Fig 3 - uploaded by Alejandro Baldominos
Content may be subject to copyright.
Source publication
Epilepsy is one of the most common neurological conditions, affecting 2.2 million people only in the U.S., causing seizures that can have a very serious impact in affected people's lives, including death. Because of this, there is a remarkable research interest in detecting epilepsy as it occurs, so that it effects and consequences can be mitigated...
Context in source publication
Context 1
... a seizure occurs, it is often reflected in the EEG signal with a higher electric activity. An example of this effect is shown in figure 3, which plots a portion of an EEG channel where a seizure occurs. The seizure onset and ending is depicted in red, and it is visible how brain activity is much higher during the seizure. ...
Similar publications
Diagnosis of post-stroke epilepsy is often challenging because of a low incidence of epileptiform abnormalities on electroencephalography (EEG). Hence, this study evaluated whether postictal subtraction single-photon emission computed tomography (SPECT) could visualize epileptic activity and act as a diagnostic modality in post-stroke epilepsy. Fif...
Citations
... Baldominos and Ramon-Lozano [44] have discussed the problem of epilepsy seizures as a vital neurological condition that causes seizures with a severe probable impact on human health. This paper has described a seizure detection system based on energy. ...
... Then, Bat has shown the second-best accuracy with 98%. ACO has shown a demonstrated average accuracy of around 90%. Table 7. Accuracy result for other optimizer approaches group References Methods Dataset Accuracy (%) Baldominos and Ramon-Lozano [44] GA CHB-MIT Scalp EEG Shon et al. [45] GA+KNN DEAP 71.76% Abdi et al. [46] MOBCS-KNN standard EEG motor imagery 93.86% Pratiwi et al. [47] Hybrid cuckoo research the University of Bonn 90.0 % Yang et al. [48] KNN ADLs 94% Mo and Zhao [49] Magnetic bacteria+SVM BCI Competition IV dataset II-a 67% Figure 1. ...
span lang="EN-US">This paper presents a survey for optimization approaches that analyze and classify Electroencephalogram (EEG) signals. The automatic analysis of EEG presents a significant challenge due to the high-dimensional data volume. Optimization algorithms seek to achieve better accuracy by selecting practical features and reducing unwanted features. Forty-seven reputable research papers are provided in this work, emphasizing the developed and executed techniques divided into seven groups based on the applied optimization algorithm particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), grey wolf optimizer (GWO), Bat, Firefly, and other optimizer approaches). The main measures to analyze this paper are accuracy, precision, recall, and F1-score assessment. Several datasets have been utilized in the included papers like EEG Bonn University, CHB-MIT, electrocardiography (ECG) dataset, and other datasets. The results have proven that the PSO and GWO algorithms have achieved the highest accuracy rate of around 99% compared with other techniques.</span
... Various technologies for determining the epileptic features have been developed and investigated in the literature based on EEG recordings [10]- [30], ECG recordings [31]- [33], or both ECG and EEG recordings [7], [8], [34] as listed in Table I. It is noticed that the extracted features in most of the previous work are based on time [11], [16], [20], [35] or/and frequencydomain [8], [12], [14], [15], [28], [29], [31], [32] which could not capture the behavior of the non-stationary recordings due to the wide variety of frequencies, amplitudes, spikes, and waves that can appear during the seizure onset time [10]. Moreover, most of existing methods cannot generate a general capability model for seizure detection because they depend on limited subjects datasets, no more than 24 patients, with only one seizure type (i.e. ...
Automatic detection of epileptic seizures is still a challenging problem due to the intolerance of EEG. Introducing ECG can help with EEG for detecting seizures. However, the existing methods depended on fusing either the extracted features or the classification results of EEG-only and ECG-only with ignoring the interaction between them, so the detection rate did not improve much. Also, all EEG channels were considered in a complex manner. Moreover, the detection of epilepsy firing location, which is an important issue for diagnosing epilepsy, is not considered before. Therefore, we propose a new method based on the brain-heart interaction (BHI) for detecting the seizure onset and its firing location in the brain with lower complexity and better performance. BHI allows us to study the nonlinear coupling and variation of phase-synchronization between brain regions and heart activity, which are effective for distinguishing seizures. In our method, the EEG channels are mapped into two surrogate channels to reduce the computational complexity. Moreover, the firing location detector is triggered only once the seizure is detected to save the system's power. Evaluation using different proposed classification networks based on the TUSZ, the largest available EEG/ECG dataset with 315 subjects and 7 seizure types, showed that our BHI method improves the sensitivity by 48% with only 4 false alarms/24h compared to using only EEG. Moreover, it outperforms the performance of the average human detector based on the quantitative EEG tools by achieving a sensitivity of 68.2% with 11.9 false alarms/ 24h and a latency of 11.94 sec.
... Two databases were used in the experiments, and the performance of the classifier was evaluated for both. The results showed that the relevant features using a genetic algorithm produce better accuracy for seizure detection [15]. Alfahoumi et al. [16] proposed a new method for collecting the features from the required technique and selecting the properties of EEG signals. ...
