ISSN: 0973-7510

E-ISSN: 2581-690X

R. Sampath1 and A. Saradha2
1Anna University, Chennai, India.
2Institute of Road Transport and Technology, Erode, Tamil Nadu, India.
J Pure Appl Microbiol. 2015;9(Spl. Edn. 1):691-699
© The Author(s). 2015
Received: 08/01/2015 | Accepted: 24/03/2015 | Published: 31/05/2015

Alzheimer’s disease (AD) is the most common type of dementia which is a significant public health problem. Therefore, several different automatic techniques have been established to support the clinicians in their diagnosis of AD and its stages. In this paper, a new novel combination of efficient and well-known techniques is introduced to effectively diagnosis of Alzheimer’s disease (AD) with its prodromal stages including Mild Cognitive Impairment (MCI). The 2D Gabor Wavelet approach is implemented on the images to extract the possible features from the images. The features are minimized by using the feature selection process and it is done using the genetic algorithm. The optimal minimized features are fed into the extreme machine learning classifier which classifies the prodromal stages of AD patients.  Structural MRI (SMRI) is a promising tool for diagnosing AD image for measuring the brain atrophy. The input data images are taken from the Alzheimer’s disease Neuroimaging Initiative (ADNI) database. The input sample images are given. The proposed 2D Gabor Wavelet feature extraction technique is compared with the Gray-Level Co-occurrence Matrix method and the Extreme Machine Learning classifier is compared with existing techniques such as Support Vector Machine (SVM), Adaptive Neuro Fuzzy Inference System and the Hybrid Neuro Fuzzy Runge Kutta. The results of this comparison show that the proposed techniques outperform all other techniques. The proposed system as a whole is evaluated in the final.


Alzheimer’s disease (AD), Structural MRI, 2D Gabor Wavelet (GW), Genetic Algorithm(GA), Extreme Machine Learning Classifier (EMLC)

Article Metrics

Article View: 867

Share This Article

© The Author(s) 2015. Open Access. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, sharing, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.