Citation

Lee, Gin Chong and Loo, Chu Kiong (2022) On the Post Hoc Explainability of Optimized Self-Organizing Reservoir Network for Action Recognition. Sensors, 22 (5). p. 1905. ISSN 1424-8220

Text On the Post Hoc Explainability.pdf Restricted to Repository staff only Download (20MB)

Abstract

This work proposes a novel unsupervised self-organizing network, called the Self-Organizing Convolutional Echo State Network (SO-ConvESN), for learning node centroids and interconnectivity maps compatible with the deterministic initialization of Echo State Network (ESN) input and reservoir weights, in the context of human action recognition (HAR). To ensure stability and echo state property in the reservoir, Recurrent Plots (RPs) and Recurrence Quantification Analysis (RQA) techniques are exploited for explainability and characterization of the reservoir dynamics and hence tuning ESN hyperparameters. The optimized self-organizing reservoirs are cascaded with a Convolutional Neural Network (CNN) to ensure that the activation of internal echo state representations (ESRs) echoes similar topological qualities and temporal features of the input time-series, and the CNN efficiently learns the dynamics and multiscale temporal features from the ESRs for action recognition. The hyperparameter optimization (HPO) algorithms are additionally adopted to optimize the CNN stage in SO-ConvESN. Experimental results on the HAR problem using several publicly available 3D-skeleton-based action datasets demonstrate the showcasing of the RPs and RQA technique in examining the explainability of reservoir dynamics for designing stable self-organizing reservoirs and the usefulness of implementing HPOs in SO-ConvESN for the HAR task. The proposed SO-ConvESN exhibits competitive recognition accuracy.

Item Type:	Article
Uncontrolled Keywords:	Echo state networks, action recognition, self-organizing networks, deep neural networks
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	06 Apr 2022 02:06
Last Modified:	06 Apr 2022 02:06
URII:	http://shdl.mmu.edu.my/id/eprint/10048

Downloads

Edit (login required)