Portable Drowsiness Detection through Use of a Prefrontal Single-Channel Electroencephalogram

Improved drowsiness detection in drivers through optimum pairing of EEG features using an optimal EEG channel comparable to a multichannel EEG system

Multichannel electroencephalography (EEG)-based drowsiness detection (DD) offers higher coverage but comes with increased computational demands, hardware requirements, and user discomfort, whereas single-channel devices are cost-effective and user-friendly but provide lower coverage. We hypothesized that an optimal channel with optimum paired EEG features could achieve coverage comparable to a multichannel system. Subject-specific, EEG-feature-specific thresholding techniques were introduced to classify 927 EEG epochs, derived from visual-based scoring through image processing of fifty drivers' facial expressions during a 50-min driving simulation, using six individual EEG channels with paired features. Ten normalized EEG features were extracted per epoch using discrete wavelet transform (DWT), and seven thresholding techniques were applied to identify the most consistent method across subjects. Epochs were classified as drowsy or wakeful based on whether their normalized values exceeded or fell below a specific threshold. We then assessed the coverage of each channel by comparing EEG patterns with visual-based scoring. To determine the optimal feature pair for classifying each epoch in alignment with visual-based scoring, 45 feature combinations were evaluated. The pairing of power spectral density (PSD) alpha and PSD theta in channels Frontal4 (F4) and Occipital2 (O2) yielded the highest coverage, achieving 96.1% and 95% with corresponding accuracies of 95.4% and 94.7%, respectively. These results slightly surpassed the coverage achieved using six channels with a single feature, with increases of 1.47% for F4 and 0.32% for O2. Our study demonstrates that an optimal EEG channel with optimum paired EEG features can reduce channels from six to one, lowering computational demands for wearable DD devices.

EEG-based multi-band functional connectivity using corrected amplitude envelope correlation for identifying unfavorable driving states

Recognition of unfavorable driving state (UDS) based on Electroencephalography (EEG) signals and functional connectivity has a significant contribution to reducing casualties. However, when the functional connectivity approach directly applies to recognize drivers' UDS, it may encounter great challenges, because of spurious synchronization phenomenon. We introduce a novel functional connectivity matrix construction approach combined with the ensemble algorithm to identify drivers' UDS in the research. First, EEG data from a previously designed simulated driving experiment containing two driving tasks are extracted, and then functional connectivity matrix construction approach based on amplitude envelope correlation with leakage correction (AEC-c) in multiple frequency bands are calculated. Furthermore, the random subspace is utilized to improve the performances of the k-nearest neighbors (KNN) algorithm. Classification performances of the proposed approach are assessed by confusion matrix, accuracy (ACC), sensitivity (SEN), specificity (SPF), precision (PRE) and receiver operating characteristic (ROC) curve with 5-fold cross-validation strategy. The statistical analysis shows that the regional AEC-c values of 30 EEG channels for the driver's UDS are overall significantly lower than those for the driver's non-unfavorable driving state (NUDS) in the beta, gamma and all frequency bands. Further analysis about performance results shows that the proposed AEC-c-based functional connection matrix analysis approach in all frequency bands combined with the random subspace ensembles KNN achieves a highest ACC of 96.88%. The results suggests that our proposed framework is beneficial for EEG-based driver's UDS recognition, which is helpful to the transmission and interaction of information in man-machine system.

ID3RSNet: cross-subject driver drowsiness detection from raw single-channel EEG with an interpretable residual shrinkage network

Accurate monitoring of drowsy driving through electroencephalography (EEG) can effectively reduce traffic accidents. Developing a calibration-free drowsiness detection system with single-channel EEG alone is very challenging due to the non-stationarity of EEG signals, the heterogeneity among different individuals, and the relatively parsimonious compared to multi-channel EEG. Although deep learning-based approaches can effectively decode EEG signals, most deep learning models lack interpretability due to their black-box nature. To address these issues, we propose a novel interpretable residual shrinkage network, namely, ID3RSNet, for cross-subject driver drowsiness detection using single-channel EEG signals. First, a base feature extractor is employed to extract the essential features of EEG frequencies; to enhance the discriminative feature learning ability, the residual shrinkage building unit with attention mechanism is adopted to perform adaptive feature recalibration and soft threshold denoising inside the residual network is further applied to achieve automatic feature extraction. In addition, a fully connected layer with weight freezing is utilized to effectively suppress the negative influence of neurons on the model classification. With the global average pooling (GAP) layer incorporated in the residual shrinkage network structure, we introduce an EEG-based Class Activation Map (ECAM) interpretable method to enable visualization analysis of sample-wise learned patterns to effectively explain the model decision. Extensive experimental results demonstrate that the proposed method achieves the superior classification performance and has found neurophysiologically reliable evidence of classification.

