碩士 / 國立雲林科技大學 / 工業工程與管理系 / 104 / There will be one new cases of dementia every three seconds! The elderly population with dementia is common of disease. It’s a neurodegeneration in Alzheimer's Disease. The disease usually occurs on 65 years or older people. In recent year, the patients with Dementia increase in the elderly population in Taiwan. There are many causes of dementia living conditions, according to the degree of disorder were assessed cognitive function tests among patients with dementia, these methods are commonly used in clinical dementia assessment tools aim of this study was to add a new measure of the way to find effective identification of dementia disease and normal classification.
Our methods are MRI images segmentation of brain regions, the left half, right half, the integrity of the white matter and gray matter of the whole brain seven regions of the brain (Frontal、Temporal、Parietal 、Occipital、Limbic、midbrain、Sub lobar), hippocampus and the use of diffusion tensor imaging in λ1, λ2, λ3, FA(Fractional Anisotropy), MD(Mean Diffusivity), Cl(Linear), Cp(Planar), Cs(Spherical), RD(Radial Diffusivity) quantitative information to feature selection and CART (Classification And Regression Tree) decision tree model, performance measures for the receiver operating characteristic decision tree model, the probability of drawing each node curve.
This study combines attribute ranking and GRNN in classification of Alzheimer's Disease and decision tree creating decision rule. Experimental results showed that the accuracy of the GRNN classifier applied the input attribute ranking was 1.0000, and the classifier CART was 0.8787. GRNN classifier combined the attribute ranking provides the best classification performance.
| Identifer | oai:union.ndltd.org:TW/104YUNT0031030 |
| Date | January 2016 |
| Creators | Li,Mengchao, 李孟昭 |
| Contributors | Fu,Jachih, 傅家啟 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 113 |
Page generated in 0.0068 seconds