MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202641095643 A) filed by Mohan Babu University on August 07, 2026, for Deep Learning-Based Eeg Classification System For Psychiatric Disorder Diagnosis.
Inventors include Ms. T. Ramya; Mr. M. Jayanth Reddy; Mr. M. Pavan Bala Subash Reddy; Ms. C. Ramya Triveni; and Mr. N. Sri Varun.
The application for the patent was published on August 14, 2026, under issue no. 33/2026.
Abstract: The present invention relates to a deep learning-based electroencephalogram (EEG) classification system for the automated diagnosis of psychiatric disorders using advanced biomedical signal processing and artificial intelligence techniques. The invention comprises an EEG signal acquisition module, preprocessing module, Markov Transition Field (MTF) transformation module, data augmentation module, deep convolutional neural network classifier, performance evaluation module, automated report generation module, and clinical decision support interface. During operation, raw EEG signals are acquired from a subject and undergo Butterworth band-pass filtering and Independent Component Analysis (ICA) to eliminate noise and physiological artifacts. The preprocessed one-dimensional EEG signals are transformed into two-dimensional Markov Transition Field images, preserving temporal characteristics while enabling efficient spatial feature extraction by deep convolutional neural networks. Advanced augmentation techniques, including MixUp and geometric transformations, enhance model robustness and improve classification performance under limited and imbalanced datasets. The transformed EEG images are processed using deep residual learning architectures to accurately classify multiple psychiatric disorders. The system subsequently evaluates prediction performance using statistical metrics and automatically generates diagnostic reports for clinical interpretation. s. The invention provides a reliable, scalable, economical, and clinically applicable solution that significantly improves diagnostic accuracy, reduces subjective interpretation, enables early psychiatric disorder detection, accelerates clinical decision-making, and supports personalized mental healthcare through intelligent EEG-based automated diagnosis.
Disclaimer: Curated by HT Syndication.