VME-EFD : A novel framework to eliminate the Electrooculogram artifact from single-channel EEGs

The diagnosis of neurological disorders often involves analyzing EEG data, which can be contaminated by artifacts from eye movements or blinking (EOG). To improve the accuracy of EEG-based analysis, we propose a novel framework, VME-EFD, which combines Variational Mode Extraction (VME) and Empirical Fourier Decomposition (EFD) for effective EOG artifact removal. In this approach, the EEG signal is first decomposed by VME into two segments: the desired EEG signal and the EOG artifact. The EOG component is further processed by EFD, where decomposition levels are analyzed based on energy and skewness. The level with the highest energy and skewness, corresponding to the artifact, is discarded, while the remaining levels are reintegrated with the desired EEG. Simulations on both synthetic and real EEG datasets demonstrate that VME-EFD outperforms existing methods, with lower RRMSE (0.1358 versus 0.1557, 0.1823, 0.2079, 0.2748), lower ΔPSD in theαband (0.10 ± 0.01 and 0.17 ± 0.04 versus 0.89 ± 0.91 and 0.22 ± 0.19, 1.32 ± 0.23 and 1.10 ± 0.07, 2.86 ± 1.30 and 1.19 ± 0.07, 3.96 ± 0.56 and 2.42 ± 2.48), and higher correlation coefficient (CC: 0.9732 versus 0.9695, 0.9514, 0.8994, 0.8730). The framework effectively removes EOG artifacts and preserves critical EEG features, particularly in theαband, making it highly suitable for brain-computer interface (BCI) applications.

Dynamical Embedding of Single-Channel Electroencephalogram for Artifact Subspace Reconstruction

This study introduces a novel framework to apply the artifact subspace reconstruction (ASR) algorithm on single-channel electroencephalogram (EEG) data. ASR is known for its ability to remove artifacts like eye-blinks and movement but traditionally relies on multiple channels. Embedded ASR (E-ASR) addresses this by incorporating a dynamical embedding approach. In this method, an embedded matrix is created from single-channel EEG data using delay vectors, followed by ASR application and reconstruction of the cleaned signal. Data from four subjects with eyes open were collected using Fp1 and Fp2 electrodes via the CameraEEG android app. The E-ASR algorithm was evaluated using metrics like relative root mean square error (RRMSE), correlation coefficient (CC), and average power ratio. The number of eye-blinks with and without the E-ASR approach was also estimated. E-ASR achieved an RRMSE of 43.87% and had a CC of 0.91 on semi-simulated data and effectively reduced artifacts in real EEG data, with eye-blink counts validated against ground truth video data. This framework shows potential for smartphone-based EEG applications in natural environments with minimal electrodes.

FBLPF-ABOW: An Effective Method for Blink Artifact Removal in Single-Channel EEG Signal

OBJECTIVE

The latest development in low-cost single-channel Electroencephalography (EEG) devices is gaining widespread attention because it reduces hardware complexity. Discrete wavelet transform (DWT) has been a popular solution to eliminate the blink artifacts in EEG signals. However, the existing DWT-based methods share the same wavelet function among subjects, which ignores the individual difference. To remedy this deficiency, this article proposes a novel approach to eliminate the blink artifacts in single-channel EEG signals.

METHODS

Firstly, the forward-backward low-pass filter (FBLPF) and a fixed-length window are used to detect blink artifact intervals. Secondly, the adaptive bi-orthogonal wavelet (ABOW) is constructed based on the most representative blink signal. Thirdly, these detected signals are filtered by ABOW-DWT. The DWT's decomposition depth is automatically chosen by a similarity-based method.

RESULTS

Compared to eight state-of-the-art methods, experiments on semi-simulated and real EEG signals demonstrate the proposed method's superiority in removing the blink artifacts with less neural information loss.

SIGNIFICANCE

To filter the blink artifacts in single-channel EEG signals, the innovative idea of constructing an adaptive wavelet function based on the signal characteristics rather than using the conventional wavelet is proposed for the first time.

Method for analyzing sequential services using EEG: Micro-meso analysis of emotional changes in real flight service

Capturing customers' emotional changes in sequential service should be realized using physiological measurements to assess customer delight. Questionnaire-based customer surveys may miss significant and dissipating emotional responses. This study developed a micro‑meso analysis method of capturing emotional changes for sequential service using electroencephalograph (EEG) measurement, dealing with both service encounters (micro-level) and servicescape (meso‑level) over a couple of hours. Customers' emotion states were defined based on emotional arousal and valence. Emotional responses caused by human interactions were evaluated, and periods of high positive affect throughout the customer journey were visualized. Experiments in actual flight services demonstrated successful emotion estimation across flight phases using a single-channel EEG measurement over two hours. Analysis results on the measurement data revealed emotional peaks outside service encounters that are not captured in customers' individual self-reports. The results also statistically revealed that two individual services (asking about a refill and conversations started by flight attendants) evoked high positive affect. Temporal dynamic analyses around high positive affect suggested patterns of interplay between joy and surprise, which are key components of customer delight. Compared with questionnaire-based evaluation, the proposed method contributes significantly to empirical studies on sequential services in marketing and design by enabling the extraction of "high positive affect," which needs to be identified for customer delight. This study supplements existing research on the interactions among physiology (EEG), behavior (emotional changes), and customer service research.

