Comparing the Performance of Different Classifiers for Posture Detection

Suresh Kumar, Sagar; Dashtipour, Kia; Gogate, Mandar; Ahmad, Jawad; Assaleh, Khaled; Arshad, Kamran; Imran, Muhammad Ali; Abbasi, Qammer; Ahmad, Wasim

Abstract

Human Posture Classification (HPC) is used in many fields such as human computer interfacing, security surveillance, rehabilitation, remote monitoring, and so on. This paper compares the performance of different classifiers in the detection of 3 postures, sitting, standing, and lying down, which was recorded using Microsoft Kinect cameras. The Machine Learning classifiers used included the Support Vector Classifier, Naive Bayes, Logistic Regression, K-Nearest Neighbours, and Random Forests. The Deep Learning ones included the standard Multi-Layer Perceptron, Convolutional Neural Networks (CNN), and Long Short Term Memory Networks (LSTM). It was observed that Deep Learning methods outperformed the former and that the one-dimensional CNN performed the best with an accuracy of 93.45%.

Citation

Suresh Kumar, S., Dashtipour, K., Gogate, M., Ahmad, J., Assaleh, K., Arshad, K., Imran, M. A., Abbasi, Q., & Ahmad, W. (2021, October). Comparing the Performance of Different Classifiers for Posture Detection. Presented at 16th EAI International Conference, BODYNETS 2021, Online

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 16th EAI International Conference, BODYNETS 2021
• Start Date: Oct 25, 2021
• End Date: Oct 26, 2021
• Acceptance Date: Aug 31, 2021
• Online Publication Date: Feb 11, 2022
• Publication Date: 2022
• Deposit Date: Apr 26, 2022
• Publisher: Springer
• Pages: 210-218
• Series Title: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
• Series Number: 420
• Series ISSN: 1867-822X
• Book Title: Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021
• ISBN: 978-3-030-95592-2
• DOI: https://doi.org/10.1007/978-3-030-95593-9_17
• Keywords: Machine learning, Deep learning, Detecting Alzheimer
• Public URL: http://researchrepository.napier.ac.uk/Output/2866967