MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641076683 A) filed by Kondanna Kanamaneni; and Dr. Venkata Raju K on June 20, 2026, for Cnn And Som-Based Eeg Analysis For Epileptic Seizure Detection.
Inventors include Kondanna Kanamaneni; and Dr. Venkata Raju K.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: CNN and SOM-based EEG analysis for epileptic seizure detection is the proposed invention. Epilepsy is a neurological disorder characterized by recurrent seizures, making early detection and intervention crucial for patient management. Electroencephalography (EEG) is a primary diagnostic tool for epilepsy, providing valuable insights into brain activity. In this study, we propose a novel approach that combines Convolutional Neural Networks (CNNs) with Self Organizing Maps (SOMs) for EEG-based epileptic seizure detection. The proposed method begins with preprocessing EEG data to remove noise and artifacts, followed by CNN-based feature extraction. The CNN is trained to automatically learn spatial and temporal features from EEG signals, capturing patterns indicative of seizure activity. Subsequently, the extracted features are mapped onto a SOM, enabling dimensionality reduction and clustering of the high-dimensional feature space.
Disclaimer: Curated by HT Syndication.
