Presentation 2021-03-01
A Comparison of Context Analysis and Estimation Methods for Mobile Users Considering the Time Series of Data
Hiromi Shimizu, Mutsumi Suganuma, Wataru Kameyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, the demand for analyzing mobile user’s activities has been increasing in the fields such as customer behavior analysis. In our previous study, we conduct mobile user’s context analysis and estimation using various sensor data of mobile phone and user’s bio-signals, and achieve the accuracy of more than 97% by applying convolutional neural network (CNN) considering the time series of data. However, the number of subjects is limited to 2, and the optimization of various parameters for machine learning methods is not sufficiently studied. So, in this paper, we increase the number of subjects to 8, and compare the accuracy of context analysis and estimation by examining various parameters for machine learning methods including CNN. The results show that CNN achieves the highest macro F1-score for many of the subjects where its values are more than 98%. Therefore, it is suggested that the proposed methods considering the time series of data are effective and versatile.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Mobile User / Behavior Analysis / Context Analysis / Context Estimation / Bio-signal / Sensor Data / CNN
Paper # CQ2020-107
Date of Issue 2021-02-22 (CQ)

Conference Information
Committee MVE / IMQ / IE / CQ
Conference Date 2021/3/1(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Masayuki Ihara(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Hideaki Kimata(NTT) / Hideyuki Shimonishi(NEC)
Vice Chair Kiyoshi Kiyokawa(NAIST) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.)
Secretary Kiyoshi Kiyokawa(Oosaka Inst. of Tech.) / Mitsuru Maeda(NTT) / Kenya Uomori(Univ. of ToKyo) / Kazuya Kodama(Shizuoka Univ.) / Keita Takahashi(Sony Semiconductor Solutions) / Jun Okamoto(KDDI Research) / Takefumi Hiraguri(Nagoya Inst. of Tech.)
Assistant Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Communication Quality
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Comparison of Context Analysis and Estimation Methods for Mobile Users Considering the Time Series of Data
Sub Title (in English)
Keyword(1) Mobile User
Keyword(2) Behavior Analysis
Keyword(3) Context Analysis
Keyword(4) Context Estimation
Keyword(5) Bio-signal
Keyword(6) Sensor Data
Keyword(7) CNN
1st Author's Name Hiromi Shimizu
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Mutsumi Suganuma
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Wataru Kameyama
3rd Author's Affiliation Waseda University(Waseda Univ.)
Date 2021-03-01
Paper # CQ2020-107
Volume (vol) vol.120
Number (no) CQ-392
Page pp.pp.1-5(CQ),
#Pages 5
Date of Issue 2021-02-22 (CQ)