A Novel Wavelet Approach for Multiclass iEEG Signal Classification in Automated Diagnosis of Epilepsy

Rafiuddin, Nidal; Khan, Yusuf Uzzaman; Farooq, Omar

doi:10.1109/tim.2022.3207799

Cited by 4 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive research has been done on EEG signal processing to explore the underpinnings of specific regions of the brain. This is consistent with the EEG's ability to characterize a variety of neurological disorders including seizures [2], Alzheimer, dementia, brain tumors and sleep disturbances. However, due to inconsistent findings when dealing with neuropsychiatric disorders including, ADHD, autism, schizophrenia, depression, etc., it is still not accepted to be used as a diagnostic tool in clinical practice [3].…”

Section: Introductionsupporting

confidence: 78%

See 1 more Smart Citation

Automatic identification of ADHD children during visual attention task using variable length EEG

2023

1st International Conference on Modern and Advanced Research Icmar 2023

View full text Add to dashboard Cite

neuropsychiatric disorders affect millions of people of all ages worldwide. Attention deficit/Hyperactivity Disorder (ADHD), a typical neurodevelopmental disorder, deteriorates the performance of children in family and school settings thereby, hindering typical brain development. ADHD children, in most cases, are predominantly inattentive. In this research, automatic identification of neuronal patterns in ADHD children undergoing visual continuous performance tasks (CPT) is used to successfully differentiate between ADHD and typically developing children. The proposed methodology utilizes wavelet packet decomposition to extract relative energy from different EEG sub-bands, namely-delta (0.5-4 Hz) theta (4-8 Hz), alpha (8-13 Hz), beta1 (13-20 Hz), beta2 (20-30 Hz) and gamma (>30 Hz). The obtained feature from all bands is then passed to the Support Vector Machine (SVM) for the classification of children as normal and those with ADHD. The performance of the algorithm is assessed by following performance parameters, accuracy, sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve. While testing the classification performance keeping the relative energy of individual bands in feature space, it is observed that between groups difference in normal and ADHD is much higher in high-frequency bands i.e., beta and gamma compared to low-frequency bands. However, all other bands are interacting features that performed well along with the relevant features (beta and gamma energy bands, here). The area under the curve obtained with a subject-independent approach and combined EEG sub-band's relative energy in feature space is found to be 0.99.

show abstract

Section: Introductionsupporting

confidence: 78%

“…where, 𝑛 = 0, 1, 2, … … … . 2 𝑗 − 1 and fs is the sampling frequency [2], [19]. The signal decomposition block in Fig.…”

Section: Discrete Wavelet Packet Transformmentioning

confidence: 99%

Automatic identification of ADHD children during visual attention task using variable length EEG

2023

1st International Conference on Modern and Advanced Research Icmar 2023

View full text Add to dashboard Cite

show abstract

“…This process can be recursively repeated on successive approximations, creating a wavelet tree. The choice of an appropriate wavelet function for signal analysis can be somewhat complex since there are many different wavelet functions to choose from, such as the Morlet wavelet, Haar wavelet, Daubechies wavelet, and Coiflet wavelet, among others [66]. However, the final selection of the wavelet may depend on individual preferences and the characteristics of the signal.…”

Section: Higher-order Statistics For Wavelet Transformmentioning

confidence: 99%

Implementation of Machine Learning and Deep Learning Techniques for the Detection of Epileptic Seizures Using Intracranial Electroencephalography

Kołodziej,

Majkowski,

Rysz

2023

Applied Sciences

View full text Add to dashboard Cite

The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient’s electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy research is developing an automated system capable of detecting epileptic seizures with high sensitivity and precision. Moreover, there is an ongoing search for universal features in iEEG signals that can be easily interpreted by neurophysiologists. This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. The study presents standard approaches for analyzing iEEG signals, including chaos theory, energy in different frequency bands (alpha, beta, gamma, theta, and delta), wavelet transform, empirical mode decomposition, and machine learning techniques such as support vector machines. It also discusses modern deep learning algorithms such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. Our goal was to gather and comprehensively compare various artificial intelligence techniques, including both traditional machine learning methods and deep learning techniques, which are most commonly used in the field of seizure detection. Detection results were tested on a separate dataset, demonstrating classification accuracy, sensitivity, precision, and specificity of seizure detection. The best results for seizure detection were obtained with features related to iEEG signal energy (accuracy of 0.97, precision of 0.96, sensitivity of 0.99, and specificity of 0.96), as well as features related to chaos, Lyapunov exponents, and fractal dimension (accuracy, precision, sensitivity, and specificity all equal to 0.95). The application of CNN and LSTM networks yielded significantly better results (CNN: Accuracy of 0.99, precision of 0.98, sensitivity of 1, and specificity of 0.99; LSTM: Accuracy of 0.98, precision of 0.96, sensitivity of 1, and specificity of 0.99). Additionally, the use of the gradient-weighted class activation mapping algorithm identified iEEG signal fragments that played a significant role in seizure detection.

show abstract

Mother Wavelet for Optimal Feature Analysis in Multiclass EEG Signals

Rafiuddin

Khan

Farooq

2023

2023 International Conference on Recent Advances in Electrical, Electronics &Amp; Digital Healthcare Technologies (REEDCON)

View full text Add to dashboard Cite

A Novel Wavelet Approach for Multiclass iEEG Signal Classification in Automated Diagnosis of Epilepsy

Cited by 4 publications

References 52 publications

Automatic identification of ADHD children during visual attention task using variable length EEG

Automatic identification of ADHD children during visual attention task using variable length EEG

Implementation of Machine Learning and Deep Learning Techniques for the Detection of Epileptic Seizures Using Intracranial Electroencephalography

Mother Wavelet for Optimal Feature Analysis in Multiclass EEG Signals

Contact Info

Product

Resources

About