆頭著者,　責任著者   記述言語：英語   掲載種別：研究論文（学術雑誌）  

DOI： 10.48550/arXiv.2205.13375

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.18293/seke2021-122

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/compsac51774.2021.00247

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：最終著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

掲載種別：研究論文（学術雑誌）   出版者・発行元：Elsevier BV  

DOI： 10.1016/j.infsof.2020.106346

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/acsos-c51401.2020.00063

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1587/transinf.2019KBP0015

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IOS Press  

© 2020 - IOS Press and the authors. All rights reserved. Combinatorial interaction testing is an efficient software testing strategy. If all interactions among test parameters or factors needed to be covered, the size of a required test suite would be prohibitively large. In contrast, this strategy only requires covering t-wise interactions where t is typically very small. As a result, it becomes possible to significantly reduce test suite size. Locating arrays aim to enhance the ability of combinatorial interaction testing. In particular, ( 1 ,t ) -locating arrays can not only execute all t-way interactions but also identify, if any, which of the interactions causes a failure. In spite of this useful property, there is only limited research either on how to generate locating arrays or on their minimum sizes. In this paper, we propose an approach to generating minimum locating arrays. In the approach, the problem of finding a locating array consisting of N tests is represented as a Constraint Satisfaction Problem (CSP) instance, which is in turn solved by a modern CSP solver. The results of using the proposed approach reveal many ( 1 ,t ) -locating arrays that are smallest known so far. In addition, some of these arrays are proved to be minimum.

DOI： 10.3233/fi-2020-1929

Scopus

researchmap

担当区分：責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

担当区分：最終著者,　責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：ACM  

DOI： 10.1145/3341105.3374033

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/sac/sac2020.html#NakagawaOAK20

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：岩波書店  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Elsevier  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）  

DOI： 10.3233/FI-2020-1929

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

担当区分：筆頭著者,　責任著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Outstanding paper

DOI： 10.1007/978-3-030-25213-7_5

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/ACISicis/ACISicis2019b.html#YamagataNSTO19

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：責任著者   記述言語：日本語   掲載種別：研究論文（研究会，シンポジウム資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   出版者・発行元：日本ソフトウェア科学会  

<p></p>

DOI： 10.11309/jssst.36.2_2

CiNii Article

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/APSEC.2018.00089

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/apsec/apsec2018.html#AokiOKN18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/APSEC.2018.00089

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/apsec/apsec2018.html#AokiOKN18

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1007/978-3-030-03098-8_44

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1007/978-3-030-03098-8_44

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.11309/jssst.35.1_67

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Springer Verlag  

A goal model, which is one of the common requirements models, has advantages of formalizing and visualizing results of requirements analysis. The model regards a requirement as a goal, and the root goal that is achieved by system execution should be decomposed to precondition goals. Current systems are large and complexed, so that there are a lot of requirements to be implemented. Therefore it is difficult to extract all goals and construct an elaborated goal model manually. In this paper we propose a process to support constructing goal models from requirements descriptions written in a natural language. In the proposed process, extraction rules are used to extract goals from requirements descriptions and then to construct a goal model from the goals. To evaluate our process, we applied the process to two system descriptions to construct goal models. The results show that the proposed process extracted appropriate goals and successfully assembled these goals in a goal hierarchy. We also report preliminary results of automating the proposed process.

DOI： 10.1007/978-981-10-7796-8_14

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Scopus

researchmap

担当区分：筆頭著者,　責任著者   記述言語：日本語  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Institute of Electrical and Electronics Engineers Inc.  

Code coverage is a metric used to represent how much code is tested when particular test cases are executed. As is code coverage, specification coverage is expected to help us to comprehend how much specification to be implemented is tested. In this study, we propose a visualization process for specification coverage. This process finds traceability links between specifications and test cases using a similarity metric and constructs two views for visualization. We develop a prototype tool for automatically executing the process and evaluate the process in a preliminary experiment on a web application development in industry. This extended abstract explains the overview of our study and the preliminary results.

DOI： 10.1109/ICSE-C.2017.117

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Institute of Electrical and Electronics Engineers Inc.  

Code coverage is a metric used to represent how much code is tested when particular test cases are executed. As is code coverage, specification coverage is expected to help us to comprehend how much specification to be implemented is tested. In this study, we propose a visualization process for specification coverage. This process finds traceability links between specifications and test cases using a similarity metric and constructs two views for visualization. We develop a prototype tool for automatically executing the process and evaluate the process in a preliminary experiment on a web application development in industry. This extended abstract explains the overview of our study and the preliminary results.

DOI： 10.1109/ICSE-C.2017.117

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Locating arrays provide combinatorial test suites not only for detecting the presence of an interaction fault but also for locating the fault. Compared with test suites for ordinary combinatorial testing, however, the fault locating capability entails a substantial increase in the size of test suites. In this position paper, we consider the problem: how small can locating arrays be? To answer the question, we develop a method that finds a locating array of a given size using a SAT solver. We report the size of the smallest locating arrays discovered by using our method. This result provides the smallest known upper bound on the size of the minimum locating arrays.

DOI： 10.1109/ICSTW.2017.49

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Specifications for a software system are usually verified using test cases in the testing phase. As is code coverage, specification coverage is expected to help comprehend how many specifications to be implemented are tested. In this study, we apply a visualization process for specification coverage to a web application development project in industry. This process provides two views for visualization from different viewpoints. The process also provides a classification of specifications according to the assurance degree of test execution. The results of the case study demonstrate that the process provides effective measures to comprehend how many specifications are covered and discovers trends related to the project.

DOI： 10.1109/ISSREW.2017.19

Web of Science

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1587/transinf.2015KBP0010

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

FIT奨励賞受賞：津田宏軌

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Pair-wise testing is an effective test planning technique for finding interaction faults using a small set of test cases. Constraint elicitation is an important process in the pair-wise testing design since constraints determine the test space; however, the constraint elicitation process has not been well studied. It usually requires manual capturing and precise definition of constraints. In this paper, we propose a constraint elicitation process that helps combinatorial test design. Our elicitation process consists of two steps: parameter combination identification and value pair determination. We conduct experiments on some test models, and demonstrate that some extracted rules match constraints and others helps to define constraints.

