A novel WO-ANT: whale-ant optimization algorithm for detection of Parkinson’s disease

Parkinson’s disease (PD) is a neurological condition that impacts the quality of life for millions of people all over the world. A prompt and precise diagnosis of PD is absolutely necessary for the successful treatment and management of the condition. For the detection of PD, numerous methods exist in the literature, including speech-based methods, gait-based methods, and handwriting-based methods. Compared to the other two methods, the speech-based method is regarded as the most effective and competitive. The Whale-Ant Optimization Algorithm (WO-ANT) is a novel swarm optimization strategy that is presented in this paper as a potential method for the detection of PD via feature selection. To help in early detection, the proposed method attempts to enhance classification accuracy of PD detection by selecting an optimum subset of features from a wide feature space. In this paper, authors evaluate the classification efficacy of WO-ANT for PD using a speech-based method. MATLAB is used to implement the proposed method on the PD dataset obtained from Kaggle.com. The efficacy of the algorithm is evaluated based on the optimal subset of features, accuracy, and computational cost. WO-ANT accurately reduced the number of features from 23 to 4 giving an accuracy of 90.29%. According to the numerical results, the algorithm performed well in terms of accuracy and selection of the optimal number of features.