Epileptic Seizure Detection Using Probability Distribution Based On Equal Frequency Discretization

Orhan, Umut; Hekim, Mahmut; Özer, Mahmut

doi:10.1007/s10916-011-9689-y

Cited by 27 publications

(16 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the selected problem area, the researcher should choose the most suitable method from the several that are available. In this study, a time series adapted neural network model, which can be used without having expertise on data, is proposed by combining a feature extraction method [27,28] and a conventional single layer perceptron classifier. This combination is a new entity like a chemical compound.…”

Section: Sfd Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Time series adapted supervised fuzzy discretization: an application to ECG signals

Orhan

2016

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

Abstract:In this study, a new method called supervised fuzzy discretization (SFD), which can be used without having expertise on data, is proposed for classifying time series datasets. Because an ECG signal has a partially stationary characteristic, its classification process is more difficult than it would be for completely stationary signals. On the other hand, because the method proposed can be used without having expertise on the data, comprehensive data like ECG signals are enough to introduce one such method. To prove the efficacy of the SFD, RR intervals selected from a common ECG database are used in the classification experiments. Some parameters, such as the coefficients of discretization, equal time slicing, learning rate, and momentum, are analyzed for the highest level of success in classification. A new mechanism called an inconsistency detector is suggested for increasing the level of success in supervised learning by adjusting the learning rate. The best results of the SFD method are compared with those of other studies in the same database, which hopefully establishes the proposed method as worth investigating in other areas because of its projected success.

show abstract

Section: Sfd Methodsmentioning

confidence: 99%

“…The frequencies of the amplitude values in time series are used as the features of the input signal in some studies [27,28]. In those studies aiming to extract the most meaningful features of a signal, a probability term is used to represent the likelihood of having an amplitude value in any discrete interval.…”

Section: Introductionmentioning

confidence: 99%

Time series adapted supervised fuzzy discretization: an application to ECG signals

Orhan

2016

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

show abstract

“…Assume that the signal has N patterns and this signal will be separated into K intervals. In this case, each interval between the cut-points c i will have N /K patterns [21].…”

Section: Ewd-and Efd-based Entropy Approachesmentioning

confidence: 99%

The classification of EEG signals using discretization-based entropy and the adaptive neuro-fuzzy inference system

Hekim¹

2016

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:A novel feature extraction called discretization-based entropy is proposed for use in the classification of EEG signals. To this end, EEG signals are decomposed into frequency subbands using the discrete wavelet transform (DWT), the coefficients of these subbands are discretized into the desired number of intervals using the discretization method, the entropy values of the discretized subbands are calculated using the Shannon entropy method, and these are then used as the inputs of the adaptive neuro-fuzzy inference system (ANFIS). The equal width discretization (EWD) and equal frequency discretization (EFD) methods are used for the discretization. In order to evaluate their performances in terms of classification accuracy, three different experiments are implemented using different combinations of healthy segments, epileptic seizure-free segments, and epileptic seizure segments. The experiments show that the EWD-based entropy approach achieves higher classification accuracy rates than the EFD-based entropy approach.

show abstract

“…With the fast development of EEG learning, we now can catch the EEG data quickly and analyze it in different ways, such as time domain and frequency domain analysis [2][3][4][5][6][7], neural network [7][8][9][10][11][12], chaotic analysis [13][14][15], etc. In this paper, we use multiscale symbolic transfer entropy (MSTE) to analyze the EEG with Lead Fp1 and Fp2.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Symbolic Transfer Entropy (MSTE) Analysis in Closing Eyes and Being Idle

Du¹,

Yao²,

Wang³

2017

Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 20

View full text Add to dashboard Cite

Abstract. It's impressive to learn about how our minds work. In this work, we have discovered that when a person closes his or her eyes, the value of multiscale symbolic transfer entropy(MSTE) [1] of electroencephalogram (EEG, Lead Fp1 and Fp2) grows larger. In other words, the coupling of Lead Fp1 and Fp2 is more significant when the experimenter closes his or her eyes, and we can capture the dynamic information and the its change more easily, which is useful for BCI and other practical uses.

show abstract

Epileptic Seizure Detection Using Probability Distribution Based On Equal Frequency Discretization

Cited by 27 publications

References 32 publications

Time series adapted supervised fuzzy discretization: an application to ECG signals

Time series adapted supervised fuzzy discretization: an application to ECG signals

The classification of EEG signals using discretization-based entropy and the adaptive neuro-fuzzy inference system

Multiscale Symbolic Transfer Entropy (MSTE) Analysis in Closing Eyes and Being Idle

Contact Info

Product

Resources

About