โก Quick Summary
This study introduces the Optimised Hybrid Deep Learning Model for Human Activity Recognition Using Metaheuristic Optimisation Algorithms (OHDLM-HARMOA), achieving an impressive 99.00% accuracy in classifying human activity patterns among disabled individuals. The model leverages advanced deep learning techniques to enhance the quality of life for people with disabilities through effective activity monitoring.
๐ Key Details
- ๐ Dataset: WISDM dataset
- ๐งฉ Features used: Gesture analysis data
- โ๏ธ Technology: Hybrid model combining CNN and BiGRU with attention
- ๐ Performance: Achieved 99.00% accuracy in activity classification
๐ Key Takeaways
- ๐ค Deep learning plays a crucial role in human activity recognition (HAR) for individuals with disabilities.
- ๐ก The OHDLM-HARMOA model utilizes a combination of convolutional neural networks and bidirectional gated recurrent units.
- ๐ Parameter tuning was enhanced using the Sine-Cosine Algorithm (SCA).
- ๐ Ant colony optimization (ACO) was employed for effective feature selection.
- ๐ Z-score normalization was applied during the data pre-processing stage.
- ๐ The model’s performance significantly outperformed existing models in the field.
- ๐ This research has implications for improving assistive technologies for disabled individuals.
- ๐ Published in: Sci Rep, 2025.
๐ Background
Human activity recognition (HAR) has emerged as a vital area of research within the field of computer vision, with applications ranging from video surveillance to human-computer interaction. For individuals with disabilities, accurate activity recognition can significantly enhance their quality of life by enabling better monitoring and assistance. The integration of artificial intelligence (AI) and deep learning (DL) methodologies has opened new avenues for developing effective HAR systems tailored to this demographic.
๐๏ธ Study
The study focused on developing the OHDLM-HARMOA model, which aims to provide an effective HAR method for individuals with disabilities. The researchers utilized the WISDM dataset to evaluate the model’s performance. The process began with data pre-processing, followed by feature selection using ACO, and culminated in the application of a hybrid deep learning architecture for classification.
๐ Results
The OHDLM-HARMOA model demonstrated a remarkable 99.00% accuracy in classifying human activity patterns, showcasing its effectiveness compared to existing models. This high level of accuracy indicates the model’s potential for real-world applications in monitoring and assisting individuals with disabilities.
๐ Impact and Implications
The findings from this study could have a transformative impact on the development of assistive technologies for disabled individuals. By leveraging advanced deep learning techniques, the OHDLM-HARMOA model can facilitate more accurate activity monitoring, ultimately improving the quality of life for users. This research paves the way for further innovations in the field of human activity recognition, with the potential for broader applications in various domains.
๐ฎ Conclusion
This study highlights the significant advancements in human activity recognition through the integration of deep learning models. The OHDLM-HARMOA model not only achieves impressive accuracy but also demonstrates the potential of AI in enhancing the lives of individuals with disabilities. Continued research in this area is essential for developing more effective and accessible technologies that cater to the needs of diverse populations.
๐ฌ Your comments
What are your thoughts on the integration of deep learning in human activity recognition? We would love to hear your insights! ๐ฌ Leave your comments below or connect with us on social media:
An integration of deep learning models for effective classification of human activity patterns in disabled people using gesture analysis.
Abstract
Human activity recognition (HAR) has numerous applications due to its widespread use of procurement tools, such as smartphones and video cameras, and its ability to capture data on human activity. HAR became a hot scientific area in the computer vision (CV) domain. It is complicated in the expansion of many substantial applications, namely video surveillance, home monitoring, security, virtual reality, and human-computer interaction. Subsequently, a wide range of activity recognition methods were developed for individuals with disabilities. HAR is identified as the technique of naming and recognizing actions using artificial intelligence (AI)-based deep learning (DL) methodologies. DL models are crucial to the activity recognition process for individuals with disabilities and older people. This paper presents an Optimised Hybrid Deep Learning Model for Human Activity Recognition Using Metaheuristic Optimisation Algorithms (OHDLM-HARMOA) model. The aim is to develop an effective HAR method that assists and improves the quality of life for people with disabilities through accurate activity monitoring. Initially, the data pre-processing stage applies Z-score normalization for converting the input data into a structured pattern. For the feature selection process, the ant colony optimization (ACO) model is employed to select the most relevant and significant features from a dataset. Furthermore, the OHDLM-HARMOA model utilizes the hybridization of a convolutional neural network and a bidirectional gated recurrent unit with attention (CNN-BiGRU-A) technique for classification. Finally, the parameter tuning process is performed using the Sine-Cosine Algorithm (SCA) technique to enhance the classification performance of the CNN-BiGRU-A model. The experimental evaluation of the OHDLM-HARMOA approach is performed under the WISDM dataset. The comparison analysis of the OHDLM-HARMOA approach demonstrated a superior accuracy value of 99.00% over existing models.
Author: [‘Alkahtani HK’, ‘Al-Kahtani N’, ‘Mohammed GP’, ‘Marzouk R’]
Journal: Sci Rep
Citation: Alkahtani HK, et al. An integration of deep learning models for effective classification of human activity patterns in disabled people using gesture analysis. An integration of deep learning models for effective classification of human activity patterns in disabled people using gesture analysis. 2025; 15:43671. doi: 10.1038/s41598-025-27450-7