2026-07-062026-07-062026-06-10https://repositorio.ifal.edu.br/handle/123456789/3108Our research focuses on the study of Parkinson’s Disease (PD). But what is Parkinson’s Disease? It is a progressive neurological disorder that develops gradually and compromises the sensorimotor system. For example, it causes symptoms such as tremors, slowness of movement (bradykinesia), and postural imbalance. PD affects millions of people worldwide, across all age groups; however, the elderly population is the most affected. Data from the World Health Organization (WHO) show that approximately 1% of the global population over the age of 65 has the disease. The main reason is the progressive loss of dopamine, which, in confirmed cases of PD, is found to be far below normal levels. Interestingly, studies have shown that reading and writing stimulate the production of neurotransmitters that increase dopamine. Thus, among the various possibilities for preventing the disease, we highlight that studying and writing, when practiced regularly as a personal and social habit, may mitigate the effects of Parkinson’s Disease. Diagnosing PD with precision is challenging, especially in its early stages. Among the existing techniques, micrography is commonly employed. This method essentially consists of handwriting examinations. It is precisely in the refinement of such techniques that Machine Learning (ML) emerges as a powerful category within computer science, improving data classification methods that identify patterns and assist in PD detection. Our research employs three ML models: HOG (Histogram of Oriented Gradients) + Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Transfer Learning (MobileNetV2), with the aim of classifying handwriting samples and contributing to greater accuracy and efficiency in medical diagnosis of PD. The results of our study highlight the use of a supervised ML program (developed by us and named Triple-N, after the author), which achieved promising performance. Specifically, it reached accuracy rates of 80% for HOG + SVM, 96% for CNN, and 98% for Transfer Learning, when combined with Data Augmentation techniques. These findings suggest that the application of Machine Learning, particularly with Data Augmentation, in the classification of handwriting examinations, can be a valuable tool in PD diagnosis. Two key advantages stand out: [1] low cost and [2] rapid delivery of results, enabling the majority of patients to access diagnosis from the early stages of the disease.ptAttribution-NonCommercial-NoDerivs 3.0 BrazilDoença de ParkinsonAprendizado de MáquinaAumentação de dadosMétodo do estudo imanenteParkinson's diseaseMachine learningData augmentationImmanent study methodTrabalho de Conclusão de CursoCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO::SISTEMAS DE INFORMACAO