E EG - Based Epileptic Seizures Detection with Adaptive Learning Capability

Ibrahim, Sutrisno; Majzoub, Sohaib

doi:10.15676/ijeei.2017.9.4.13

Cited by 5 publications

(2 citation statements)

References 30 publications

(73 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Ibrahim et al [116] proposed a methodology based on the DWT, the Shannon entropy and the k-nearest neighbors algorithm. Specifically, the DWT analyzes the signal into individual frequencies and Shannon entropy and the standard deviation are calculated for each frequency and for the whole spectrum.…”

Section: ) Time-frequency Domain Analysis A: Short-time Fourier Trans...mentioning

confidence: 99%

Machine Learning Algorithms for Epilepsy Detection Based on Published EEG Databases: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

Epilepsy is the only neurological condition for which electroencephalography (EEG) is the primary diagnostic and important prognostic clinical tool. However, the manual inspection of EEG signals is a time-consuming procedure for neurologists. Thus, intense research has been made on creating machine learning methodologies for automated epilepsy detection. Also, many research or medical facilities have published databases of epileptic EEG signals to accommodate this research effort. The vast number of studies concerning epilepsy detection with EEG makes this systematic review necessary. It presents a detailed evaluation of the signal processing and classification methodologies employed on the different databases and provides valuable insights for future work. 190 studies were included in this systematic review according to the PRISMA guidelines, acquired from a systematic literature search in PubMed, Scopus, ScienceDirect and IEEE Xplore on 1st May 2021. Studies were examined based on the Signal Transformation technique, classification methodology and database for evaluation. Along with other findings, the increasing tendency to employ Convolutional Neural Networks that use a combination of Time-Frequency decomposition methodology images is noticed.

show abstract

Section: ) Time-frequency Domain Analysis A: Short-time Fourier Trans...mentioning

confidence: 99%

Machine Learning Algorithms for Epilepsy Detection Based on Published EEG Databases: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Ibrahim and Majzoub [32] have incorporated discrete wavelet transform (DWT), standard deviation and Shannon entropy for seizure detection using an EEG signal. The researchers have employed K-nearest neighbors (KNN) for classification and used ten patients from the CHB-MIT dataset.…”

Section: Related Workmentioning

confidence: 99%

Automatic Seizure Detection Using Multi-Resolution Dynamic Mode Decomposition

et al. 2019

View full text Add to dashboard Cite

Epilepsy is one of the most prevalent neurological issues faced by a large population around the globe. Epilepsy is marked by intermittent seizures, the detection of which can be a challenging problem. Therefore, reliably detecting the onset of seizures has evoked the interest of researchers over the last few years. Major leaps in the domain of machine learning, signal processing methods, and computational capabilities have made it a tractable task. In this paper, we apply multi-resolution dynamic mode decomposition (MRDMD), which is a data-driven dimensionality reduction technique, on the problem of epileptic seizure detection. This method can effectively separate a complex non-linear system into a collection of timescale components at different resolutions. We have applied this algorithm on two different scalp EEG datasets, i.e., CHB-MIT and KU Leaven datasets. We have applied necessary post-processing steps to reduce the false alarm rate and boost the sensitivity and specificity. A detailed analysis of the results has been presented for the proposed method applied to both the datasets. The algorithm achieves a sensitivity of 0.937 and 0.96, a specificity of 0.99 and 0.99, a false alarm rate of 0.587 and 0.413 per hour, and a latency of 3.12 and 2.75 s for CHB-MIT and KU Leuven, respectively. The results indicate that the multi-resolution analysis yields a significant improvement in sensitivity compared with the basic dynamic mode decomposition.

show abstract