Mental fatigue assessment by an arbitrary channel EEG based on morphological features and LSTM-CNN

In order to achieve more sensitive mental fatigue assessment (MFA) based on an arbitrary channel EEG, this study proposed a series of feature extraction methods that combine mathematical morphology (MM), as well as an LSTM-CNN architecture. Firstly, 37 subjects had their resting-state EEGs collected at rested wakefulness (RW) and after 24 h of sleep deprivation (SD) using a 30-channel EEG acquisition device, the RW and SD groups were regarded as the negative and positive groups of mental fatigue, respectively, and the EEG collection were further categorized into two conditions: eye-opened state (EO) and eye-closed state (EC). Then, since MM can reflect the morphological characteristics of EEG rhythms and their potentials relatively independently of the time-frequency analysis and phase calculation, the MM methods were found to better reflect the mental fatigue after SD statistically, whether for single features (ANOVA: p<0.000001), multiple features (clustering by K-means, t-test: p<0.01), or time series feature spaces (calculating CD, t-test: p<0.01) of a single channel. Finally, the LSTM-CNN enhanced the generalization ability when dealing with different single-channel EEG by combining GRUs with convolutional layers: comparing the AUCs of different architectures for MFA based on an arbitrary channel, LSTM-CNN (0.992) > LSTM network (0.94) > CNN (0.831) > MLP (0.754). Moreover, the use of MM also improved the accuracy of analyzed architectures, and the true/false positive rate (TPR/FPR) of the LSTM-CNN architecture for MFA based on an arbitrary channel reached 97.024 %/3.497 %, which provided a feasible solution for the arbitrary channel EEG-based MFA.

Driver drowsiness detection methods using EEG signals: a systematic review

Electroencephalography (EEG) is a complex signal that may require several years of training, advanced signal processing, and feature extraction methodologies to interpret correctly. Recently, many methods have been used to extract and classify EEG data. This study reviews 62 papers that used EEG signals to detect driver drowsiness, published between January 2018 and 2022. We extract trends and highlight interesting approaches from this large body of literature to inform future research and formulate recommendations. To find relevant papers published in scientific journals, conferences, and electronic preprint repositories, researchers searched major databases covering the domains of science and engineering. For each investigation, many data items about (1) the data, (2) the channels used, (3) the extraction and classification procedure, and (4) the outcomes were extracted. These items were then analyzed one by one to uncover trends. Our analysis reveals that the amount of EEG data used across studies varies. We saw that more than half the studies used simulation driving experimental. About 21% of the studies used support vector machine (SVM), while 19% used convolutional neural networks (CNN). Overall, we can conclude that drowsiness and fatigue impair driving performance, resulting in drivers who are more exposed to risky situations.

Transdiagnostic association between subjective insomnia and depressive symptoms in major psychiatric disorders

In psychiatric disorders, comorbid depressive symptoms are associated with clinically important issues such as reduced quality of life, a poor prognosis, and increased suicide risk. Previous studies have found a close relationship between insomnia and depressive symptoms in major depressive disorder (MDD), and that actively improving insomnia heightens the improvement of depressive symptoms. This study aimed to investigate whether the association between insomnia and depressive symptoms is also found in other psychiatric disorders besides MDD. The subjects were 144 patients with MDD (n = 71), schizophrenia (n = 25), bipolar disorder (n = 22), or anxiety disorders (n = 26). Sleep status was assessed subjectively and objectively using the Athens Insomnia Scale (AIS) and sleep electroencephalography (EEG), respectively. Sleep EEG was performed using a portable EEG device. Depressive symptoms were assessed using the Beck Depression Inventory. Subjective insomnia, as defined by the AIS, was associated with depressive symptoms in all disorders. Moreover, in schizophrenia, a relation between depressive symptoms and insomnia was also found by objective sleep assessment methods using sleep EEG. Our findings suggest that the association between subjective insomnia and depressive symptoms is a transdiagnostic feature in major psychiatric disorders. Further studies are needed to clarify whether therapeutic interventions for comorbid insomnia can improve depressive symptoms in major psychiatric disorders, similar to MDD.

A Kinematic Data-Driven Approach to Differentiate Involuntary Choreic Movements in Individuals With Neurological Conditions

OBJECTIVE

The ability to differentiate similar choreic involuntary movements could lay the groundwork for the development of a minimally-invasive screening tool for their etiology and provide in-depth understandings of pathophysiology. As a first step, we investigate kinematic differences between Huntington's disease (HD) chorea and Parkinson's disease (PD) choreic levodopa-induced dyskinesia (LID), which have distinct pathological causes yet share a great kinematic resemblance.

METHODS

Twenty subjects with HD and ten subjects with PD stood with both upper limbs in front of them for approximately 60 seconds. The three-dimensional velocity time-series of involuntary movements of both hands were segmented into one-dimensional sub-movements abutted by velocity zero-crossings. A combination of unsupervised and supervised machine learning algorithms was employed to automatically select data features extracted from sub-movements and distinguish the two types of involuntary choreic movements.

RESULTS

The trained model was able to accurately classify chorea vs. LID with an Area Under the Receiver Operating Characteristic Curve of 99.5%. A set of important features contributing to the construction of the classification model were identified and investigated.

CONCLUSION

The trained model may serve as a tool for the automatic identification of different types of involuntary choreic movements, enabling continuous monitoring and personalized treatment for patients in various clinical settings.

SIGNIFICANCE

The results provide insights into kinematic characteristics of HD chorea and PD LID, which is the first step towards an improved general understanding of involuntary choreic movements.

