Analysis of High-Dimensional Phase Space via Poincaré Section for Patient-Specific Seizure Detection

Zabihi, Morteza; Kıranyaz, Serkan; Rad, Ali Bahrami; Katsaggelos, Aggelos K.; Gabbouj, Moncef; İnce, Türker

doi:10.1109/tnsre.2015.2505238

Cited by 118 publications

(56 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for classification, due to the huge individual difference of EEG characteristics, the training data of the same patient as test data were used for SVM model training. The model trained in our work can be viewed as a patient-specific model, which is consistent with most automated seizure detection studies in the literature [7,38,39]. Similarly, we employed sensitivity, specificity, precision, accuracy and F1 score as classification evaluation metrics.…”

Section: Chb-mit Databasementioning

confidence: 86%

“…However, acquisition of data from the test patient is required to train the seizure detection model or fine-tune the pre-trained model. Most automated seizure detection studies in literature focus on patient-specific classification models [7,38,39]. The generalization performance is a common limitation and remains a future work of our study.…”

Section: Limitations Of the Proposed Rr-dtdwtmentioning

confidence: 99%

See 1 more Smart Citation

Redundancy Removed Dual-Tree Discrete Wavelet Transform to Construct Compact Representations for Automated Seizure Detection

Jiang

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

With the development of pervasive sensing and machine learning technologies, automated epileptic seizure detection based on electroencephalogram (EEG) signals has provided tremendous support for the lives of epileptic patients. Discrete wavelet transform (DWT) is an effective method for time-frequency analysis of EEG and has been used for seizure detection in daily healthcare monitoring systems. However, the shift variance, the lack of directionality and the substantial aliasing, limit the effects of DWT in some applications. Dual-tree discrete wavelet transform (DTDWT) can overcome those drawbacks but may increase information redundancy. For classification tasks with small dataset sizes, such redundancy can greatly reduce learning efficiency and model performance. In this work, we proposed a novel redundancy removed DTDWT (RR-DTDWT) framework for automated seizure detection. Energy and modified multi-scale entropy (MMSE) features in a dual tree wavelet domain were extracted to construct a complete picture of mental states. To the best of our knowledge, this is the first study to employ MMSE as an indicator of epileptic seizures. Moreover, a compact EEG representation can be obtained after removing useless information redundancy (redundancy between wavelet trees, adjacent channels and entropy scales) by a general auto-weighted feature selection framework via global redundancy minimization (AGRM). Through validation on Bonn and CHB-MIT databases, the proposed RR-DTDWT method can achieve better performance than previous studies.

show abstract

Section: Chb-mit Databasementioning

confidence: 86%

Section: Limitations Of the Proposed Rr-dtdwtmentioning

confidence: 99%

Redundancy Removed Dual-Tree Discrete Wavelet Transform to Construct Compact Representations for Automated Seizure Detection

Jiang

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A series of studies have focused on Nonlinear Dynamical Analysis (NDA) of EEG signals to extract features for detection of epilepsy (Srinivasan, Eswaran, & Sriraam, 2007; Chen et al, 2011; Niknazar et al, 2013; Yaylali, Koçak, & Jayakar, 1996; Cerf, Amri, Ouasdad, & Hirsch, 1999; Adeli, Ghosh-Dastidar, & Dadmehr, 2007; Ghosh-Dastidar, Adeli, & Dadmehr, 2007; Iasemidis et al, 2003; Van Drongelen et al, 2003; Easwaramoorthy & Uthayakumar, 2011; Zhou, Liu, Yuan, & Li, 2013; Zabihi et al, 2016; Thomasson, Hoeppner, Webber, & Zbilut, 2001; Li, Ouyang, Yao, & Guan, 2004; Ouyang, Li, Dang, & Richards, 2008; Niknazar, Mousavi, Vahdat, & Sayyah 2013). These features include Approximate Entropy (ApEn) (Srinivasan et al, 2007; Chen et al, 2011; Niknazar et al, 2013), correlation dimension (Yaylali et al, 1996; Cerf et al, 1999; Adeli et al, 2007; Ghosh-Dastidar et al, 2007), Lyapunov exponent (Niknazar et al, 2013; Adeli et al, 2007; Ghosh-Dastidar et al, 2007; Iasemidis et al, 2003), Kolmogorov entropy (Van Drongelen et al, 2003), fractal dimension (Niknazar et al, 2013; Easwaramoorthy & Uthayakumar, 2011), lacunarity (Zhou et al, 2013), and features extracted from Poincaré section (Zabihi et al, 2016) as well as Recurrence Quantification Analysis (RQA) (Niknazar et al, 2013; Thomasson et al, 2001; Li et al, 2004; Ouyang et al, 2008; Niknazar et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

