Paper Details: Downloads: 477
Serial Number: P1121102458
Title: Dementia Diagnosis relying on Texture based features and SVM classification
Authors: T. R. Sivapriya and V. Saravanan
Abstract: This research paper proposes an intelligent classification technique to identify normal and demented patients using Support vector machine. The manual interpretation of large volumes of brain MRI may lead to incomplete diagnosis. Hence the SVM approach is trained with multiple biomarkers to facilitate effective, accurate classification which is a requirement of the hour. SVM Classifier is compared with Backpropagation Neural Network (BPN) and BPN trained with Particle Swarm Optimisation (PSO). SVM classifier outperforms other classifiers in terms of sensitivity, specificity and accuracy in this analysis.
Keywords: Support vector machine, Neural Network, Backpropagation Neural Network,PSO
Journal/Conference: International Journal of Artificial Intelligence and Machine Learning
Volume: 11
Issue: 1
Submission Date: 1/10/2011 12:00:00 AM
Review Date: 2/26/2011 12:00:00 AM
Publishing Date: 4/20/2011 12:00:00 AM
Article Downloads: 477
Download:

Facebook