Research on the Method of Depression Detection by Single-Channel Electroencephalography Sensor

Depression is a common mental health illness worldwide that affects our quality of life and ability to work. Although prior research has used EEG signals to increase the accuracy to identify depression, the rates of underdiagnosis remain high, and novel methods are required to identify depression. In this study, we built a model based on single-channel, dry-electrode EEG sensor technology to detect state depression, which measures the intensity of depressive feelings and cognitions at a particular time. To test the accuracy of our model, we compared the results of our model with other commonly used methods for depression diagnosis, including the PHQ-9, Hamilton Depression Rating Scale (HAM-D), and House-Tree-Person (HTP) drawing test, in three different studies. In study 1, we compared the results of our model with PHQ-9 in a sample of 158 senior high students. The results showed that the consistency rate of the two methods was 61.4%. In study 2, the results of our model were compared with HAM-D among 71 adults. We found that the consistency rate of state-depression identification by the two methods was 63.38% when a HAM-D score above 7 was considered depression, while the consistency rate increased to 83.10% when subjects showed at least one depressive symptom (including depressed mood, guilt, suicide, lack of interest, retardation). In study 3, 68 adults participated in the study, and the results revealed that the consistency rate of our model and HTP drawing test was 91.2%. The results showed that our model is an effective means to identify state depression. Our study demonstrates that using our model, people with state depression could be identified in a timely manner and receive interventions or treatments, which may be helpful for the early detection of depression.

EEG Signals Based Internet Addiction Diagnosis Using Convolutional Neural Networks

Internet addiction (IA), as a new and often unrecognized psychosocial disorder, endangers people’s health and their lives. However, the common biometric analysis based on the combination of EEG signals and results of questionnaires is not quantitative, and thus difficult to ensure a specific biomarker. This work aims to develop a deep learning algorithm (no need to identify biomarkers) used for diagnosing IA and evaluating therapy efficacy. Herein, a five-layer CNN model combined with a fast Fourier transform is proposed to diagnose IA quantitatively. This algorithm is validated in the Lemon dataset by using it to process raw data, full spectral power, and alpha-beta-gamma spectral power (related to IA). In contrast to alpha-beta-gamma spectral power, the results based on full spectral power show better performance (87.59% accuracy, 88.80% sensitivity, and 86.41% specificity), which confirms that the proposed algorithm can diagnose IA without biomarkers. In addition, this proposed CNN model presents obvious advantages in processing raw data, achieving 81.1% accuracy. Such results verify that this method can contribute to the reduction of diagnosis time and be potentially used in real-time health monitoring systems. This work provides a quantitative approach to diagnose IA and evaluate therapy efficacy, as a general strategy, and can be widely used in other disorder diagnoses that affect EEG signals, such as psychiatric disorders, substance dependence, and depression.

Frontotemporal EEG as potential biomarker for early MCI: a case-control study

BACKGROUND

Previous studies using EEG (electroencephalography) as biomarker for dementia have attempted to research, but results have been inconsistent. Most of the studies have extremely small number of samples (average N = 15) and studies with large number of data do not have control group. We identified EEG features that may be biomarkers for dementia with 120 subjects (dementia 10, MCI 33, against control 77).

METHODS

We recorded EEG from 120 patients with dementia as they stayed in relaxed state using a single-channel EEG device while conducting real-time noise reduction and compared them to healthy subjects. Differences in EEG between patients and controls, as well as differences in patients' severity, were examined using the ratio of power spectrum at each frequency.

RESULTS

In comparing healthy controls and dementia patients, significant power spectrum differences were observed at 3 Hz, 4 Hz, and 10 Hz and higher frequencies. In patient group, differences in the power spectrum were observed between asymptomatic patients and healthy individuals, and between patients of each respective severity level and healthy individuals.

CONCLUSIONS

A study with a larger sample size should be conducted to gauge reproducibility, but the results implied the effectiveness of EEG in clinical practice as a biomarker of MCI (mild cognitive impairment) and/or dementia.

Characteristics of single-channel electroencephalogram in depression during conversation with noise reduction technology

Background

Previous studies have attempted to characterize depression using electroencephalography (EEG), but results have been inconsistent. New noise reduction technology allows EEG acquisition during conversation.

Methods

We recorded EEG from 40 patients with depression as they engaged in conversation using a single-channel EEG device while conducting real-time noise reduction and compared them to those of 40 healthy subjects. Differences in EEG between patients and controls, as well as differences in patients’ depression severity, were examined using the ratio of the power spectrum at each frequency. In addition, the effects of medications were examined in a similar way.

Results

In comparing healthy controls and depression patients, significant power spectrum differences were observed at 3 Hz, 4 Hz, and 10 Hz and higher frequencies. In the patient group, differences in the power spectrum were observed between asymptomatic patients and healthy individuals, and between patients of each respective severity level and healthy individuals. In addition, significant differences were observed at multiple frequencies when comparing patients who did and did not take antidepressants, antipsychotics, and/or benzodiazepines. However, the power spectra still remained significantly different between non-medicated patients and healthy individuals.

Limitations

The small sample size may have caused Type II error. Patients’ demographic characteristics varied. Moreover, most patients were taking various medications, and cannot be compared to the non-medicated control group.

Conclusion

A study with a larger sample size should be conducted to gauge reproducibility, but the methods used in this study could be useful in clinical practice as a biomarker of depression.

Drowsiness detection using portable wireless EEG

BACKGROUND AND OBJECTIVE

The 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.

METHODS

A 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.

