Scribd
Upload
15 views2 pages

Abstract

The document discusses a hybrid classification-based system for the automatic detection and prevention of epileptic seizures using machine learning and EEG data. It highlights the importance of accurate seizure detection for effective epilepsy diagnosis and outlines the use of advanced algorithms like Nonlinear Vector Decomposed Neural Network and Wavelet analysis to improve accuracy. The proposed system demonstrates superior performance compared to conventional methods, achieving a high accuracy rate in classifying seizure signals.

Uploaded by

kingsaidsict
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
15 views2 pages

Abstract

The document discusses a hybrid classification-based system for the automatic detection and prevention of epileptic seizures using machine learning and EEG data. It highlights the importance of accurate seizure detection for effective epilepsy diagnosis and outlines the use of advanced algorithms like Nonlinear Vector Decomposed Neural Network and Wavelet analysis to improve accuracy. The proposed system demonstrates superior performance compared to conventional methods, achieving a high accuracy rate in classifying seizure signals.

Uploaded by

kingsaidsict
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

ABSTRACT

Health care sectors can achieve their development and accurately perform medical data

analysis and early disease detection with the use of medical data. The main objective is to

provide the effective and automatic detection of epileptic seizure classification using

intelligent feature extraction with machine learning models. Epilepsy is an emerging disease

distinguished by constant likelihood for growing epileptic seizures. A seizure is a brief

occurrence of symptoms or signs in the brain caused by abnormally high or synchronised

neuronal activity. A seizure does not necessarily mean that a person has epilepsy, unless the

criteria for diagnosis of epilepsy are met. If not properly treated in the early stage also results

in severe health issues and even some times to mortality. The proposed hybrid classification-

based detection and prevention system is designed with machine leaning algorithm. The

images are obtained from the [Link] this is an open-source

platform designed for developing and benchmarking epilepsy seizure-detection algorithms

using EEG data. The detection of epileptic discharges occurring in the EEG between seizures

is essential in epilepsy diagnosis. Several automatic EEG signalling classifications and

seizure discovery methods have been used in recent years, using various approaches. Still,

most of the existing techniques suffer from missed detection, have a high rate of false alarms

and low accuracy. Therefore, this research work provides EEG, an automated mechanism for

improving epilepsy seizure detection, using multiple domain features and hybrid ML analysis

to detect the sequencing process efficiency based on advanced novel soft computing

strategies such as Nonlinear Vector Decomposed Neural Network (NVDN-TM) with template

matching algorithms and Wavelet analysis based Asymmetrical Back Propagation Neural

Network (ABPN). The preprocessing is performed by hybrid gaussian blur spatial filter and

improving the accuracy of the proposed system is primarily based on designing an

appropriate representation space. Identifying the combination of all the extracted features by
using the Nonlinear Vector Decomposed Neural Network (NVDN-TM) with template

matching algorithms that increase the isolation between classes and Wavelet analysis based

Asymmetrical Back Propagation Neural Network (ABPN) can accurately categorize the

capture signal. The findings indicated that the proposed model emerged as the most effective

classifier and achieving a highest accuracy rate. The simulation result demonstrates that the

proposed system achieved the high-performance rate than the conventional methods.

You might also like