Support Vector Machine Based Detection of Drowsiness Using Minimum EEG Features

Epilepsy is a persistent neurological condition of the brain in which the activity of the brain goes out of normal state. Classification and Analysis of EEG signal is the early approach for epilepsy diagnosis. During this paper, we have a tendency to propose an EEG signal classification approach based on Support Vector Machine (SVM) classifier. In extracting features from the raw EEG data we applied the Hilbert Transform method and used its coefficients. Then, after the PCA dimension reduction a two-class SVM classifier is used for EEG signals automatic classification, one class for healthy subjects and another for subjects with epilepsy. In SVM classifier we need to divide the EEG signals into a training dataset and testing dataset for classification. We have used five sets of EEG signals which are publicly accessible on EEG time series database. The evaluation and comparison of SVM based classifier with two other classification methods such as KNN and LVQ based classifier was done. The average classification accuracy of our study is 95.33%.

Comparative exploration on EEG signal filtering using window control methods

Electroencephalogram (EEG) comprises valuable details related to the different physiological state of the brain. In this paper, a framework is offered for detecting the epileptic seizures from EEG data recorded from normal subjects and epileptic patients. This framework is based on a discrete wavelet transform (DWT) analysis of EEG signals using linear and nonlinear classifiers. The performance of the different combinations of two-class epilepsy detection is studied using Support Vector Machine (SVM) and neural network analysis (NNA) classifiers for the derived statistical features from DWT. In this new approach first parse EEG signals to sub-bands in different categories with the help of discrete wavelet transform (DWT) and then we derive statistical features such as Mean, Median, Standard Deviation, Kurtosis, Entropy, Skewness for each sub-band. These features, extracted from details and approximation coefficients of DWT sub-bands, are used as input to Principal Component Analysis (PCA). The classification is based on reducing the feature dimension using PCA and deriving the Support Vector Machine (SVM) and neural network analysis (NNA). In classification of normal and epileptic, results obtained exhibited an accuracy of 100% by applying NNA and 99% by SVM it has been found that the computation time of NNA classifier is lesser than SVM to provide 100% accuracy.

This paper analyzes the underlying complexity and non-linearity of electroencephalogram (EEG) signals by computing a novel multi-scale entropy measure for the classification of seizure, seizure-free and normal EEG signals. The quality factor (Q) based multi-scale entropy measure is proposed to compute the entropy of the EEG signal in different frequency-bands of interest. The Q -based entropy (QEn) is computed by decomposing the signal with the tunable-Q wavelet transform (TQWT) into the number of sub-bands and estimating K-nearest neighbor (K-NN) entropies from various sub-bands cumulatively. The optimal selection of Q and the redundancy parameter (R) of TQWT showed better robustness for entropy computation in the presence of high- and low-frequency components. The extracted features are fed to the support vector machine (SVM) classifier with the wrapper-based feature selection method. The proposed method has achieved accuracy of 100% in classifying normal (eyes-open and eyes-closed) and seizure EEG signals, 99.5% in classifying seizure-free EEG signals (from the hippocampal formation of the opposite hemisphere of the brain) from seizure EEG signals and 98% in classifying seizure-free EEG signals (from the epileptogenic zone) from seizure EEG signals, respectively, using the SVM classifier. We have also achieved classification accuracies of 99% and 98.6% in classifying seizure versus non-seizure EEG signals and the individual three classes, namely normal, seizure-free and seizure EEG signals, respectively. The performance measure of the proposed multi-scale entropy has been found to be comparable with the existing state of the art epileptic EEG signals classification methods studied using the same database.

In this study cyclic changes of human sleep structure were examined. For whole-night polysomnograms of 35 healthy volunteers of both sexes, manual hypnograms were created and divided into NREM-REM cycles. EEG signals from C3-A2 derivation were analysed by computer using a Fast Fourier Transform (FFT). For consecutive NREM-REM cycles of individual sleep stages, EEG power density contents for delta, theta, alpha, sigma and beta waves were analysed. For consecutive sleep cycles, a clear decrease in NREM sleep duration, especially slow wave sleep duration, was obtained. In addition, a decrease in power density of delta waves was observed. For consecutive sleep cycles, increases in REM sleep duration and in power density of theta and alpha waves were obtained. In consecutive sleep cycles, high amplitude delta slow waves are replaced by higher frequency and lower amplitude waves. Thus stages of NREM sleep are replaced by stages of REM.

