作者: Vitoantonio Bevilacqua , Angelo Antonio Salatino , Carlo Di Leo , Giacomo Tattoli , Domenico Buongiorno
DOI: 10.1109/IJCNN.2015.7280463
关键词:
摘要: In this study, we compared several classifiers for the supervised distinction between normal elderly and Alzheimer's disease individuals, based on resting state electroencephalographic markers, age, gender education. Three main preliminary procedures served to perform features dimensionality reduction were used discussed: a Support Vector Machines Recursive Features Elimination, Principal Component Analysis novel method correlation. particular, five different compared: two configurations of SVM three optimal topologies Error Back Propagation Multi Layer Perceptron Artificial Neural Networks (EBP MLP ANNs). Best result, in terms classification (accuracy 86% sensitivity 92%), was obtained by Network with 3 hidden layers that as input: gender, education 20 EEG selected