Faculty Profiles - KAWAGUCHI, Nobuo

Papers - KAWAGUCHI, Nobuo

Division display 221 - 240 of about 548 ／ All the affair displays >>

Origin and activity of NPO location information service research agency

Kawaguchi N.

Journal of the Institute of Electronics, Information and Communication Engineers Vol. 97 ( 6 ) page： 488 - 492 2014.6

距離画像による空間情報マッチングに基づくマーカレスARシステムの設計と実装 Reviewed

山川健司，梶克彦，河口信夫

情報処理学会論文誌（コンシューマ・デバイス＆システム研究会トランザクション，CDS9) Vol. 4 ( 1 ) page： 1-10 2014.4

HASC-IPSC : 屋内歩行センシングコーパス (モバイルネットワークとアプリケーション)

梶克彦, 渡辺穂高, 坂涼司, 河口信夫

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 Vol. 113 ( 495 ) page： 69-76 2014.3

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

近年モバイルコンピューティング分野で盛んな研究テーマとして,屋内位置推定や建物構造の自動推定が挙げられる.しかし,現在までにこれらの研究で共通して利用可能なデータが存在せず,新たな手法を提案しても,既存研究との精度の比較検討が困難であった.我々は,屋内位置推定研究と建物構造推定研究を主なターゲットとした,屋内歩行センシングコーパス(GASC-IPSC)を構築した.被験者はスマートフォンを装着して建物内の様々な経路を移動する.スマートフォンに記録された加速度等のセンサデータに対して,右左折や階段昇降といった詳細な行動ラベルが人手で付与されている.また各歩行移動データには,スタート地点を原点とした1秒ごとの3次元座標の正解データも用意されている.このデータを利用して,各研究で提案された歩行者デッドレコニング手法の精度を検証可能である.また建物全体の歩行空間ネットワーク構造の正解データが用意されており,複数の歩行センシングデータを統合して建物構造を自動推定する研究のリファレンスデータとして利用できる.

HASC-IPSC: 屋内歩行センシングコーパス

梶克彦 , 渡辺穂高 , 坂涼司 , 河口信夫

情報処理学会研究報告. MBL, [モバイルコンピューティングとユビキタス通信研究会研究報告] Vol. 2014 ( 41 ) page： 1-8 2014.3

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

近年モバイルコンピューティング分野で盛んな研究テーマとして,屋内位置推定や建物構造の自動推定が挙げられる.しかし,現在までにこれらの研究で共通して利用可能なデータが存在せず,新たな手法を提案しても,既存研究との精度の比較検討が困難であった.我々は,屋内位置推定研究と建物構造推定研究を主なターゲットとした,屋内歩行センシングコーパス (HASC-IPSC) を構築した.被験者はスマートフォンを装着して建物内の様々な経路を移動する.スマートフォンに記録された加速度等のセンサデータに対して,右左折や階段昇降といった詳細な行動ラベルが人手で付与されている.また各歩行移動データには,スタート地点を原点とした 1 秒ごとの 3 次元座標の正解データも用意されている.このデータを利用して,各研究で提案された歩行者デッドレコニング手法の精度を検証可能である.また建物全体の歩行空間ネットワーク構造の正解データが用意されており,複数の歩行センシングデータを統合して建物構造を自動推定する研究のリファレンスデータとして利用できる.

