Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques

Fatima Hassan, Syed Fawad Hussain*, Saeed Mian Qaisar

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Schizophrenia is a severe mental disorder that has adverse effects on the behavior of an individual such as disorganized speech and delusions. Electroencephalography (EEG) signals are widely used for its identification as they are non-invasive and have high temporal resolution. EEG signals may be captured using wearable devices but transmission of complete data from all channels is both battery and data consuming. Several studies on Schizophrenia have either used all channels or relied on sophisticated feature extraction algorithms to find the most relevant EEG channels for further processing. That too, however, needs data from all channels beforehand to identify the most relevant features. In this study, a publicly available multi-channel EEG signals dataset from the institute of Psychiatry and Neurology in Warsaw, Poland is studied for an automated identification of Schizophrenia using only a subset of data from selected channels. To achieve this, we device a channel selection mechanism based on a rigorous performance analysis of the Convolutional Neural Network (CNN) while considering the individual EEG channels at different brain regions. The selected channels are combined, and we use a fusion of CNN and different machine learning (ML) classifiers to train the classification model. Our experiments show that a combination of three channels namely, T4, T3, and Cz achieves 90% and 98% accuracies on subject-based and non-subject based testing, respectively, using a hybridization of CNN and logistic regression (LR).

Original languageEnglish
Pages (from-to)466-478
Number of pages13
JournalInformation Fusion
Early online date21 Dec 2022
Publication statusPublished - Apr 2023

Bibliographical note

Funding Information:
This work was primarily done as part of an MS thesis carried out by the first author at the G.I.K. Institute under supervision of Prof. Hussain. The corresponding author has since joined the University of Birmingham, where part of the manuscript and revisions were done.

Publisher Copyright:
© 2022 Elsevier B.V.


  • Convolutional neural network (CNN)
  • Electroencephalography (EEG)
  • Logistic regression
  • Schizophrenia

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Information Systems
  • Hardware and Architecture


Dive into the research topics of 'Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques'. Together they form a unique fingerprint.

Cite this