DOI： 10.1587/transinf.2015KBP0010

Web of Science

researchmap

その他リンク： http://dblp.uni-trier.de/db/journals/ieicet/ieicet99d.html#journals/ieicet/NakagawaT16

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

学生論文特集秀逸論文

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

The objective of this paper is to recognize and classify the poses of idols in still images on the web. The poses found in Japanese idol photos are often complicated and their classification is highly challenging. Although advances in computer vision research have made huge contributions to image recognition, it is not enough to estimate human poses accurately. We thus propose a method that refines result of human pose estimation by Pose Guide Ontology (PGO) and a set of energy functions. PGO, which we introduce in this paper, contains useful background knowledge, such as semantic hierarchies and constraints related to the positional relationship between body parts. Energy functions compute the right positions of body parts based on knowledge of the human body. Through experiments, we also refine PGO iteratively for further improvement of classification accuracy. We demonstrate pose classification into 8 classes on a dataset containing 400 idol images on the web. Result of experiments shows the efficiency of PGO and the energy functions; the F-measure of classification is 15% higher than the non-refined results. In addition to this, we confirm the validity of the energy functions.

DOI： 10.1587/transinf.2015EDP7067

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

The objective of this paper is to recognize and classify the poses of idols in still images on the web. The poses found in Japanese idol photos are often complicated and their classification is highly challenging. Although advances in computer vision research have made huge contributions to image recognition, it is not enough to estimate human poses accurately. We thus propose a method that refines result of human pose estimation by Pose Guide Ontology (PGO) and a set of energy functions. PGO, which we introduce in this paper, contains useful background knowledge, such as semantic hierarchies and constraints related to the positional relationship between body parts. Energy functions compute the right positions of body parts based on knowledge of the human body. Through experiments, we also refine PGO iteratively for further improvement of classification accuracy. We demonstrate pose classification into 8 classes on a dataset containing 400 idol images on the web. Result of experiments shows the efficiency of PGO and the energy functions; the F-measure of classification is 15% higher than the non-refined results. In addition to this, we confirm the validity of the energy functions.

DOI： 10.1587/transinf.2015EDP7067

Web of Science

researchmap

その他リンク： http://dblp.uni-trier.de/db/journals/ieicet/ieicet99d.html#journals/ieicet/TashiroKSNTO16

出版者・発行元：CEUR-WS.org  

researchmap

その他リンク： http://dblp.uni-trier.de/db/conf/models/runtime2016.html#conf/models/NakagawaOT16

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

For systems that have time constraints, an increase of processing time causes a delay of behavior and may result in a system failure. Although it is desirable to implement these systems as self-adaptive systems, there is no programming framework for self-adaptive systems that can deal with time constraints dynamically. In this study, we propose a mechanism for verifying system behaviors against time constraints at runtime. This mechanism uses UPPAAL, a model checking tool, for dynamic verification. We develop a prototype of a programming framework that uses the proposed mechanism. The results of evaluating the framework on a simulation experiment demonstrate the feasibility of our approach.

DOI： 10.1109/FAS-W.2016.62

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

For systems that have time constraints, an increase of processing time causes a delay of behavior and may result in a system failure. Although it is desirable to implement these systems as self-adaptive systems, there is no programming framework for self-adaptive systems that can deal with time constraints dynamically. In this study, we propose a mechanism for verifying system behaviors against time constraints at runtime. This mechanism uses UPPAAL, a model checking tool, for dynamic verification. We develop a prototype of a programming framework that uses the proposed mechanism. The results of evaluating the framework on a simulation experiment demonstrate the feasibility of our approach.

DOI： 10.1109/FAS-W.2016.62

Web of Science

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Japan Society for Software Science and Technology  

ソフトウェア開発において，ビジネスプロセスのモデル化は重要である．適切なビジネスプロセスモデルを構築するためには，ステークホルダの要求をモデルへ反映する必要がある．そこで本研究ではリファインメントパターンに基づいて構築されたゴールモデルをビジネスプロセスモデルへ変換する手法を提案する．リファインメントパターンに基づいたゴール分解の関係をビジネスプロセスモデルへ変換するためのルール及びアルゴリズムを示す．本手法によって，リファインメントパターンに基づいてステークホルダの要求を形式的に捉えることで，ビジネスプロセスモデル構築に役立てることができる．複数の事例に本手法を適用すること及び，モデル検査による検証によって本手法の有効性を評価する．

DOI： 10.11309/jssst.32.4_141

CiNii Article

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/RET.2015.14

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1527/tjsai.30.152

Scopus

researchmap

記述言語：日本語  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Constraint elicitation is an important process in test design since constraints determine the test space; however, the constraint elicitation process, which is known as a daunting task, has not been well studied. It usually requires manual capturing and precise definition of constraints. In this paper, we try to automate a part of the constraint elicitation process in combinatorial test design. Pair-wise testing, a common combinatorial testing approach, is an effective test planning technique for finding interaction faults using a small set of test cases. We propose a collective intelligence approach to determining which value combinations are potential constraints. We conduct preliminary experiments on two examples, a traditional cross-browser testing example and an ATM system example, and evaluate the feasibility of our approach.

DOI： 10.1109/ASEW.2015.13

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER INT PUBLISHING AG  

Self-adaptive systems can deal with environmental changes by changing their own behaviors. Since self-adaptive systems modify their own behaviors dynamically, runtime verification is necessary to guarantee the correctness of the systems' behaviors. Discrete time Markov chain model checking is a promising approach for implementing runtime verification; however, the computational cost of the current model checking approach increases as the number of parameterized transition probabilities increases. In this study, we conduct experiments on various instances of Markov chain models and demonstrate that repeated application of Laplace expansion leads to the large computational cost. The results suggest that an approach to reducing the number of times of performing Laplace expansion should be developed.

DOI： 10.1007/978-3-662-49224-6_21

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER INT PUBLISHING AG  

Self-adaptive systems can deal with environmental changes by changing their own behaviors. Since self-adaptive systems modify their own behaviors dynamically, runtime verification is necessary to guarantee the correctness of the systems' behaviors. Discrete time Markov chain model checking is a promising approach for implementing runtime verification; however, the computational cost of the current model checking approach increases as the number of parameterized transition probabilities increases. In this study, we conduct experiments on various instances of Markov chain models and demonstrate that repeated application of Laplace expansion leads to the large computational cost. The results suggest that an approach to reducing the number of times of performing Laplace expansion should be developed.

DOI： 10.1007/978-3-662-49224-6_21

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Self-adaptive systems can adapt to environmental changes. In spite of many studies of self-adaptive systems, there are few implementations of them on real-world hardware. One of the main reasons for this is that the existing programming frameworks do not pay enough attention to the constraints on real-world hardware. In this study, we focus on an adaptation mechanism for real-world embedded systems and present a preliminary programming framework to implement self-adaptive embedded systems. As a case study we build a self-adaptive system using our framework on LEGO Mindstorms EV3 to demonstrate the feasibility of our framework.