HASC-IPSC: 屋内歩行センシングコーパス

梶克彦 , 渡辺穂高 , 坂涼司 , 河口信夫

情報処理学会研究報告. UBI, [ユビキタスコンピューティングシステム] Vol. 2014 ( 41 ) page： 1 - 8 2014.3

Publishing type：Research paper (scientific journal) Publisher：一般社団法人情報処理学会

近年モバイルコンピューティング分野で盛んな研究テーマとして,屋内位置推定や建物構造の自動推定が挙げられる.しかし,現在までにこれらの研究で共通して利用可能なデータが存在せず,新たな手法を提案しても,既存研究との精度の比較検討が困難であった.我々は,屋内位置推定研究と建物構造推定研究を主なターゲットとした,屋内歩行センシングコーパス (HASC-IPSC) を構築した.被験者はスマートフォンを装着して建物内の様々な経路を移動する.スマートフォンに記録された加速度等のセンサデータに対して,右左折や階段昇降といった詳細な行動ラベルが人手で付与されている.また各歩行移動データには,スタート地点を原点とした 1 秒ごとの 3 次元座標の正解データも用意されている.このデータを利用して,各研究で提案された歩行者デッドレコニング手法の精度を検証可能である.また建物全体の歩行空間ネットワーク構造の正解データが用意されており,複数の歩行センシングデータを統合して建物構造を自動推定する研究のリファレンスデータとして利用できる.

BI-7 Big Data for Ambient Intelligence and Sensor Networks

OHASHI Masayoshi, KAWAGUCHI Nobuo, KOHTAKE Naohiko, UEDA Naonori

Proceedings of the IEICE General Conference Vol. 2014 ( 2 ) page： "SS-71" 2014.3

An Indoor Positioning Method Integrating Pedestrian Dead Reckoning with Magnetic Filed and WiFi Map

BAN Ryoji, KAJI Katsuhiko, KAWAGUCHI Nobuo

IEICE technical report. ASN, Ambient intelligence and sensor networks Vol. 113 ( 399 ) page： 23-28 2014.1

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

An indoor positioning method is required for the realization of life-log, navigation and so on, because the accuracy of GPS is generally not enough in indoor environments such as commercial facilities and stations. As a indoor positioning method, pedestrian dead reckoning and using the WiFi radio waves have been studied. In this paper, we propose an indoor positioning method using residual magnetism in addition to the above described methods. Moreover, we evaluated this method in real environment and confirmed that this method can provide accurate indoor positioning with an error of mean less than 4m.

A Gate Passing Detection Method Based on WiFi Significant Point

Katsuhiko Kaji, Nobuo Kawaguchi

IPSJ Journal Vol. 55 ( 1 ) page： 366 - 377 2014.1

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

We propose a gate passing detection method based on WiFi signal strength and accelerometer of the user's smartphone. Gate such as door and elevater devides physical areas such as room and hallway. Thus, the WiFi environments of them tend to vary on a large scale. Conversely, it can be said that a gate should exist when the point that the WiFi environment varies on a large scale. We define such point "WiFi Significant Point." We propose the detection method based on WiFi distance function and estimated moving distance according to accelerometer. We evaluated the proposal method and found out that more than half part of gate passing can be detected. We also found that the existence of gates that can be estimated same gate passing with a high degree of accuracy.

researchmap

A Gate Passing Detection Method Based on WiFi Significant Point Reviewed

Vol. 55 ( 1 ) page： 366-377 2014.1

Design and Implementation of Event Information Summarization System

Liao Chenyi, Kaji Katsuhiko, Hiroi Kei, Kawaguchi Nobuo

2014 38TH ANNUAL IEEE INTERNATIONAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE WORKSHOPS (COMPSACW 2014) page： 572-577 2014

Proposal of a Platform Integrating POI Information

Ichien Shinji, Kaji Katsuhiko, Kawaguchi Nobuo

2014 SEVENTH INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND UBIQUITOUS NETWORKING (ICMU) page： 123 - 128 2014

Taxonomy of Survey Technology:—From Celestial Navigation to Indoor Localization—

KAWAGUCHI Nobuo

IEEJ Transactions on Sensors and Micromachines Vol. 134 ( 12 ) page： 832 - 835 2014

