Parkinson Data Analysis and Prediction System Using Multi-Variant Stacked Auto Encoder

Parkinson Disease (PD) is a kind of neural disorder that affects a range of people. This disease has continuously growing stages to halt entire neural activities of any people. There are many techniques proposed to detect and predict PD using medical symptoms and measurements. The medical measurements provided by different experiments must be effectively handled to produce concrete results on the detection of PD. This saves many people from PD at earlier stage itself. Recent technologies focus on Machine Learning (ML) and Deep Learning (DL) techniques for effective PD data analysis for making efficient prediction system. They are concentrating to build complex artificial neural systems using effective learning functions. However, the existing systems are lacking to attain multi-attribute and multi-variant data analysis to predict PD. To attain multi-variant Parkinson symptom analysis, the artificial neural systems must be equipped with more characteristics. In this regard, the Proposed system is developed using Multi-Variant Stacked Auto Encoder (MVSAE). The MVSAE based PD Prediction System (MSAEPD) helps to analyze more PD symptoms than existing systems. This article provides four different variants of SAE construction procedures to predict PD symptoms. The MSAEPD is implemented and compared with existing works such as MANN, GAE and UMLBD. This comparison shows the MSAEPD system gives 5% to 10% better results than existing works.