DOI： 10.1109/SASO.2015.33

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Knowledge Systems Institute Graduate School  

Feedback comments, such as mailing lists and reviews, contain beneficial suggestion for software developers. Recently, developers have received more and more feedback comments
but it is still difficult to extract beneficial comments from a large amount of e-mail message or reviews. Latent Dirichlet Allocation (LDA) is a promising way of topic modeling, which classifies documents according to implicit multiple topics. In this paper, we tried to apply a requirements elicitation based on LDA to two different sources, i.e., Apache Commons User List and App Store reviews, and discuss the feasibility of this approach. An interesting finding was that some usual stop words indicated requirements description. This suggests that these words should be removed from the stop word list before applying LDA.

DOI： 10.18293/SEKE2015-103

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Self-adaptive systems can adapt to environmental changes. In spite of many studies of self-adaptive systems, there are few implementations of them on real-world hardware. One of the main reasons for this is that the existing programming frameworks do not pay enough attention to the constraints on real-world hardware. In this study, we focus on an adaptation mechanism for real-world embedded systems and present a preliminary programming framework to implement self-adaptive embedded systems. As a case study we build a self-adaptive system using our framework on LEGO Mindstorms EV3 to demonstrate the feasibility of our framework.

DOI： 10.1109/SASO.2015.33

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Knowledge Systems Institute Graduate School  

Feedback comments, such as mailing lists and reviews, contain beneficial suggestion for software developers. Recently, developers have received more and more feedback comments
but it is still difficult to extract beneficial comments from a large amount of e-mail message or reviews. Latent Dirichlet Allocation (LDA) is a promising way of topic modeling, which classifies documents according to implicit multiple topics. In this paper, we tried to apply a requirements elicitation based on LDA to two different sources, i.e., Apache Commons User List and App Store reviews, and discuss the feasibility of this approach. An interesting finding was that some usual stop words indicated requirements description. This suggests that these words should be removed from the stop word list before applying LDA.

DOI： 10.18293/SEKE2015-103

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

This paper focuses on the constraints elicitation in the combinatorial test design. Pair-wise testing, a common combinatorial testing approach, is an effective test planning technique to find interaction faults from the relatively small set of test cases. The test space is modeled by a set of parameters, their individual values, and constraints on the value combinations. Constraints reduce the test space; however, little consideration has been given to the process of finding them. The goal of our study is to establish an automatic constraints acquisition from the requirements document. We try to establish a constraints elicitation mechanism that helps to extract constraints from the requirements document based on a linguistic approach. In this paper, as the first step, we attempt to extract the coupling strength between parameters from the requirements document. We conducted a preliminary experiment on an ATM system example and evaluated the feasibility of our approach.

DOI： 10.1109/RET.2015.14

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Computer Society  

This article discusses the location of faulty interactions in software testing. We propose an algorithm to generate a test suite that can be used to identify a faulty pair-wise interaction. This approach works as follows. First, a test suite is generated using an existing method for pair-wise testing. Pair-wise testing requires testing all pair-wise interactions but does not guarantee that the faulty interaction can be located. Second, pair-wise interactions that cannot be located by the test suite are enumerated. Finally, test cases are repeatedly added to the test suite until all pair-wise interactions can be located. The results of applying the algorithm to several problem instances show that the test suites obtained using the algorithm are nearly twice as large as those for ordinary pair-wise testing which does not ensure fault locating ability.

DOI： 10.1109/PRDC.2014.26

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）   出版者・発行元：一般社団法人情報処理学会  

本稿では，2014 年 8 月 18 日から 22 日にかけて，スウェーデンのカールスクルーナにて開催された第 22 回要求工学国際会議 (RE2014) について紹介する．This paper gives our report on the 22st IEEE International Requirements Engineering Conference (RE2014) held in Karlskrona of Sweden on August 18-22, 2014.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.11309/jssst.31.3_58

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.11309/jssst.31.3_70

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.11309/jssst.31.2_67

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SciTePress  

DOI： 10.5220/0004916606390644

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

This article discusses the location of faulty interactions in software testing. We propose an algorithm to generate a test suite that can be used to identify a faulty pair-wise interaction. This approach works as follows. First, a test suite is generated using an existing method for pair-wise testing. Pair-wise testing requires testing all pair-wise interactions but does not guarantee that the faulty interaction can be located. Second, pair-wise interactions that cannot be located by the test suite are enumerated. Finally, test cases are repeatedly added to the test suite until all pair-wise interactions can be located. The results of applying the algorithm to several problem instances show that the test suites obtained using the algorithm are nearly twice as large as those for ordinary pair-wise testing which does not ensure fault locating ability.

DOI： 10.1109/PRDC.2014.26

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

This article discusses the location of faulty interactions in software testing. We propose an algorithm to generate a test suite that can be used to identify a faulty pair-wise interaction. This approach works as follows. First, a test suite is generated using an existing method for pair-wise testing. Pair-wise testing requires testing all pair-wise interactions but does not guarantee that the faulty interaction can be located. Second, pair-wise interactions that cannot be located by the test suite are enumerated. Finally, test cases are repeatedly added to the test suite until all pair-wise interactions can be located. The results of applying the algorithm to several problem instances show that the test suites obtained using the algorithm are nearly twice as large as those for ordinary pair-wise testing which does not ensure fault locating ability.

DOI： 10.1109/PRDC.2014.26

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

This paper reports a case study where pair-wise testing was applied to a real-world program. In particular we focus on weighting, an added feature which allows the tester to prioritize particular parameter values. In our previous work we proposed a weighting method that can reflect given weights in the resulting test suite more directly than can existing methods. To asses the effects of weighting in a practical testing process, we compare the number of execution times of the program's methods among three pair-wise test suites, including the test suite generated by our weighting method and those generated by an existing test case generation tool with and without the weighting option. The results show that the effects of weighting were most clearly observed when our weighting method was used.

DOI： 10.1109/ISSREW.2014.63

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

This paper reports a case study where pair-wise testing was applied to a real-world program. In particular we focus on weighting, an added feature which allows the tester to prioritize particular parameter values. In our previous work we proposed a weighting method that can reflect given weights in the resulting test suite more directly than can existing methods. To asses the effects of weighting in a practical testing process, we compare the number of execution times of the program's methods among three pair-wise test suites, including the test suite generated by our weighting method and those generated by an existing test case generation tool with and without the weighting option. The results show that the effects of weighting were most clearly observed when our weighting method was used.

