APSIPA Transactions on Signal and Information Processing > Vol 7 > Issue 1

Daily activity recognition based on recurrent neural network using multi-modal signals

Akira Tamamori, Aichi Institute of Technology, Japan, akira-tamamori@aitech.ac.jp , Tomoki Hayashi, Nagoya University, Japan, Tomoki Toda, Nagoya University, Japan, Kazuya Takeda, Nagoya University, Japan
 
Suggested Citation
Akira Tamamori, Tomoki Hayashi, Tomoki Toda and Kazuya Takeda (2018), "Daily activity recognition based on recurrent neural network using multi-modal signals", APSIPA Transactions on Signal and Information Processing: Vol. 7: No. 1, e21. http://dx.doi.org/10.1017/ATSIP.2018.25

Publication Date: 01 Jan 2018
© 2018 Akira Tamamori, Tomoki Hayashi, Tomoki Toda and Kazuya Takeda
 
Subjects
 
Keywords
Human activity recognitionDeep neural networkRecurrent neural networkMulti-modal signal
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 1374 times

In this article:
I. INTRODUCTION 
II. A DIGEST OF PREVIOUS STUDY 
III. TOWARDS REALIZATION OF TARGET LIFE-LOGGING SYSTEM 
IV. EXPERIMENTAL EVALUATION 
V. CONCLUSION 

Abstract

Our aim is to develop a smartphone-based life-logging system. Human activity recognition (HAR) is one of the core techniques to realize it. Recent studies reported the effectiveness of feed-forward neural network (FF-NN) and recurrent neural network (RNN) as a classifier for HAR task. However, there are still unresolved problems in those studies: (1) a life-logging system using only a smartphone for recording device has not been developed, (2) only indoor activities have been utilized for evaluation, (3) insufficient investigations/evaluations of RNN. In this study, we address these unresolved problems as follows: (1) we build a prototype system for life-logging and conduct data recording experiment on this system to include both indoor and outdoor activities. The experimental results of HAR on this new dataset showed that RNN-based classifier was still effective. (2) From the results of a HAR experiment, it was demonstrated that a multi-layered Simple Recurrent Unit with a non-linear transform at the bottom layer and a highway-connection was the most effective. (3) We could grasp the reason for the improvement of RNN from FF-NN by observing the posterior probabilities over test data.

DOI:10.1017/ATSIP.2018.25