Presentation | 2020-03-04 Classification of caretaker's trajectory: A time-series classifier approach Yui Ichikawa, Daisuke Ichimura, Rie Asada, Tadashi Yamazaki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Along with the aging population, Japanese caretaking industry is facing a severe labor shortage. Utilizing data could improve the efficiency of caretakers’ daily work and thus be one of the solutions for this problem. In this paper, we analyzed caretakers’ trajectory data, aiming to reduce recording times and human error, and tried estimating the caretakers’ actions. We applied two models, a model using conventional Hidden Markov Models (HMMs) and Recurrent Neural Networks (RNN), especially Long Short-Term Memory (LSTM), which recently have gathered attention due to their high performance regarding sequence prediction tasks. Our human trajectory classifying task, focusing on the two most important cares, feeding and excretion care, revealed that LSTM prevailed over HMM by achieving 91.6% estimating correctly, while the model using HMMs estimated 74.4% correctly. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Elderly care / Human trajectory / LSTM / HMM / Classification / Time series analysis / RNN |
Paper # | NC2019-78 |
Date of Issue | 2020-02-26 (NC) |
Conference Information | |
Committee | NC / MBE |
---|---|
Conference Date | 2020/3/4(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | University of Electro Communications |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Neuro Computing, Medical Engineering, etc. |
Chair | Hayaru Shouno(UEC) / Taishin Nomura(Osaka Univ.) |
Vice Chair | Kazuyuki Samejima(Tamagawa Univ) / Takashi Watanabe(Tohoku Univ.) |
Secretary | Kazuyuki Samejima(NAIST) / Takashi Watanabe(NTT) |
Assistant | Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Yasuyuki Suzuki(Osaka Univ.) / Akihiro Karashima(Tohoku Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Classification of caretaker's trajectory: A time-series classifier approach |
Sub Title (in English) | |
Keyword(1) | Elderly care |
Keyword(2) | Human trajectory |
Keyword(3) | LSTM |
Keyword(4) | HMM |
Keyword(5) | Classification |
Keyword(6) | Time series analysis |
Keyword(7) | RNN |
Keyword(8) | |
1st Author's Name | Yui Ichikawa |
1st Author's Affiliation | The University of Electro-Communications(UEC) |
2nd Author's Name | Daisuke Ichimura |
2nd Author's Affiliation | The University of Electro-Communications/Oouchi Hospital(UEC/Oouchi Hosp.) |
3rd Author's Name | Rie Asada |
3rd Author's Affiliation | The University of Electro-Communications(UEC) |
4th Author's Name | Tadashi Yamazaki |
4th Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2020-03-04 |
Paper # | NC2019-78 |
Volume (vol) | vol.119 |
Number (no) | NC-453 |
Page | pp.pp.15-20(NC), |
#Pages | 6 |
Date of Issue | 2020-02-26 (NC) |