DOI： 10.1109/ISSREW.2014.63

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Software evolution is an essential activity that adapts existing software to changes in requirements. Because of recent rapid requirements changes, systems are strongly required to evolve even if the target systems are embedded systems, whose implementation code is generally hard to be changed. This paper discusses the feasibility of applying self-adaptation mechanism for software evolution. We use the MAPE loop mechanism to evolve embedded systems without changing code inside the existing systems. This paper also reports preliminary results that we experimentally evolved a cleaning robot by following our approach. Our demonstrations show a part of additional behaviors as the results of software evolution that makes the cleaning robot possible to move obstacles. We also discuss the future directions of software evolution for embedded systems with the self-adaptive mechanism.

DOI： 10.1109/SASO.2014.45

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

Software evolution is an essential activity that adapts existing software to changes in requirements. Because of recent rapid requirements changes, systems are strongly required to evolve even if the target systems are embedded systems, whose implementation code is generally hard to be changed. This paper discusses the feasibility of applying self-adaptation mechanism for software evolution. We use the MAPE loop mechanism to evolve embedded systems without changing code inside the existing systems. This paper also reports preliminary results that we experimentally evolved a cleaning robot by following our approach. Our demonstrations show a part of additional behaviors as the results of software evolution that makes the cleaning robot possible to move obstacles. We also discuss the future directions of software evolution for embedded systems with the self-adaptive mechanism.

DOI： 10.1109/SASO.2014.45

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

In this paper, we propose an image classification method that recognizes several poses of idol photographs. The proposed method takes unannotated idol photos as input, and classifies them according to their poses based on spatial layouts of the idol in the photos. Our method has two phases; the first one is to estimate the spatial layout of ten body parts (head, torso, upper and lower arms and legs) using Eichner's Stickman Pose Estimation. The second one is to classify the poses of the idols using Bayesian Network classifiers. In order to improve accuracy of the classification, we introduce Pose Guide Ontology (PGO). PGO contains useful background knowledge, such as semantic hierarchies and constraints related to the positional relationship between the body parts. The location information of body parts is amended by PGO. We also propose iterative procedures for making further refinements of PGO. Finally, we evaluated our method on a dataset consisting of 400 images in 8 poses, and the final results indicated that F-measure of the classification has become 15% higher than non-amended results.

DOI： 10.1109/ICSC.2014.20

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

In this paper, we propose an image classification method that recognizes several poses of idol photographs. The proposed method takes unannotated idol photos as input, and classifies them according to their poses based on spatial layouts of the idol in the photos. Our method has two phases; the first one is to estimate the spatial layout of ten body parts (head, torso, upper and lower arms and legs) using Eichner's Stickman Pose Estimation. The second one is to classify the poses of the idols using Bayesian Network classifiers. In order to improve accuracy of the classification, we introduce Pose Guide Ontology (PGO). PGO contains useful background knowledge, such as semantic hierarchies and constraints related to the positional relationship between the body parts. The location information of body parts is amended by PGO. We also propose iterative procedures for making further refinements of PGO. Finally, we evaluated our method on a dataset consisting of 400 images in 8 poses, and the final results indicated that F-measure of the classification has become 15% higher than non-amended results.

DOI： 10.1109/ICSC.2014.20

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Association for Computing Machinery  

It is important to make sure that software satisfies stakeholders' requirements. However, as software has been getting more large-scale and complicated in recent years, it has certainly become more difficult to satisfy requirements. Even if there are goal-oriented requirements analysis approaches as techniques to systematically satisfy stakeholders' requirements, it is still difficult to maintain consistency of goal models and other requirements artifacts. In this paper, we propose a transformation approach that transforms models of KAOS, a well-known goal modeling methodology, into preliminary BPMN models by using refinement pattern of KAOS in a systematic way. It can assure consistency between systematically defined user's requirements and their realization process. Copyright 2014 ACM.

DOI： 10.1145/2554850.2555119

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Information Processing Society of Japan  

The existing music recommendation systems rely on user's contexts or content analysis to satisfy the users' music playing needs. They achieved a certain degree of success and inspired future researches to get more progress. However, a cold start problem and the limitation to the similar music have been pointed out. Therefore, this paper proposes a unique recommendation method using a 'renso' alignment among Linked Data, aiming to realize the music recommendation agent in smartphone. We first collect data from Last.fm, Yahoo! Local, Twitter and LyricWiki, and create a large scale of Linked Open Data (LOD), then create the 'renso' relation on the LOD and select the music according to the context. Finally, we confirmed an evaluation result demonstrating its accuracy and serendipity. © 2014 Information Processing Society of Japan.

DOI： 10.2197/ipsjjip.22.279

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Association for Computing Machinery  

It is important to make sure that software satisfies stakeholders' requirements. However, as software has been getting more large-scale and complicated in recent years, it has certainly become more difficult to satisfy requirements. Even if there are goal-oriented requirements analysis approaches as techniques to systematically satisfy stakeholders' requirements, it is still difficult to maintain consistency of goal models and other requirements artifacts. In this paper, we propose a transformation approach that transforms models of KAOS, a well-known goal modeling methodology, into preliminary BPMN models by using refinement pattern of KAOS in a systematic way. It can assure consistency between systematically defined user's requirements and their realization process. Copyright 2014 ACM.

DOI： 10.1145/2554850.2555119

Scopus

researchmap

その他リンク： http://dblp.uni-trier.de/db/conf/sac/sac2014.html#conf/sac/HoritaHSNTO14

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER-VERLAG BERLIN  

A goal for the creation and improvement of music recommendation is to retrieve users' preferences and select the music adapting to the preferences. Although the existing researches achieved a certain degree of success and inspired future researches to get more progress, problem of the cold start recommendation and the limitation to the similar music have been pointed out. Hence we incorporate concept of serendipity using 'renso' alignments over Linked Data to satisfy the users' music playing needs. We first collect music-related data from Last. fm, Yahoo! Local, Twitter and LyricWiki, and then create the 'renso' relation on the Music Linked Data. Our system proposes a way of finding suitable but novel music according to the users' contexts. Finally, preliminary experiments confirm balance of accuracy and serendipity of the music recommendation.

DOI： 10.1007/978-3-319-06826-8_2

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Information Processing Society of Japan  

The existing music recommendation systems rely on user's contexts or content analysis to satisfy the users' music playing needs. They achieved a certain degree of success and inspired future researches to get more progress. However, a cold start problem and the limitation to the similar music have been pointed out. Therefore, this paper proposes a unique recommendation method using a 'renso' alignment among Linked Data, aiming to realize the music recommendation agent in smartphone. We first collect data from Last.fm, Yahoo! Local, Twitter and LyricWiki, and create a large scale of Linked Open Data (LOD), then create the 'renso' relation on the LOD and select the music according to the context. Finally, we confirmed an evaluation result demonstrating its accuracy and serendipity. © 2014 Information Processing Society of Japan.

