Skip to main content

Research Repository

Advanced Search

Intelligent human action recognition using an ensemble model of evolving deep networks with swarm-based optimization.

Zhang, Li; Lim, Chee Peng; Yu, Yonghong

Authors

Chee Peng Lim

Yonghong Yu



Abstract

Automatic interpretation of human actions from realistic videos attracts increasing research attention owing to its growing demand in real-world deployments such as biometrics, intelligent robotics, and surveillance. In this research, we propose an ensemble model of evolving deep networks comprising Convolutional Neural Networks (CNNs) and bidirectional Long Short-Term Memory (BLSTM) networks for human action recognition. A swarm intelligence (SI)-based algorithm is also proposed for identifying the optimal hyper-parameters of the deep networks. The SI algorithm plays a crucial role for determining the BLSTM network and learning configurations such as the learning and dropout rates and the number of hidden neurons, in order to establish effective deep features that accurately represent the temporal dynamics of human actions. The proposed SI algorithm incorporates hybrid crossover operators implemented by sine, cosine, and tanh functions for multiple elite offspring signal generation, as well as geometric search coefficients extracted from a three-dimensional super-ellipse surface. Moreover, it employs a versatile search process led by the yielded promising offspring solutions to overcome stagnation. Diverse CNN–BLSTM networks with distinctive hyper-parameter settings are devised. An ensemble model is subsequently constructed by aggregating a set of three optimized CNN–BLSTM​ networks based on the average prediction probabilities. Evaluated using several publicly available human action data sets, our evolving ensemble deep networks illustrate statistically significant superiority over those with default and optimal settings identified by other search methods. The proposed SI algorithm also shows great superiority over several other methods for solving diverse high-dimensional unimodal and multimodal optimization functions with artificial landscapes.

Citation

ZHANG, L., LIM, C.P. and YU, Y. 2021. Intelligent human action recognition using an ensemble model of evolving deep networks with swarm-based optimization. Knowledge-based systems [online], 220, article ID 106918. Available from: https://doi.org/10.1016/j.knosys.2021.106918

Journal Article Type Article
Acceptance Date Mar 2, 2021
Online Publication Date Mar 5, 2021
Publication Date May 23, 2021
Deposit Date Mar 15, 2021
Publicly Available Date Mar 6, 2022
Journal Knowledge-Based Systems
Print ISSN 0950-7051
Electronic ISSN 1872-7409
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 220
Article Number 106918
DOI https://doi.org/10.1016/j.knosys.2021.106918
Keywords Swarm intelligence; Evolutionary algorithm; Deep hybrid neural network; Ensemble classifier; Human action recognition
Public URL https://rgu-repository.worktribe.com/output/1255620

Files

This file is under embargo until Mar 6, 2022 due to copyright reasons.

Contact publications@rgu.ac.uk to request a copy for personal use.




You might also like



Downloadable Citations