A multidimensional data analysis and evaluation of parkinson symptoms using deeply constructed networks

Abstract

Parkinson Disease (PD) is a severe kind of growing neural system newlinedisorder that disturbs the regular human activities. PD interrupts the human newlineactivities regularly regarding physical actions and mental actions based on the newlinelevel of disease development index. The development index of this PD changes from initial stages to extreme stages at gradual intervals. PD can affect any range of persons and is not purely curable and detectable at the initial stage. According to the medical survey, this disease affects older people significantly compared to the young people. Medical world is doing many researches to detect the PD symptoms as soon as possible to reduce the growth rate. This effort may not be successful unless the medical observations are analyzed by effective computerized techniques such as Artificial Neural Networks (ANN) based programs. ANN is an advanced technique that can be applied in various fields including medical data analysis. In the domain of ANN development, Machine Learning (ML) and Deep Learning (DL) algorithms are significantly taken for data evaluation procedures to detect the disease symptoms. These techniques are used to train the PD diagnosis systems to newlinedetect the symptoms as early as possible. Comparing to the ML techniques, DL techniques give more accurate results in PD detection. These DL techniques are helpful in increasing the knowledge of PD detection systems with the help of efficient PD datasets and features. newline newline