The problem with development of the support vector machine (SVM) classifiers using modified particle swarm optimization (PSO) algorithm and their ensembles has been considered. Solving this problem would allow fulfilling the high-precision data classification, especially Big Data classification, with the acceptable time expenditures. The modified PSO algorithm conducts a simultaneous search of the type of kernel functions, the parameters of the kernel function and the value of the regularization parameter for the SVM classifier. The idea of particles' «regeneration» served as the basis for the modified PSO algorithm. In the implementation of this algorithm, some particles change the type of their kernel function to the one which corresponds to the particle with the best value of the classification accuracy. The offered PSO algorithm allows reducing the time expenditures for the developed SVM classifiers, which is very important for Big Data classification problem. In most cases such SVM classifier provides the high quality of data classification. In exceptional cases the SVM ensembles based on the decorrelation maximization algorithm for the different strategies of the decision-making on the data classification and the majority vote rule can be used. Also, the two-level SVM classifier has been offered. This classifier works as the group of the SVM classifiers at the first level and as the SVM classifier on the base of the modified PSO algorithm at the second level. The results of experimental studies confirm the efficiency of the offered approaches for Big Data classification.

Drowsiness or fatigue condition refers to feeling abnormally sleepy at an inappropriate time, especially during day time. It reduces the level of concentration and slowdown the response time, which eventually increases the error rate while doing any day-to-day activity. It can be dangerous for some people who require higher concentration level while doing their work. Study shows that 25–30% of road accidents occur due to drowsy driving. There are number of methods available for the detection of drowsiness out of which most of the methods provide an indirect measurement of drowsiness whereas electroencephalography provides the most reliable and direct measurement of the level of consciousness of the subject. The aim of this paper is to design and develop a portable and low cost brain–computer interface system for detection of drowsiness. In this study, we are using three dry electrodes out of which two active electrodes are placed on the forehead whereas the reference electrode is placed on the earlobe to acquire electroencephalogram (EEG) signal. Previous research shows that, there is a measurable change in the amplitude of theta ([Formula: see text]) wave and alpha ([Formula: see text]) wave between the active state and the drowsy state and based on this fact theta ([Formula: see text]) wave and alpha ([Formula: see text]) wave are separated from the normal EEG signal. The signal processing unit is interfaced with the microcontroller unit which is programmed to analyze the drowsiness based on the change in the amplitude of theta ([Formula: see text]) wave. An alarm will be activated once drowsiness is detected. The experiment was conducted on 20 subjects and EEG data were recorded to develop our drowsiness detection system. Experimental results have proved that our system has achieved real-time drowsiness detection with an accuracy of approximately 85%.

Alcoholism is a complex condition that mainly disturbs the neuronal networks in Central Nervous System (CNS). This disorder not only disturbs the brain, but also affects the behavior, emotions, and cognitive judgements. Electroencephalography (EEG) is a valuable tool to examine the neuropsychiatric disorders like alcoholism. The EEG is a well-established modality to diagnose the electrical activity produced by the populations of neurons in cerebral cortex. However, EEG signals are non-linear in nature; hence very challenging to interpret the valuable information from them using linear methods. Thus, using non-linear methods to analyze EEG signals can be beneficial in order to predict the brain signals condition. This paper presents a computer-aided diagnostic method for the detection of alcoholic EEG signals from normal by employing the non-linear techniques. First, the EEG signals are subjected to six levels of Wavelet Packet Decomposition (WPD) to obtain seven wavebands (delta ([Formula: see text]), theta ([Formula: see text]), lower alpha (la), upper alpha (ua), lower beta (lb), upper beta (ub), lower gamma (lg)). From each wavebands (activity bands), 19 non-linear features such as Recurrence Quantification Analysis (RQA) ([Formula: see text]), Approximate Entropy ([Formula: see text]), Energy ([Formula: see text]), Fractal Dimension (FD) ([Formula: see text]), Permutation Entropy ([Formula: see text]), Detrended Fluctuation Analysis ([Formula: see text]), Hurst Exponent ([Formula: see text]), Largest Lyapunov Exponent ([Formula: see text]), Sample Entropy ([Formula: see text]), Shannon’s Entropy ([Formula: see text]), Renyi’s entropy ([Formula: see text]), Tsalli’s entropy ([Formula: see text]), Fuzzy entropy ([Formula: see text]), Wavelet entropy ([Formula: see text]), Kolmogorov–Sinai entropy ([Formula: see text]), Modified Multiscale Entropy ([Formula: see text]), Hjorth’s parameters (activity ([Formula: see text]), mobility ([Formula: see text]), and complexity ([Formula: see text])) are extracted. The extracted features are then ranked using Bhattacharyya, Entropy, Fuzzy entropy-based Max-Relevancy and Min-Redundancy (mRMR), Receiver Operating Characteristic (ROC), [Formula: see text]-test, and Wilcoxon. These ranked features are given to train Support Vector Machine (SVM) classifier. The SVM classifier with radial basis function (RBF) achieved 95.41% accuracy, 93.33% sensitivity and 97.50% specificity using four non-linear features ranked by Wilcoxon method. In addition, an integrated index called Alcoholic Index (ALCOHOLI) is developed using highly ranked two features for identification of normal and alcoholic EEG signals using a single number. This system is rapid, efficient, and inexpensive and can be employed as an EEG analysis assisting system by clinicians in the detection of alcoholism. In addition, the proposed system can be used in rehabilitation centers to evaluate person with alcoholism over time and observe the outcome of treatment provided for reducing or reversing the impact of the condition on the brain.

