Authors:
Mubarak G. Abdu-Aguye
1
;
Walid Gomaa
2
;
Yasushi Makihara
3
and
Yasushi Yagi
3
Affiliations:
1
Computer Science and Engineering Department, Egypt-Japan University of Science and Technology and Egypt
;
2
Computer Science and Engineering Department, Egypt-Japan University of Science and Technology, Egypt, Faculty of Engineering, Alexandria University and Egypt
;
3
The Institute of Scientific and Industrial Research, Osaka University and Japan
Keyword(s):
Activity Recognition, Transfer Learning, Deep Learning, Data Augmentation.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Engineering Applications
;
Image and Video Analysis
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Optimization Problems in Signal Processing
;
Robotics and Automation
;
Sensors Fusion
;
Signal Processing, Sensors, Systems Modeling and Control
;
Signal Reconstruction
;
Time-Frequency Analysis
Abstract:
In the domain of human activity recognition, the primary goal is to determine the action a user was performing based on data collected through some sensor modalities. Common modalities adopted to this end include visual and Inertial Measurement Units (IMUs), with the latter taking precedence in recent times due to their unobtrusiveness, low cost and mobility. However, a secondary challenge arises in such sensor-based activity recognition. Difficulties in collecting and annotating training samples are significant and can hinder the performance of models trained on such limited data. As such, there is a need to explore techniques capable of tackling this problem in this domain. In this work, we explore the feasibility of reusing samples collected from different ”source” body locations in activity recognition at different ”target” body locations. This is achieved through the use of ”roaming” models based on recurrent neural networks. We investigate the predictive performance of the tran
sferred samples relative to the performance from samples collected natively at the target body locations. Our results suggest that such roaming models can permit the reuse of cross-body samples without a significant loss in discriminative performance.
(More)