Optimized Convolutional Neural Network Using Hierarchical Particle Swarm Optimization for Sensor Based Human Activity Recognition
Document Type
Article
Publication Title
SN Computer Science
Abstract
Hyperparameter optimization poses a significant challenge when developing deep neural networks. Building a convolutional neural network (CNN) for implementation can be an arduous and time-intensive task. This work proposed an approach to optimize the hyperparameters of one dimensional (1D-CNN) to improve the accuracy of human activity recognition (HAR). The framework includes a parametric depiction of 1D-CNNs along with an optimization process for hyperparameters aimed at maximizing the model's performance. This work designed the method called OPTConvNet for hyperparameter optimization of 1D-CNN using Hierarchical Particle Swarm Optimization (H-PSO). The H-PSO algorithm is designed to optimize the architectural, layer and training parameters of 1D-CNN. The H-PSO optimizes the architecture of the 1D-CNN at initial level. Layer and training hyperparameters will be optimized at the next level. The proposed approach employs an exponential-like inertia weight to fine-tune the balance between exploration and exploitation of particles to prevent premature convergence to a local optimum solution in the PSO algorithm. The H-PSO- CNN is evaluated on publicly available sensor- human activity recognition (S-HAR) datasets namely, UCI-HAR, Daphnet Gait, Opportunity and PAMPA2 datasets.
DOI
10.1007/s42979-024-02794-5
Publication Date
6-1-2024
Recommended Citation
Ankalaki, Shilpa and Thippeswamy, M. N., "Optimized Convolutional Neural Network Using Hierarchical Particle Swarm Optimization for Sensor Based Human Activity Recognition" (2024). Open Access archive. 6532.
https://impressions.manipal.edu/open-access-archive/6532