A novel peak detection algorithm using particle swarm optimization for chew count estimation of a contactless chewing detection

Selamat, Nur Asmiza and Md. Ali, Sawal Hamid and Minhad, Khairun Nisa’ and Ahmad, Siti Anom (2022) A novel peak detection algorithm using particle swarm optimization for chew count estimation of a contactless chewing detection. IEEE Transactions on Instrumentation and Measurement, 71. pp. 1-12. ISSN 0018-9456

Text A_NOVEL_PEAK_02025.PDF Restricted to Registered users only Download (3MB)

Abstract

This article uses a proximity sensor to perform noncontact-based (sensing) chewing activity detection, capturing the temporalis muscle movement during food intake. The proposed approach is validated using data from a larger number of participants, 20, and different food types, eight. The proposed chewing detection classifies the chewing activity with an overall accuracy of 96.4% using a medium Gaussian support vector machine (SVM). In accordance with the result, this article proposes a novel chew count estimation based on particle swarm optimization (PSO). First, the base of the algorithm is developed based on counting the peak of the chewing signal. Next, the insignificant peak is removed by introducing an argument of minimum peak prominence and maximum peak width where the value of the parameters needs to be determined. As the individual chewing pattern varies from person to person, this article uses a novel parameter search using the PSO method to find the multiplier (parameter values) according to the average peak prominence and width value within each chewing episode. The proposed estimation approach simplifies the typical trial-and-error method. During optimization, within 100 iterations, the chewing count is reduced by 12.9% from its first iteration. Overall, the proposed methods achieve a 4.26% mean absolute error of chewing count estimation.

Item Type:	Article
Uncontrolled Keywords:	Chewing count estimation, Chewing detection, Peak detection algorithm
Divisions:	Faculty of Electrical Engineering
Depositing User:	mr eiisaa ahyead
Date Deposited:	14 Apr 2023 14:55
Last Modified:	14 Apr 2023 14:55
URI:	http://eprints.utem.edu.my/id/eprint/26774
Statistic Details:	View Download Statistic

Actions (login required)

View Item