Random Subspace Ensemble Artificial Neural Networks for First-episode Schizophrenia Classification

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F65269705%3A_____%2F16%3A00065861" target="_blank" >RIV/65269705:_____/16:00065861 - isvavai.cz</a>

Alternative codes found

RIV/00216224:14110/16:00091907

Result on the web

<a href="http://dx.doi.org/10.15439/2016F333" target="_blank" >http://dx.doi.org/10.15439/2016F333</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.15439/2016F333" target="_blank" >10.15439/2016F333</a>

Result language

angličtina

Original language name

Random Subspace Ensemble Artificial Neural Networks for First-episode Schizophrenia Classification

Original language description

Computer-aided schizophrenia diagnosis is a difficult task that has been developing for last decades. Since traditional classifiers have not reached sufficient sensitivity and specificity, another possible way is combining the classifiers in ensembles. In this paper, we take advantage of random subspace ensemble method and combine it with multilayer perceptron (MLP) and support vector machines (SVM). Our experiment employs voxel-based morphometry to extract the grey matter densities from 52 images of first-episode schizophrenia patients and 52 healthy controls. MLP and SVM are adapted on random feature vectors taken from predefined feature pool and the classification results are based on their voting. Random feature ensemble method improved prediction of schizophrenia when short input feature vector (100 features) was used, however the performance was comparable with single classifiers based on bigger input feature vector (1000 and 10000 features).

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2016

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 2016 Federated Conference on Computer Science and Information Systems (FEDCSIS)

ISBN

978-83-60810-90-3

ISSN

2300-5963

e-ISSN

—

Number of pages

5

Pages from-to

317-321

Publisher name

IEEE

Place of publication

New York

Event location

Gdansk, Poland

Event date

Sep 11, 2016

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000392436600050