• Suresha H.S.
• Dr. S.S. Parthasarathi

In recent years, several brain scans are collected from different tools to analyze human brain activities for Alzheimer disease detection. Among the available tools, Magnetic Resonance Imaging (MRI) is an effective tool to analyze the functions of the human brain. Initially, the MRI scans were collected from a dataset: Minimal Interval Resonance Imaging in Alzheimer's Disease (MIRIAD). After the collection of brain scans, pre-processing and skull stripping were performed by using histogram equalization and Otsu thresholding approaches. Then, segmentation was carried-out using modified- Kernelized Fuzzy C-Means (KFCM) for segmenting brain tissues: white matter, Cerebro-Spinal Fluid (CSF), and grey matter from the pre-processed brain scans. In addition, hybrid feature extraction (Histogram of Oriented Gradients (HOG), and Dual tree complex wavelet transform (DTCWT)) was used to extract the feature values from the segmented brain tissues. After extracting the feature values, Orthogonal Locality Preserving Projections (OLPP) approach was used for selecting the optimal feature values. Finally, the dimensionally reduced feature vectors were given as the input for multiclass classifier: Multi Support Vector Machine (MSVM) to classify three Alzheimer classes: normal, Alzheimer disease and Mild Cognitive Impairment (MCI). The experimental result showed that the proposed system improved the classification accuracy up to 15% as compared to the existing systems.

Dual tree complex wavelet transform, histogram of oriented gradients, kernelized fuzzy c-means, multi support vector machine, and orthogonal locality preserving projections.

"Early Diagnosis of Alzheimer’s Disease on the basis of Orthogonal Locality Preserving Projections and Multi Support Vector Machine", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.526-532, April-2019, Available :http://www.jetir.org/papers/JETIR1904B80.pdf

"Early Diagnosis of Alzheimer’s Disease on the basis of Orthogonal Locality Preserving Projections and Multi Support Vector Machine", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp526-532, April-2019, Available at : http://www.jetir.org/papers/JETIR1904B80.pdf