“…These features include Approximate Entropy (ApEn) (Srinivasan et al, 2007; Chen et al, 2011; Niknazar et al, 2013), correlation dimension (Yaylali et al, 1996; Cerf et al, 1999; Adeli et al, 2007; Ghosh-Dastidar et al, 2007), Lyapunov exponent (Niknazar et al, 2013; Adeli et al, 2007; Ghosh-Dastidar et al, 2007; Iasemidis et al, 2003), Kolmogorov entropy (Van Drongelen et al, 2003), fractal dimension (Niknazar et al, 2013; Easwaramoorthy & Uthayakumar, 2011), lacunarity (Zhou et al, 2013), and features extracted from Poincaré section (Zabihi et al, 2016) as well as Recurrence Quantification Analysis (RQA) (Niknazar et al, 2013; Thomasson et al, 2001; Li et al, 2004; Ouyang et al, 2008; Niknazar et al, 2013). …”

Section: Introductionmentioning

confidence: 99%

Automatic Seizure Detection Based on Nonlinear Dynamical Analysis of EEG Signals and Mutual Information

Akbarian

Erfanian

2018

BCN

View full text Add to dashboard Cite

Introduction:In this paper, nonlinear dynamical analysis based on Recurrence Quantification Analysis (RQA) is employed to characterize the nonlinear EEG dynamics. RQA can provide useful quantitative information on the regular, chaotic, or stochastic property of the underlying dynamics.Methods:We use the RQA-based measures as the quantitative features of the nonlinear EEG dynamics. Mutual Information (MI) was used to find the most relevant feature subset out of RQA-based features. The selected features were fed into an artificial neural network for grouping of EEG recordings to detect ictal, interictal, and healthy states. The performance of the proposed procedure was evaluated using a database for different classification cases.Results:The combination of five selected features based on MI achieved 100% accuracy, which demonstrates the superiority of the proposed method.Conclusion:The results showed that the nonlinear dynamical analysis based on Rcurrence Quantification Analysis (RQA) can be employed as a suitable approach for characterizing the nonlinear EEG dynamics and detecting the seizure.

show abstract

“…27 Using geometric features, regardless of any assumptions about the type of dynamics of the basis, provides studies independent of the hypothesis of chaos and therefore independent of the analysis of alternative data. 29 This study attempts to apply features based on phase space geometry to discover whether EEG changes can effectively identify absence seizures.…”

Section: Introductionmentioning

confidence: 99%

Detection and Prediction of Absence Seizures Based on Nonlinear Analysis of the EEG in Wag/Rij Animal Model

Lashkari

Sheikhani

Golpayegani

et al. 2018

Int Clin Neurosci J

View full text Add to dashboard Cite

Background: Epilepsy is a common neurological disorder with a prevalence of 1% of the world population. Absence epilepsy is a form of generalized seizures with Spike wave discharge in EEG. Epileptic patients have frequent absence seizures that cause immediate loss of consciousness. Methods: In this study, it has been tried to explore whether EEG changes can effectively detect epilepsy in animal model applying non-linear features. To predict the occurrence of absence epilepsy, a long-term EEG signal has been recorded from frontal cortex in seven Wag/Rij rats. After preprocessing, the data was transferred to the phase space to extract the brain system dynamic and geometric properties of this space. Finally, the ability of each features to predict and detect absence epilepsy with two criteria of predictive time and the accuracy of detection and its results were compared with previous studies. Results:The results indicate that the brain system dynamic changes during the transition from freeseizure to pre-seizure and then seizure. Proposed approach diagnostic characteristics yielded 97% accuracy of absence epilepsy diagnosis indicating that due to the nonlinear and complex nature of the system and the brain signal, the use of methods consistent with this nature is important in understanding the dynamic transfer between different epileptic seizures. Conclusion: By changing the state of the absence Seizures, the dynamics are changing, and the results of this research can be useful in real-time applications such as predicting epileptic seizures.

show abstract

Analysis of High-Dimensional Phase Space via Poincaré Section for Patient-Specific Seizure Detection

Cited by 118 publications

References 34 publications

Redundancy Removed Dual-Tree Discrete Wavelet Transform to Construct Compact Representations for Automated Seizure Detection

Redundancy Removed Dual-Tree Discrete Wavelet Transform to Construct Compact Representations for Automated Seizure Detection

Automatic Seizure Detection Based on Nonlinear Dynamical Analysis of EEG Signals and Mutual Information

Detection and Prediction of Absence Seizures Based on Nonlinear Analysis of the EEG in Wag/Rij Animal Model

Contact Info

Product

Resources

About