RESULTS

Using 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.

CONCLUSIONS

The 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.

SSA with CWT and k-Means for Eye-Blink Artifact Removal from Single-Channel EEG Signals

Recently, the use of portable electroencephalogram (EEG) devices to record brain signals in both health care monitoring and in other applications, such as fatigue detection in drivers, has been increased due to its low cost and ease of use. However, the measured EEG signals always mix with the electrooculogram (EOG), which are results due to eyelid blinking or eye movements. The eye-blinking/movement is an uncontrollable activity that results in a high-amplitude slow-time varying component that is mixed in the measured EEG signal. The presence of these artifacts misled our understanding of the underlying brain state. As the portable EEG devices comprise few EEG channels or sometimes a single EEG channel, classical artifact removal techniques such as blind source separation methods cannot be used to remove these artifacts from a single-channel EEG signal. Hence, there is a demand for the development of new single-channel-based artifact removal techniques. Singular spectrum analysis (SSA) has been widely used as a single-channel-based eye-blink artifact removal technique. However, while removing the artifact, the low-frequency components from the non-artifact region of the EEG signal are also removed by SSA. To preserve these low-frequency components, in this paper, we have proposed a new methodology by integrating the SSA with continuous wavelet transform (CWT) and the k-means clustering algorithm that removes the eye-blink artifact from the single-channel EEG signals without altering the low frequencies of the EEG signal. The proposed method is evaluated on both synthetic and real EEG signals. The results also show the superiority of the proposed method over the existing methods.

Fatigue Monitoring Through Wearables: A State-of-the-Art Review

The objective measurement of fatigue is of critical relevance in areas such as occupational health and safety as fatigue impairs cognitive and motor performance, thus reducing productivity and increasing the risk of injury. Wearable systems represent highly promising solutions for fatigue monitoring as they enable continuous, long-term monitoring of biomedical signals in unattended settings, with the required comfort and non-intrusiveness. This is a p rerequisite for the development of accurate models for fatigue monitoring in real-time. However, monitoring fatigue through wearable devices imposes unique challenges. To provide an overview of the current state-of-the-art in monitoring variables associated with fatigue via wearables and to detect potential gaps and pitfalls in current knowledge, a systematic review was performed. The Scopus and PubMed databases were searched for articles published in English since 2015, having the terms "fatigue," "drowsiness," "vigilance," or "alertness" in the title, and proposing wearable device-based systems for non-invasive fatigue quantification. Of the 612 retrieved articles, 60 satisfied the inclusion criteria. Included studies were mainly of short duration and conducted in laboratory settings. In general, researchers developed fatigue models based on motion (MOT), electroencephalogram (EEG), photoplethysmogram (PPG), electrocardiogram (ECG), galvanic skin response (GSR), electromyogram (EMG), skin temperature (T_sk), eye movement (EYE), and respiratory (RES) data acquired by wearable devices available in the market. Supervised machine learning models, and more specifically, binary classification models, are predominant among the proposed fatigue quantification approaches. These models were considered to perform very well in detecting fatigue, however, little effort was made to ensure the use of high-quality data during model development. Together, the findings of this review reveal that methodological limitations have hindered the generalizability and real-world applicability of most of the proposed fatigue models. Considerably more work is needed to fully explore the potential of wearables for fatigue quantification as well as to better understand the relationship between fatigue and changes in physiological variables.

Concerns in the Blurred Divisions between Medical and Consumer Neurotechnology

Neurotechnology has traditionally been central to the diagnosis and treatment of neurological disorders. While these devices have initially been utilized in clinical and research settings, recent advancements in neurotechnology have yielded devices that are more portable, user-friendly, and less expensive. These improvements allow laypeople to monitor their brain waves and interface their brains with external devices. Such improvements have led to the rise of wearable neurotechnology that is marketed to the consumer. While many of the consumer devices are marketed for innocuous applications, such as use in video games, there is potential for them to be repurposed for medical use. How do we manage neurotechnologies that skirt the line between medical and consumer applications and what can be done to ensure consumer safety? Here, we characterize neurotechnology based on medical and consumer applications and summarize currently marketed uses of consumer-grade wearable headsets. We lay out concerns that may arise due to the similar claims associated with both medical and consumer devices, the possibility of consumer devices being repurposed for medical uses, and the potential for medical uses of neurotechnology to influence commercial markets related to employment and self-enhancement.

A Review of EEG Signal Features and their Application in Driver Drowsiness Detection Systems

Detecting drowsiness in drivers, especially multi-level drowsiness, is a difficult problem that is often approached using neurophysiological signals as the basis for building a reliable system. In this context, electroencephalogram (EEG) signals are the most important source of data to achieve successful detection. In this paper, we first review EEG signal features used in the literature for a variety of tasks, then we focus on reviewing the applications of EEG features and deep learning approaches in driver drowsiness detection, and finally we discuss the open challenges and opportunities in improving driver drowsiness detection based on EEG. We show that the number of studies on driver drowsiness detection systems has increased in recent years and that future systems need to consider the wide variety of EEG signal features and deep learning approaches to increase the accuracy of detection.

