杨婷1,
蒲秀娟1, 2,
黄谦1
1.重庆大学微电子与通信工程学院 重庆 400044
2.生物感知与智能信息处理重庆市重点实验室 重庆 400044
基金项目:重庆市自然科学基金(cstc2016jcyjA0376)
详细信息
作者简介:韩亮：男，1975年生，副教授，博士，研究方向为信号处理和图像处理
杨婷：女，1996年生，硕士生，研究方向为生物医学信号处理
蒲秀娟：女，1979年生，讲师，博士，研究方向为生物医学信号处理
黄谦：男，1998年生，硕士生，研究方向为信号与信息处理
通讯作者:韩亮 hanliangaa@cqu.edu.cn
中图分类号:TN911.7计量
文章访问数:489
HTML全文浏览量:144
PDF下载量:42
被引次数:0
出版历程
收稿日期:2020-11-10
修回日期:2021-01-31
网络出版日期:2021-03-01
刊出日期:2021-11-23
Method on Alzheimer’s Disease Classification Utilizing Fuzzy Logic Feature Selection and Heterogeneous Ensemble Learning
Liang HAN1, 2,,,Ting YANG1,
Xiujuan PU1, 2,
Qian HUANG1
1. School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
2. Chongqing Key Laboratory of Bio-perception & Intelligent Information Processing, Chongqing 400044, China
Funds:The Natural Science Foundation of Chongqing (cstc2016jcyjA0376)
摘要
摘要:阿尔茨海默症(AD)分类有助于在AD早期阶段及时采取针对性的治疗和干预措施，对降低老年群体的AD发病率和延缓AD疾病进展具有重要意义。该文提出一种改进的高斯模糊逻辑特征选择方法，首先采用互信息量和方差齐性分析两种方法给出特征重要性评分并分别进行归一化，然后使用改进的高斯模糊逻辑方法对其加权得到最终的特征重要性评分，最后依据特征重要性评分选取特征。该文还使用逻辑回归、随机森林、LightGBM、支持向量机和深度前馈网络作为初级分类器，多项式朴素贝叶斯分类器作为次级分类器，构建异质集成分类器，利用选取的特征进行AD分类。在TADPOLE数据集上进行实验，实验结果证实了所提特征选择方法是有效的，且采用所提特征选择方法，基于多项式朴素贝叶斯的异质集成分类器在AD分类上的性能要优于传统分类器。
关键词:阿尔茨海默症/
模糊逻辑/
特征选择/
多项式朴素贝叶斯/
异质集成分类器
Abstract:Early diagnosis of dementia is critical for timely treatment and intervention. Alzheimer’s Disease(AD) classification is an effective method on identifying AD at its early stage. In this paper, a feature selection method using improved Gauss fuzzy logic is proposed. Firstly, the normalized feature importance scores are calculated utilizing mutual information and variance analysis respectively. Then the final feature importance score is obtained by using improved Gauss fuzzy logic. At last, the features for AD classification are selected in accordance with the feature importance score. Furthermore, the heterogeneous ensemble classifier is constructed to classify AD patient utilizing selected features, which using logistic regression, random forest, LightGBM, support vector machine and depth feedforward network as primary classifier and multinomial naive Bayes classifier as secondary classifier. The proposed AD classification method is evaluated on the TADPOLE dataset. The experimental results show that the proposed feature selection method is effective and the integrated classifier based on Bayesian fusion is better than other conventional classification model on AD classification using the proposed feature selection method.
Key words:Alzheimer’s Disease(AD)/
Fuzzy logic/
Feature selection/
Multinomial naive Bayes/
Heterogeneous ensemble classifier
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=809f1263-c622-41b4-89a2-82b5e5bb569e
