Optimal features for online seizure detection

Logesparan, Lojini; Casson, Alexander J.; Rodriguez‐Villegas, Esther

doi:10.1007/s11517-012-0904-x

Cited by 103 publications

(73 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this practice, skewness [37], kurtosis [37] [38], number of maxima and minima [37] [39], mean [40], variance [40] [41], standard deviation [38] and coefficient of variation [40] of each non-overlapping moving window with a length of 1 second as seven statistical features are extracted. In addition, root mean square amplitude [37] where , and are the mean, signal and the standard deviation of , respectively.…”

Section: Time Domain Featuresmentioning

confidence: 99%

“…However, the frequency domain for electroneurophysiologists is mostly defined as traditional EEG waves such as alpha, beta, theta and gamma. In this sub-section the maximum, minimum, and mean of power spectral density, spectral entropy [38] [39], and median frequency [38] as the most common features from frequency-domain are extracted.…”

Section: Frequency Domain Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Patient-specific epileptic seizure detection in long-term EEG recording in paediatric patients with intractable seizures

Zabihi

Kıranyaz

İnce

et al. 2013

IET Intelligent Signal Processing Conference 2013 (ISP 2013)

View full text Add to dashboard Cite

Over recent years, due to the increase in the epileptic patient population, issues of diagnosing and treatment of epilepsy have become more and more prominent and much research has been done in this field in consequence. However, there are still many gaps and lack of knowledge in interpreting Electroencephalograph (EEG) signals in order to solve the problem.Particular problems in this area include difficulties in detecting the seizure events (due to the different seizure types and their variability from patient to patient or even in an individual over time), and dealing with long-term EEG recordings, which is an onerous and time consuming task for electroencephalographers.The thesis discusses the two problem areas using EEG data from four subjects with overall 21 hours of recording from the CHB-MIT scalp benchmark EEG dataset. We propose a patient specific seizure detection technique, which selects the optimal feature subsets, and train a dedicated classifier for each patient in order to maximize the classification performance. To exploit the characteristics of a patient's EEG pattern as much as possible, we used a large set of features in the proposed framework, namely time domain, frequency domain, time-frequency domain and nonlinear features, and selected the most crucial features among them by using Conditional Mutual Information Maximization (CMIM) technique. We further performed extensive comparative evaluations against 6 other feature selection methods to demonstrate the superiority of the CMIM.Support Vector Machine (SVM) with the linear kernel is used as the classifier. The experimental results show a delicate classification performance over the test set, i.e. an average of 90.62% sensitivity and 99.32% specificity are acquired when all channels and recordings are used to form a composite feature vector. In addition, an average sensitivity and specificity rates of 93.78% and 99.05% are obtained using CMIM, respectively. PREFACEThis master thesis was carried out in the MUVIS group at the signal processing department of Tampere University of Technology. It was funded by the Academy of Finland.I wish to express my sincere gratitude to Professor Serkan Kiranyaz, whose inspiring guidance and inexhaustible patience have helped me cultivate a systematic approach towards the research. I am indebted to him for the freedom he gave me in implementing my ideas. I have also acquired valuable insights through his instruction in academic approach.I am very much grateful to Professor Turker Ince for his warm support and his valuable suggestions. Besides, I would also like to thank Professor Moncef Gabbouj for providing me with the opportunity for the thesis work. He gave me a lot of trust and flexibility in the project.I have been extremely fortunate in having valuable friends who have made a homely atmosphere for me during my stay in Tampere

show abstract

Section: Time Domain Featuresmentioning

confidence: 99%

Section: Frequency Domain Featuresmentioning

confidence: 99%

Patient-specific epileptic seizure detection in long-term EEG recording in paediatric patients with intractable seizures

Zabihi

Kıranyaz

İnce

et al. 2013

IET Intelligent Signal Processing Conference 2013 (ISP 2013)

View full text Add to dashboard Cite

show abstract

“…Seizure detection algorithms have been developed to solve different specific problems such as: seizure occurrence detection [1], onset detection [2], termination detection [7] and seizure recording/data selection [8]. Each type of algorithm discriminates between a specific seizure and non-seizure state at different times within the duration of the seizure.…”

Section: Introductionmentioning

confidence: 99%

“…In such studies, the performance metrics selected to evaluate the performance of these features must reflect the seizure detection problem to be solved. For example, the largest feature comparison study on adult scalp EEG [8] evaluates 65 different features using performance metrics pertinent to data selection for low power devices [12]. Another study [9] evaluated 21 features using performance metrics relevant to neonatal data selection [5] in applications where computational complexity/power consumption is not a limiting factor.…”

Section: Introductionmentioning

confidence: 99%

“…This paper demonstrates that the best features/algorithm bases will not be the same for every type of seizure detection problem, but depend on the testing methodology and type of seizure detection wanted. In particular, [8] evaluated 65 features for the seizure data selection case. This paper reevaluates the performance of these features when used in the seizure occurrence detection problem case.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminating between best performing features for seizure detection and data selection

Logesparan

Casson

Imtiaz

et al. 2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

Self Cite

View full text Add to dashboard Cite

Abstract-Seizure detection algorithms have been developed to solve specific problems, such as seizure onset detection, occurrence detection, termination detection and data selection. It is thus inherent that each type of seizure detection algorithm would detect a different EEG characteristic (feature). However most feature comparison studies do not specify the seizure detection problem for which their respective features have been evaluated. This paper shows that the best features/algorithm bases are not the same for all types of algorithms but depend on the type of seizure detection algorithm wanted. To demonstrate this, 65 features previously evaluated for online seizure data selection are re-evaluated here for seizure occurrence detection, using performance metrics pertinent to each seizure detection type whilst keeping the testing methodology the same. The results show that the best performing features/algorithm bases for data selection and occurrence detection algorithms are different and that it is more challenging to achieve high detection accuracy for the former seizure detection type. This paper also provides a comprehensive evaluation of the performance of 65 features for seizure occurrence detection to aid future researchers in choosing the best performing feature(s) to improve seizure detection accuracy.

show abstract