Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176096,
        author = {C Manoj kumar and Gudivada Lokesh and V Sridhar},
        title = {A HYBRID DEEP LEARNING APPROACH FOR EARLY PARKINSON’S DETECTION FROM HANDWRITING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4932-4941},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176096},
        abstract = {The Hybrid Deep Learning Approach study presents an enhanced Parkinson’s Disease (PD) detection model using deep transfer learning and genetic algorithm-based feature optimization. Unlike traditional approaches relying on error-prone handcrafted features, the proposed method employs VGG19, InceptionV3, and ResNet50 to extract robust features from NEWHANDPD spiral handwriting images. These features are further refined using a genetic algorithm to improve accuracy. K-Nearest Neighbour (KNN) is then used for classification. While Support Vector Machine (SVM) showed limited accuracy, KNN outperformed significantly. As an extension, hyperparameter tuning was applied to KNN, achieving improved accuracy of 96–98%, compared to the standard KNN’s 92–95%. This hybrid and optimized approach enhances early PD detection, supporting clinical decision-making with higher reliability.},
        keywords = {Disease, K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Parkinson’s Disease, Deep Learning, Convolutional Neural Networks (CNNs).},
        month = {April},
        }