Daily Activity Recognition with Large-Scaled Real-Life Recording Datasets Based on Deep Neural Network Using Multi-Modal Signals

Tomoki HAYASHI; Masafumi NISHIDA; Norihide KITAOKA; Tomoki TODA; Kazuya TAKEDA

doi:10.1587/transfun.E101.A.199

Daily Activity Recognition with Large-Scaled Real-Life Recording Datasets Based on Deep Neural Network Using Multi-Modal Signals

Tomoki HAYASHI, Masafumi NISHIDA, Norihide KITAOKA, Tomoki TODA, Kazuya TAKEDA

Full Text Views

0

Cite this

Summary :

In this study, toward the development of smartphone-based monitoring system for life logging, we collect over 1,400 hours of data by recording including both the outdoor and indoor daily activities of 19 subjects, under practical conditions with a smartphone and a small camera. We then construct a huge human activity database which consists of an environmental sound signal, triaxial acceleration signals and manually annotated activity tags. Using our constructed database, we evaluate the activity recognition performance of deep neural networks (DNNs), which have achieved great performance in various fields, and apply DNN-based adaptation techniques to improve the performance with only a small amount of subject-specific training data. We experimentally demonstrate that; 1) the use of multi-modal signal, including environmental sound and triaxial acceleration signals with a DNN is effective for the improvement of activity recognition performance, 2) the DNN can discriminate specified activities from a mixture of ambiguous activities, and 3) DNN-based adaptation methods are effective even if only a small amount of subject-specific training data is available.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E101-A No.1 pp.199-210

Publication Date: 2018/01/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E101.A.199

Type of Manuscript: PAPER

Category: Engineering Acoustics

Authors

Tomoki HAYASHI
  Nagoya University
Masafumi NISHIDA
  Shizuoka University
Norihide KITAOKA
  Tokushima University
Tomoki TODA
  Nagoya University
Kazuya TAKEDA
  Nagoya University

Keyword

human activity recognition, activity of daily living, database, deep neural networks, adaptation

Cite this

Copy

Tomoki HAYASHI, Masafumi NISHIDA, Norihide KITAOKA, Tomoki TODA, Kazuya TAKEDA, "Daily Activity Recognition with Large-Scaled Real-Life Recording Datasets Based on Deep Neural Network Using Multi-Modal Signals" in IEICE TRANSACTIONS on Fundamentals, vol. E101-A, no. 1, pp. 199-210, January 2018, doi: 10.1587/transfun.E101.A.199.
Abstract: In this study, toward the development of smartphone-based monitoring system for life logging, we collect over 1,400 hours of data by recording including both the outdoor and indoor daily activities of 19 subjects, under practical conditions with a smartphone and a small camera. We then construct a huge human activity database which consists of an environmental sound signal, triaxial acceleration signals and manually annotated activity tags. Using our constructed database, we evaluate the activity recognition performance of deep neural networks (DNNs), which have achieved great performance in various fields, and apply DNN-based adaptation techniques to improve the performance with only a small amount of subject-specific training data. We experimentally demonstrate that; 1) the use of multi-modal signal, including environmental sound and triaxial acceleration signals with a DNN is effective for the improvement of activity recognition performance, 2) the DNN can discriminate specified activities from a mixture of ambiguous activities, and 3) DNN-based adaptation methods are effective even if only a small amount of subject-specific training data is available.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.199/_p

Copy

@ARTICLE{e101-a_1_199,
author={Tomoki HAYASHI, Masafumi NISHIDA, Norihide KITAOKA, Tomoki TODA, Kazuya TAKEDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Daily Activity Recognition with Large-Scaled Real-Life Recording Datasets Based on Deep Neural Network Using Multi-Modal Signals},
year={2018},
volume={E101-A},
number={1},
pages={199-210},
abstract={In this study, toward the development of smartphone-based monitoring system for life logging, we collect over 1,400 hours of data by recording including both the outdoor and indoor daily activities of 19 subjects, under practical conditions with a smartphone and a small camera. We then construct a huge human activity database which consists of an environmental sound signal, triaxial acceleration signals and manually annotated activity tags. Using our constructed database, we evaluate the activity recognition performance of deep neural networks (DNNs), which have achieved great performance in various fields, and apply DNN-based adaptation techniques to improve the performance with only a small amount of subject-specific training data. We experimentally demonstrate that; 1) the use of multi-modal signal, including environmental sound and triaxial acceleration signals with a DNN is effective for the improvement of activity recognition performance, 2) the DNN can discriminate specified activities from a mixture of ambiguous activities, and 3) DNN-based adaptation methods are effective even if only a small amount of subject-specific training data is available.},
keywords={},
doi={10.1587/transfun.E101.A.199},
ISSN={1745-1337},
month={January},}

Copy

TY - JOUR
TI - Daily Activity Recognition with Large-Scaled Real-Life Recording Datasets Based on Deep Neural Network Using Multi-Modal Signals
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 199
EP - 210
AU - Tomoki HAYASHI
AU - Masafumi NISHIDA
AU - Norihide KITAOKA
AU - Tomoki TODA
AU - Kazuya TAKEDA
PY - 2018
DO - 10.1587/transfun.E101.A.199
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2018
AB - In this study, toward the development of smartphone-based monitoring system for life logging, we collect over 1,400 hours of data by recording including both the outdoor and indoor daily activities of 19 subjects, under practical conditions with a smartphone and a small camera. We then construct a huge human activity database which consists of an environmental sound signal, triaxial acceleration signals and manually annotated activity tags. Using our constructed database, we evaluate the activity recognition performance of deep neural networks (DNNs), which have achieved great performance in various fields, and apply DNN-based adaptation techniques to improve the performance with only a small amount of subject-specific training data. We experimentally demonstrate that; 1) the use of multi-modal signal, including environmental sound and triaxial acceleration signals with a DNN is effective for the improvement of activity recognition performance, 2) the DNN can discriminate specified activities from a mixture of ambiguous activities, and 3) DNN-based adaptation methods are effective even if only a small amount of subject-specific training data is available.
ER -