Presentation 2016-02-29
Continuous Activity Recognition Using Array Sensor
Yusuke Hino, Jihoon Hong, Tomoaki Ohtsuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Nowadays, the population of elderly who live alone is increasing in Japan. It is needful to recognize the activity of them to know when some accidents happen. Some sensors are available to monitor those persons' activities such as accelerometer and camera. However, these systems have some limitations that those sensors might cause physical burden and invasion of privacy. Therefore, we are using a sensor called array sensor. Array sensor is a sensor that has multiple antennas, and it can measure the change of the radio wave propagation of the interest. The advantage of this sensor is that it has a wide range and it would not invade privacy. In our previous work, we have proposed a method to recognize activity by using an array sensor. In the conventional method, it can only detect when the activity starts and ends by stillness. However, most of the activity in real life is continuous activities (ex. People may fall after walk without standing still). In this paper, we propose a continuous activity recognition using array sensor. We detect the person's activity (fall, walk, sit, and stand still) by analyzing the information of radio wave propagation. To improve the recognition accuracy, we set thresholds for the continuous number of each activity, and correct the result which continues less than the threshold.Also, we use the state transition of the activity, and correct the activity transition which is impossible. To recognize continuous activities, we switch several training models used in support vector machine (SVM).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sensor / array sensor / activity recognition
Paper # ASN2015-99
Date of Issue 2016-02-22 (ASN)

Conference Information
Committee ASN / MoNA / IPSJ-MBL / IPSJ-UBI
Conference Date 2016/2/29(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Tokyo University of Science
Topics (in Japanese) (See Japanese page)
Topics (in English) Ambient Intelligence, Sensor Networks, Mobile Networks, Mobile Applications, Field Sensing, etc.
Chair Hiroshi Tohjo(NTT) / Hiroaki Morino(Shibaura Inst. of Tech.) / Hiroshi Inamura(NTTドコモ) / Kazushige Ouchi(東芝)
Vice Chair Hiroo Sekiya(Chiba Univ.) / Hiraku Okada(Nagoya Univ.) / Kiyohito Yoshihara(KDDI R&D Labs.) / Ryoichi Shinkuma(Kyoto Univ.)
Secretary Hiroo Sekiya(Kanagawa Inst. of Tech.) / Hiraku Okada(NTT) / Kiyohito Yoshihara(KDDI R&D Labs.) / Ryoichi Shinkuma(Kumamoto Univ.) / (NTTドコモ) / (KDDI研究所)
Assistant Yuichi Igarashi(Hitachi) / Katsuhiro Naito(Aichi Inst. of Tech.) / Kiyohiko Hattori(NICT) / Hiroshi Fujita(Fujitsu Labs.) / Takuro Yonezawa(Keio Univ.) / Yoshifumi Morihiro(NTT DoCoMo) / Hisashi Kurasawa(NTT) / Makoto Suzuki(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Ambient intelligence and Sensor Networks / Technical Committee on Mobile Network and Applications / Special Interest Group on Mobile Computing and Pervasive Systems / Special Interest Group on Ubiquitous Computing System
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Continuous Activity Recognition Using Array Sensor
Sub Title (in English)
Keyword(1) sensor
Keyword(2) array sensor
Keyword(3) activity recognition
1st Author's Name Yusuke Hino
1st Author's Affiliation Keio University(Keio Univ.)
2nd Author's Name Jihoon Hong
2nd Author's Affiliation Keio University(Keio Univ.)
3rd Author's Name Tomoaki Ohtsuki
3rd Author's Affiliation Keio University(Keio Univ.)
Date 2016-02-29
Paper # ASN2015-99
Volume (vol) vol.115
Number (no) ASN-467
Page pp.pp.13-18(ASN),
#Pages 6
Date of Issue 2016-02-22 (ASN)