Presentation | 2020-01-31 Proposal and Initial Evaluation of Refrigerator Door Identification Method Using Door Opening and Closing Sound Yudai Mitsukude, Kenta Hayashi, Shigemi Ishida, Yutaka Arakawa, Akira Fukuda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In recent years, the development of sensing technology has enabled sensing in various situations.IoT products have been developed one after another, and users can easily obtain information associated with their actions.The conventional method of attaching sensors to users and the method of using a camera in the recognition of daily activities has a problem that the user's mental burden is large.There is also a problem that it is expensive to introduce a dedicated device or product.In this paper, for the purpose of sensing eating habits,we propose an open / close door identification method using a microphone on a tablet terminal installed on the refrigerator door.Depending on the size of the door, packing, and rail types, each door shows different sound characteristics when opening / closing the door.Therefore, the door opening / closing is identified by analyzing the data when the door is opened / closed.Discrimination is performed by machine learning using features extracted from the data obtained from the microphone on the tablet terminal.We conducted experiments with four subjects.The experiment result demonstrated that our identification method successfully identifies doors with an average accuracy of 0.95. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | activity recognition / refrigerator / door / voice analysis |
Paper # | SeMI2019-115 |
Date of Issue | 2020-01-23 (SeMI) |
Conference Information | |
Committee | SeMI |
---|---|
Conference Date | 2020/1/30(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Susumu Ishihara(Shizuoka Univ.) |
Vice Chair | Kazuya Monden(Hitachi) / Koji Yamamoto(Kyoto Univ.) |
Secretary | Kazuya Monden(Kyoto Univ.) / Koji Yamamoto(NTT DOCOMO) |
Assistant | Akira Uchiyama(Osaka Univ.) / Kenji Kanai(Waseda Univ.) / Masafumi Hashimoto(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Sensor Network and Mobile Intelligence |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Proposal and Initial Evaluation of Refrigerator Door Identification Method Using Door Opening and Closing Sound |
Sub Title (in English) | |
Keyword(1) | activity recognition |
Keyword(2) | refrigerator |
Keyword(3) | door |
Keyword(4) | voice analysis |
1st Author's Name | Yudai Mitsukude |
1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
2nd Author's Name | Kenta Hayashi |
2nd Author's Affiliation | Kyushu University(Kyushu Univ.) |
3rd Author's Name | Shigemi Ishida |
3rd Author's Affiliation | Kyushu University(Kyushu Univ.) |
4th Author's Name | Yutaka Arakawa |
4th Author's Affiliation | Kyushu University(Kyushu Univ.) |
5th Author's Name | Akira Fukuda |
5th Author's Affiliation | Kyushu University(Kyushu Univ.) |
Date | 2020-01-31 |
Paper # | SeMI2019-115 |
Volume (vol) | vol.119 |
Number (no) | SeMI-406 |
Page | pp.pp.63-68(SeMI), |
#Pages | 6 |
Date of Issue | 2020-01-23 (SeMI) |