Stacking ensemble based deep neural networks modeling for effective epileptic seizure detection
Introduction
Epilepsy, which is one of the brain diseases, indicates itself as a blackout, out of balance physique acts, preternatural sensuality or muscle contraction as a result of the abnormal pathological oscillatory activity of a bunch of connected neurons in the brain (Kaya, Uyar, Tekin & Yıldırım, 2014; Raghu, Sriraam, Hegde & Kubben, 2019; Yuan, Zhou, Li & Cai, 2011; Zazzaro et al., 2019). This disease can cause physical injury and mental trauma or in the worst case scenario death because of reasons such as genetic and physical brain damage during seizures (Kalbkhani & Shayesteh, 2017; Kocadagli & Langari, 2017).
Epileptic seizures affect more than 50 million people in the world, but only 2/3 of them could be cure by antiepileptic drugs, and another 7–8% could be treated by surgical operations. Overall, 25% of individuals with epilepsy suffers because of lack of available therapy (Litt & Echauz, 2002).
Neurologists or field specialists mostly use Electroencephalography, in short called as EEG, signals to diagnose this disease (Rosas-Romero et al., 2019; Zazzaro et al., 2019). The EEG signals plotted by brain waves indicate the electrical activity of the brain and contain useful information about the condition of the brain Niedermeyer and Lopes da Silva (2005). The identification of these signals is conventionally performed by field-specialist. Manual scoring is liable to subject to human mistakes and is time-consuming, costly, and insufficient for creditworthy information (Bajaj & Pachori, 2012; Kabir, Siuly & Zhang, 2016; Kutlu, Kuntalp & Kuntalp, 2009). Therefore, automatic EEG seizure detection is of great importance for researchers in neuro-informatics. In other words, the diagnosis of this disease is a substantial subject in biomedical scrutiny and its evaluation. Automated systems are being developed to assess and detect epileptic seizure via EEG signals to prevent the situation which is field-specialist missing information (Kabir et al., 2016). The patients’ safety and life quality are improved if seizures can be predicted as early as possible before their occurrence (Chu, Chung, Jeong & Cho, 2017).
In sum, epilepsy detecting is conducted frequently by utilizing efficient automatic methods. Since the interpreting of EEG brain signals occupies many hours of neurologists, and reduces their efficiency, an expert system or decision support system is needed. In the literature, it has been observed that the studies that provide prediction performances of the base algorithms have been performed generally for EEG signals detection.
Due to the nature of science, new approaches are proposed day by day in terms of machine learning. In recent years, researchers have tried to find a more successful solution to improve the prediction performance in machine learning area. Inspired by this, in this study, a different methodological solution from the studies in literature that are of the same nature was employed to unleash an effective model with the utmost accuracy for automatically identification the two classes of EEG signals. The solution mainly focuses on the SEA-based modeling to improve the prediction performance. Stacking ensemble is a powerful technique which can enhance the prediction performance, and the model based on this approach is an up-to-date popular research topic in this field. It is core component of this study, and the fact that applying this model to epileptic seizure detection problem is the original side of this study. To the best my knowledge, so far no study has used SEA-based DNN modeling for epilepsy detection. To evaluate the performance of the model designed, 10-fold cross-validation technique was performed on training, validation and testing sets. The base DNN model was used also for evaluating and comparing of the performance of Stacking ensemble based DNN. In this context, the main focus of the study is to show the effectiveness of stacking ensemble approach where there is DNN as base learner and meta learner in automatically detection of epileptic seizure, and shows its performance better than base DNN model. Moreover, the main contributions of this study could be outlined as follows:
- (a)
Proposing of the SEA-based model to predict the epileptic seizure or not efficiently. This approach is valuable in terms of in expert and intelligent systems, and the experimental results are state-of-the-art.
- (b)
Adapting of the base DNN and SEA based DNN models, and comparing of them considering the accuracy, sensitivity and specificity metrics.
- (c)
Empirically results show that proposed model achieves superior performance to base DNN model; specifically, sensitivity measure.
The rest of the study is organized as follows. Section 2 presents the literature review. Section 3 describes the methodology in detail. Section 4 introduces the experimental design. Section 5 presents the experiments and results. Section 6 discusses the results and compares them with those by the state-of-the-art studies. Finally, Section 7 concludes the study.
Section snippets
Related work
The medical examines of EEG signals is a substantial classification topic. There have been distinctive studies for this subject throughout years. In this section, only recent publications were examined. Mahmoodian et al. detected the epileptic seizure by using a Support Vector Machine (SVM). They used the multi-channel intracranial EEG data from the Freiburg intracranial EEG recordings (Mahmoodian, Boese, Friebe & Haddadnia, 2019). Fan et al. early detected epileptic seizures by using
Methodology
This section presents a brief idea about the base DNN and Stacked Ensemble based DNN modeling used in this study.
