Dementia Prediction on OASIS Dataset using Supervised and Ensemble Learning Techniques
Shanmuga Skandh Vinayak E1, Shahina A2, Nayeemulla Khan A3
1Shanmuga Skandh Vinayak E*, Department of Information Technology, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India.
2Shahina A, Department of Information Technology, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India.
3Nayeemulla Khan A, School of Computing Sciences and Engineering, Vellore Institute of Technology, Chennai, India.Email: nayeemulla.khan@vit.ac.in
Manuscript received on October 05, 2020. | Revised Manuscript received on October 10, 2020. | Manuscript published on October 30, 2020. | PP: 244-254 | Volume-10 Issue-1, October 2020. | Retrieval Number: 100.1/ijeat.A18271010120 | DOI: 10.35940/ijeat.A1827.1010120
Open Access | Ethics and Policies | Cite | Mendeley
© 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: The Magnetic Resonance Imaging (MRI) data, which are a prevalent source of insight in understanding the inner functioning of the human body is one of the most preliminarymechanisms in the analysis of the human brain, including and not limited to detecting the presence of dementia. In this article, 7 machine learning models are proposed in the analysis and detection of dementiain the subjects ofOpen Access Series of Imaging Studies(OASIS) Brains 1, using OASIS 2 MRI and demographic data. The article also compares the performances of the machine learning models in terms of accuracy and prediction duration. The proposed model, eXtreme Gradient Boosting (XGB) algorithm performs with the highest accuracy of 97.87% and the fastest prediction durationof 0.031s/sample.
Keywords: Dementia, detection, Machine Learning, Algorithms, OASIS, feature selection, dimension reduction.