A Comparative Study of Naive Bayes, LDA and Gradient Boosting Classifiers for Epileptic Seizure Detection Using Discrete Wavelet Transform | IEEE Conference Publication | IEEE Xplore

A Comparative Study of Naive Bayes, LDA and Gradient Boosting Classifiers for Epileptic Seizure Detection Using Discrete Wavelet Transform


Abstract:

Epilepsy is a neurological condition that causes recurrent seizures and has a severe impact on an individual's quality of life. The precise diagnosis of epilepsy will ass...Show More

Abstract:

Epilepsy is a neurological condition that causes recurrent seizures and has a severe impact on an individual's quality of life. The precise diagnosis of epilepsy will assist doctors in providing patients with the relevant treatment. The Discrete Wavelet Transform (DWT) method is used to identify scalp EEG signals from electroencephalogram (EEG) data. The 'db4' mother wavelet of DWT is used for evaluating six sub-bands from EEG inputs. The sub-band signals are used to extract statistical and entropy features. Using the publicly accessible EEG dataset from the Children's Hospital of Boston-MIT, the collected features are subjected to Nave Bayes, Gradient Boosting, and Linear Discriminant Analysis. Conclusions from the analysis show that the Bayes algorithm produces the best results, with accuracy, sensitivity, specificity, and Negative Mean Squared Error of 96.12%, 96.12%, 100%, and 0.0453, respectively.
Date of Conference: 06-08 July 2023
Date Added to IEEE Xplore: 23 November 2023
ISBN Information:

ISSN Information:

Conference Location: Delhi, India

Contact IEEE to Subscribe

References

References is not available for this document.