Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

A Hybrid Hierarchical Framework for Gym Physical Activity Recognition and Measurement Using Wearable Sensors

Qi, J, Yang, P, Hanneghan, M, Tang, SO and Zhou, B (2018) A Hybrid Hierarchical Framework for Gym Physical Activity Recognition and Measurement Using Wearable Sensors. IEEE Internet of Things Journal. ISSN 2327-4662

[img]
Preview
Text
GPA-v4.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Due to the many beneficial effects on physical and mental health and strong association with many fitness and rehabilitation programs, physical activity (PA) recognition has been considered as a key paradigm for internet of things (IoT) healthcare. Traditional PA recognition techniques focus on repeated aerobic exercises or stationary PA. As a crucial indicator in human health, it covers a range of bodily movement from aerobics to anaerobic that may all bring health benefits. However, existing PA recognition approaches are mostly designed for specific scenarios and often lack extensibility for application in other areas, thereby limiting their usefulness. In this paper, we attempt to detect more gym physical activities (GPAs) in addition to traditional PA using acceleration, A two layer recognition framework is proposed that can classify aerobic, sedentary and free weight activities, count repetitions and sets for the free weight exercises, and in the meantime, measure quantities of repetitions and sets for free weight activities. In the first layer, a one-class SVM (OC-SVM) is applied to coarsely classify free weight and non-free weight activities. In the second layer, a neural network (NN) is utilized for aerobic and sedentary activities recognition; a hidden Markov model (HMM) is to provide a further classification in free weight activities. The performance of the framework was tested on 10 healthy subjects (age: 30 ± 5; BMI: 25 ± 5.5 kg/ and compared with some typical classifiers. The results indicate the proposed framework has better performance in recognizing and measuring GPAs than other approaches. The potential of this framework can be potentially extended in supporting more types of PA recognition in complex applications.

Item Type: Article
Subjects: G Geography. Anthropology. Recreation > GV Recreation Leisure
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Computer Science
Publisher: IEEE
Date Deposited: 30 May 2018 11:41
Last Modified: 14 Jun 2018 10:54
DOI or Identification number: 10.1109/JIOT.2018.2846359
URI: http://researchonline.ljmu.ac.uk/id/eprint/8738

Actions (login required)

View Item View Item