Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Leakage Current Analysis of Glass, Porcelain, and Silicone Insulators Under Icing Conditions Using Spectrogram-Based Deep Convolutional Neural Networks.

Sensors (Basel, Switzerland)·2026
Same author

CONECT: Novel Weighted Networks Framework Leveraging Angle-Relation Connection (ARC) and Metaheuristic Algorithms for EEG-Based Dementia Classification.

Sensors (Basel, Switzerland)·2025
Same author

Fast Fractional Fourier Transform-Aided Novel Graphical Approach for EEG Alcoholism Detection.

Bioengineering (Basel, Switzerland)·2024
Same author

A NEW ARTIFICIAL INTELLIGENCE-BASED CLINICAL DECISION SUPPORT SYSTEM FOR DIAGNOSIS OF MAJOR PSYCHIATRIC DISEASES BASED ON VOICE ANALYSIS.

Psychiatria Danubina·2023
Same author

Exploring deep residual network based features for automatic schizophrenia detection from EEG.

Physical and engineering sciences in medicine·2023
Same author

Real-Time Depth of Anaesthesia Assessment Based on Hybrid Statistical Features of EEG.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Aug 28, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.2K

SchizoGoogLeNet: The GoogLeNet-Based Deep Feature Extraction Design for Automatic Detection of Schizophrenia.

Siuly Siuly1, Yan Li2, Peng Wen3

  • 1Institute for Sustainable Industries & Liveable Cities, Victoria University, Melbourne, Australia.

Computational Intelligence and Neuroscience
|September 19, 2022
PubMed
Summary

This study introduces SchizoGoogLeNet, a deep learning model for detecting schizophrenia (SZ) using electroencephalogram (EEG) signals. It achieves high accuracy, outperforming traditional methods for diagnosing this brain disorder.

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

Related Experiment Videos

Last Updated: Aug 28, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.2K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Schizophrenia (SZ) is a severe brain disorder characterized by abnormal reality interpretation.
  • Traditional SZ detection relies on tedious, manual feature extraction, limiting efficiency and accuracy.
  • Existing methods struggle to balance performance in distinguishing SZ from healthy controls (HC).

Purpose of the Study:

  • To develop an automated, deep learning-based feature extraction scheme for SZ detection using EEG signals.
  • To introduce the "SchizoGoogLeNet" model for efficient and accurate discrimination between SZ patients and HC subjects.
  • To evaluate the performance of deep features extracted by GoogLeNet using various classifiers.

Main Methods:

  • EEG data preprocessing using average filtering to enhance signal-to-noise ratio.
  • Employing a GoogLeNet model for automated deep feature extraction from denoised EEG signals.
  • Classifying SZ patients and HC subjects using extracted deep features evaluated by GoogLeNet and other machine learning classifiers.

Main Results:

  • The SchizoGoogLeNet model achieved a 99.02% classification rate for SZ and 98.84% overall accuracy when combined with a support vector machine classifier.
  • The proposed deep feature extraction method significantly outperformed existing approaches.
  • The model demonstrated high efficacy in accurately discriminating between SZ and HC individuals.

Conclusions:

  • The "SchizoGoogLeNet" deep learning framework offers an efficient and accurate method for SZ detection using EEG signals.
  • This approach surpasses traditional manual feature extraction in terms of performance.
  • The developed model holds potential for creating advanced diagnostic tools for schizophrenia.