DOI： 10.2197/ipsjjip.22.279

Scopus

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Knowledge Systems Institute Graduate School  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER-VERLAG BERLIN  

A goal for the creation and improvement of music recommendation is to retrieve users' preferences and select the music adapting to the preferences. Although the existing researches achieved a certain degree of success and inspired future researches to get more progress, problem of the cold start recommendation and the limitation to the similar music have been pointed out. Hence we incorporate concept of serendipity using 'renso' alignments over Linked Data to satisfy the users' music playing needs. We first collect music-related data from Last. fm, Yahoo! Local, Twitter and LyricWiki, and then create the 'renso' relation on the Music Linked Data. Our system proposes a way of finding suitable but novel music according to the users' contexts. Finally, preliminary experiments confirm balance of accuracy and serendipity of the music recommendation.

DOI： 10.1007/978-3-319-06826-8_2

Web of Science

researchmap

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SciTePress  

DOI： 10.5220/0004817304280436

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Best Poster &amp; Demo Award

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/RE.2013.6636715

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/re/re2013.html#NakagawaOH13

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

近年推薦システムの研究において,その有用性は予測精度(適合率,再現率)の高さとされていたが,既存の推薦方法では,ユーザは予測精度の高さだけでは満足しないということが報告されている.したがって,今後の推薦システムの課題として,未知性や意外性といった予測精度以外の新たな観点が重要とされている.こうした課題を踏まえ,本論文では推薦リストの未知性という観点に着目し,ユーザの嗜好に合致するが,まだ知らないコンテンツの発見を促す推薦手法を提案する.多面的に付与されたタグの話題単位で推薦リストを多様化することにより,予測精度を維持しつつ,未知性を向上させる.評価実験の結果,推薦リストの約6割に嗜好に合致し,かつ知らないコンテンツが含まれ,未知性の高い推薦が実現できていることを確認した.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

学生研究賞受賞:吉田豊

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

DOI： 10.11309/jssst.31.2_67

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）   出版者・発行元：一般社団法人電子情報通信学会  

Webアプリケーションの開発においては,クライアント側のユーザビリティ向上が重要になってきている。たとえばAJaxなとの技術における非同期通信の利用により,クライアント側の操作をブロックせすに動作することか可能となっている しかしなから,非同期通信によって予期しない順序てサーバ処理か行われる可能性かある 本研究では,特に資源へのアクセスと非同期通信の使用時に起こる可能性のある問題と解決方法を示す 従来はこのような問題に対し,モデル検査などの形式検証手法が有効てあると考えられてきたか,専門知識が必要てかつ検証の労力か大きいという課題があった 本論文では,モデル検査による検証手法を,一般の技術者にも容易に利用可能とするための検証手法を提案する これにより開発者は資源競合の検証において, Webアプリケーションのモデルを記述せす,資源へのアクセスの順序を記述するだけて良くなるのて,専門知識か不要となり,かつ検証時の労力の大幅な軽減か可能となった.

CiNii Article

CiNii Books

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

We study a heterogeneous autonomous robot team composed of UAVs (Unmanned Air Vehicles) and UGVs (Unmanned Ground Vehicles) cooperate with each other to carry out global tasks. We introduce the system that UAVs and UGVs remove obstacles cooperatively. In our system, there are multiple type UGVs that have good points and shortcomings, and these UGVs remove a obstacle that block the way. Therefore, our systems can deal with more value of obstacles than existing systems. However our system is more complicated and has many problems to be solved. Therefore, we clarified the problems that our system need to be realized and implemented the robots. The system determines some ways to remove the obstacles using the aerial photograph taken by the UAV and the information of the obstacles by the UGVs, and then outputs a processed aerial photograph and some ways to remove the obstacles. The experimental results reminded us some necessary things for to carry out our goal. Our study has the goal that the autonomous robot team explores under unknown environment such as planetary explorations, or performs search and rescue operations in disaster areas. Copyright 2013 ACM.

DOI： 10.1145/2480362.2480379

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

There is a need for the development of systems that are compliant with laws in public administration, because their administrative activities are based on laws. When new laws are made or existing laws are amended, however, civil servants need to develop or modify the systems in the short time before the laws are issued. Related work in requirements elicitation from the legal texts includes approaches using ontology but there are difficulties in building an ontology for practical use. In this paper we propose pre-defined templates with the expression of functional requirements to identify legal texts, including their functional requirements, and a support tool consisting of two functions, one for automatic summary creation from complicated legal texts and one for the suggestion of the legal texts, including their functional requirements. We have also applied this approach to Japanese laws and have evaluated its accuracy. Our research revealed that using this approach can identify functional requirements with high accuracy. © 2013 The authors and IOS Press.

DOI： 10.3233/978-1-61499-359-9-175

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Springer Verlag  

In these days, an algorithmic trading in stock or foreign exchange (henceforth forex) market is in fashion, and needs for automatically performing stable asset management are growing. Machine learning techniques are increasingly used to construct trading rules of the algorithmic trading, as researches on the algorithmic trading advance. Our study aims to build an automatic trading agent, and in this paper, we concentrate in designing a module which determines trading rules by machine learning. We use Genetic Algorithm (henceforth GA), and we build trading rules by learning parameters of technical indices. Our contribution in this paper is that we propose new fitness functions in GA, in order to make them robuster to change of market trends. Although profits were used as a fitness function in the previous study, we propose the fitness functions which pay more attention to not making a loss than to gaining profits. As a result of our experiment using real TSE(Tokyo Stock Exchange) data for eight years, the proposed method has outperformed the previous method in terms of gained profits. © 2013 Springer International Publishing Switzerland.

DOI： 10.1007/978-3-319-00651-2_15

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IOS Press  

There is a need for the development of systems that are compliant with laws in public administration, because their administrative activities are based on laws. When new laws are made or existing laws are amended, however, civil servants need to develop or modify the systems in the short time before the laws are issued. Related work in requirements elicitation from the legal texts includes approaches using ontology but there are difficulties in building an ontology for practical use. In this paper we propose pre-defined templates with the expression of functional requirements to identify legal texts, including their functional requirements, and a support tool consisting of two functions, one for automatic summary creation from complicated legal texts and one for the suggestion of the legal texts, including their functional requirements. We have also applied this approach to Japanese laws and have evaluated its accuracy. Our research revealed that using this approach can identify functional requirements with high accuracy. © 2013 The authors and IOS Press.

