Presentation 2020-03-05
FMCW Radar-based Anomaly Detection in Toilet by Spectrogram Analysis with LSTM
Takabatake Wataru, Mondher Bouazizi, Kohei Yamamoto, Tomoaki Ohtsuki, Yohei Shibata, Atushi Nagate,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With the increase in the population of elderly, elderly monitoring techniques are receiving more andmore attention all over the world. In particular, it is highly demanded to develop the system that detects accidents in a toilet, since such accidents are likely to get worse due to late detection. In this report, we propose an FMCW(Frequency Modulated Continuous Wave) radar-based anomaly detection method in toilet. In the proposed method, at rst, time-series data of the statistics such as mean, standard deviation, skewness, and kurtosis for each time and power changes for each distance. The data for about 9 seconds are classi ed into a faint or a non-faint by LSTM (Long Short Term Memory). LSTM, the one of the deep learning methods needs more data and more variousdata. Though, collecting the data is not easy. Thus, we make new data from the existing data by GAN(Generative Adversarial Network). In the experiments, we observed 4 fainting behaviors: (i) stooping on the seat, (ii) leaning on the backrest, (iii) leaning on the sidewall on the seat, and (iv) lying on the floor after the fall. Also we observed the following normal behaviors such as sitting still after the button operation and sitting down. We conducted the experiments with 13 people. As a result, we con rmed that our proposed method detected the fainting behaviors with the Accuray of 0.83.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) FMCW radar / Anomaly detection / Toilet
Paper # RCS2019-351
Date of Issue 2020-02-26 (RCS)

Conference Information
Committee RCS / SR / SRW
Conference Date 2020/3/4(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Tokyo Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Mobile Communication Workshop
Chair Tomoaki Otsuki(Keio Univ.) / Masayuki Ariyoshi(NEC) / Satoshi Denno(Okayama Univ.)
Vice Chair Satoshi Suyama(NTT DoCoMo) / Fumiaki Maehara(Waseda Univ.) / Toshihiko Nishimura(Hokkaido Univ.) / Suguru Kameda(Tohoku Univ.) / Osamu Takyu(Shinshu Univ.) / Kentaro Ishidu(NICT) / Keiichi Mizutani(Kyoto Univ.)
Secretary Satoshi Suyama(NTT) / Fumiaki Maehara(Kyushu Univ.) / Toshihiko Nishimura(ATR) / Suguru Kameda(Univ. of Electro-Comm.) / Osamu Takyu(Mie Univ.) / Kentaro Ishidu(Tokyo Inst. of Tech.) / Keiichi Mizutani(Anritsu)
Assistant Kazushi Muraoka(NEC) / Shinsuke Ibi(Doshisha Univ.) / Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Mai Ohta(Fukuoka Univ.) / Teppei Oyama(Fujitsu Lab.) / Kentaro Kobayashi(Nagoya Univ.) / Masaaki Fuse(Anritsu) / Tomoki Murakami(NTT)

Paper Information
Registration To Technical Committee on Radio Communication Systems / Technical Committee on Smart Radio / Technical Committee on Short Range Wireless Communications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) FMCW Radar-based Anomaly Detection in Toilet by Spectrogram Analysis with LSTM
Sub Title (in English)
Keyword(1) FMCW radar
Keyword(2) Anomaly detection
Keyword(3) Toilet
1st Author's Name Takabatake Wataru
1st Author's Affiliation Keio University(Keio Univ.)
2nd Author's Name Mondher Bouazizi
2nd Author's Affiliation Keio University(Keio Univ.)
3rd Author's Name Kohei Yamamoto
3rd Author's Affiliation Keio University(Keio Univ.)
4th Author's Name Tomoaki Ohtsuki
4th Author's Affiliation Keio University(Keio Univ.)
5th Author's Name Yohei Shibata
5th Author's Affiliation ()
6th Author's Name Atushi Nagate
6th Author's Affiliation ()
Date 2020-03-05
Paper # RCS2019-351
Volume (vol) vol.119
Number (no) RCS-448
Page pp.pp.165-170(RCS),
#Pages 6
Date of Issue 2020-02-26 (RCS)