Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 9:00 AM CET
Settings

Settings

Goto Application

1. IN202141041813 - ELECTROENCEPHALOGRAPHIC SIGNAL CLASSIFICATION VIA OPTIMISED FEATURE SELECTION ALGORITHMS FOR RECOGNITION OF ASD

Office
India
Application Number 202141041813
Application Date 16.09.2021
Publication Number 202141041813
Publication Date 12.11.2021
Publication Kind A
IPC
A61B
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
G06K
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
Applicants Ms. ROOPARECHAL TANIKONDA
Prof. P. RAJESH KUMAR
Dr. SK EBRAHEEM KHALEELULLA
Inventors Ms. ROOPARECHAL TANIKONDA
Prof. P. RAJESH KUMAR
Dr. SK EBRAHEEM KHALEELULLA
Title
(EN) ELECTROENCEPHALOGRAPHIC SIGNAL CLASSIFICATION VIA OPTIMISED FEATURE SELECTION ALGORITHMS FOR RECOGNITION OF ASD
Abstract
(EN) ABSTRACTTitle: Electroencephalographic Signal Classification via Optimised Feature SelectionAlgorithms for Recognition of ASDAutism spectrum disorder (ASD) is a complex formative condition that incorporates typical autism, pervasive developmental disorder, and Asperger's syndrome. Examination of electroencephalographic (EEG) signals based on autism is explored in this work. Even so, it is critical to. identify autism by the analysis of the EEG signal. The methodology includes EEG data acquisition, pre-processing, feature extraction, feature optimization finally, classification. In the first stage, The EEG signal obtained from pre-processing is fed to the feature extraction stage. The feature extraction stage extracts useful information from EEG for autism identification. Generally, the vital characteristics of EEG signals depend on amplitude and frequency ranges of different stages such as theta, alpha, delta, gamma, and beta. In this work, MATLAB software and an advanced signal processing tool kit will be used to extract information from EEG. The feature set from the extraction stage may contain irrelevant, correlated, and noisy features, misleading the classification. The feature optimization techniques are employed to select smaller feature subsets from original features, which improves system accuracy and reduces computation time. The Metaheuristic based optimization algorithms RELIEFF, FMFS, and PIE, are being implemented for feature selection. The outcome shows that the PIE with SVM method achieves high accuracy, showing a convincing way to recognize and classify autism.