Toward practical driving fatigue detection using three frontal EEG channels: a proof-of-concept study

Objective. Although various driving fatigue detection strategies have been introduced, the limited practicability is still an obstacle for the real application of these technologies. This study is based on the newly proposed non-hair-bearing (NHB) method to achieve practical driving fatigue detection with fewer channels from NHB areas and more efficient electroencephalogram (EEG) features.Approach. EEG data were recorded from 20 healthy subjects (15 males, age = 22.2 ± 3.2 years) in a 90 min simulated driving task using a remote wireless cap. Behaviorally, subjects demonstrated a salient fatigue effect, as reflected by a monotonic increase in reaction time. Using a sliding-window approach, we determined the vigilant and fatigued states at individual level to reduce the inter-subject differences in behavioral impairment and brain activity. Multiple EEG features, including power-spectrum density (PSD), functional connectivity (FC), and entropy, were estimated in a pairwise manner, which were set as input for fatigue classification.Main results. Intriguingly, this data-driven approach showed that the best classification performance was achieved using three EEG channel pairs located in the NHB area. The mixed features of the frontal NHB area lead to the high within-subject detection rate of driving fatigue (92.7% ± 0.92%) with satisfactory generalizability for fatigue classification across different subjects (77.13% ± 0.85%). Moreover, we found the most prominent contributing features were PSD of different frequency bands within the frontal NHB area and FC within the frontal NHB area and between frontal and parietal areas.Significance. In summary, the current work provided objective evidence to support the effectiveness of the NHB method and further improved the performance, thereby moving a step forward towards practical driving fatigue detection in real-world scenarios.

Vehicle driver drowsiness detection method using wearable EEG based on convolution neural network

Vehicle drivers driving cars under the situation of drowsiness can cause serious traffic accidents. In this paper, a vehicle driver drowsiness detection method using wearable electroencephalographic (EEG) based on convolution neural network (CNN) is proposed. The presented method consists of three parts: data collection using wearable EEG, vehicle driver drowsiness detection and the early warning strategy. Firstly, a wearable brain computer interface (BCI) is used to monitor and collect the EEG signals in the simulation environment of drowsy driving and awake driving. Secondly, the neural networks with Inception module and modified AlexNet module are trained to classify the EEG signals. Finally, the early warning strategy module will function and it will sound an alarm if the vehicle driver is judged as drowsy. The method was tested on driving EEG data from simulated drowsy driving. The results show that using neural network with Inception module reached 95.59% classification accuracy based on one second time window samples and using modified AlexNet module reached 94.68%. The simulation and test results demonstrate the feasibility of the proposed drowsiness detection method for vehicle driving safety.

A compact and interpretable convolutional neural network for cross-subject driver drowsiness detection from single-channel EEG

Driver drowsiness is one of the main factors leading to road fatalities and hazards in the transportation industry. Electroencephalography (EEG) has been considered as one of the best physiological signals to detect drivers' drowsy states, since it directly measures neurophysiological activities in the brain. However, designing a calibration-free system for driver drowsiness detection with EEG is still a challenging task, as EEG suffers from serious mental and physical drifts across different subjects. In this paper, we propose a compact and interpretable Convolutional Neural Network (CNN) to discover shared EEG features across different subjects for driver drowsiness detection. We incorporate the Global Average Pooling (GAP) layer in the model structure, allowing the Class Activation Map (CAM) method to be used for localizing regions of the input signal that contribute most for classification. Results show that the proposed model can achieve an average accuracy of 73.22% on 11 subjects for 2-class cross-subject EEG signal classification, which is higher than conventional machine learning methods and other state-of-art deep learning methods. It is revealed by the visualization technique that the model has learned biologically explainable features, e.g., Alpha spindles and Theta burst, as evidence for the drowsy state. It is also interesting to see that the model uses artifacts that usually dominate the wakeful EEG, e.g., muscle artifacts and sensor drifts, to recognize the alert state. The proposed model illustrates a potential direction to use CNN models as a powerful tool to discover shared features related to different mental states across different subjects from EEG signals.

Convolutional Neural Network for Drowsiness Detection Using EEG Signals

Drowsiness detection (DD) has become a relevant area of active research in biomedical signal processing. Recently, various deep learning (DL) researches based on the EEG signals have been proposed to detect fatigue conditions. The research presented in this paper proposes an EEG classification system for DD based on DL networks. However, the proposed DD system is mainly realized into two procedures; (i) data acquisition and (ii) model analysis. For the data acquisition procedure, two key steps are considered, which are the signal collection using a wearable Emotiv EPOC+ headset to record 14 channels of EEG, and the signal annotation. Furthermore, a data augmentation (DA) step has been added to the proposed system to overcome the problem of over-fitting and to improve accuracy. As regards the model analysis, a comparative study is also introduced in this paper to argue the choice of DL architecture and frameworks used in our DD system. In this sense, The proposed DD protocol makes use of a convolutional neural network (CNN) architecture implemented using the Keras library. The results showed a high accuracy value (90.42%) in drowsy/awake discrimination and revealed the efficiency of the proposed DD system compared to other research works.