This study aims to analyze the relationship between brainwave activity and the learning readiness of students with disabilities by utilizing EEG (Electroencephalography) signals. EEG signals are used to detect the brain's electrical activity that reflects mental states, including focus, concentration, and readiness to receive learning. This study was conducted at SLB 'Aisyiyah Krian with a quantitative approach through EEG signal measurement before and during the learning process. The results showed a significant correlation between the dominance of alpha and beta waves with learning readiness, while the dominance of theta and delta waves indicated unpreparedness. These findings provide a foundation for the development of a more inclusive, objective, and adaptive neurotechnology-based learning approach for students with disabilities.

BackgroundHighly structured electroencephalography (EEG) oscillations can occur in adults during etomidate-induced general anesthesia, but the link between these two phenomena is poorly understood. Therefore, in the present study, we investigated the electroencephalogram dynamics of etomidate-induced loss of consciousness (LOC) in order to understand the neurological mechanism of etomidate-induced LOC.MethodsThis study is a prospective observational study. Etomidate-induced anesthesia was performed on eligible patients undergoing elective surgery. We analyzed EEG data from 20 patients who received etomidate for the induction of general anesthesia. We used power spectra and coherence methods to process and analyze the EEG data. Our study was based on 4-channel EEG recordings.ResultsCompared with the baseline (awake period), etomidate induced an increase in power in delta, theta, alpha and beta waves during LOC. Compared with the awake period, the delta-wave (1–4 Hz), alpha-wave(8–13 Hz), and theta-wave(4–8 Hz) coherence increased significantly during LOC, while the slow-wave (< 1 Hz) coherence decreased. However, the delta wave (1.0–4.0 Hz) during etomidate-induced LOC was more coherent than during the awake period (1.86–3.17 Hz, two-group test for coherence, p < 0.001).ConclusionsThe neural circuit mechanism of etomidate-induced LOC is closely related to the induction of oscillation in delta, theta, alpha and beta waves and the enhancement of delta-wave coherence.Trial registrationChiCTR1800017110

Background and ObjectiveThe ever-increasing fatality rate due to traffic and workplace accidents, resulting from drowsiness have been a persistent concern during the past years. An efficient technology capable of monitoring and detecting drowsiness can help to alleviate this concern and has potential applications in driver vigilance monitoring, vigilance monitoring in air traffic control rooms and other safety critical work places. In this paper, we present the feasibility of a wearable light weight wireless consumer grade Electroencephalogram (EEG)-based drowsiness detection. MethodsA set of informative features were extracted from short daytime nap EEG signals and their applicability in discriminating between alert and drowsy state was studied. We derived an optimal set of EEG features, that give maximum detection rate for the drowsy state. In addition, heart rate was also recorded concurrently with EEG and correlation between heart rate and the EEG features corresponding to drowsiness was also studied. ResultsUsing the selected features, the EEG data is shown to be capable of classifying alert and drowsy states with an accuracy of 78.3% using Support Vector Machine classifier employing cross subject validation. The feature selection results also revealed that, the EEG features extracted from the temporal electrodes are more significant for drowsiness detection than the features from frontal electrodes. In addition, EEG features extracted from the temporal electrodes yielded higher correlation coefficient with heart rate, which was in concordance with the feature selection results. ConclusionsThe results reveal that using the proposed drowsiness detection algorithm, it is possible to perform drowsiness detection using a single EEG electrode placed behind the ear.

The objective of this work is to identity the occurrence of seizure in an epileptic patient from his/her Electroencephalogram (EEG) signals and also to avoid aggressive situations during their seizure. In this paper an efficient method is proposed for detecting the presence of seizure in EEG signal using wavelet transform and Support Vector Machine (SVM) classifier. In this work, EEG signal is decomposed into seven levels using discrete wavelet transform to obtain the delta, alpha, theta, beta and gamma subbands. Among the five subbands, alpha wave has the very high amplitude in the range of 100μv which is mostly used to detect the seizure. Then the statistical features are extracted from the alpha band and finally classification of EEG signal has been done using SVM classifier. This method is applied for two groups of EEG signal: 1) Normal EEG dataset; 2) seizure dataset during a seizure period. The implementation of the proposed method utilized 76% of LUTs and 20% of registers. Total power analyzed for implementing this proposed work is 0.017W and classification accuracy is 95.6%.