Many approaches have been proposed using Electroencephalogram (EEG) to detect epilepsy seizures in their early stages. Epilepsy seizure is a severe neurological disease. Practitioners continue to rely on manual testing of EEG signals. Artificial intelligence (AI) and Machine Learning (ML) can effectively deal with this problem. ML can be used to classify EEG signals employing feature extraction techniques. This work focuses on automated detection for epilepsy seizures using ML techniques. Various algorithms are investigated, such as Bagging, Decision Tree (DT), Adaboost, Support vector machine (SVM), K-nearest neighbors(KNN), Artificial neural network(ANN), Naïve Bayes, and Random Forest (RF) to distinguish injected signals from normal ones with high accuracy. In this work, 54 Discrete wavelet transforms (DWTs) are used for feature extraction, and the similarity distance is applied to identify the most powerful features. The features are then selected to form the features matrix. The matrix is subsequently used to train ML. The proposed approach is evaluated through different metrics such as F-measure, precision, accuracy, and Recall. The experimental results show that the SVM and Bagging classifiers in some data set combinations, outperforming all other classifiers
... Two databases were used in the experiments, and the performance of the classifier was evaluated for both. The results showed that the relevant features using a genetic algorithm produce better accuracy for seizure detection [15]. Alfahoumi et al. [16] proposed a new method for collecting the features from the required technique and selecting the properties of EEG signals. ...
Many approaches have been proposed using Electroencephalogram (EEG) to detect epilepsy seizures in their early stages. Epilepsy seizure is a severe neurological disease. Practitioners continue to rely on manual testing of EEG signals. Artificial intelligence (AI) and Machine Learning (ML) can effectively deal with this problem. ML can be used to classify EEG signals employing feature extraction techniques. This work focuses on automated detection for epilepsy seizures using ML techniques. Various algorithms are investigated, such as Bagging, Decision Tree (DT), Adaboost, Support vector machine (SVM), K-nearest neighbors(KNN), Artificial neural network(ANN), Naïve Bayes, and Random Forest (RF) to distinguish injected signals from normal ones with high accuracy. In this work, 54 Discrete wavelet transforms (DWTs) are used for feature extraction, and the similarity distance is applied to identify the most powerful features. The features are then selected to form the features matrix. The matrix is subsequently used to train ML. The proposed approach is evaluated through different metrics such as F-measure, precision, accuracy, and Recall. The experimental results show that the SVM and Bagging classifiers in some data set combinations, outperforming all other classifiers
... Due to weak wavelet transformation signals, accurate methods have been established, however, the prediction accuracy cannot be demonstrated clearly. In order to minimize the time and improve the depiction accuracy level, classifications are evaluated using the FCM with MPSODT model (2)(3)(4) . Instant energy correlated with changes in the electro signals is calculated based on the features describing energy activity over time from different dimensions. ...
... These characteristics were nourished in different classifiers and achieved a net sensitivity of 70.4% [55]. An energy-based seizure detection algorithm was performed, and the genetic algorithm for optimization was used to refine the accuracy of the detection [56]. The Fast Wavelet Decomposition (FWD) approach was applied to extract features that were given to the Relevance Vector Machine (RVM) for the discrimination of epileptic and non-epileptic signals achieving a sensitivity of 96% [57]. ...
... LGBP features were extracted and nourished into different classifiers such as Logistic regression, random forest, and linear kernel SVM for seizure detection [55]. A genetic algorithm was utilized to provide seizure detection [56]. Energy and temporal features were extracted, and RVM was used to discriminate between seizure and non-seizure events [57]. ...
Epilepsy is a neurological disorder of the brain that causes frequent occurrence of seizures. Electroencephalography (EEG) is a tool that assists neurologists in detecting epileptic seizures caused by an unexpected flow of electrical activities in the brain. Automated detection of an epileptic seizure is a crucial task in diagnosing epilepsy which overcomes the drawback of a visual diagnosis. The dataset analyzed in this article, collected from Children's Hospital Boston (CHB) and the Massachusetts Institute of Technology (MIT), contains long-term EEG records from 24 pediatric patients. This review paper focuses on various patient-dependent and patient-independent personalized medicine approaches involved in the computer-aided diagnosis of epileptic seizures in pediatric subjects by analyzing EEG signals, thus summarizing the existing body of knowledge and opening up an enormous research area for biomedical engineers. This review paper focuses on the features of four domains, such as time, frequency, time-frequency, and nonlinear features, extracted from the EEG records, which were fed into several classifiers to classify between seizure and non-seizure EEG signals. Performance metrics such as classification accuracy, sensitivity, and specificity were examined, and challenges in automatic seizure detection using the CHB-MIT database were addressed.
... In other words, these features are evaluating EEG signal behaviors in T domain. T domain features like mean, median, mode, minimum, maximum, skewness, standard deviation, kurtosis, energy, correlation and histograms have been computed from EEG signal, previously [3][4][5][6][7][8][9][10][11][12]. The T domain cannot show many inherent behaviors of the EEG signal. ...