DOI： 10.3233/978-1-61499-359-9-175

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1109/WI-IAT.2012.178

researchmap

その他リンク： https://dblp.uni-trier.de/db/conf/webi/webi2012.html#IshinoONTO12

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

学生優秀論文賞受賞: 越川兼地

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER-VERLAG BERLIN  

Multi-agent systems (MASs) are one of the effective approaches for dealing with the recent increase in software complexity and their autonomy. In the MAS research community, there has recently been increasing interest in the adoption of requirements engineering techniques to bridge the gap between the system requirements and the system design. One of the most important tasks based on the requirements description in the MAS design activity is the extraction of roles, which are the fundamental components of multi-agent systems, from it. It is also important to comprehend the relative degree of responsibility of the individual roles. The comprehension helps the developer decide the system architecture and discuss the performance and stability of the system. We introduce the concept of importance as a quantitative metric and an evaluation framework for the extraction of a suitable role set for the system and the task assignment to these roles. The importance is propagated from the requirements to the roles through their assigned tasks. We demonstrate the effectiveness of our framework through a case study and show that our metric and evaluation framework help not only to identify the importance of each role, but also to determine the system architecture.

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Recently, the video hosting is one of the most popular services on the Web. The service user can search movies by title, tag, date, and so on. However, the user can hardly obtain information on a particular scene of a movie. Thus, it is very difficult to determine whether a movie contains interesting scenes or not. This research aims to provide information in order to help a user to choose a movie. Concretely, this paper proposes a method for labeling scenes in a movie using a video hosting service called "Nico Nico Douga". The proposed method extracts important scenes in a movie from "Nico Nico Douga" based on the statistics of social annotations attached to them. Also, using the characteristics of folksonomy the authors extract feature words for labeling. Moreover, in order to take advantage of the feature words, the authors estimate their semantic categories. We use the attached comments themselves to label the important scenes. In order to select the comments, the authors take into account the importance of the feature words with semantic categories in a scene. Finally, the authors carry out experiments to evaluate the proposed method and to discuss future works. © 2012 IEEE.

DOI： 10.1109/WI-IAT.2012.178

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Self-Adaptive systems, which enable runtime adaptation, are promising ways of dealing with environmental changes, including system intrusions or faults. Such software systems must modify themselves to better fit their environment. One of the main approaches to constructing such systems is to introduce multiple control loops. Software evolution is an essential activity for expanding this adaptation capability, and dynamic evolution has been envisaged as a way of systems adapting themselves at runtime. In this paper, we establish a development process to deal with dynamic evolution. We devise a goal model compiler to generate models for designing dynamic evolutions and a programming framework that supports dynamic deployment of control loops. We experimentally applied our approach to a system and discuss how our compiler and framework support dynamic evolution of self-Adaptive systems. © 2012 IEEE.

DOI： 10.1109/SASO.2012.17

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IOS PRESS  

In the upstream software development processes, from requirements definition to design, one of the most important tasks is to make the requirements completely satisfied in the design process, therefore actually realizing the required system. Thus, a seamless connection between the requirements model and the design model is very effective to completely realize user requirements. KAOS [1] is one of the typical methodologies of Goal-oriented requirements engineering [2]. It elicits and builds up the requirements systematically and exhaustively. ICONIX process [3] designs a system using UML diagrams. In the ICONIX process, requirements are reviewed using use case models, and then designed with class and sequence diagrams to realize the use cases through robustness diagrams. Based on these methodologies, this paper presents an approach to transfer as much information as possible from KAOS requirements models to preliminary design of system behaviors in ICONIX. Our approach allows the use case models and robustness diagrams to reflect the requirements of the KAOS model with the refinement patterns. We also conducted a case study where flight reservations in an international airline were modeled for the requirements definition and the preliminary design. We could find every requirements defined by the KAOS model in the use case models and the robustness diagrams. Our approach was confirmed to be feasible through this case study.

DOI： 10.3233/978-1-61499-094-9-171

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Self-adaptive systems have recently been receiving much attention because of their ability to cope with the changes of environment, failures, and unanticipated events. These systems need an adaptation mechanism, which automatically computes the possible configurations, and decides the most appropriate configuration to fit the environment. In particular, the satisfaction of non-functional requirements must be considered when selecting the best reconfiguration. However, there are trade-off problems among non-functional requirements. Moreover, the adaptation mechanisms are typically developed separately from the components to be implemented, and it complicates the construction of such systems. We propose (1) a feature-oriented analysis technique, which can identify adaptation points, and calculate the contribution to non-functional goals of the configuration
(2) a component specification model, which extends an architectural description language for self-adaptation
(3) a reconfiguration framework aimed to reduce the complexity of the reconfiguration and generate the best configuration at run-time. We evaluate the feasibility of our framework by four different scenarios, and show that our framework reduces the complexity of the reconfiguration, and solves the trade-off problem among non-functional requirements. © 2012 ACM.

DOI： 10.1145/2245276.2231956

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Consistency between various phases of the software development process is an important aspect in software engineering. Without this aspect, software products may not satisfy users' needs. The cause of the inconsistency is that users' requirements may not be sufficiently reflected in software products. We consider this situation as a gap between the requirements and the products. We focus on the early phases of the software development, because we need to deal with the problem before the inconsistency in the early phases affects the later phases. KAOS has been attracting attentions and UML has been widely adopted, in the early phases, for requirements analysis and design respectively. However, the requirements analysis phase and the design phase are often practiced separately which may cause a gap between them. In this paper, we propose a systematic approach, to reduce the gap between the requirement analysis phase and the design phase, by generating UML class diagram and OCL constraints from the KAOS model. We propose transformation rules between operation models and class diagrams and rules for producing OCL constraints from the KAOS model. In addition, we carried out a case study to confirm the validity of this approach. © 2012 ACM.

