ABSTRACT
The disease of Parkinson’s is a neurological progressive disease which can affect anyone around the world and causes abnormalities in brain activity and motor function. For the early diagnosis of Parkinson’s disease symptoms, medical research has recently used computational intelligence tools, notably machine learning and deep learning approaches. These methods make use of numerous medical measurements made using various medical equipment, such as voice volume, handwriting fluctuations, bodily motions, brain signal variations, and protein aggregations. The moderate nature of the earliest indicators, however, makes it difficult to recognize Parkinson’s disease in its early stages. The algorithms of ML diagnose and predict with the help of audio data, is the main topic of this research study. Particularly, the examination of voice-related symptoms offers a potential route for practical and non-invasive screening methods. This problem is identified based on a combination of kinetic and other signs, including sluggishness, stiffness, balance problems, tremors, anxiety, breathing problems, sadness, etc. Our work intends to identify the most accurate diagnostic method/algorithm for early Parkinson’s disease identification by taking into account speech characteristics and patient data.
