An efficient method for identification of epileptic seizures from EEG signals using Fourier analysis

Mehla, Virender Kumar; Singhal, Amit; Singh, Pushpendra; Pachori, Ram Bilas

doi:10.1007/s13246-021-00995-3

Cited by 39 publications

(14 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We would also like to point out that some other recent studies not listed in Table 4 , such as Li et al ( 55 ) and Mehla et al ( 33 ), also report very high values of the performance measures of accuracy, sensitivity and specificity for the same EEG database. However, the seizure detection methodology in such studies is also constructed in a way which may not be conducive in a practical scenario, as mentioned in the previous paragraph.…”

Section: Discussionmentioning

confidence: 64%

“…If specificity is also taken into account, the best seizure detection performance is still obtained using Feature 3 with SVM classifier. This is not surprising, as SVM has been the classifier of choice for seizure detection [e.g., ( 24 , 33 , 47 , 48 )]. The seizure detection results obtained using Feature 3 and SVM classifier for the EMD-based dictionary approach in terms of the averaged values of accuracy, sensitivity and specificity are 86.5, 89.9, and 86.4%, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…However, the seizure detection methodology in such studies is also constructed in a way which may not be conducive in a practical scenario, as mentioned in the previous paragraph. For example, the study in Li et al ( 55 ) balances the data using an over-sampling technique by adding synthetic data, whereas the study in Mehla et al ( 33 ) selects 1 h long records randomly from seizure and non-seizure data of all patients combined. In this regard, we would like to reiterate our position that our proposed approach caters to the realistic scenario of using a small portion of patients' historical data for the steps that lead to seizure detection using newer data.…”

Section: Discussionmentioning

confidence: 99%

“…Since the EEG recordings were originally sampled at 256 samples per second, a 4-s segment length contains 1,024 samples. Different lengths have been used in previous studies, with lengths of 1, 2, 3, 4, and even 10 s having been used ( 2 , 7 , 11 , 33 , 36 , 37 ).…”

Section: Methodsmentioning

confidence: 99%

“…A common aspect of the majority of seizure detection studies is pre-processing of EEG records for removal of artifacts [e.g., as mentioned in Mehla et al ( 33 ) and Zabihi et al ( 13 ) etc.]. The dictionary learning algorithm selects atoms (DWT components or IMFs) most similar to the seizure and non-seizure classes for inclusion in the trained dictionary, thereby excluding any components that may contain artifacts.…”

Section: Methodsmentioning

confidence: 99%

See 4 more Smart Citations

Comparison of Empirical Mode Decomposition, Wavelets, and Different Machine Learning Approaches for Patient-Specific Seizure Detection Using Signal-Derived Empirical Dictionary Approach

Kaleem¹,

Guergachi²,

Krishnan³

2021

Front. Digit. Health

View full text Add to dashboard Cite

Analysis of long-term multichannel EEG signals for automatic seizure detection is an active area of research that has seen application of methods from different domains of signal processing and machine learning. The majority of approaches developed in this context consist of extraction of hand-crafted features that are used to train a classifier for eventual seizure detection. Approaches that are data-driven, do not use hand-crafted features, and use small amounts of patients' historical EEG data for classifier training are few in number. The approach presented in this paper falls in the latter category, and is based on a signal-derived empirical dictionary approach, which utilizes empirical mode decomposition (EMD) and discrete wavelet transform (DWT) based dictionaries learned using a framework inspired by traditional methods of dictionary learning. Three features associated with traditional dictionary learning approaches, namely projection coefficients, coefficient vector and reconstruction error, are extracted from both EMD and DWT based dictionaries for automated seizure detection. This is the first time these features have been applied for automatic seizure detection using an empirical dictionary approach. Small amounts of patients' historical multi-channel EEG data are used for classifier training, and multiple classifiers are used for seizure detection using newer data. In addition, the seizure detection results are validated using 5-fold cross-validation to rule out any bias in the results. The CHB-MIT benchmark database containing long-term EEG recordings of pediatric patients is used for validation of the approach, and seizure detection performance comparable to the state-of-the-art is obtained. Seizure detection is performed using five classifiers, thereby allowing a comparison of the dictionary approaches, features extracted, and classifiers used. The best seizure detection performance is obtained using EMD based dictionary and reconstruction error feature and support vector machine classifier, with accuracy, sensitivity and specificity values of 88.2, 90.3, and 88.1%, respectively. Comparison is also made with other recent studies using the same database. The methodology presented in this paper is shown to be computationally efficient and robust for patient-specific automatic seizure detection. A data-driven methodology utilizing a small amount of patients' historical data is hence demonstrated as a practical solution for automatic seizure detection.

show abstract

Section: Discussionmentioning

confidence: 64%