Epileptic seizure detection by exploiting temporal correlation of electroencephalogram signals

Parvez, Mohammad Zavid; Paul, Manoranjan

doi:10.1049/iet-spr.2013.0288

Cited by 31 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parvez and Paul [ 8 ] have presented a brief review of literature on feature extraction from the ictal and interictal signal using various established transformation methods. The authors have proposed different methods employed in the transform domain and its corresponding feature used for classification.…”

Section: Prior Researchmentioning

confidence: 99%

Review on Epileptic Seizure Prediction: Machine Learning and Deep Learning Approaches

Natu

Bachute

Gite

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Epileptic seizures occur due to brain abnormalities that can indirectly affect patient’s health. It occurs abruptly without any symptoms and thus increases the mortality rate of humans. Almost 1% of world’s population suffers from epileptic seizures. Prediction of seizures before the beginning of onset is beneficial for preventing seizures by medication. Nowadays, modern computational tools, machine learning, and deep learning methods have been used to predict seizures using EEG. However, EEG signals may get corrupted with background noise, and artifacts such as eye blinks and physical movements of muscles may lead to “pops” in the signal, resulting in electrical interference, which is cumbersome to detect through visual inspection for longer duration recordings. These limitations in automatic detection of interictal spikes and epileptic seizures are preferred, which is an essential tool for examining and scrutinizing the EEG recording more precisely. These restrictions bring our attention to present a review of automated schemes that will help neurologists categorize epileptic and nonepileptic signals. While preparing this review paper, it is observed that feature selection and classification are the main challenges in epilepsy prediction algorithms. This paper presents various techniques depending on various features and classifiers over the last few years. The methods presented will give a detailed understanding and ideas about seizure prediction and future research directions.

show abstract

Section: Prior Researchmentioning

confidence: 99%

Review on Epileptic Seizure Prediction: Machine Learning and Deep Learning Approaches

Natu

Bachute

Gite

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Parvez et al Enhanced seizure detection was carried out utilizing the temporal correlation within the EEG signals. According to their approach, the EEG signal is parted into a few epochs and then arranged into a 2D matrix and different transformation/decomposition methods are applied to dig out a few statistical features and these features are then applied as input into LS-SVM (Least Square-Support Vector Machine) for further classification [2]. The reason for using LS-SVM is the minimized operational error, maximized margin hyperplane, and the better classification obtained by taking into consideration by the accuracy of the ictal and interictal period of epilepsy.…”

Section: Related Workmentioning

confidence: 99%

Overhauled Approach to Effectuate the Amelioration in EEG Analysis

Beatrice¹,

Meena²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Discovering the information about several disorders prevailing in brain and neurology is by no means a new scientific technique. A neurological disorder of any human being can be analyzed using EEG (Electroencephalography) signal from the electrode's output. Epilepsy (spontaneous recurrent seizure) detection is usually carried out by the physicians using a visual scanning of the signals produced by EEG, which is onerous and may be inaccurate. EEG signal is often used to determine epilepsy, for its merits, such as non-invasive, portable, and economical, can exhibit superior temporal tenacity. This paper surveys the existing artifact removal methods. It puts a new-fangled mode forward to confiscate artifacts and hauls informative derived values from EEG to automate Epilepsy detection. The automated Epilepsy detection has to precisely indicate and detect the neural abnormality of the brain. This indication and detection process necessitates a proficient approach for the prompt removal of artifacts of the EEG signals. An effective artifact removal of EEG signals can alone enable the useful features of the original signals for further processing. Once the original signals excluding the noise is obtained, a delicate strategy for extracting the features of the signals, becomes mandatory in order to accomplish robust classification of the signal. Then an expert classification technique is implemented to aid the automated analysis process to correctly distinguish the EEG signal features.

show abstract

“…Then the energy concentration ratio (ECR) is determined between the energy of low-frequency coefficients against the energy of all-frequency coefficients after applying DCT on PME vector. In this way, temporal correlation [26] is exploited to determine the relative change of the signal in time domain. The main reason of using DCT is that it is an effective transformation to convert signal from the time domain to the frequency domain and to arrange them from low to high frequency coefficients [29].…”

Section: Feature Extraction Using Phase Correlationmentioning

confidence: 99%

Epileptic Seizure Prediction by Exploiting Spatiotemporal Relationship of EEG Signals Using Phase Correlation

Parvez

Paul

2016

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Automated seizure prediction has a potential in epilepsy monitoring, diagnosis, and rehabilitation. Electroencephalogram (EEG) is widely used for seizure detection and prediction. This paper proposes a new seizure prediction approach based on spatiotemporal relationship of EEG signals using phase correlation. This measures the relative change between current and reference vectors of EEG signals which can be used to identify preictal/ictal (before the actual seizure onset/ actual seizure period) and interictal (period between adjacent seizures) EEG signals to predict the seizure. The experiments show that the proposed method is less sensitive to artifacts and provides higher prediction accuracy (i.e., 91.95%) and lower number of false alarms compared to the state-of-the-art methods using intracranial EEG signals in different brain locations of 21 patients from a benchmark data set.

show abstract

Epileptic seizure detection by exploiting temporal correlation of electroencephalogram signals

Cited by 31 publications

References 27 publications

Review on Epileptic Seizure Prediction: Machine Learning and Deep Learning Approaches

Review on Epileptic Seizure Prediction: Machine Learning and Deep Learning Approaches

Overhauled Approach to Effectuate the Amelioration in EEG Analysis

Epileptic Seizure Prediction by Exploiting Spatiotemporal Relationship of EEG Signals Using Phase Correlation

Contact Info

Product

Resources

About