Presentation 2017-07-28
Human Moving Pattern Recognition Based on Communication Quality Using Mobile Sensing and Machine Learning
Wataru Kawakami, Kenji Kanai, Wei Bo, Jiro Katto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we recognized human moving patterns based on communication quality, such as cellular download throughputs, Received Signal Strength Indicators (RSSIs) and cellular base station IDs. To construct classifier, we apply three machine learning algorithms, such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Random Forest (RF). Evaluation results conclude that the communication quality, especially cellular base station IDs, contribute to recognition of moving patterns with high accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Human activity recognition / Mobile sensing / Communication quality / Machine learning
Paper # CS2017-34
Date of Issue 2017-07-20 (CS)

Conference Information
Committee CS
Conference Date 2017/7/27(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Fukue Bunka Kaikan
Topics (in Japanese) (See Japanese page)
Topics (in English) Next generation networks, access network, broadband access system, power-line communications, wireless communication systems, coding system, etc.
Chair Tetsuya Yokotani(Kanazawa Inst. of Tech.)
Vice Chair Hidenori Nakazato(Waseda Univ.)
Secretary Hidenori Nakazato(Kyushu Univ.)
Assistant Kenji Kanai(Waseda Univ.) / Kazutaka Hara(NTT)

Paper Information
Registration To Technical Committee on Communication Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Human Moving Pattern Recognition Based on Communication Quality Using Mobile Sensing and Machine Learning
Sub Title (in English)
Keyword(1) Human activity recognition
Keyword(2) Mobile sensing
Keyword(3) Communication quality
Keyword(4) Machine learning
1st Author's Name Wataru Kawakami
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Kenji Kanai
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Wei Bo
3rd Author's Affiliation Waseda University(Waseda Univ.)
4th Author's Name Jiro Katto
4th Author's Affiliation Waseda University(Waseda Univ.)
Date 2017-07-28
Paper # CS2017-34
Volume (vol) vol.117
Number (no) CS-156
Page pp.pp.111-116(CS),
#Pages 6
Date of Issue 2017-07-20 (CS)