Power Spectral Density Features Research Articles

Driver Vigilance Detection Based on Limited EEG Signals

Driver vigilance detection is an important topic for traffic safety improvement and brain-computer interface design. Electroencephalography (EEG) can directly provide real-time information and is sensitive to the change of vigilance. Thus, EEG signals are widely used for driver vigilance detection. Previous studies commonly acquired EEG signals from a large number of electrode channels and utilized all the collected data for recognition tasks, which may introduce a large amount of noise and redundant data and limit their application potentials in practical systems. This paper examines the potential of using EEG signals from only one frequency band or from only a small subset of related electrode channels in recognizing driver vigilance state. The widely used SEED VIG dataset is adopt for experiments. Four candidate sets of EEG frequency bands and four candidate sets of EEG electrode channels are determined according to the statistical significance results of EEG power spectral density (PSD) features and differential entropy (DE) features. The experimental results show that the recognition accuracy is higher when using EEG signals from the selected frequency band (i.e., alpha band) or the selected electrodes (i.e., T7, TP7, CP1) than when using all the data. Specifically, the best recognition accuracy is 91.31% for the alpha band and 76.81% for the selected electrodes. These results indicate that higher driver vigilance recognition accuracy can be achieved with much less amount of data, which would facilitate the development of wearable equipment based on EEG signals.

Age-integrated artificial intelligence framework for sleep stage classification and obstructive sleep apnea screening.

Sleep is an essential function to sustain a healthy life, and sleep dysfunction can cause various physical and mental issues. In particular, obstructive sleep apnea (OSA) is one of the most common sleep disorders and, if not treated in a timely manner, OSA can lead to critical problems such as hypertension or heart disease. The first crucial step in evaluating individuals' quality of sleep and diagnosing sleep disorders is to classify sleep stages using polysomnographic (PSG) data including electroencephalography (EEG). To date, such sleep stage scoring has been mainly performed manually via visual inspection by experts, which is not only a time-consuming and laborious process but also may yield subjective results. Therefore, we have developed a computational framework that enables automatic sleep stage classification utilizing the power spectral density (PSD) features of sleep EEG based on three different learning algorithms: support vector machine, k-nearest neighbors, and multilayer perceptron (MLP). In particular, we propose an integrated artificial intelligence (AI) framework to further inform the risk of OSA based on the characteristics in automatically scored sleep stages. Given the previous finding that the characteristics of sleep EEG differ by age group, we employed a strategy of training age-specific models (younger and older groups) and a general model and comparing their performance. The performance of the younger age-specific group model was similar to that of the general model (and even higher than the general model at certain stages), but the performance of the older age-specific group model was rather low, suggesting that bias in individual variables, such as age bias, should be considered during model training. Our integrated model yielded an accuracy of 73% in sleep stage classification and 73% in OSA screening when MLP algorithm was applied, which indicates that patients with OSA could be screened with the corresponding accuracy level only with sleep EEG without respiration-related measures. The current outcomes demonstrate the feasibility of AI-based computational studies that when combined with advances in wearable devices and relevant technologies could contribute to personalized medicine by not only assessing an individuals' sleep status conveniently at home but also by alerting them to the risk of sleep disorders and enabling early intervention.

Spectral features of resting-state EEG in Parkinson's Disease: A multicenter study using functional data analysis

ObjectiveThis study aims 1) To analyse differences in resting-state electroencephalogram (rs-EEG) spectral features of Parkinson's Disease (PD) and healthy subjects (non-PD) using Functional Data Analysis (FDA) and 2) To explore, in four independent cohorts, the external validity and reproducibility of the findings using both epoch-to-epoch FDA and averaged-epochs approach. MethodsWe included 169 subjects (85 non-PD; 84 PD) from four centres. Rs-EEG signals were preprocessed with a combination of automated pipelines. Sensor-level relative power spectral density (PSD), dominant frequency (DF), and DF variability (DFV) features were extracted. Differences in each feature were compared between PD and non-PD on averaged epochs and using FDA to model the epoch-to-epoch change of each feature. ResultsFor averaged epochs, significantly higher theta relative PSD in PD was found across all datasets. Also, higher pre-alpha relative PSD was observed in three of four datasets in PD patients. For FDA, similar findings were achieved in theta, but all datasets showed consistently significant posterior pre-alpha differences across multiple epochs. ConclusionsIncreased generalised theta, with posterior pre-alpha relative PSD, was the most reproducible finding in PD. SignificanceRs-EEG theta and pre-alpha findings are generalisable in PD.FDA constitutes a reliable and powerful tool to analyse epoch-to-epoch the rs-EEG.