DOI： 10.1145/2245276.2231940

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

近年,政策やサービスなどの評判を調査するためにアンケート形式による調査が増加しているが,回収率が低落傾向にあることや,人的コストが増加するなどの問題が生じている.一方,Web上にはユーザの意見を含む評価情報が多数存在している.そこで本研究では,評判傾向予測システムの構築を目的として評判傾向の時間的変化とその原因をマイクロブログから抽出する評判傾向抽出エージェントの実現を目指す.特に本論文では,評判傾向の抽出と評判傾向が変化した原因の抽出に注力する.評価情報の感情を抽出するセンチメント分析に着目し,回帰式から評判傾向の変化点を抽出した後に,変化点におけるトピックをチャンキングにより抽出する手法を提案する.本手法は,従来の評価判定法であるp/n判定にセンチメント分析を組み合わせることで,p/n判定単体よりも人手による調査と相関の高い時系列変化を抽出できる点が特徴であり,政治及びテレビドラマに関するコンテンツを対象に実際の支持率,視聴率に対する評価実験を実施した結果,政治(自由度調整済決定係数R'^2(p/n判定単体:0.22,提案手法:0.60)),テレビドラマ(自由度調整済決定係数R'^2(p/n判定単体:0.26,提案手法:0.56))ともに相関の高い時系列変化を抽出できることが確認できた.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

近年増加したコンテンツ投稿型SNSでは日々膨大にコンテンツが増え続けるため,嗜好には合っているもののユーザが見逃してしまうようなコンテンツは少なくない.また,多くの推薦技術では精度を重視するあまり,その推薦結果に面白みがないという課題がある.本論文では,主に音楽,イラスト,詩等の創作者向けであるコンテンツ投稿型SNSにおける未知性,意外性を考慮した推薦手法について述べる.未知性に関しては,質の高いコンテンツを投稿する投稿者(有力投稿者)に注目し,コンテンツの質を確保しつつもロングテールのテール部分に属する,ユーザがまだ知らないコンテンツを推薦する.意外性に関しては,多くのコンテンツ投稿型SNSで利用されているFolksonomyを利用する.以上の二つの推薦部からなる推薦エージェントを提案し,イラスト投稿型SNSであるPixivの実データを用い,未知性,意外性に関する評価実験を実施した.その結果,推薦リストの6割に未知性,意外性のあるコンテンツが含まれ,本研究の有効性が確かめられた.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

近年,食や環境への意識の高まりから野菜作りやインテリアグリーンに関心が集まっている.しかし,都市の限られた環境で緑を育てるのは容易ではなく,その環境に適した植物を選択するには専門的な知識が必要ということもあり,不用意に繁茂させたり,逆に枯らしてしまうケースも多い.また,インテリア/エクステリアとしては周辺環境との調和が気になるが,成長時の生い茂った姿を想像するのは素人には難しい.そこで本論文では,携帯電話のセンサを用いて,植裁スペースの環境(日照,温度,気温等)に適した植物を推薦するエージェントシステムの開発について述べる.また,本システムでは,推薦した植物の成長した姿を3DCGで表示するという拡張現実手法を用いて,周辺の景観とマッチするかどうかを視覚的に確認することもできる.これにより,植物や園芸に関する特別な知識がなくとも,環境に適しており,かつ周辺の景観との調和のとれた植物を選ぶことが可能となる.今回の実験では約70%の精度で適した植物を推薦できることを確認できた.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

本論文では,閲覧中のWeb上のニュース記事に対する意見を個人のブログから収集し,その本文中の主張部分を抽出して提示するシステムの提案を行う.現在ニュースサイトにコメント欄が用意されているところは少なく,検索エンジンを用いても個人の意見のみを収集するのは容易ではない.そこで個人の意見を述べやすい場であるブログに着目してニュース記事に関連した意見を集め,主張を抽出する.本研究では主張とは意見の中で筆者が強く述べている主観的な部分を指す.開発中の主張提示システムの中で,本論文では主張抽出に焦点を当てる.主張抽出には人手により主張であるとされた文章から形態素解析を利用して特徴的な抽出ルールを設定した.本システムによりユーザはニュースサイトを閲覧すると同時に意見の多角的な見方が可能になり,より深い洞察が得られるようになる.評価実験において人手による正解との適合率を求めたところ70.0%となった.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

e-Commerceの急速な発展を背景に,Web検索結果への検索連動型広告(スポンサーリンクなど)が広告配信手段として注目されている.しかし,ユーザの検索意図と異なる広告の配信は,長期的に見てユーザの不快感を招き,逆効果となるリスクがある.そこで,ユーザの検索行動から検索の目的を推測し,適切な情報を提供することが重要となってきている.これまでも検索結果に対するユーザのブラウザ側の操作(インタラクション)に注目した研究は行われているが,一連のインタラクションの前後関係を考慮した研究は行われていない.そこで,本研究では商品検索結果に対するユーザのインタラクションシーケンスに着目し,検索の目的を購入目的か,情報収集目的かに分類するエージェントを提案する.実験により,先行手法と提案手法を組み合わせることにより,商品検索目的の抽出精度を10%以上向上できることを確認した.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）   出版者・発行元：一般社団法人電子情報通信学会  

インターネットの普及に伴い,Web上には商品やサービス(対象物)に対する多くの評判情報が蓄積されている.しかし,誰でも発信できるが故に,情報は膨大となり,それら全てに目を通すことは利用者にとって多大な負担となる.そのような背景から,レビューから意見を自動的に抽出する研究が盛んに行われており,意見を<対象物,評価視点(属性),評価値>の三つ組と捉え抽出する研究も行われている.しかしながら多くの研究は,評価視点や評価値の抽出に辞書を用いており,ジャンルごとに必要となる辞書の構築のためのコストは小さいとはいえない.また,単に辞書を用いてマッチングを行っただけでは,精度が上がらないのが現状である.そこで本論文では,教師あり学習を用いて,レビューサイトから意見を抽出する手法を提案する.提案手法は,従来の手法のように大規模な辞書をあらかじめ用意する必要がないため,コストを大幅に抑えることが可能である.実験の結果,辞書をあらかじめ用意しない既存手法と比較して,最大で適合率は約26%,再現率は約47%向上した.また,既存研究では個別の辞書を必要とするような他ジャンルに対して本手法を適用した結果,ほぼ変わらない精度で抽出することができ,他ジャンルへの適用の可能性を示すことができた.

CiNii Article

CiNii Books

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1527/tjsai.26.1

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

Self-adaptive systems have recently attracted attention because of their ability to cope with changing environments, including system intrusions or faults. Such software must modify itself to better fit its environment, and one of the approaches by which we expect this capability to be achieved is the introduction of multiple control loops to assess the situation and to determine whether a change in behaviors or configurations is necessary and how to implement the change. Development of such systems with multiple control loops complicates the task of identifying components, and could be greatly aided by appropriate tool support. In this paper, we propose an architectural compiler for self-adaptive systems, which generates architectural configurations from the goal-oriented requirements descriptions. We also present a framework for generating such configurations with this compiler and a pattern in the requirements description. We evaluate the framework experimentally and show that it helps to generate suitable configurations that have high performance, and that the compiler scales well to large input models. © 2011 ACM.