Background. The method of anterior decompression (discectomy) for monosegmental stenosis of the cervical spinal canal is subjectively assessed as highly effective by both neurosurgeons and the vast majority of patients. However, the objective criteria for the early effectiveness of this intervention have not been sufficiently studied to date. Aim of the study to evaluate the dynamics of electroencephalography parameters in the preoperative and early postoperative period in patients with monosegmental stenosis of the cervical spine. Materials and methods. Electroencephalography studies were conducted on 22 patients of the neurosurgery department, before and after surgical treatment under code A16.23.085.001. The spectral composition of the bioelectrical activity of the brain (alpha, beta, delta and theta rhythms), as well as the coherence of oscillations in selected leads, were studied. Results. In the preoperative period, a disorganized type of electroencephalogramm was recorded in the examined group according to the classification of E.A. Zhirmunskaya; there was a decrease in the index and amplitude of the alpha rhythm in the parietal-occipital leads; predominance of high-amplitude beta activity in the frontal-central leads; presence of diffuse delta activity of the average index and theta activity of the average index, localized in leads P3, P4, C3, C4. On the 5th day after the operation, an organized type of electroencephalography was recorded on the encephalogram; a well-modulated alpha rhythm was observed, with a frequency in the range from 9 to 10 Hz, and an amplitude of 70 to 80 microvolts. Low-amplitude beta rhythm activity was recorded in the frontocentral leads. Low-amplitude delta and theta rhythms were recorded in the parieto-occipital leads and had a low index. Overall, the obtained data indicated positive dynamics in the restoration of cortical rhythms. Conclusion. The positive dynamics of cerebral cortex biorhythms in the early postoperative period allows the use of the electroencephalography method to objectify the results of surgical treatment, and in the future for the purposes of neurorehabilitation.

In order to improve the performance of Support Vector Machine (SVM) classifier for imbalanced data, this paper proposes dynamic cost-sensitive SVM classifier based on chaos particle swarm optimization (CPDC_SVM). Firstly, this paper introduces dynamic cost-sensitive thought to SVM classifier, and gives the method for structuring dynamic cost and cost-sensitive SVM model. Secondly, we propose the evaluation methodology performance for classifier, and adopts decimal base to code the particles. At last, chaos thought is introduced in particle swarm optimization algorithm, and the Algorithm of the dynamic cost-sensitive SVM classifier is given, which improves convergent speed and accuracy of particle swarm optimization, and can optimize dynamic cost-sensitive SVM well, so CPDC_SVM adds effectively the convergence speed and accuracy for the particle swarm optimization algorithm. Experimental results show CPDC_SVM has higher precision than traditional SVM classifier, and dynamic cost and chaos particle swarm optimization can improve the performance for classifier.

BackgroundThis study aimed to screen the feature modules and characteristic genes related to ulcerative colitis (UC) and construct a support vector machine (SVM) classifier to distinguish UC patients.MethodsFour datasets that contained UC and control samples were obtained from the Gene Expression Omnibus database. Differentially expressed genes (DEGs) with consistency were screened via the MetaDE method. The weighted gene coexpression network (WGCNA) was used to distinguish significant modules based on the four datasets. The protein–protein interaction network was established based on intersection genes. Enrichment analysis of Gene Ontology (GO) biological processes (BPs) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment were established based on DAVID. An SVM combined with recursive feature elimination was also applied to construct a disease classifier for the disease diagnosis of UC patients. The efficacy of the SVM classifier was evaluated through receiver operating characteristic curves.ResultsTwelve highly preserved modules were obtained using the WGCNA, and 2009 DEGs with significant consistency were selected using the MetaDE method. Sixteen significantly related GO BPs and 12 KEGG pathways were obtained, such as cytokine-cytokine receptor interaction, cell adhesion molecules, and leukocyte transendothelial migration. Subsequently, 41 genes were used to construct an SVM classifier, such as CXCL1, CCR2, IL1B, and IL1A. The area under the curve (AUC) was 0.999 in the training dataset, whereas the AUC was 0.886, 0.790, and 0.819 in the validation set (GSE65114, GSE37283, and GSE36807, respectively).ConclusionsAn SVM classifier based on feature genes might correctly identify healthy people or UC patients.