A Volterra-PEM approach for random vibration spectrum analysis of nonlinear systems

In this paper, the Volterra series and the pseudo-excitation method (PEM) are combined to establish a frequency domain method for the power spectral density (PSD) analysis of random vibration of nonlinear systems. The explicit expression of the multi-dimensional power spectral density (MPSD) of the random vibration response is derived analytically. Furthermore, a fast calculation strategy from MPSD to physical PSD is given. The PSD characteristics analysis of the random vibration response of nonlinear systems is effectively achieved. First, within the framework of Volterra series theory, an improved PEM is established for MPSD analysis of nonlinear systems. As a generalized PEM for nonlinear random vibration analysis, the Volterra-PEM is used to analyse the response MPSD, which also has a very concise expression. Second, in the case of computation difficulties with multi-dimensional integration from MPSD to PSD, the computational efficiency is improved by converting the multi-dimensional integral into a matrix operation. Finally, as numerical examples, the Volterra-PEM is used to estimate the response PSD for stationary random vibration of a nonlinear spring-damped oscillator and a non-ideal boundary beam with geometrical nonlinearity. Compared with Monte Carlo simulation, the results show that by constructing generalized pseudo-excitation and matrix operation methods, Volterra-PEM can be used for input PSD with arbitrary energy distribution, not only restricted to broadband white noise excitation, and accurately predict the secondary resonance phenomenon of the random vibration response of nonlinear systems in the frequency domain.

Automatic Features Extraction Integrated With Exact Gaussian Process for Respiratory Rate and Uncertainty Estimations

Respiratory rate monitoring has become necessary for people with respiratory diseases, especially those living alone. Sudden changes in respiratory rate (RR) in these individuals may indicate a severe illness. Hence, estimating the RR is essential for cardiopulmonary health conditions. Capnography is a well-known standard technique for measuring RR. This study presents a novel methodology that uses an automatic feature extraction algorithm integrated with a robust feature selection technique based on exact Gaussian process regression (EGPR) for RR and uncertainty estimations. As EGPR is vital to noisy data and is naturally normalized, it can generate uncertainty estimates. Uncertainty estimation is essential for estimating physiological parameters. In the proposed methodology, data dimension is obtained using a power spectral density feature based on an autocorrelation function; subsequently, the long-resampled wave signal is split to increase the number of input data samples. Selecting an appropriate high-dimensional feature is necessary to predict a response effectively. Herein, we use a robust feature selection method based on neighbor component analysis. The proposed EGPR with automatic feature extraction is more accurate than conventional algorithms for RR and confidence intervals (CIs) estimations. The proposed methodology proves superior to conventional algorithms in terms of saving computer resources. We confirm that the proposed methodology, 2.085 breath per minute (bpm), and EGPR with robust feature selection, 2.049 bpm, show the lowest mean absolute error compared to the conventional algorithms in the Beth Israel Deaconess Medical Center data set.

Pleasantness Recognition Induced by Different Odor Concentrations Using Olfactory Electroencephalogram Signals.

Olfactory-induced emotion plays an important role in communication, decision-making, multimedia, and disorder treatment. Using electroencephalogram (EEG) technology, this paper focuses on (1) exploring the possibility of recognizing pleasantness induced by different concentrations of odors, (2) finding the EEG rhythm wave that is most suitable for the recognition of different odor concentrations, (3) analyzing recognition accuracies with concentration changes, and (4) selecting a suitable classifier for this classification task. To explore these issues, first, emotions induced by five different concentrations of rose or rotten odors are divided into five kinds of pleasantness by averaging subjective evaluation scores. Then, the power spectral density features of EEG signals and support vector machine (SVM) are used for classification tasks. Classification results on the EEG signals collected from 13 participants show that for pleasantness recognition induced by pleasant or disgusting odor concentrations, considerable average classification accuracies of 93.5% or 92.2% are obtained, respectively. The results indicate that (1) using EEG technology, pleasantness recognition induced by different odor concentrations is possible; (2) gamma frequency band outperformed other EEG rhythm-based frequency bands in terms of classification accuracy, and as the maximum frequency of the EEG spectrum increases, the pleasantness classification accuracy gradually increases; (3) for both rose and rotten odors, the highest concentration obtains the best classification accuracy, followed by the lowest concentration.

