STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition
Human activity recognition (HAR) has gained significant attention in computer vision and human-computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal featu...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Applied Computational Intelligence and Soft Computing |
| Online Access: | http://dx.doi.org/10.1155/2024/1832298 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559622824656896 |
|---|---|
| author | Md. Khaliluzzaman Md. Furquan Mohammod Sazid Zaman Khan Md. Jiabul Hoque |
| author_facet | Md. Khaliluzzaman Md. Furquan Mohammod Sazid Zaman Khan Md. Jiabul Hoque |
| author_sort | Md. Khaliluzzaman |
| collection | DOAJ |
| description | Human activity recognition (HAR) has gained significant attention in computer vision and human-computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal features from sequential data. Traditional machine learning approaches necessitate manual feature extraction, hindering their effectiveness. For temporal features, RNNs have been widely used for HAR; however, they need help processing long sequences, leading to information bottlenecks. This work introduces a framework that effectively integrates spatial and temporal features by utilizing a series of layers that incorporate a self-attention mechanism to overcome these problems. Here, spatial characteristics are derived using 1D convolutions coupled with pooling layers to capture essential spatial information. After that, GRUs are used to make it possible to effectively represent the temporal dynamics that are inherent in sequential data. Furthermore, the utilization of an attention mechanism serves the purpose of dynamically selecting the significant segments within the sequence, thereby improving the model’s comprehension of context and enhancing the efficacy of deep neural networks (DNNs) in the domain of human activity recognition (HAR). Three different optimizers, namely, Adam, SGD, and RMSprop, were employed to train the model. Each optimizer was tested with three distinct learning rates of 0.1, 0.001, and 0.0001. Experiments on the UCI-HAR dataset have shown that the model works well, with an impressive 97% accuracy rate when using the Adam optimizer with a learning rate of 0.001. |
| format | Article |
| id | doaj-art-5caa47d498a94a72a87a705f4f0045ae |
| institution | Kabale University |
| issn | 1687-9732 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Computational Intelligence and Soft Computing |
| spelling | doaj-art-5caa47d498a94a72a87a705f4f0045ae2025-02-03T01:29:41ZengWileyApplied Computational Intelligence and Soft Computing1687-97322024-01-01202410.1155/2024/1832298STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity RecognitionMd. Khaliluzzaman0Md. Furquan1Mohammod Sazid Zaman Khan2Md. Jiabul Hoque3Department of Computer Science and EngineeringDepartment of Computer Science and EngineeringDepartment of Computer Science and EngineeringDepartment of Computer and Communication EngineeringHuman activity recognition (HAR) has gained significant attention in computer vision and human-computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal features from sequential data. Traditional machine learning approaches necessitate manual feature extraction, hindering their effectiveness. For temporal features, RNNs have been widely used for HAR; however, they need help processing long sequences, leading to information bottlenecks. This work introduces a framework that effectively integrates spatial and temporal features by utilizing a series of layers that incorporate a self-attention mechanism to overcome these problems. Here, spatial characteristics are derived using 1D convolutions coupled with pooling layers to capture essential spatial information. After that, GRUs are used to make it possible to effectively represent the temporal dynamics that are inherent in sequential data. Furthermore, the utilization of an attention mechanism serves the purpose of dynamically selecting the significant segments within the sequence, thereby improving the model’s comprehension of context and enhancing the efficacy of deep neural networks (DNNs) in the domain of human activity recognition (HAR). Three different optimizers, namely, Adam, SGD, and RMSprop, were employed to train the model. Each optimizer was tested with three distinct learning rates of 0.1, 0.001, and 0.0001. Experiments on the UCI-HAR dataset have shown that the model works well, with an impressive 97% accuracy rate when using the Adam optimizer with a learning rate of 0.001.http://dx.doi.org/10.1155/2024/1832298 |
| spellingShingle | Md. Khaliluzzaman Md. Furquan Mohammod Sazid Zaman Khan Md. Jiabul Hoque STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition Applied Computational Intelligence and Soft Computing |
| title | STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition |
| title_full | STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition |
| title_fullStr | STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition |
| title_full_unstemmed | STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition |
| title_short | STA-HAR: A Spatiotemporal Attention-Based Framework for Human Activity Recognition |
| title_sort | sta har a spatiotemporal attention based framework for human activity recognition |
| url | http://dx.doi.org/10.1155/2024/1832298 |
| work_keys_str_mv | AT mdkhaliluzzaman staharaspatiotemporalattentionbasedframeworkforhumanactivityrecognition AT mdfurquan staharaspatiotemporalattentionbasedframeworkforhumanactivityrecognition AT mohammodsazidzamankhan staharaspatiotemporalattentionbasedframeworkforhumanactivityrecognition AT mdjiabulhoque staharaspatiotemporalattentionbasedframeworkforhumanactivityrecognition |