Parkinson Disease Detection Using Optimization Algorithm

The detection of Parkinson's disease is crucial for early diagnosis and effective treatment. In this study, we propose a comprehensive approach for Parkinson's disease detection using optimization algorithms. We begin by preprocessing the Parkinson's dataset, employing data cleaning, normalization, and PCA feature selection to enhance data quality and reduce dimensionality. The dataset is then split into training and testing sets for model development and evaluation. We implement Multilayer Perceptron (MLP) and Support Vector Machine (SVM) models using the PCA-selected features as input. To enhance model performance, we apply optimization algorithms including Firefly Algorithm, Particle Swarm Optimization (PSO), Grasshopper Optimizer, Grey Wolf Optimizer, and Genetic Algorithm (GA) to fine-tune hyper parameters and model architecture. The optimized MLP and SVM models are rigorously assessed using various performance metrics such as accuracy, precision, recall, F1-score, and ROC curves. This research aims to provide an efficient and accurate method for Parkinson's disease detection, contributing to early diagnosis and improved patient care.

Keywords: ML evaluation, ML techniques, etc..