Seizure detection by means of Hidden Markov Model and Stationary Wavelet Transform of electroencephalograph signals

Abdullah, Mohd Hezri; Abdullah, Jafri Malin; Abdullah, Mohd Zaid

doi:10.1109/bhi.2012.6211506

Cited by 14 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FP is the number of positives identified by experts but missed by the detection method. Conversely, TN is the number of negatives identified by the detection method and by experts, and FN is the number of negatives identified by experts but missed by the detection method .…”

Section: Resultsmentioning

confidence: 99%

Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals

Lee

Ryu²,

Kim

2020

ETRI Journal

View full text Add to dashboard Cite

Long‐term electroencephalography (EEG) monitoring is time‐consuming, and requires experts to interpret EEG signals to detect seizures in patients. In this paper, we propose a novel automated method called adaptive slope of wavelet coefficient counts over various thresholds (ASCOT) to classify patient episodes as seizure waveforms. ASCOT involves extracting the feature matrix by calculating the mean slope of wavelet coefficient counts over various thresholds in each frequency subband. We validated our method using our own database and a public database to avoid overtuning. The experimental results show that the proposed method achieved a reliable and promising accuracy in both our own database (98.93%) and the public database (99.78%). Finally, we evaluated the performance of the method considering various window sizes. In conclusion, the proposed method achieved a reliable seizure detection performance with a short‐term window size. Therefore, our method can be utilized to interpret long‐term EEG results and detect momentary seizure waveforms in diagnostic systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals

Lee

Ryu²,

Kim

2020

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…Perceiving iEEG as a sequence, Hidden Markov Models (HMM) [23,24,46] in this regard, is recommended as HMM is well acclaimed into many different types of sequence analysis, for example, speech recognition, molecular biology, data compression and time series. A limited number of works on the application of HMM have been published exploring various aspects of epilepsy as well, on privately acquired or publicly available iEEG data sets [2,7,15,17,26,58]. The essence of a few such relevant works are summarized below.…”

Section: Related Workmentioning

confidence: 99%

“…This can be viewed as a derived (or indirect) parsing of the amplitude (the recorded voltage values) generating labels for classification. In another study, Abdullah et al [2] used stationary wavelet transforms (SWT) to extract features from seven intractable focal epilepsy cases. This study also have three states labelled as ictal (seizure or clinical seizure), interictal (non-seizure or short or normal) and preictal (or maybe regarded as in-between or subclinical bursts).…”

Section: Related Workmentioning

confidence: 99%

“…The perspectives and understanding of the domain are what prevents this choice to be an arbitrary trial. In our case, as described in "Related Work", we rely on the findings of the previous studies in determining the number of hidden states [2,7,15,26,58]. Thereby, we consider three hidden, which are: (1) either the data given by the voltage values or the amplitude are reflection of the normal state of the diseased brain, or (2) there are tremor like seizure events (or preictal or in-between), which are below the threshold of danger and designated as the subclinical events, or (3) the full-blown seizure i.e.…”

Section: Viterbi Investigationmentioning

confidence: 99%

See 1 more Smart Citation

Analyzing Intracranial EEG in Pharmacoresistant Epilepsy Patients Using Hidden Markov Models and Time Series Forecasting Methods

2020

View full text Add to dashboard Cite

Various brain activities can be captured by electroencephalographic signals, which can then be used to detect epilepsy considering that the epileptic seizures are caused by a disturbance in the electrophysiological activity of the brain. Accordingly, epileptic seizure prediction usually requires a careful analysis of electroencephalography (EEG) records. In this study, we examined a large intracranial EEG dataset obtained from five pharmacoresistant epilepsy patients. Specifically, we first applied hidden Markov models to parse the amplitude under a probabilistic description considering the observed data as the outcome of either one of the three hidden states, namely, normal, subclinical (seizure) and clinical (seizure), which is in line with the setup proposed in previous studies. Our results indicate that there are indeed a maximum of 1.7% subclinical and about 1% clinical events, which comply with the observations from other studies. Next, we assumed EEG signals to form complex time series, and considered time-series prediction methods to forecast the future events. Such predictions are of interest to predetermine the possibility of a seizure onset and taking a preventive strategy. This task was performed within a deterministic framework by applying deep learning methods. An ensemble model was created using one-dimensional convolution net in conjunction with long short-term memory units and deep neural networks. We observe that the proposed time series prediction method is highly accurate as indicated by the low mean absolute error values and the high conformity of the predictions to the ground truth values.

show abstract

“…/ #%6--") &5 "-?4 [13] work Hidden Markov Model (HMM) was applied on vector quantized Stationary Wavelet Transform coefficients of intracranial EEG signal. Their work resulted with 96.38% and 96.82% average sensitivity and specificity respectively.…”

Section: Existing Workmentioning

confidence: 99%

Computer Assisted Analysis System of Electroencephalogram for Diagnosing Epilepsy

Ahmad

Khan

Majeed

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Automation of Electroencephalogram (EEG)analysis can significantly help the neurologist during the diagnosis of epilepsy. During last few years lot of work has been done in the field of computer assisted analysis to detect an epileptic activity in an EEG. Still there is a significant amount of need to make these computer assisted EEG analysis systems more convenient and informative for a neurologist. After briefly discussing some of the existing work we have suggested an approach which can make these systems more helpful, detailed and precise for the neurologist. In our proposed approach we have handled each epoch of each channel for each type of epileptic pattern exclusive to each other. In our approach feature extraction starts with an application of multilevel Discrete Wavelet Transform (DWT) on each 1 sec non-overlapping epochs. Then we apply Principal Component Analysis (PCA) to reduce the effect of redundant and noisy data. Afterwards we apply Support Vector Machine (SVM) to classify these epochs as Epileptic or not. In our system a user can mark any mistakes he encounters. The concept behind the inclusion of the retraining is that, if there is more than one example with same attributes but different labels, the classifier is going to get trained to the one with most population. These corrective marking will be saved as examples. On retraining the classifier will improve its classification, hence it will tries to adapt the user. In the end we have discussed the results we have acquired till now. Due to limitation in the available data we are only able to report the classification performance for generalised absence seizure. The reported accuracy is resulted on very versatile dataset of 21 patients from Punjab Institute of Mental Health (PIMH) and 21 patients from Children Hospital Boston (CHB) which have different number of channel and sampling frequency. This usage of the data proves the robustness of our algorithm.

show abstract

Seizure detection by means of Hidden Markov Model and Stationary Wavelet Transform of electroencephalograph signals

Cited by 14 publications

References 9 publications

Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals

Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals

Analyzing Intracranial EEG in Pharmacoresistant Epilepsy Patients Using Hidden Markov Models and Time Series Forecasting Methods

Computer Assisted Analysis System of Electroencephalogram for Diagnosing Epilepsy

Contact Info

Product

Resources

About