Online Seizure Detection from EEG and ECG Signals for Monitoring of Epileptic Patients

Mporas, Iosif; Tsirka, Vasiliki; Zacharaki, Evangelia I.; Koutroumanidis, Michalis; Megalooikonomou, Vasileios

doi:10.1007/978-3-319-07064-3_37

Cited by 13 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diagnosis of epilepsy is more challenging compared to the detection of seizure onset due to the semiological resemblance between epileptic and non-epileptic events, especially when video-EEG monitoring is not incorporated [25]. Also, the classification of abnormal episodes into different types requires a broad knowledge of EEG patterns across patients, while seizure detection can rely on patient-specific models which are easier to learn, especially for generalized seizures [26]. For the evaluation, we examined a number of different classification algorithms.…”

Section: Figurementioning

confidence: 99%

See 1 more Smart Citation

Improving classification of epileptic and non-epileptic EEG events by feature selection

et al. 2016

Self Cite

View full text Add to dashboard Cite

This is the Accepted Manuscript version of the following article: E. Pippa, et al, ???Improving classification of epileptic and non-epileptic EEG events by feature selection???, Neurocomputing, Vol. 171: 576-585, July 2015. The final published version is available at: http://www.sciencedirect.com/science/article/pii/S0925231215009509?via%3Dihub Copyright ?? 2015 Elsevier B.V.Correctly diagnosing generalized epileptic from non-epileptic episodes, such as psychogenic non epileptic seizures (PNES) and vasovagal or vasodepressor syncope (VVS), despite its importance for the administration of appropriate treatment, life improvement of the patient, and cost reduction for patient and healthcare system, is rarely tackled in the literature. Usually clinicians differentiate between generalized epileptic seizures and PNES based on clinical features and video-EEG. In this work, we investigate the use of machine learning techniques for automatic classification of generalized epileptic and non-epileptic events based only on multi-channel EEG data. For this purpose, we extract the signal patterns in the time domain and in the frequency domain and then combine all features across channels to characterize the spatio-temporal manifestation of seizures. Several classification algorithms are explored and evaluated on EEG epochs from 11 subjects in an inter-subject cross-validation setting. Due to large number of features feature ranking and selection is performed prior to classification using the ReliefF ranking algorithm within two different voting strategies. The classification models using feature subsets, achieved higher accuracy compared to the models using all features reaching 95% (Bayesian Network), 89% (Random Committee) and 87% (Random Forest) for binary classification (epileptic versus non-epileptic). The results demonstrate the competitiveness of this approach as opposed to previous methods

show abstract

Section: Figurementioning

confidence: 99%

“…For the evaluation, we examined a number of different classification algorithms. Our classification methodology can be used as part of our previous seizure detection architecture [26,27] in order to discriminate the detected events into epileptic or non-epileptic.…”

Section: Figurementioning

confidence: 99%

Improving classification of epileptic and non-epileptic EEG events by feature selection

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…A Matlab model has been created that extracts these features and is used in the ARMOR project for algorithm evaluation and optimization [14]. In parallel, an FPGA implementation based on Verilog code has been developed, which allows feature extraction on hardware -saving power and reducing communication bandwidth while reducing the overall workload of the main Micro Controller Unit (MCU) of the sensor.…”

Section: Functional Verificationmentioning

confidence: 99%

“…As shown, such capability yields a 95 % decrease of the data transmission required for Epilepsy seizure automatic identification. The proposed hardware accelerator has been thoroughly validated in comparison with the Matlab based feature vector extraction algorithms [14,15]. Moreover, the evaluation of the efficiency of the hardware accelerator reveals significant enhancements compared to software based implementations.…”

Section: Introductionmentioning

confidence: 99%

EEG Feature Extraction Accelerator Enabling Long Term Epilepsy Monitoring Based on Ultra Low Power WSNs

Mariatos

Antonopoulos

Voros

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Wireless sensor networks based on miniaturized ultra low power nodes are increasingly utilized in highly demanding cyberphysical systems required to offer extended time periods of non-intrusive and unattended monitoring of specific biophysical signals. However, although significant performance enhancements are offered by state of the art WSN platforms, still scarce energy availability comprises the Achilles' Hill of respective platforms. A prominent approach to remedy this deficiency is to transfer part of the overall processing applied on raw data into the WSN node, aiming to reduce drastically the amount of data than need to be wirelessly transmitted, thus allowing the radio chip to be turned off most of the time. The proposed approach has been applied in the context of ARMOR project, which focuses on EEG based Epilepsy monitoring and automated seizure detection, considering that seizure detection is based upon specific EEG feature vectors representing just *5 % of the total amount of raw data. In that respect, this paper presents the design, implementation and evaluation of a novel EEG feature vector extraction hardware accelerator module. The validity of the module's functionality is verified against already published Matlab based seizure detection algorithms while performance benefits are also estimated.

show abstract

“…Based on a thorough study of previous works [14], [15] we extracted the time domain features that has been proved to present the higher degree of correlation with sleep activity. This processing resulted in the extraction of the respective following features: …”

Section: B Feature Extractionmentioning

confidence: 99%

A Comparative Study between SVM and Fuzzy Inference System for the Automatic Prediction of Sleep Stages and the Assessment of Sleep Quality

Panagiotou¹,

Σαμαράς²,

Gialelis³

et al. 2015

Proceedings of the 9th International Conference on Pervasive Computing Technologies for Healthcare

View full text Add to dashboard Cite

Abstract-this paper compares two supervised learning algorithms for predicting the sleep stages based on the human brain activity. The first step of the presented work regards feature extraction from real human electroencephalography (EEG) data together with its corresponding sleep stages that are utilized for training a support vector machine (SVM), and a fuzzy inference system (FIS) algorithm. Then, the trained algorithms are used to predict the sleep stages of real human patients. Extended comparison results are demonstrated which indicate that both classifiers could be utilized as a basis for an unobtrusive sleep quality assessment.

show abstract

Online Seizure Detection from EEG and ECG Signals for Monitoring of Epileptic Patients

Cited by 13 publications

References 11 publications

Improving classification of epileptic and non-epileptic EEG events by feature selection

Improving classification of epileptic and non-epileptic EEG events by feature selection

EEG Feature Extraction Accelerator Enabling Long Term Epilepsy Monitoring Based on Ultra Low Power WSNs

A Comparative Study between SVM and Fuzzy Inference System for the Automatic Prediction of Sleep Stages and the Assessment of Sleep Quality

Contact Info

Product

Resources

About