Classification of Parkinson's Disease using CNN and ANN with the aid of Drawing and Acoustic Feature

Fiza, Syed and Kumar, Ashish and Yadav, Jatin and Reddy, Sainandan and et al, . (2022) Classification of Parkinson's Disease using CNN and ANN with the aid of Drawing and Acoustic Feature. In: 2nd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2022, 28 April 2022 through 29 April 2022, Greater Noida.

[img] Text
2022_2nd_International_Conference_on_Advance_Computing.pdf - Published Version
Restricted to Registered users only

Download (454kB) | Request a copy


Parkinson's disease manifests itself in a variety of ways. slurred speech, muscle rigidity, and tremors. The condition can also affect the production of the brain's dopamine. Therapies can help treat conditions after a diagnosis, however, there is no remedy. The paper primarily analyses the many drawing evaluation methods and disease diagnoses that have been used. The AI deep learning idea was used, along with convolutional neural networks and artificial neural networks. However, this article proposes a model for detecting disease using drawings of different persons from two classes. Disease detection on photos has been accomplished using a variety of techniques such as data augmentation, sequential, and CNN. The acoustic feature data was processed using a Decision tree and ANN with GridsearchCV, and the overall accuracy on testing data was 98 percent. © 2022 IEEE.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Artificial neural network; Convolutional neural network; Decision Tree; GridSearchCV; Parkinson's disease
Subjects: Computer science
Others > Information sciences
Civil Engineering
Divisions: Department of Civil Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 16 Aug 2022 07:04
Last Modified: 16 Aug 2022 07:04
Publisher URL:
Related URLs:

    Actions (login required)

    View Item View Item
    Statistics for RAIITH ePrint 10182 Statistics for this ePrint Item