Presentation | 2022-01-20 Anomaly detection based on the unity, duality and dependence of entropy Akira Imori, Shunji Maeda, Takashi Komatsu, Tetsuji Taniguchi, Osamu Toda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Monitoring with multiple sensors is important for system diagnosis, and active researches are being conducted using machine learning. However, treating multiple sensors having different units may result in the loss of information necessary for anomaly detection, and the handling and interpretation of sensor data, which do not lose information are desired in the industry. In this paper, we analyze equipment deterioration and anomalies based on the changes of information entropy. That is to say, we show that entropy, Kullback-Leibler divergence and mutual information, which are the basic concepts of information theory, are of great value for anomaly detection and diagnosis. The keywords for each role are unification, duality and dependency. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | IT2021-53,SIP2021-61,RCS2021-221 |
Date of Issue | 2022-01-13 (IT, SIP, RCS) |
Conference Information | |
Committee | RCS / SIP / IT |
---|---|
Conference Date | 2022/1/20(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Eiji Okamoto(Nagoya Inst. of Tech.) / Yukihiro Bandou(NTT) / Tadashi Wadayama(Nagoya Inst. of Tech.) |
Vice Chair | Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) / Tetsuya Kojima(Tokyo Kosen) |
Secretary | Toshihiko Nishimura(NEC) / Tomoya Tandai(Panasonic) / Fumihide Kojima(Xiaomi) / Toshihisa Tanaka(Takushoku Univ.) / Takayuki Nakachi(Tokyo Univ. Agri.&Tech.) / Tetsuya Kojima(Saitamai Univ.) |
Assistant | Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) / Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Masanori Hirotomo(Saga Univ.) |
Paper Information | |
Registration To | Technical Committee on Radio Communication Systems / Technical Committee on Signal Processing / Technical Committee on Information Theory |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Anomaly detection based on the unity, duality and dependence of entropy |
Sub Title (in English) | Usefulness of Entropy, Kullback-Leibler divergence and Mutual Information |
Keyword(1) | |
Keyword(2) | |
Keyword(3) | |
Keyword(4) | |
Keyword(5) | |
1st Author's Name | Akira Imori |
1st Author's Affiliation | Hiroshima Institute of Technology(HIT) |
2nd Author's Name | Shunji Maeda |
2nd Author's Affiliation | Hiroshima Institute of Technology/Math. Research Institute Calc for Industry(HIT/*) |
3rd Author's Name | Takashi Komatsu |
3rd Author's Affiliation | Math. Research Institute Calc for Industry(*) |
4th Author's Name | Tetsuji Taniguchi |
4th Author's Affiliation | Hiroshima Institute of Technology/Math. Research Institute Calc for Industry(HIT/*) |
5th Author's Name | Osamu Toda |
5th Author's Affiliation | MEIDENSHA CORPORATION(*) |
Date | 2022-01-20 |
Paper # | IT2021-53,SIP2021-61,RCS2021-221 |
Volume (vol) | vol.121 |
Number (no) | IT-327,SIP-328,RCS-329 |
Page | pp.pp.137-142(IT), pp.137-142(SIP), pp.137-142(RCS), |
#Pages | 6 |
Date of Issue | 2022-01-13 (IT, SIP, RCS) |