Fault Detection and Diagnosis of Gear Train Based on Motor Current Signature Analysis

Gear fault diagnosis generally uses oscillation signals to extract fault features, but the oscillation identify technique is inconvenient to set up sensors and is easily affected by the surrounding and noise. The motor itself has the property of a sensor, and signals such as motor current is able to reflect the change of the load torque. This paper proposes a gear fault detection approach, which applies the Motor Current Signature Analysis (MCSA) to exploit spectral characteristics to recognize malfunction in servo motor drive gears. First, we calculate the nominal revolutions per minute (rpm) to explore frequencies of interest. Second, frequency bands where faulty signals would be appear are constructed. Next, we extract power spectral density (PSD) feature data. Finally, the paper computes spectral metrics for the frequency band of interest. By using two spectral metrics, gear health and failure data are clearly grouped in different areas of the scatter chart. The experimental results give evidence of the effectiveness of analyzing current characteristics of servo motors to classify fault and health data.

A multiwavelet-based sparse time-varying autoregressive modeling for motor imagery EEG classification

Brain-computer Interface (BCI) system based on motor imagery (MI) heavily relies on electroencephalography (EEG) recognition with high accuracy. However, modeling and classification of MI EEG signals remains a challenging task due to the non-linear and non-stationary characteristics of the signals. In this paper, a new time-varying modeling framework combining multiwavelet basis functions and regularized orthogonal forward regression (ROFR) algorithm is proposed for the characterization and classification of MI EEG signals. Firstly, the time-varying coefficients of the time-varying autoregressive (TVAR) model are precisely approximated with the multiwavelet basis functions. Then a powerful ROFR algorithm is employed to dramatically alleviate the redundant model structure and accurately recover the relevant time-varying model parameters to obtain high resolution power spectral density (PSD) features. Finally, the features are sent to different classifiers for the classification task. To effectively improve the accuracy of classification, a principal component analysis (PCA) algorithm is utilized to determine the best feature subset and Bayesian optimization algorithm is performed to obtain the optimal parameters of the classifier. The proposed method achieves satisfactory classification accuracy on the public BCI Competition II Dataset III, which proves that this method potentially improves the recognition accuracy of MI EEG signals, and has great significance for the construction of BCI system based on MI.

Measurement of spot welding nugget diameter using power spectral density variation of laser ultrasonic Lamb wave

In applications of spot welding, the nugget determines reliability of the material joining, which is characterized by nugget diameter. However, the conventional methods are complex and rough to measure the diameter of the nugget. This paper aims to propose a novel convenient method for measuring the diameter of spot welding nugget. The characteristic curve of laser ultrasonic Lamb waves in nugget area are obtained by laser ultrasonic detection technology under completely non-contact conditions. The variation characteristics of power spectral density in nugget area are analyzed by Fast Fourier Transform, to determine the geometric relationship between the scanning area and the nugget diameter, and the nugget diameter are obtained by further calculation. Experiments show that the accuracy of the proposed method is within 0.2 mm, and the relative errors of experimental data are within 3%. This paper provides an alternative method for the measurement of spot welding nugget diameter, and has great significance for the application of laser ultrasonic detection in spot welding.

PSD characteristics for the random vibration signals used in bridge structural health monitoring in Vietnam based on a multi-sensor system

This study proposes two parameters, including the appearance frequency of harmonics (AFH) and the change in shape of the power spectral density (PSD), which are examined to assess the decline in stiffness of a bridge span. PSDs are obtained from the real vibration signals of the randomized traffic load model based on accelerometer multi-sensors that indicate the change in mechanical behavior of the structure over time. In addition, AFHs evaluate the workability of the structure. With these parameters in mind, actual vibrations in real beam structures are studied with the aim of using structural health monitoring to assess the bearing capacity reduction on Saigon Bridge’s spans. The results show that AFHs and the high-frequency regions relate to the decreased stiffness of the bridge’s spans over a given period of time. In the future, this research can be used to monitor structural health for various types of structure materials and many different bridge spans.