Drowsiness Detection Based on Intelligent Systems with Nonlinear Features for Optimal Placement of Encephalogram Electrodes on the Cerebral Area

Drowsiness while driving can lead to accidents that are related to the loss of perception during emergencies that harm the health. Among physiological signals, brain waves have been used as informative signals for the analyses of behavioral observations, steering information, and other biosignals during drowsiness. We inspected the machine learning methods for drowsiness detection based on brain signals with varying quantities of information. The results demonstrated that machine learning could be utilized to compensate for a lack of information and to account for individual differences. Cerebral area selection approaches to decide optimal measurement locations could be utilized to minimize the discomfort of participants. Although other statistics could provide additional information in further study, the optimized machine learning method could prevent the dangers of drowsiness while driving by considering a transitional state with nonlinear features. Because brain signals can be altered not only by mental fatigue but also by health status, the optimization analysis of the system hardware and software will be able to increase the power-efficiency and accessibility in acquiring brain waves for health enhancements in daily life.

VME-DWT: An Efficient Algorithm for Detection and Elimination of Eye Blink From Short Segments of Single EEG Channel

OBJECTIVE

Recent advances in development of low-cost single-channel electroencephalography (EEG) headbands have opened new possibilities for applications in health monitoring and brain-computer interface (BCI) systems. These recorded EEG signals, however, are often contaminated by eye blink artifacts that can yield the fallacious interpretation of the brain activity. This paper proposes an efficient algorithm, VME-DWT, to remove eye blinks in a short segment of the single EEG channel.

METHOD

The proposed algorithm: (a) locates eye blink intervals using Variational Mode Extraction (VME) and (b) filters only contaminated EEG interval using an automatic Discrete Wavelet Transform (DWT) algorithm. The performance of VME-DWT is compared with an automatic Variational Mode Decomposition (AVMD) and a DWT-based algorithms, proposed for suppressing eye blinks in a short segment of the single EEG channel.

RESULTS

The VME-DWT detects and filters 95% of the eye blinks from the contaminated EEG signals with SNR ranging from -8 to +3 dB. The VME-DWT shows superiority to the AVMD and DWT with the higher mean value of correlation coefficient (0.92 vs. 0.83, 0.58) and lower mean value of RRMSE (0.42 vs. 0.59, 0.87).

SIGNIFICANCE

The VME-DWT can be a suitable algorithm for removal of eye blinks in low-cost single-channel EEG systems as it is: (a) computationally-efficient, the contaminated EEG signal is filtered in millisecond time resolution, (b) automatic, no human intervention is required, (c) low-invasive, EEG intervals without contamination remained unaltered, and (d) low-complexity, without need to the artifact reference.

A Systemic Review of Available Low-Cost EEG Headsets Used for Drowsiness Detection

Drowsiness is a leading cause of traffic and industrial accidents, costing lives and productivity. Electroencephalography (EEG) signals can reflect awareness and attentiveness, and low-cost consumer EEG headsets are available on the market. The use of these devices as drowsiness detectors could increase the accessibility of safety and productivity-enhancing devices for small businesses and developing countries. We conducted a systemic review of currently available, low-cost, consumer EEG-based drowsiness detection systems. We sought to determine whether consumer EEG headsets could be reliably utilized as rudimentary drowsiness detection systems. We included documented cases describing successful drowsiness detection using consumer EEG-based devices, including the Neurosky MindWave, InteraXon Muse, Emotiv Epoc, Emotiv Insight, and OpenBCI. Of 46 relevant studies, ~27 reported an accuracy score. The lowest of these was the Neurosky Mindwave, with a minimum of 31%. The second lowest accuracy reported was 79.4% with an OpenBCI study. In many cases, algorithmic optimization remains necessary. Different methods for accuracy calculation, system calibration, and different definitions of drowsiness made direct comparisons problematic. However, even basic features, such as the power spectra of EEG bands, were able to consistently detect drowsiness. Each specific device has its own capabilities, tradeoffs, and limitations. Widely used spectral features can achieve successful drowsiness detection, even with low-cost consumer devices; however, reliability issues must still be addressed in an occupational context.

Passive Brain-Computer Interfaces for Enhanced Human-Robot Interaction

Brain-computer interfaces (BCIs) have long been seen as control interfaces that translate changes in brain activity, produced either by means of a volitional modulation or in response to an external stimulation. However, recent trends in the BCI and neurofeedback research highlight passive monitoring of a user's brain activity in order to estimate cognitive load, attention level, perceived errors and emotions. Extraction of such higher order information from brain signals is seen as a gateway for facilitation of interaction between humans and intelligent systems. Particularly in the field of robotics, passive BCIs provide a promising channel for prediction of user's cognitive and affective state for development of a user-adaptive interaction. In this paper, we first illustrate the state of the art in passive BCI technology and then provide examples of BCI employment in human-robot interaction (HRI). We finally discuss the prospects and challenges in integration of passive BCIs in socially demanding HRI settings. This work intends to inform HRI community of the opportunities offered by passive BCI systems for enhancement of human-robot interaction while recognizing potential pitfalls.

