TY - GEN
T1 - Feature selection and time regression software
T2 - 18th European Signal Processing Conference, EUSIPCO 2010
AU - Ververidis, Dimitrios
AU - Van Gils, Mark
AU - Koikkalainen, Juha
AU - Lötjönen, Jyrki
PY - 2010
Y1 - 2010
N2 - In this paper, the Bayes classifier is used to predict Alzheimer's disease progress. The classifier is trained on a subset of the Alzheimer's Disease Neuroimaging Initiative database. Subjects are diagnosed by doctors as belonging to healthy, mild-cognitive impaired, and Alzheimer's disease class. A software tool for features selection and time regression is developed. The tool utilizes a variant of the Sequential Forward Selection (SFS) algorithm for feature selection, where the criterion used for selecting features is the correct classification rate of the Bayes classifier. The tool also employs linear regression to predict future values of selected biomarkers, such as the hippocampus volume, from past measurements, so that future class of the subject can be predicted.
AB - In this paper, the Bayes classifier is used to predict Alzheimer's disease progress. The classifier is trained on a subset of the Alzheimer's Disease Neuroimaging Initiative database. Subjects are diagnosed by doctors as belonging to healthy, mild-cognitive impaired, and Alzheimer's disease class. A software tool for features selection and time regression is developed. The tool utilizes a variant of the Sequential Forward Selection (SFS) algorithm for feature selection, where the criterion used for selecting features is the correct classification rate of the Bayes classifier. The tool also employs linear regression to predict future values of selected biomarkers, such as the hippocampus volume, from past measurements, so that future class of the subject can be predicted.
M3 - Conference contribution
AN - SCOPUS:84863799520
T3 - European Signal Processing Conference
SP - 1179
EP - 1183
BT - Proceedings of EUSIPCO
Y2 - 23 August 2010 through 27 August 2010
ER -