The Applications of Metaheuristics for Human Activity Recognition and Fall Detection Using Wearable Sensors: A Comprehensive Analysis

Abstract

In this paper, we study the applications of metaheuristics (MH) optimization algorithms in human activity recognition (HAR) and fall detection based on sensor data. It is known that MH algorithms have been utilized in complex engineering and optimization problems, including feature selection (FS). Thus, in this regard, this paper used nine MH algorithms as FS methods to boost the classification accuracy of the HAR and fall detection applications. The applied MH were the Aquila optimizer (AO), arithmetic optimization algorithm (AOA), marine predators algorithm (MPA), artificial bee colony (ABC) algorithm, genetic algorithm (GA), slime mold algorithm (SMA), grey wolf optimizer (GWO), whale optimization algorithm (WOA), and particle swarm optimization algorithm (PSO). First, we applied efficient prepossessing and segmentation methods to reveal the motion patterns and reduce the time complexities. Second, we developed a light feature extraction technique using advanced deep learning approaches. The developed model was ResRNN and was composed of several building blocks from deep learning networks including convolution neural networks (CNN), residual networks, and bidirectional recurrent neural networks (BiRNN). Third, we applied the mentioned MH algorithms to select the optimal features and boost classification accuracy. Finally, the support vector machine and random forest classifiers were employed to classify each activity in the case of multi-classification and to detect fall and non-fall actions in the case of binary classification. We used seven different and complex datasets for the multi-classification case: the PAMMP2, Sis-Fall, UniMiB SHAR, OPPORTUNITY, WISDM, UCI-HAR, and KU-HAR datasets. In addition, we used the Sis-Fall dataset for the binary classification (fall detection). We compared the results of the nine MH optimization methods using different performance indicators. We concluded that MH optimization algorithms had promising performance in HAR and fall detection applications.

Human Activity Recognition Using Attention-Mechanism-Based Deep Learning Feature Combination

“…Despite the KU-HAR dataset being relatively new, the AM-DLFC model demonstrated superior performance when compared to the two previously published articles. Specifically, the proposed model exhibited 7.2% and 8.33% enhancement in overall classification accuracy when compared to the studies conducted by [19] and [34], respectively. In terms of the F1 score, the achieved score was enhanced by around 9.33%, 8.4%, 3.81%, and 2.67% compared to [19,34,35], respectively.…”

“…Specifically, the proposed model exhibited 7.2% and 8.33% enhancement in overall classification accuracy when compared to the studies conducted by [19] and [34], respectively. In terms of the F1 score, the achieved score was enhanced by around 9.33%, 8.4%, 3.81%, and 2.67% compared to [19,34,35], respectively. Despite having a close accuracy result with [36], the AM-DLFC showed better performance overall.…”

“…Accuracy (%) F1 Score (%) [19] 89.67 87.59 [36] 96.67 (Peak) 96.41 (Peak) [34] 88.53 88.52 [35] Not Provided 94.25 Proposed 96.86 96.92…”

Algorithmic material selection for wearable medical devices a genetic algorithm-based framework with multiscale modeling

“…Recognizing these shortcomings, recent research has witnessed a growing interest in computational techniques, with genetic algorithms emerging as a promising avenue. Inspired by natural selection, genetic algorithms offer a robust optimization approach by iteratively evolving a population of candidate materials based on their performance in a given set of criteria (Al-Qaness, M. A., et al, 2022). This evolutionary process allows for the exploration of a vast design space, enabling the identification of materials with tailored properties for specific applications.…”