شنبه 3 شهریور 1403
دوره 10، شماره 1 - ( 10-1402 )
جلد 10 شماره 1 صفحات 86-77 |
برگشت به فهرست نسخه ها
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Rezvani S, Chaibakhsh A. An Efficient Multiobjective Feature Optimization Approach for Improving Motor Imagery-based Brain-computer Interface Performance. Caspian J Neurol Sci 2024; 10 (1) :77-86
URL: http://cjns.gums.ac.ir/article-1-693-fa.html
URL: http://cjns.gums.ac.ir/article-1-693-fa.html
An Efficient Multiobjective Feature Optimization Approach for Improving Motor Imagery-based Brain-computer Interface Performance. مجله علوم اعصاب کاسپین. 1402; 10 (1) :77-86
چکیده: (332 مشاهده)
Background: Applying efficient feature extraction and selection methods is essential in improving the performance of machine learning algorithms employed in brain-computer interface (BCI) systems.
Objectives: The current study aims to enhance the performance of a motor imagery-based BCI by improving the feature extraction and selection stages of the machine-learning algorithm applied to classify the different imagined movements.
Materials & Methods: In this study, a multi-rate system for spectral decomposition of the signal is designed, and then the spatial and temporal features are extracted from each sub-band. To maximize the classification accuracy while simplifying the model and using the smallest set of features, the feature selection stage is treated as a multiobjective optimization problem, and the Pareto optimal solutions of these two conflicting objectives are obtained. For the feature selection stage, non-dominated sorting genetic algorithm II (NSGA-II), an evolutionary-based algorithm, is used wrapper-based, and its effect on the BCI performance is explored. The proposed method is
implemented on a public dataset known as BCI competition III dataset IVa.
Results: Extracting the spatial and temporal features from different sub-bands and selecting the features with an evolutionary optimization approach in this study led to an improved classification accuracy of 92.19% which has a higher value compared to the state of the art.
Conclusion: The results show that the proposed improved classification accuracy could achieve a high-performance subject-specific BCI system.
Objectives: The current study aims to enhance the performance of a motor imagery-based BCI by improving the feature extraction and selection stages of the machine-learning algorithm applied to classify the different imagined movements.
Materials & Methods: In this study, a multi-rate system for spectral decomposition of the signal is designed, and then the spatial and temporal features are extracted from each sub-band. To maximize the classification accuracy while simplifying the model and using the smallest set of features, the feature selection stage is treated as a multiobjective optimization problem, and the Pareto optimal solutions of these two conflicting objectives are obtained. For the feature selection stage, non-dominated sorting genetic algorithm II (NSGA-II), an evolutionary-based algorithm, is used wrapper-based, and its effect on the BCI performance is explored. The proposed method is
implemented on a public dataset known as BCI competition III dataset IVa.
Results: Extracting the spatial and temporal features from different sub-bands and selecting the features with an evolutionary optimization approach in this study led to an improved classification accuracy of 92.19% which has a higher value compared to the state of the art.
Conclusion: The results show that the proposed improved classification accuracy could achieve a high-performance subject-specific BCI system.
| بازنشر اطلاعات | |
 | این مقاله تحت شرایط Creative Commons Attribution-NonCommercial 4.0 International License قابل بازنشر است. |
