Presentation | 2018-01-19 Evaluation of Methods for Detecting Change of Indoor Walking Patterns Using Sparse Position Information Kazuki Takagi, Ryoichi Shinkuma, Hideyuki shimizu, Hisashi Sakamoto, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, the Internet-of-Things (IoT) technology has been attracting a lot of attention as a solution that detects health risk.Using cameras or wearable devices is a typical approach to track people’s behaviors in their house.However,these devices have drawbacks: people feel uncomfortable from the privacy aspect if they are always watched by cameras; people feel annoyed if they are required to always carry wearable devices.Therefore, vibration sensors or human sensors could be more appropriate for behavior monitoring in a indoor private environment like houses though they might be able to collect discrete and sparse data.The authors previously proposed a method that detects changes in behavior patterns of elderly people who live alone by using sparse position information from sensors.Our method successfully models usual behavior patters by representing movement patterns between multiple sensors of people as a network graph.Then, our method detects changes in people’s behaviors by scoring the similarity of network graphs between the measured behavior pattern and the usual behavior patters. This report shows how the performance of detection by our method varies with the density f placement of sensors. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Anomaly Detection / Elderly Care / Position Tracking / Network Graph |
Paper # | MoNA2017-59 |
Date of Issue | 2018-01-11 (MoNA) |
Conference Information | |
Committee | MoNA |
---|---|
Conference Date | 2018/1/18(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Campus Plaza Kyoto |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Mobile Network, Application of Machine Learning, Mobile Data, etc. |
Chair | Ryoichi Shinkuma(Kyoto Univ.) |
Vice Chair | Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.) |
Secretary | Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NTT) |
Assistant | Takayuki Nishio(Kyoto Univ.) / Takato Saito(NTT) |
Paper Information | |
Registration To | Technical Committee on Mobile Network and Applications |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Evaluation of Methods for Detecting Change of Indoor Walking Patterns Using Sparse Position Information |
Sub Title (in English) | |
Keyword(1) | Anomaly Detection |
Keyword(2) | Elderly Care |
Keyword(3) | Position Tracking |
Keyword(4) | Network Graph |
1st Author's Name | Kazuki Takagi |
1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
2nd Author's Name | Ryoichi Shinkuma |
2nd Author's Affiliation | Kyoto University(Kyoto Univ.) |
3rd Author's Name | Hideyuki shimizu |
3rd Author's Affiliation | NEC Solution Innovators, Ltd.(NEC Solution Innovators) |
4th Author's Name | Hisashi Sakamoto |
4th Author's Affiliation | NEC Solution Innovators, Ltd.(NEC Solution Innovators) |
Date | 2018-01-19 |
Paper # | MoNA2017-59 |
Volume (vol) | vol.117 |
Number (no) | MoNA-390 |
Page | pp.pp.99-102(MoNA), |
#Pages | 4 |
Date of Issue | 2018-01-11 (MoNA) |