Presentation | 2017-09-16 Feature Extraction Using Denoising Autoencoders for Activity Recognition from Acceleration Data Toru Takeyama, Kiyoshi Kogure, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We have experimentally evaluated how the performance of activity recognition from acceleration data depends on the way of extracting features using denoising autoencoders. The experimental results show that when each of stacked denoising autoencoders is given 3-axis acceleration data from a body part, the accuracy of classification using their output features changes saliently according to the number of nodes in each of their output layers and that when a stacked denoising autoencoder is given 3-axis acceleration data from six body parts, the accuracy of classification monotonically increases with the increasing number of nodes in its output layer as long as the number is less than or equal to the number of nodes in its input layer. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | activity recognition / acceleration / feature extraction / denoising autoencoder |
Paper # | PRMU2017-58,IBISML2017-30 |
Date of Issue | 2017-09-08 (PRMU, IBISML) |
Conference Information | |
Committee | PRMU / IBISML / IPSJ-CVIM |
---|---|
Conference Date | 2017/9/15(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) / Kenji Fukumizu(ISM) |
Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Masashi Sugiyama(Univ. of Tokyo) |
Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Masashi Sugiyama(Kyoto Univ.) / (Univ. of Tokyo) |
Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Ichiro Takeuchi(Nagoya Inst. of Tech.) / Toshihiro Kamishima(AIST) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Feature Extraction Using Denoising Autoencoders for Activity Recognition from Acceleration Data |
Sub Title (in English) | |
Keyword(1) | activity recognition |
Keyword(2) | acceleration |
Keyword(3) | feature extraction |
Keyword(4) | denoising autoencoder |
1st Author's Name | Toru Takeyama |
1st Author's Affiliation | Kanazawa Institute of Technology(KIT) |
2nd Author's Name | Kiyoshi Kogure |
2nd Author's Affiliation | Kanazawa Institute of Technology(KIT) |
Date | 2017-09-16 |
Paper # | PRMU2017-58,IBISML2017-30 |
Volume (vol) | vol.117 |
Number (no) | PRMU-210,IBISML-211 |
Page | pp.pp.161-166(PRMU), pp.161-166(IBISML), |
#Pages | 6 |
Date of Issue | 2017-09-08 (PRMU, IBISML) |