• Dr Puja Shashi

Parkinson's disease is first and foremost described as a neurologic condition which impacts the brain and spinal cord and makes sufferers unable to speak, walk, or control their tremors. This technique examines the categorization of audio signals feature sets to determine Parkinson's disease (PD); the classifiers utilized within this process are on machine learning algorithms. Parkinson's disease patients frequently have low-volume, monotonous noise. The sound component dataset retrieved from the UCI dataset repository, parametric regression, and XGboost classifiers are all commonly used in our approach. The system produced a significantly better prediction of the palladium patient's condition thanks to XGBoost, which had an overall accuracy rate of 96% and an MCC of 89%. Millions of people all over the world suffer with Parkinson's disease, a neurological disorder. In persons older than 50, Parkinson's disease (PD) affects 60% of them. Parkinson's disease patients find it challenging to get to appointments for medical care and surveillance since they have trouble speaking and functioning. Parkinson's disease can be treated if it is discovered early, allowing patients to lead regular lives. The requirement for quickly, accurate, distant Parkinson's disease detection is emphasized by the aging global population. Recent advances within machine learning indicate immense potential for early identification and evaluation of Parkinson's disease. In this study, we introduce a novel approach for diagnosing Parkinson's disease using machine learning methods and the Xception structure. Our algorithms worked brilliantly, showing training success for Parkinson's disease detecting from circular pictures of 95.34% and validate efficiency of 93.00% as well as training efficiency for Parkinson's disease detecting from wave pictures of 93.34% and 86.00%, respectively.Our research demonstrates that prompt Parkinson's disease detection and diagnosis are possible using machine learning and the Xception structure. Our approach may enhance the disorder's diagnosis precision and timeliness, leading to better treatment results and greater quality of life.

Parkinson’s Disease Prediction, XGBOOST, SVM, Machine learning.

"Parkinson's Disease Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.210-215, May-2024, Available :http://www.jetir.org/papers/JETIRGG06033.pdf

"Parkinson's Disease Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. pp210-215, May-2024, Available at : http://www.jetir.org/papers/JETIRGG06033.pdf