距離画像による空間情報マッチングに基づくマーカレスARシステムの設計と実装 Reviewed

山川健司, 梶克彦, 河口信夫

情報処理学会論文誌コンシューマ・デバイス＆システム（CDS） Vol. 4 ( 1 ) page： 12 - 21 2014

Privacy Protection in WiFi-based Location Estimation Reviewed

Zuotao Peng, Katsuhiko Kaji, Nobuo Kawaguchi

2014 SEVENTH INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND UBIQUITOUS NETWORKING (ICMU) page： 62 - 67 2014

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

In recent years, along with the spread of WiFi-based location estimation service, the privacy problem has been pointed out. For existing WiFi-based location estimation service, users' traces and position information can be obtained fraudulently. Personal privacy may be compromised. This research proposes an algorithm that determines the reliability of the user by considering the probability of both spatial and temporal to resolve the privacy problem in WiFi-based location estimation. Meanwhile, we are operating a portal Locky. jp on location estimation using WiFi. Based on the actual data of base stations stored in the Locky. jp database, we confirm this algorithm. As a result, the percentage of returning position for privacy invasion data and whole data (privacy invasion data is also included) are about 20% and 55% respectively. In summary, we know that this algorithm reduced the privacy invasion to about 20% in the WiFi-based location estimation system.

DOI： 10.1109/ICMU.2014.6799059

Web of Science

Scopus

researchmap

International workshop on human activity sensing corpus and its application (HASCA2014) Reviewed

Nobuo Kawaguchi, Nobuhiko Nishio, Daniel Roggen, Sozo Inoue, Susanna Pirttikangas

UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing page： 715 - 719 2014

Language：Japanese Publishing type：Research paper (international conference proceedings) Publisher：Association for Computing Machinery, Inc

Recent advancement of technology enables installations of small sized accelerometers or gyroscopes on various kinds of wearable/portable information devices. By using such wearable sensors, these devices can estimate its posture or status. However, most of current devices only utilize these sensors for simple orientation and gesture recognition. More deep understandings and recognition of human activity through these sensors will enable the next-generation human-oriented computing. To enable the real-world application by these kinds of wearable sensors, a large scale human activity sensing corpus might play an important role. Additionally, we have now a lot of high-performance mobile devices in real-world such as smart-phones. It is a great challenge to utilize such an enormous number of wearable sensors to collect a large-scale activity corpus. In recent years, there are several ongoing projects which are collecting human activities. Following on a huge success of last year's workshop, we are further planning to share these experiences of current research on human activity corpus and its applications among the researchers and the practitioners and to have a deep discussion for future of activity sensing.

DOI： 10.1145/2638728.2641314

Web of Science

Scopus

researchmap

Other Link： http://dblp.uni-trier.de/db/conf/huc/ubicomp2014ap.html#conf/huc/KawaguchiINPR14

Pedestrian dead reckoning based on human activity sensing knowledge Reviewed

Yuya Murata, Katsuhiko Kaji, Kei Hiroi, Nobuo Kawaguchi

UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing page： 797 - 806 2014

Language：Japanese Publishing type：Research paper (international conference proceedings) Publisher：Association for Computing Machinery, Inc

This research addresses improvement of the accuracy of pedestrian dead reckoning (PDR), which is one effective technique to estimate indoor positions using smartphone sensors. Even though various techniques using step lengths and their number have been previously proposed for PDR, insufficient accuracy is gotten from smartphone sensors. In this research, we define human activity sensing knowledge and propose improvements to PDR accuracy based on it. Human activity sensing knowledge consists of four kinds of information: pedestrian, environmental, activity, and terminal. Previous studies separately used these kinds of information
however, no study has systematically arranged them for use in PDR. We improved PDR accuracy by adjusting the step length in passages and on stairs and revised activity recognition error with human activity sensing knowledge. To investigate the effectiveness of that strategy, we used HASC-IPSC, which is an indoor pedestrian sensing corpus. After our investigation, activity recognition accuracy improved from 71.2% to 91.4%, and the distance estimation error was reduced from approximately 27 m to approximately 7 m using human activity sensing knowledge. Copyright 2014 ACM.

DOI： 10.1145/2638728.2641305

Web of Science

Scopus

researchmap

Other Link： http://dblp.uni-trier.de/db/conf/huc/ubicomp2014ap.html#conf/huc/MurataHKK14

Privacy Protection in WiFi-based Location Estimation

Peng Zuotao, Kaji Katsuhiko, Kawaguchi Nobuo

2014 SEVENTH INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND UBIQUITOUS NETWORKING (ICMU) page： 62 - 67 2014