HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones
Smartphone-based human activity recognition (HAR) is an important research area due to its wide-ranging applications in health, security, gaming, etc. Existing HAR models face challenges such as tedious manual feature extraction/selection techniques, limited model generalisation, high computational...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ital Publication
2025-02-01
|
| Series: | Emerging Science Journal |
| Subjects: | |
| Online Access: | https://ijournalse.org/index.php/ESJ/article/view/2571 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823865079623319552 |
|---|---|
| author | Sarmela Raja Sekaran Ying Han Pang Ooi Shih Yin Lim Zheng You |
| author_facet | Sarmela Raja Sekaran Ying Han Pang Ooi Shih Yin Lim Zheng You |
| author_sort | Sarmela Raja Sekaran |
| collection | DOAJ |
| description | Smartphone-based human activity recognition (HAR) is an important research area due to its wide-ranging applications in health, security, gaming, etc. Existing HAR models face challenges such as tedious manual feature extraction/selection techniques, limited model generalisation, high computational cost, and inability to retain longer-term dependencies. This work aims to overcome the issues by proposing a lightweight, homogenous stacked deep ensemble model, termed Homogenous Stacking Temporal Convolutional Network with Nu-Support Vector Classifier (HSTCN-NuSVC), for activity classification. In this model, multiple enhanced TCN networks with diverse architectures are organised parallelly to capture hierarchical spatial-temporal patterns from raw inertial signals. Each base model (i.e., TCN) incorporates dilations and residual connections to preserve longer effective histories, allowing the model to retain longer-term dependencies. Additionally, dilations can diminish the number of trainable parameters, reducing the model complexity and computational cost. The base models’ predictions are concatenated and fed into a meta-learner (i.e., Nu-SVC) for final classification. The proposed HSTCN-NuSVC is evaluated using a publicly available database, i.e., UCI HAR, and a subject-independent protocol is implemented. The empirical results demonstrate that HSTCN-NuSVC achieves 97.25% accuracy with only 0.51 million parameters. The results exhibit the model’s effectiveness in enhancing generalisation across individuals with better accuracy and computational efficiency.
Doi: 10.28991/ESJ-2025-09-01-026
Full Text: PDF |
| format | Article |
| id | doaj-art-5be1e2d2ecbd46fc8fa1c344103edebc |
| institution | Kabale University |
| issn | 2610-9182 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Ital Publication |
| record_format | Article |
| series | Emerging Science Journal |
| spelling | doaj-art-5be1e2d2ecbd46fc8fa1c344103edebc2025-02-08T14:26:27ZengItal PublicationEmerging Science Journal2610-91822025-02-019146848410.28991/ESJ-2025-09-01-026786HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using SmartphonesSarmela Raja Sekaran0Ying Han Pang1Ooi Shih Yin2Lim Zheng You3Faculty of Information Science and Technology, Multimedia University, Malacca,Faculty of Information Science and Technology, Multimedia University, Malacca,Faculty of Information Science and Technology, Multimedia University, Malacca,Faculty of Information Science and Technology, Multimedia University, Malacca,Smartphone-based human activity recognition (HAR) is an important research area due to its wide-ranging applications in health, security, gaming, etc. Existing HAR models face challenges such as tedious manual feature extraction/selection techniques, limited model generalisation, high computational cost, and inability to retain longer-term dependencies. This work aims to overcome the issues by proposing a lightweight, homogenous stacked deep ensemble model, termed Homogenous Stacking Temporal Convolutional Network with Nu-Support Vector Classifier (HSTCN-NuSVC), for activity classification. In this model, multiple enhanced TCN networks with diverse architectures are organised parallelly to capture hierarchical spatial-temporal patterns from raw inertial signals. Each base model (i.e., TCN) incorporates dilations and residual connections to preserve longer effective histories, allowing the model to retain longer-term dependencies. Additionally, dilations can diminish the number of trainable parameters, reducing the model complexity and computational cost. The base models’ predictions are concatenated and fed into a meta-learner (i.e., Nu-SVC) for final classification. The proposed HSTCN-NuSVC is evaluated using a publicly available database, i.e., UCI HAR, and a subject-independent protocol is implemented. The empirical results demonstrate that HSTCN-NuSVC achieves 97.25% accuracy with only 0.51 million parameters. The results exhibit the model’s effectiveness in enhancing generalisation across individuals with better accuracy and computational efficiency. Doi: 10.28991/ESJ-2025-09-01-026 Full Text: PDFhttps://ijournalse.org/index.php/ESJ/article/view/2571deep ensemble learningsmartphone-based human activity recognitionstacking ensemblelightweight modelhierarchical deep features. |
| spellingShingle | Sarmela Raja Sekaran Ying Han Pang Ooi Shih Yin Lim Zheng You HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones Emerging Science Journal deep ensemble learning smartphone-based human activity recognition stacking ensemble lightweight model hierarchical deep features. |
| title | HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones |
| title_full | HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones |
| title_fullStr | HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones |
| title_full_unstemmed | HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones |
| title_short | HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones |
| title_sort | hstcn nusvc a homogeneous stacked deep ensemble learner for classifying human actions using smartphones |
| topic | deep ensemble learning smartphone-based human activity recognition stacking ensemble lightweight model hierarchical deep features. |
| url | https://ijournalse.org/index.php/ESJ/article/view/2571 |
| work_keys_str_mv | AT sarmelarajasekaran hstcnnusvcahomogeneousstackeddeepensemblelearnerforclassifyinghumanactionsusingsmartphones AT yinghanpang hstcnnusvcahomogeneousstackeddeepensemblelearnerforclassifyinghumanactionsusingsmartphones AT ooishihyin hstcnnusvcahomogeneousstackeddeepensemblelearnerforclassifyinghumanactionsusingsmartphones AT limzhengyou hstcnnusvcahomogeneousstackeddeepensemblelearnerforclassifyinghumanactionsusingsmartphones |