Variable Channel Configuration Supporting Model for the Diagnosis of Schizophrenia

Author(s)	Subhang Mall
Country	United States
Abstract	When trying to classify schizophrenia using electroencephalography (EEG) data and a machine learning model, online datasets, research labs, and hospitals all use different EEG channel configurations and have different datasets. This strongly limits the interoperability between datasets and different institutions, preventing optimal training and classification. The purpose of this study was to figure out a way to be able to diagnose schizophrenia while maintaining compatibility with data sets with various channel configurations. A random zeroing of channels per epoch was used to make the model adaptable to different channel configurations. This model showed a relatively high level of accuracy from zero percent of the channels being zeroed out up to ninety percent of the channels being zeroed out. Therefore, it can be concluded that there is a high potential in the future for labs and datasets with different EEG configurations to eventually be able to share and use data, as shown by the relatively consistent accuracy, meaning more accurate and better classification.
Keywords	Artificial Intelligence, Schizophrenia, Machine Learning, Diagnosis
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-07-05

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research