Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6951326 | Biomedical Signal Processing and Control | 2015 | 16 Pages |
Abstract
- We take the whole brain (not the ROIs) as the research objective, so there is no need for brain segmentation.
- The sensitivity of NC is up to 93.81%. The specificities of MCI and AD are 93.39% and 92.21%.
- We use 3D-DWT to capture the 3D texture feature of brain, use ALS-PCA for feature reduction of dataset containing missing attributes.
- We use TVAC-PSO to get the optimal kernel parameter of each individual KSVM.
- We compare three different multiclass KSVM methods, and find that WTA performs best.
Keywords
WTAKNNMSEMMSEasfROICDRRBFSMOMR(I)Magnetic resonance (imaging)Multiclass SVMk-nearest neighborSESmild cognitive impairmentCross validationGenetic algorithmClinical Dementia RatingSimulated annealingQuadratic programmingParticle swarm optimizationPSOsequential minimal optimizationAlzheimer's diseaseALSMagnetic resonance imagingRandom searchAlternating least squaresClassification accuracyDAGRadial basis functionConfusion matrixMini-Mental State Examinationregion of interestMCIOasissocio-economic statusNormal controlDirected acyclic graph
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Yudong Zhang, Shuihua Wang, Preetha Phillips, Zhengchao Dong, Genlin Ji, Jiquan Yang,