Assessment of learning a new skill using nonlinear and spectral features of EEG

The goal of this paper was to assess the impact of learning a new skill on several electroencephalographic (EEG) measurements. In addition, it intended to examine the active brain regions associated with learning. To this effect, changes in brain activity during the pre- and post-learning task were investigated using EEG power spectral density (PSD) and nonlinear features. The evaluated task was learning to type using the Colemak keyboard layout in a twelve-lesson training. 10 participants with a mean age of 29.3 ± 5.7 were included in the experiment. For the first time, Fractal dimension, approximate entropy, and Lyapunov exponents were extracted from a 9-channel EEG signal to characterize brain dynamics. In addition, the PSD of various EEG rhythms was estimated. To identify statistically significant changes in the EEG characteristics, as well as to determine the prominent channels, the t-test was performed. Our results showed maximum EEG power in Beta and Gamma waves; however, the most differences in the power distribution belonged to the Beta band. Among nonlinear features, entropy showed a significant difference in 70% of the EEG channels. This has mainly occurred in the F3, Fz, C3, Cz, POz, and P4 electrodes. Taken together, the results of this study pave the way to evaluate brain dynamics and actively involved areas in pre- and post-learning tasks.

Parkinson’s disease detection based on multi-pattern analysis and multi-scale convolutional neural networks

Parkinson’s disease (PD) is a complex neurodegenerative disease. At present, the early diagnosis of PD is still extremely challenging, and there is still a lack of consensus on the brain characterization of PD, and a more efficient and robust PD detection method is urgently needed. In order to further explore the features of PD based on brain activity and achieve effective detection of PD patients (including OFF and ON medications), in this study, a multi-pattern analysis based on brain activation and brain functional connectivity was performed on the brain functional activity of PD patients, and a novel PD detection model based on multi-scale convolutional neural network (MCNN) was proposed. Based on the analysis of power spectral density (PSD) and phase-locked value (PLV) features of multiple frequency bands of two independent resting-state electroencephalography (EEG) datasets, we found that there were significant differences in PSD and PLV between HCs and PD patients (including OFF and ON medications), especially in the β and γ bands, which were very effective for PD detection. Moreover, the combined use of brain activation represented by PSD and functional connectivity patterns represented by PLV can effectively improve the performance of PD detection. Furthermore, our proposed MCNN model shows great potential for automatic PD detection, with cross-validation accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve all above 99%. Our study may help to further understand the characteristics of PD and provide new ideas for future PD diagnosis based on spontaneous EEG activity.

The Effect of Time Window Length on EEG-Based Emotion Recognition.

Various lengths of time window have been used in feature extraction for electroencephalogram (EEG) signal processing in previous studies. However, the effect of time window length on feature extraction for the downstream tasks such as emotion recognition has not been well examined. To this end, we investigate the effect of different time window (TW) lengths on human emotion recognition to find the optimal TW length for extracting electroencephalogram (EEG) emotion signals. Both power spectral density (PSD) features and differential entropy (DE) features are used to evaluate the effectiveness of different TW lengths based on the SJTU emotion EEG dataset (SEED). Different lengths of TW are then processed with an EEG feature-processing approach, namely experiment-level batch normalization (ELBN). The processed features are used to perform emotion recognition tasks in the six classifiers, the results of which are then compared with the results without ELBN. The recognition accuracies indicate that a 2-s TW length has the best performance on emotion recognition and is the most suitable to be used in EEG feature extraction for emotion recognition. The deployment of ELBN in the 2-s TW can further improve the emotion recognition performances by 21.63% and 5.04% when using an SVM based on PSD and DE features, respectively. These results provide a solid reference for the selection of TW length in analyzing EEG signals for applications in intelligent systems.

A new feature selection approach for driving fatigue EEG detection with a modified machine learning algorithm

This study aims to identify new electroencephalography (EEG) features for the detection of driving fatigue. The most common EEG feature in driving fatigue detection is the power spectral density (PSD) of five frequency bands, i.e., alpha, beta, gamma, delta, and theta bands. PSD has proved to be useful, however its flaw is that it covers much implicit information of the time domain. In this study we propose a new approach, which combines ensemble empirical mode decomposition (EEMD) and PSD, to explore new EEG features for driving fatigue detection. Through EEMD we get a series of intrinsic mode function (IMF) components, from which we can extract PSD features. We used six features to compare with the proposed features, including the PSD of five frequency bands, PSD of empirical mode decomposition (EMD)-IMF components, PSD, permutation entropy (PE), sample entropy (SE), and fuzzy entropy (FE) of EEMD-IMF components, and common spatial pattern. Feature overlap ratio and multiple machine learning methods were applied to evaluate these feature extraction approaches. The results show that the classification accuracy and overlap ratio of experiments based on IMF's energy spectrum is far superior to other features. Through channel optimization and a comparison of accuracy, we conclude that our new feature selection approach has a better performance based on the modified hierarchical extreme learning machine algorithm with Particle Swarm Optimization (PSO–H-ELM) classifier, which has the highest average accuracy of 97.53%.

