Extraction of Electroencephalography (EEG) Features to categorize the Mental Disorder

Time series analysis techniques are major in quantitatively studying the electroencephalogram (EEG). Whether conducting fundamental neurophysical or clinical research, a quantitative approach to EEG is essential. It can also be significant for strictly clinical research for psychological effects in...

Full description

Saved in:

Bibliographic Details
Published in:	2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT) pp. 1 - 6
Main Authors:	Sarvalingam, Parameswaran, Vajravelu, Ashok, Palpandi, S, Abinaya, B, Prasad, B, Sathesh, S, Kavin Kumar, K, Manivel, Murugesan
Format:	Conference Proceeding
Language:	English
Published:	IEEE 24-06-2024
Subjects:	Autism Autism Spectrum Disorder (ASD) Electroencephalography Electroencephalography (EEG) Epilepsy Feature extraction Internet of Things Kuppuswamy's socioeconomic status scale Neurons Recording Socioeconomics Time series analysis Variable speed drives
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Time series analysis techniques are major in quantitatively studying the electroencephalogram (EEG). Whether conducting fundamental neurophysical or clinical research, a quantitative approach to EEG is essential. It can also be significant for strictly clinical research for psychological effects in indoor. Millions of neurons make up the human brain, which is crucial for regular behavior and the body in response to both internal and external inputs and motor and sensory impulses. These neurons regulate how the body and brain communicate, and decipher brain signals or pictures utilized to comprehend how the brain processes information. Here, it is examine EEG data that show variations in frequency bands among several mental conditions, including bipolar illness and autism, to identify patterns among diseases. Different signals are seen in patients with autism syndrome disorder, general epilepsy, and normal controlled participants (ASD). For every reading genre, subjects are sorted and chosen at random: Four participants were chosen for ASD, and three each for controlled subjects and general epilepsy. The recordings can achieve the best classification accuracy for the subjects that match their waveforms thanks to the inferred characteristics that have been retrieved. The values of the attributes are crucial to analyze and determine the sort of condition the person is experiencing. As previously indicated, although the readings may differ, Kuppuswamy's socioeconomic status scale classifies the degree of harshness of the recordings, which is quite helpful in predicting whether the person is prone to the kind of mental condition. The findings are transmitted to healthcare professionals via the Internet of Things (IoT) for additional consultation.
ISSN:	2473-7674
DOI:	10.1109/ICCCNT61001.2024.10724402