Data
In this study, the experiments were carried out on epileptic seizure dataset which is the publicly available EEG dataset collected from Bonn University, Germany (http://epilepsy.uni-freiburg.de/database). It consists of 11500 instances. These instances were obtained at a different point in time. The original dataset consists of 5 folders, each with 100 files. The number of attributes is 179; the outcome variable, which is the category information of the 178-dimensional input vector, is in the
Experiments and results
Fig. 3 displays the seizure detection flow chart of the proposed approach. The reason for choosing this modeling technique in this study is its effectiveness in machine learning. It is also compared with base DNN algorithm in order to evaluate the performance of this model.
Briefly, the proposed study consists of the following steps:
- (a)
To normalize of all attributes by performing min-max normalization.
- (b)
To feed the model designed.
- (c)
To classify the whole EEG signals as 1 and 0, considering whether there
Discussion
By experiments, it is concluded that EEG signals can be predicted by Stacking ensemble based DNN in acceptable level. Therefore, using this approach is much more effective than the base DNN model and it will be possible to predict the EEG signals. Many methods have been introduced to identify of EEG signals in binary; normal and epileptic, so far. A comparison with state-of-the-art methods is presented in Table 5. The comparison indicates that the proposed approach detects epileptic seizures
Conclusion
Analysis of EEG signals by visual examining puts a heavy burden on neurologists and reduces their efficiency. It should also be noted that it increases false detection. Therefore, the design of expert systems to assist neurologists in successfully classifying epileptic and non-epileptic EEG brain signals has always motivated researchers. Many studies have been carried out to address the signals as a classification problem, and have recently become increasingly common in the studies using deep
CRediT authorship contribution statement
Kemal Akyol: Conceptualization, Methodology, Software, Investigation, Data curation, Formal analysis, Validation, Supervision, Writing - original draft, Writing - review & editing.
Declaration of Competing Interest
I wish to confirm that there are no known conflicts of interest associated with this publication and there has been no financial support for this work that could have influenced its outcome.
References (40)
- et al.
Predicting epileptic seizures from scalp EEG based on attractor state analysis
Computer Methods and Programs in Biomedicine
(2017) - et al.
Automated epileptic seizure detection based on break of excitation/inhibition balance
Computers in Biology and Medicine
(2019) An introduction to ROC analysis
Pattern Recognition Letters
(2006)- et al.
Hilbert marginal spectrum analysis for automatic seizure detection in EEG signals
Biomedical Signal Processing and Control
(2015) - et al.
Automatic detection of epileptic seizure based on approximate entropy, recurrence quantification analysis and convolutional neural networks
Artificial Intelligence in Medicine
(2020) - et al.
Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks
Journal of Neuroscience Methods
(2010) - et al.
Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals
Clinical Neurophysiology
(2019) - et al.
Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals
Biomedical Signal Processing and Control
(2017) - et al.
Stockwell transform for epileptic seizure detection from EEG signals
Biomedical Signal Processing and Control
(2017) - et al.
1D-local binary pattern based feature extraction for classification of epileptic EEG signals
Applied Mathematics and Computation
(2014)
Classification of EEG signals for epileptic seizures using hybrid artificial neural networks based wavelet transforms and fuzzy relations
Expert Systems with Applications
Optimizing the performance of an MLP classifier for the automatic detection of epileptic spikes
Expert Systems with Applications
Epileptic seizure detection in EEG signals using sparse multiscale radial basis function networks and the Fisher vector approach
Knowledge-Based Systems
Prediction of epileptic seizures
The Lancet. Neurology
Epileptic seizure detection using cross-bispectrum of electroencephalogram signal
Seizure
Epileptic seizure detection in EEGs signals based on the weighted visibility graph entropy
Seizure
A study of combined lossy compression and seizure detection on epileptic EEG signals
Procedia Computer Science
Epileptic seizures detection based on some new Laguerre polynomial wavelets, artificial neural networks and support vector machines
Informatics in Medicine Unlocked
A novel approach for classification of epileptic seizures using matrix determinant
Expert Systems with Applications
Performance evaluation of DWT based sigmoid entropy in time and frequency domains for automated detection of epileptic seizures using svm classifier
Computers in Biology and Medicine
Cited by (118)
Classification of epileptic EEG signals with the utilization of Bonferroni mean based fuzzy pattern tree
2024, Expert Systems with ApplicationsHybrid VGG19 and 2D-CNN for intrusion detection in the FOG-cloud environment
2024, Expert Systems with ApplicationsTime-prior-based stacking ensemble deep learning model for ship infrared automatic target recognition in complex maritime scenarios
2024, Infrared Physics and TechnologyAn efficient feature selection and explainable classification method for EEG-based epileptic seizure detection
2024, Journal of Information Security and ApplicationsDiscriminating the default risk of small enterprises: Stacking model with different optimal feature combinations
2023, Expert Systems with Applications