Fractal and Time-series A nalyses based Rhonchi and Bronchial Auscultation: A Machine Learning Approach

Objectives: The present work reports the study of 34 rhonchi (RB) and Bronchial Breath (BB) signals employing machine learning techniques, time-frequency, fractal, and non-linear time-series analyses. Methods: The time-frequency analyses and the complexity in the dynamics of airflow in BB and RB are studied using both Power Spectral Density (PSD) features and non-linear measures. For accurate prediction of these signals, PSD and non-linear measures are fed as input attributes to various machine learning models. Findings: The spectral analyses reveal fewer, low-intensity frequency components along with its overtones in the intermittent and rapidly damping RB signal. The complexity in the dynamics of airflow in BB and RB is investigated through the fractal dimension, Hurst exponent, phase portrait, maximal Lyapunov exponent, and sample entropy values. The greater value of entropy for the RB signal provides an insight into the internal morphology of the airways containing mucous and other obstructions. The Principal Component Analysis (PCA) employs PSD features, and Linear Discriminant Analysis (LDA) along with Pattern Recognition Neural Network (PRNN) uses non-linear measures for predicting BB and RB. Signal classification based on phase portrait features evaluates the multidimensional aspects of signal intensities, whereas that based on PSD features considers mere signal intensities. The principal components in PCA cover about 86.5% of the overall variance of the data class, successfully distinguishing BB and RB signals. LDA and PRNN that use non-linear time-series parameters identify and predict RB and BB signals with 100% accuracy, sensitivity, specificity, and precision. Novelty: The study divulges the potential of non-linear measures and PSD features in classifying these signals enabling its application to be extended for low-cost, non-invasive COVID-19 detection and real-time health monitoring. Keywords: lung signal, fractal analysis, sample entropy, non­linear time­series, machine learning techniques

An EEG Data Processing Approach for Emotion Recognition

As the most direct way to measure the true emotional states of humans, EEG-based emotion recognition has been widely used in affective computing applications. In this paper, we aim to propose a novel emotion recognition approach that relies on a reduced number of EEG electrode channels and at the same time overcomes the negative impact of individual differences to achieve a high recognition accuracy. According to the statistical significance results of EEG power spectral density (PSD) features obtained from the SJTU Emotion EEG Dataset (SEED), six candidate sets of EEG electrode channels are determined. An experiment-level batch normalization (BN) is proposed and applied on the features from the candidate sets, and the normalized features are then used for emotion recognition across individuals. Eleven well-accepted classifiers are used for emotion recognition. The experimental results show that the recognition accuracy when using a small portion of the available electrodes is almost the same or even better than that when using all the channels. Based on the reduced number of electrode channels, the application of experiment-level BN can help further improve the recognition accuracy, specifically from 73.33% to 89.63% when using the LR classifier. These results demonstrate that better and easier emotion recognition performance can be achieved based on the batch normalized features from fewer channels, indicating promising applications of our proposed method in real-time emotion recognition applications in intelligent systems.

Predict Students’ Attention in Online Learning Using EEG Data

In education, it is critical to monitor students’ attention and measure the extents to which students participate and the differences in their levels and abilities. The overall goal of this study was to increase the quality of distance education. In particular, in order to craft an approach that will effectively augment online learning using objective measures of brain activity, we propose a brain–computer interface (BCI) system that aims to use electroencephalography (EEG) signals for the detection of student’s attention during online classes. This system will aid teachers to objectively assess student attention and engagement. To this end, experiments were conducted on a public dataset; we extracted power spectral density (PSD) features using used a fast Fourier transform. Different attention indexes were calculated. Then, we built three different classification algorithms: k-nearest neighbors (KNN), support vector machine (SVM), and random forest (RF). Our proposed random forest classifier achieved a higher accuracy (96%) than KNN and SVM. Moreover, our results compared to state-of-the-art attention-detection systems with respect to the same dataset. Our findings revealed that the proposed RF approach can be used to effectively distinguish the attention state of a user.