DOI： 10.1145/1988008.1988015

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1527/tjsai.26.166

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

The purpose of this study is to reduce the difficulties encountered when designing multi-agent systems (MAS). Although MAS are one of the more effective approaches for dealing with the recent increase in software complexity, they are themselves difficult to develop. We believe the difficulties in determining agent responsibilities and the organizational structure as the most significant obstacles to MAS development. In this paper, we propose a design framework for MAS, which includes restriction rules in the goal-oriented requirements description and a generator that transforms the restricted requirements description into a general MAS design model. We demonstrate the effectiveness of our framework through a case study and show how the framework can be used to construct MAS design models more precisely than conventional methods permit. © 2011 ACM.

DOI： 10.1145/1982185.1982491

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1527/tjsai.26.116

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1527/tjsai.26.107

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

During the massive Tohoku earthquake, while landlines and mobile phone lines got stuck, Twitter were used to exchange information about evacuation. On 11 March, the number of tweets from Japan dramatically increased to about 33 million, 1.8 times higher than the average figure. However, since texts on Twitter are unstructured data, are more complex than other text media, it is difficult to find a suitable evacuation center. Not only information in Twitter, people but also need to combine other information such as map information, shop information to find the suitable evacuation center. Since it takes much time to do these tasks, these manual processing are not suitable in the emergency status. Therefore, we need an approach to help computers to understand the meaning of evacuation, and to provide the most suitable evacuation center based on earthquake victims' behaviors in real-time. In this paper, we firstly design an earthquake evacuation ontology. Secondly, we indicate that by using this ontology, computers can provide the most suitable evacuation center based on earthquake victims' behaviors in real-time. © 2011 IEEE.

DOI： 10.1109/GRC.2011.6122613

Scopus

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

学生奨励賞受賞: 田中俊行

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

ベストポスター賞受賞

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：日本語   掲載種別：研究論文（その他学術会議資料等）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：ACM  

In the web research, ontologies are widely used these days. However, several difficulties in ontology building have been pointed out so far and its costs are raising problems currently. In this paper, we propose ONTOMO that enables Internet users to take part in building ontologies as a part of collective intelligence. After introducing an overview of ONTOMO, an instance and property recommendation mechanism based on the editing history of multiple users will be presented together with experimental evaluations. © 2010 ACM.

DOI： 10.1145/1774088.1774395

Scopus

researchmap

その他リンク： http://dblp.uni-trier.de/db/conf/sac/sac2010.html#conf/sac/ShinKNNTO10

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

In this paper, we define an activity by five basic attributes: actor, action, object, time and location. The goal of this paper is to describe a method to automatically extract all attributes in each sentence retrieved from Japanese weblogs. Previous work had some limitations, such as high setup cost, inability of extracting all attributes, limitation on the types of sentences that can be handled, and insufficient consideration of interdependency among attributes. To resolve these problems, this paper proposes a novel approach that uses conditional random fields and self-supervised learning. This approach treats the activity extraction as a sequence labeling problem, and has advantages such as domain-independence, scalability, and does not require any hand-tagged data. Since it is unnecessary to fix the positions and the number of the attributes in activity sentences, this approach can extract all attributes by making only a single pass over its corpus. Additionally, by converting to simpler sentences, the proposed approach can deal with complex sentences retrieved from Japanese weblogs. In an experiment, this approach achieves high precision (activity: 88.87%, attributes: over 90%). © 2010 IEEE.

DOI： 10.1109/ICIS.2010.44

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER-VERLAG BERLIN  

As there are increasing needs to view a huge number of videos on the Web in short time, the video summary technology is actively investigated. However, there exists trade-offs of costs and precision of summaries. In this paper, we propose a system called NicoScene to search desirable scenes from the videos provided in a video hosting service called Nico Nico Douga. We use the feature of the service in which we can attach comments to videos and treat the comments as social annotation. By some experiments, we demonstrate the advantages of NicoScene in particular the search precisions.

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SCITEPRESS  

The goal of this paper is to describe a method to automatically extract all basic attributes namely actor, action, object, time and location which belong to an activity, and the relationships (transition and cause) between activities in each sentence retrieved from Japanese CGM (consumer generated media). Previous work had some limitations, such as high setup cost, inability of extracting all attributes, limitation on the types of sentences that can be handled, insufficient consideration of interdependency among attributes, and inability of extracting causes between activities. To resolve these problems, this paper proposes a novel approach that treats the activity extraction as a sequence labeling problem, and automatically makes its own training data. This approach has advantages such as domain-independence, scalability, and unnecessary hand-tagged data. Since it is unnecessary to fix the positions and the number of the attributes in activity sentences, this approach can extract all attributes and relationships between activities by making only a single pass over its corpus. Additionally, by converting to simpler sentences, removing stop words, utilizing html tags, google map api, and wikipedia, the proposed approach can deal with complex sentences retrieved from Japanese CGM.

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER-VERLAG BERLIN  

The goal of this paper is to describe a method to automatically extract all basic attributes namely actor, action, object, time and location which belong to an activity, and the transition between activities in each sentence retrieved from Japanese CGM (consumer generated media). Previous work had some limitations, such as high setup cost, inability of extracting all attributes, limitation on the types of sentences that can be handled, and insufficient consideration of interdependency among attributes. To resolve these problems, this paper Proposes a novel approach that treats the activity extraction as a sequence labeling problem, and automatically makes its own training data. This approach has advantages such as domain-independence, scalability, and unnecessary hand-tagged data. Since it is unnecessary to fix the positions and the number of the attributes in activity sentences, this approach can extract all attributes and transitions between activities by making only a single pass over its corpus.

Web of Science

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

In the web research, ontologies are widely used these days. However, several difficulties in ontology building have been pointed out so far and its costs are raising problems currently. In this paper, we propose ONTOMO that enables Internet users to take part in building ontologies as a part of collective intelligence. After introducing an overview of ONTOMO, an instance and property recommendation mechanism based on the editing history of multiple users will be presented together with experimental evaluations. © 2010 ACM.

DOI： 10.1145/1774088.1774395

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：SPRINGER-VERLAG BERLIN  

Agent platforms have recently attracted attention for use as a basis for self-* systems development because it provides a mechanism for autonomous functionalities. From among these platforms, JADE allows developers to describe concurrent behaviors on it, and this can be a foundation of constructing the multi-processes on self-* systems. This paper shows an overview of our approach for implementing highly collaborative behaviors by introducing a component style behavior model and its life cycle on the basis of the agent platform.