Affiliations: [a] School of Computer Science and Engineering University of Electronic Science and Technology of China, Chengdu, China
| [b] School of Computer Science and Engineering Southeast University, Nanjing, China
| [c] School of Mathematics and Statistics, Beijing Institute of Technology, Beijing, China
| [d] Department of Computer Science, University of Swabi, Pakistan
Correspondence:
[*]
Corresponding authors. Amin Ul Haq, School of Computer Science and Engineering University of Electronic Science and Technology of China, Chengdu 611731, China. E-mail: [email protected] and Jianping Li, E-mail: [email protected].
Abstract: Accurate and efficient recognition of Parkinson’s disease is one of the prominent issues in the field of healthcare. To address this problem, different methods have been proposed in the literature. However, existing methods are lacking in accurately recognizing the Parkinson’s disease and suffer from efficiency problems. To overcome these problems faced by existing models, this paper presents a machine-learning-based model for Parkinson’s disease recognition. Specifically, a hybrid feature selection algorithm has been designed by integrating the Relief and ant-colony optimization algorithms to select relevant features for training the model. Moreover, the support vector machine has been trained and tested on the selected features to achieve optimal classification accuracy. Additionally, the K-fold cross-validation technique has been employed for the optimal hyper-parameters value evaluation of the model.The experimental results on a real-world dataset, i.e., Parkinson’s disease dataset is revealed that the proposed system outperforms baseline competitors by accurately recognizing the Parkinson’s disease and achieving 99.50% accuracy on the selected features. Due to high performance is achieved our proposed method, we are highly recommended for the recognition of PD.