Loss of Concentration May Occur by Blink Inhibition in DED Simulation Models

Purpose: Patients with dry eye disease (DED) often suffer productivity loss and distress due to bothersome symptoms. The aim of this study was to objectively quantify and compare productivity-related emotional states obtained from brain waveforms in natural and simulated DED conditions. Method: 25 healthy adults (6 females and 19 males; mean age ± standard deviation, 22.6 ± 8.3 years) were recruited for the study, which included an electroencephalogram (EEG), measurements of interblinking time, and questionnaires. DED was simulated by suppressing blinking, while spontaneous blinking served as a control. Elements of concentration, stress, and alertness were extracted from the raw EEG waveforms and the values were compared during spontaneous and suppressed blinking. The relation with DED-related parameters was then explored. Written informed consent was obtained from all participants. Results: All participants successfully completed the experimental protocol. Concentration significantly decreased during suppressed blinking in 20 participants (80%), when compared with spontaneous blinking, whereas there were no or small differences in stress or alertness between spontaneous and suppressed blinking. The change in concentration was correlated with interblinking time (β = −0.515, p = 0.011). Conclusion: Loss of concentration was successfully captured in an objective manner using the EEG. The present study may enable us to understand how concentration is affected during blink suppression, which may happen in office work, particularly during computer tasks. Further study using detailed ocular evaluation is warranted to explore the effect of different interventions.

A Prototype of EEG System for IoT

In this work, we develop open source hardware and software for eye state classification and integrate it with a protocol for the Internet of Things (IoT). We design and build the hardware using a reduced number of components and with a very low-cost. Moreover, we propose a method for the detection of open eyes (oE) and closed eyes (cE) states based on computing a power ratio between different frequency bands of the acquired signal. We compare several real- and complex-valued transformations combined with two decision strategies: a threshold-based method and a linear discriminant analysis. Simulation results show both classifier accuracies and their corresponding system delays.

Passive Brain-Computer Interfaces for Enhanced Human-Robot Interaction

Brain-computer interfaces (BCIs) have long been seen as control interfaces that translate changes in brain activity, produced either by means of a volitional modulation or in response to an external stimulation. However, recent trends in the BCI and neurofeedback research highlight passive monitoring of a user's brain activity in order to estimate cognitive load, attention level, perceived errors and emotions. Extraction of such higher order information from brain signals is seen as a gateway for facilitation of interaction between humans and intelligent systems. Particularly in the field of robotics, passive BCIs provide a promising channel for prediction of user's cognitive and affective state for development of a user-adaptive interaction. In this paper, we first illustrate the state of the art in passive BCI technology and then provide examples of BCI employment in human-robot interaction (HRI). We finally discuss the prospects and challenges in integration of passive BCIs in socially demanding HRI settings. This work intends to inform HRI community of the opportunities offered by passive BCI systems for enhancement of human-robot interaction while recognizing potential pitfalls.

An iterative cross-subject negative-unlabeled learning algorithm for quantifying passive fatigue

OBJECTIVE

This paper proposes an iterative negative-unlabeled (NU) learning algorithm for cross-subject detection of passive fatigue from labelled alert (negative) and unlabeled driving EEG data.

APPROACH

Unlike other studies which used manual labeling of the fatigue state, the proposed algorithm (PA) first iteratively uses 29 subjects' alert data and unlabeled driving data to identify the most fatigued block of EEG data in each subject in a cross-subject manner. Subsequently, the PA computes subjects' driving fatigue score. Repeated measures correlations of the score to EEG band powers are then performed.

MAIN RESULTS

The PA yields an averaged accuracy of 93.77%  ±  8.15% across subjects in detecting fatigue, which is significantly better than the various baselines. The fatigue scores obtained are also significantly positively correlated with theta band power and negatively correlated with beta band power that are known to respectively increase and decrease in presence of passive fatigue. There is a strong negative correlation with alpha band power as well.

SIGNIFICANCE

The proposed iterative NU learning algorithm is capable of labelling and quantifying the most fatigued block in a cross-subject manner despite the lack of ground truth in the fatigue levels of unlabeled driving EEG data. Together with the significant correlations with theta, alpha and beta band power, the results show promise in the application of the proposed algorithm to detect fatigue from EEG.

An oculometrics-based biofeedback system to impede fatigue development during computer work: A proof-of-concept study

A biofeedback system may objectively identify fatigue and provide an individualized timing plan for micro-breaks. We developed and implemented a biofeedback system based on oculometrics using continuous recordings of eye movements and pupil dilations to moderate fatigue development in its early stages. Twenty healthy young participants (10 males and 10 females) performed a cyclic computer task for 31–35 min over two sessions: 1) self-triggered micro-breaks (manual sessions), and 2) biofeedback-triggered micro-breaks (automatic sessions). The sessions were held with one-week inter-session interval and in a counterbalanced order across participants. Each session involved 180 cycles of the computer task and after each 20 cycles (a segment), the task paused for 5-s to acquire perceived fatigue using Karolinska Sleepiness Scale (KSS). Following the pause, a 25-s micro-break involving seated exercises was carried out whether it was triggered by the biofeedback system following the detection of fatigue (KSS≥5) in the automatic sessions or by the participants in the manual sessions. National Aeronautics and Space Administration Task Load Index (NASA-TLX) was administered after sessions. The functioning core of the biofeedback system was based on a Decision Tree Ensemble model for fatigue classification, which was developed using an oculometrics dataset previously collected during the same computer task. The biofeedback system identified fatigue with a mean accuracy of approx. 70%. Perceived workload obtained from NASA-TLX was significantly lower in the automatic sessions compared with the manual sessions, p = 0.01 Cohen’s d_z = 0.89. The results give support to the effectiveness of integrating oculometrics-based biofeedback in timing plan of micro-breaks to impede fatigue development during computer work.