Authors:
Sara Ashry
1
;
Reda Elbasiony
2
and
Walid Gomaa
3
Affiliations:
1
Cyber-Physical Systems Lab (CPS), Computer Science and Engineering Department (CSE), Egypt-Japan University of Science and Technology (E-JUST), Alexandria, Egypt, Computers and Systems Department, Electronic Research Institute (ERI), Giza and Egypt
;
2
Cyber-Physical Systems Lab (CPS), Computer Science and Engineering Department (CSE), Egypt-Japan University of Science and Technology (E-JUST), Alexandria, Egypt, Faculty of Engineering, Tanta University, Tanta and Egypt
;
3
Cyber-Physical Systems Lab (CPS), Computer Science and Engineering Department (CSE), Egypt-Japan University of Science and Technology (E-JUST), Alexandria, Egypt, Faculty of Engineering, Alexandria University, Alexandria and Egypt
Keyword(s):
Human Activity Recognition, Auto Correlation, Median, Entropy, LSTM, Smart Watch, IMU Sensors.
Related
Ontology
Subjects/Areas/Topics:
Engineering Applications
;
Informatics in Control, Automation and Robotics
;
Information-Based Models for Control
;
Intelligent Control Systems and Optimization
;
Optimization Problems in Signal Processing
;
Robotics and Automation
;
Sensors Fusion
;
Signal Processing, Sensors, Systems Modeling and Control
;
System Modeling
Abstract:
In this article, we present a public human activity dataset called ‘HAD-AW’. It consists of four types of 3D sensory signals: acceleration, angular velocity, rotation displacement, and gravity for 31 activities of daily living ADL measured by a wearable smart watch. It is created as a benchmark for algorithms comparison. We succinctly survey some existing datasets and compare them to ‘HAD-AW’. The goal is to make the dataset usable and extendible by others. We introduce a framework of ADL recognition by making various pre-processing steps based on statistical and physical features which we call AMED. These features are then classified using an LSTM recurrent network. The proposed approach is compared to a random-forest algorithm. Finally, our experiments show that the joint use of all four sensors has achieved the best prediction accuracy reaching 95.3% for all activities. It also achieves savings from 88% to 98% in the training and testing time; compared to the random forest classif
ier. To show the effectiveness of the proposed method, it is evaluated on other four public datasets: CMU-MMAC, USC-HAD, REALDISP, and Gomaa datasets.
(More)