On the Minimal Amount of EEG Data Required for Learning Distinctive Human Features for Task-Dependent Biometric Applications.

Biometrics is the process of measuring and analyzing human characteristics to verify a given person's identity. Most real-world applications rely on unique human traits such as fingerprints or iris. However, among these unique human characteristics for biometrics, the use of Electroencephalogram (EEG) stands out given its high inter-subject variability. Recent advances in Deep Learning and a deeper understanding of EEG processing methods have led to the development of models that accurately discriminate unique individuals. However, it is still uncertain how much EEG data is required to train such models. This work aims at determining the minimal amount of training data required to develop a robust EEG-based biometric model (+95% and +99% testing accuracies) from a subject for a task-dependent task. This goal is achieved by performing and analyzing 11,780 combinations of training sizes, by employing various neural network-based learning techniques of increasing complexity, and feature extraction methods on the affective EEG-based DEAP dataset. Findings suggest that if Power Spectral Density or Wavelet Energy features are extracted from the artifact-free EEG signal, 1 and 3 s of data per subject is enough to achieve +95% and +99% accuracy, respectively. These findings contributes to the body of knowledge by paving a way for the application of EEG to real-world ecological biometric applications and by demonstrating methods to learn the minimal amount of data required for such applications.

Using an Automated Speech Recognition Approach to Differentiate Between Normal and Aspirating Swallowing Sounds Recorded from Digital Cervical Auscultation in Children

Use of machine learning to accurately detect aspirating swallowing sounds in children is an evolving field. Previously reported classifiers for the detection of aspirating swallowing sounds in children have reported sensitivities between 79 and 89%. This study aimed to investigate the accuracy of using an automatic speaker recognition approach to differentiate between normal and aspirating swallowing sounds recorded from digital cervical auscultation in children. We analysed 106 normal swallows from 23 healthy children (median 13 months; 52.1% male) and 18 aspirating swallows from 18 children (median 10.5 months; 61.1% male) who underwent concurrent videofluoroscopic swallow studies with digital cervical auscultation. All swallowing sounds were on thin fluids. A support vector machine classifier with a polynomial kernel was trained on feature vectors that comprised the mean and standard deviation of spectral subband centroids extracted from each swallowing sound in the training set. The trained support vector machine was then used to classify swallowing sounds in the test set. We found high accuracy in the differentiation of aspirating and normal swallowing sounds with 98% overall accuracy. Sensitivity for the detection of aspiration and normal swallowing sounds were 89% and 100%, respectively. There were consistent differences in time, power spectral density and spectral subband centroid features between aspirating and normal swallowing sounds in children. This study provides preliminary research evidence that aspirating and normal swallowing sounds in children can be differentiated accurately using machine learning techniques.

Applicability of Hyperdimensional Computing to Seizure Detection

Hyperdimensional (HD) computing is a form of brain-inspired computing which can be applied to numerous classification problems. In past research, it has been shown that seizures can be detected from electroencephalograms (EEG) with high accuracy using local binary pattern (LBP) encoding. This paper explores applicability of binary HD computing to seizure detection from intra-cranial EEG (iEEG) data from the Kaggle seizure detection contest based on using both LBP and power spectral density (PSD) features. In the PSD method, three novel approaches to HD classification are presented for both selected features and all features. These are referred as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">single classifier long hypervector</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multiple classifiers</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">single classifier short hypervector</i> . To visualize the quality of classification of test data, a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">hypervector distance</i> plot is introduced that plots the Hamming distance of the query hpervectors from one class hypervector <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">vs.</i> that from the other. Simulation results show that: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1)</i> . LBP method offers an average 80.9% test accuracy, 71.9% sensitivity, 81.4% specificity and 76.6% test AUC whereas the PSD method can achieve an average of 91.0% test accuracy, 81.8% sensitivity, 92.0% specificity and 86.9% test AUC. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2)</i> . The average seizure detection latency is 2.5s for LBP method and is 4.5s for the PSD methods. This average latency, less than 5s, is a relevant parameter for fast drug delivery, indicating that both LBP and PSD methods are able to detect the seizures in a timely manner. The performance using selected PSD features is better than that using all features. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3)</i> . It is shown that the dimensionality of the hypervector can be reduced to 1, 000 bits for LBP and PSD methods from 10, 000. Futhermore, for some approaches of selected features, the dimensionality of the hypervector can be reduced to 100 bits.