Automatic Recognition of Parkinson’s disease via Artificial Neural Network and Support Vector Machine
Aprajita Sharma1, Ram Nivas Giri2
1Aprajita Sharma, Department of Computer Science Engineering, Raipur Institute of Technology, Raipur (Chhattisgarh), India.
2Ram Nivas Giri, Department of Computer Science Engineering, Raipur Institute of Technology, Raipur (Chhattisgarh), India.
Manuscript received on 14 August 2014 | Revised Manuscript received on 22 August 2014 | Manuscript Published on 30 August 2014 | PP: 35-41 | Volume-4 Issue-3, August 2014 | Retrieval Number: C1768084314/14©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Parkinson’s Disease (PD) is the next mainly common neurodegenerative disease only exceeds by Alzheimer’s Disease (AD). Parkinson’s disease is a general disease of central nervous system along with the aged person and its difficult symptoms introduce some complexities for the clinical diagnosis. Moreover, it is estimated to enlarge in the subsequently decade with accelerated treatment costs as an outcome. Medical results produces undesirable biases, faults and extreme clinical costs which influence the value of services offered to patients. Precise detection is extremely important for cure planning which can decreases the incurable results. Precise outcome can be achieved through Artificial Neural Network. In addition to being accurate, these methods must meet speedily in order to relate them for real time applications. Artificial Neural Network (ANN)-based diagnosis of medical diseases has been taken into great consideration in recent years.. In this paper three types of classifiers based on MLP, KNN, and SVM are used to support the experts in the diagnosis of PD. The dataset of this research is composed of a range of biomedical voice signals from 31 people, 23 with Parkinson’s disease and 8 healthy people. For this purpose, Parkinson’s disease data set, taken from UCI machine learning database was used .The results show a high accuracy of around 85.294%.
Keywords: Artificial Neural Network, Parkinson’s Disease, Pattern Recognition, Support Vector Machine.
Scope of the Article: Machine Learning