Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong
The research works on three-dimensional (3D)-skeleton-joints-based human action recognition (HAR) remains demanding. Among the approaches, Echo State Networks (ESNs) are a reservoir computing method that considers skeleton joints human actions as multivariate time series and attempts to identify and...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/14464/ http://studentsrepo.um.edu.my/14464/1/Lee_Gin_Chong.pdf http://studentsrepo.um.edu.my/14464/2/Lee_Gin_Chong.pdf |
| _version_ | 1848774973864280064 |
|---|---|
| author | Lee , Gin Chong |
| author_facet | Lee , Gin Chong |
| author_sort | Lee , Gin Chong |
| building | UM Research Repository |
| collection | Online Access |
| description | The research works on three-dimensional (3D)-skeleton-joints-based human action recognition (HAR) remains demanding. Among the approaches, Echo State Networks (ESNs) are a reservoir computing method that considers skeleton joints human actions as multivariate time series and attempts to identify and model the dynamical temporal features in 3D space. Despite the random initialization of the ESN's input and reservoir weights may reduce the computational cost, this may raise instability and variance in generalization and hence diminish reproducibility. Moreover, ESN remains a black-box algorithm. Notably, it lacks explainability consideration to understand the input-dependent reservoir dynamics, specifically while configuring the optimal hyperparameters for HAR. Besides, following the body of Convolutional Echo State Network (ConvESN) work to incorporate modeling dynamics and multiscale temporal feature in handling HAR problem, the model may be very sensitive to the selection of hyperparameters in Convolutional Neural Network (CNN). This work addresses these issues by proposing a novel approach known as Self-Organizing Convolutional Echo State Network (SO-ConvESN) for HAR. Specifically, this work proposes an unsupervised self-organizing network for learning node centroids and interconnectivity maps compatible with the deterministic initialization of ESN reservoir weights. To ensure stability and echo state property (ESP) in the self-organizing reservoir, this work further exploits the Recurrent Plots (RPs) and Recurrence Quantification Analysis (RQA) techniques for explainability and characterization of the dynamics of the self-organizing reservoir and hence tuning two critical ESN hyperparameters: input scaling ( |
| first_indexed | 2025-11-14T14:06:49Z |
| format | Thesis |
| id | um-14464 |
| institution | University Malaya |
| institution_category | Local University |
| last_indexed | 2025-11-14T14:06:49Z |
| publishDate | 2022 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | um-144642023-06-06T18:15:38Z Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong Lee , Gin Chong QA75 Electronic computers. Computer science T Technology (General) The research works on three-dimensional (3D)-skeleton-joints-based human action recognition (HAR) remains demanding. Among the approaches, Echo State Networks (ESNs) are a reservoir computing method that considers skeleton joints human actions as multivariate time series and attempts to identify and model the dynamical temporal features in 3D space. Despite the random initialization of the ESN's input and reservoir weights may reduce the computational cost, this may raise instability and variance in generalization and hence diminish reproducibility. Moreover, ESN remains a black-box algorithm. Notably, it lacks explainability consideration to understand the input-dependent reservoir dynamics, specifically while configuring the optimal hyperparameters for HAR. Besides, following the body of Convolutional Echo State Network (ConvESN) work to incorporate modeling dynamics and multiscale temporal feature in handling HAR problem, the model may be very sensitive to the selection of hyperparameters in Convolutional Neural Network (CNN). This work addresses these issues by proposing a novel approach known as Self-Organizing Convolutional Echo State Network (SO-ConvESN) for HAR. Specifically, this work proposes an unsupervised self-organizing network for learning node centroids and interconnectivity maps compatible with the deterministic initialization of ESN reservoir weights. To ensure stability and echo state property (ESP) in the self-organizing reservoir, this work further exploits the Recurrent Plots (RPs) and Recurrence Quantification Analysis (RQA) techniques for explainability and characterization of the dynamics of the self-organizing reservoir and hence tuning two critical ESN hyperparameters: input scaling ( 2022-04 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/14464/1/Lee_Gin_Chong.pdf application/pdf http://studentsrepo.um.edu.my/14464/2/Lee_Gin_Chong.pdf Lee , Gin Chong (2022) Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong. PhD thesis, Universiti Malaya. http://studentsrepo.um.edu.my/14464/ |
| spellingShingle | QA75 Electronic computers. Computer science T Technology (General) Lee , Gin Chong Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong |
| title | Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong |
| title_full | Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong |
| title_fullStr | Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong |
| title_full_unstemmed | Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong |
| title_short | Self-organizing kernel-based convolutional echo state network for human action recognition / Lee Gin Chong |
| title_sort | self-organizing kernel-based convolutional echo state network for human action recognition / lee gin chong |
| topic | QA75 Electronic computers. Computer science T Technology (General) |
| url | http://studentsrepo.um.edu.my/14464/ http://studentsrepo.um.edu.my/14464/1/Lee_Gin_Chong.pdf http://studentsrepo.um.edu.my/14464/2/Lee_Gin_Chong.pdf |