The electroencephalogram (EEG) signal is known as a nonlinear and complex signal. The EEG signal has very important information about brain activities and disorders which can detect by an accurate Computer-aided diagnosis system. The performance of the Computer-aided diagnosis system directly depends on using features in the classifiers. In this paper, we proposed nonlinear geometrical features for the classification of EEG signals. The normal, interictal and ictal EEG signals of the Bonn university EEG database are plotted in 2D space by a novel approach and considering their patterns, six features namely: area of the octagon (AOO), circle area (CA), the summation of vectors length (SVL), centroid to coordinate center (CTC), circular radius out of triangles (CRT) and triangle area (TA) are extracted on different aspects of distance in Cartesian space. Based on the Kruskal–Wallis statistical test, all of the features were found statistically significant in the discrimination of normal vs. ictal and interictal vs. ictal EEG signals (p-value≈0). Also, the edges of 2D projection EEG signals in the ictal group were sharper than normal and interictal groups. Besides, 2D projection of normal and interictal EEG signals has more regular geometrical shapes than the ictal group. Our proposed features were applied as input on support vector machine (SVM) and k-nearest neighbors (KNN) classifiers which resulted in more than 99% classification accuracy in a ten-fold cross-validation strategy.
... Tessy et al. [17] extracted two features in the time domain, namely energy and line length of signals. Baldominos et al. [18] used energy ratios resulting from the division of the energy in a small window and the energy in a much larger window. Göksu [19] extracted energy and entropies as feature vectors in the timefrequency domain. ...
... The approach under the first category makes a classification decision by comparing the value of energy with a threshold [10]. Following the second category, the scheme takes energy to form the feature set, then puts it in the classifier for signal classification [11,15,18]. The second category uses modern classifiers and compares favorably with the first category in terms of accuracy. ...
... , l o g , I x y p x y p x y p x p y dxdy (18) where x, y are two vectors, , p x y is their joint probabilistic distribution, p x and p y are the marginal probabilities. Mutual information is a tool to measure how much one vector is related to another. ...
Automatic seizure detection has been often treated as a classification problem that aims at determining the label of electroencephalogram (EEG) signals by computer science, as EEG monitoring is a helpful adjunct to the diagnosis of epilepsy. In most existing work, the traditional signal energy of EEG has been applied for classification, since the energy pattern of epileptic seizures differs from that of nonseizures. Although they are effective, the accuracy either heavily depends on additional information besides energy or is limited by the shortcoming of energy-based features. To address this issue, the proposed approach achieves the classification based on the instantaneous energy of EEG signals instead. The proposed approach first measures the instantaneous energy related to changes in EEG signals. Then the energy behavior over time is characterized by instantaneous energy-based features from different aspects. Finally, the classification is carried out on the features to produce output labels. By processing instantaneous energy, the information of energy evolution is involved. As such, the accuracy is improved without bringing in extra information besides energy, or complicated transformation. In multi-class problems, the proposed approach has obtained promising results for identifying ictal EEG, which indicates the tremendous potential of the proposed approach for epileptic seizure detection.
... Alejandro and Ramon-Lozano [18] In this paper, authors used energy of the signal in a different way. They used smaller window as the foreground windows and larger window as the background while windowing the signal. ...
Epilepsy is a chronic chaos of the central nervous system that influences individual's daily life by putting it at risk due to repeated seizures. Epilepsy affects more than 2% people worldwide of which developing countries are affected worse. A seizure is a transient irregularity in the brain's electrical activity that produces disturbing physical symptoms such as a lapse in attention and memory, a sensory illusion, etc. Approximately one out of every three patients have frequent seizures, despite treatment with multiple anti-epileptic drugs. According to a survey, population aged 65 or above in European Union is predicted to rise from 16.4% (2004) to 29.9% (2050) and also this tremendous increase in aged population is also predicted for other countries by 2050. In this paper, seizure detection techniques are classified as time, frequency, wavelet (time-frequency), empirical mode decomposition and rational function techniques. The aim of this review paper is to present state-of-the-art methods and ideas that will lead to valid future research direction in the field of seizure detection.
Epileptic seizure is detected by reading the electroencephalogram (EEG) signals which are obtained from the electrical activities of the brain which are containing information about the brain. Epileptic seizure is known as the abrupt abnormal activity of a bunch of neurons which results in an electric surge in the brain. India is also one of the countries on the globe which is having about 10 million people suffering from a seizure. In this paper, the combination of discrete wavelet transform along with power spectral density is proposed for the classification and feature extraction process to detect epileptic seizures. To achieve high accuracy of seizure detection rate and explore relevant knowledge from the EEG processed dataset, deep learning has been used. The result shows that the detection of epileptic seizures using the proposed method gives an accuracy of 90.1%. This system would be useful for clinical analysis of epileptic seizures, and appropriate action would be taken against epileptic seizures.
KeywordsEEGDWTEpilepsySeizure
