EEG System Research Articles

Automated methodology for optimal selection of minimum electrode subsets for accurate EEG source estimation based on Genetic Algorithm optimization

High-density Electroencephalography (HD-EEG) has proven to be the EEG montage that estimates the neural activity inside the brain with highest accuracy. Multiple studies have reported the effect of electrode number on source localization for specific sources and specific electrode configurations. The electrodes for these configurations are often manually selected to uniformly cover the entire head, going from 32 to 128 electrodes, but electrode configurations are not often selected according to their contribution to estimation accuracy. In this work, an optimization-based study is proposed to determine the minimum number of electrodes that can be used and to identify the optimal combinations of electrodes that can retain the localization accuracy of HD-EEG reconstructions. This optimization approach incorporates scalp landmark positions of widely used EEG montages. In this way, a systematic search for the minimum electrode subset is performed for single- and multiple-source localization problems. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) combined with source reconstruction methods is used to formulate a multi-objective optimization problem that concurrently minimizes (1) the localization error for each source and (2) the number of required EEG electrodes. The method can be used for evaluating the source localization quality of low-density EEG systems (e.g. consumer-grade wearable EEG). We performed an evaluation over synthetic and real EEG datasets with known ground-truth. The experimental results show that optimal subsets with 6 electrodes can attain an equal or better accuracy than HD-EEG (with more than 200 channels) for a single source case. This happened when reconstructing a particular brain activity in more than 88% of the cases in synthetic signals and 63% in real signals, and in more than 88% and 73% of cases when considering optimal combinations with 8 channels. For a multiple-source case of three sources (only with synthetic signals), it was found that optimized combinations of 8, 12 and 16 electrodes attained an equal or better accuracy than HD-EEG with 231 electrodes in at least 58%, 76%, and 82% of cases respectively. Additionally, for such electrode numbers, lower mean errors and standard deviations than with 231 electrodes were obtained.

Comparing Seizures Captured by Rapid Response EEG and Conventional EEG Recordings in a Multicenter Clinical Study.

ObjectiveA recent multicenter prospective study (DECIDE trial) examined the use of Ceribell Rapid Response EEG (Rapid-EEG) in the emergent evaluation and management of critically ill patients suspected to have non-convulsive seizures. We present a detailed, patient-level examination of seizures detected either on initial Rapid-EEG or subsequent conventional EEG within 24 h to investigate whether seizures were missed on Rapid-EEG due to the exclusion of midline/parasagittal coverage.MethodsWe identified from 164 patients studied in the DECIDE trial those who had seizures detected on Rapid-EEG but not conventional EEG (n = 6), conventional EEG but not Rapid-EEG (n = 4), or both Rapid-EEG and conventional EEG (n = 9). We examined the electrographic characteristics of ictal and interictal findings on both devices, especially their detection in lateral or midline/parasagittal chains, and patient clinical histories to identify contributors toward discordant seizure detection.ResultsSeizures detected on both EEG systems had similar electrographic appearance and laterality. Seizures detected only on conventional EEG (within 24 h following Rapid-EEG) were visible in the temporal chains, and external clinical factors (e.g., treatment with anti-seizure medications, sedation, and duration of recordings) explained the delayed presentation of seizures. Patients with seizures detected only by Rapid-EEG were treated with anti-seizure medications, and subsequent conventional EEG detected interictal highly epileptiform patterns with similar laterality.ConclusionsOur case series demonstrates that electrographic data obtained from initial Rapid-EEG and subsequent conventional EEG monitoring are largely concordant relative to morphology and laterality. These findings are valuable to inform future investigation of abbreviated EEG systems to optimize management of suspected non-convulsive seizures and status epilepticus. Future, larger studies could further investigate the value of Rapid-EEG findings for forecasting and predicting seizures in long-term EEG recordings.

Media Neuroscience on a Shoestring

Abstract: Event-related potentials (ERPs) capture neural responses to media stimuli with a split-second resolution, opening the door to examining how attention modulates the reception process. However, the relatively high cost and difficulty of incorporating ERP methods have prevented broader adoption. This study tested the potential of a new mobile, relatively easy-to-mount, and highly affordable device for electroencephalography (EEG) measurement – the Muse EEG system – combined with a free, open-source platform for ERP recording and analysis. Specifically, we compared ERPs with affective visual stimuli – representative of the kind of engaging content that pervades modern social media. Our results confirm that the Muse system provides robust visual ERPs, highly reliable across two samples. Although there was no difference between ERPs to moderately positive and neutral stimuli in the expected time windows (200–300 ms, 400–600 ms), an exploratory analysis provided some evidence for differential processing of positive versus neutral images at the right temporal sensor site (TP10). Additionally, a compliance-gaining manipulation in participant instructions significantly improved data quality. These results support the use of the Muse EEG system in large-scale studies examining brain responses to screen media. They also suggest an easy social influence tactic that can enhance data quality as communication neuroscience is scaled up. The availability of a mobile EEG system for 250 USD makes it possible to incorporate neuroimaging into various communication paradigms beyond visual communication.

Miniaturization for wearable EEG systems: recording hardware and data processing.

As more people desire at-home diagnosis and treatment for their health improvement, healthcare devices have become more wearable, comfortable, and easy to use. In that sense, the miniaturization of electroencephalography (EEG) systems is a major challenge for developing daily-life healthcare devices. Recently, because of the intertwined relationship between EEG recording and processing, co-research of EEG recording hardware and data processing has been emphasized for whole-in-one miniaturized EEG systems. This paper introduces miniaturization techniques in analog-front-end hardware and processing algorithms for such EEG systems. To miniaturize EEG recording hardware, various types of compact electrodes and mm-sized integrated circuits (IC) techniques including artifact rejection are studied to record accurate EEG signals in a much smaller manner. Active electrode and in-ear EEG technologies are also researched to make small-form-factor EEG measurement structures. Furthermore, miniaturization techniques for EEG processing are discussed including channel selection techniques that reduce the number of required electrode channel and hardware implementation of processing algorithms that simplify the EEG processing stage.

SSVEP-based brain–computer interface for music using a low-density EEG system

ABSTRACT In this paper, we present a bespoke brain–computer interface (BCI), which was developed for a person with severe motor-impairments, who was previously a Violinist, to allow performing and composing music at home. It uses steady-state visually evoked potential (SSVEP) and adopts a dry, low-density, and wireless electroencephalogram (EEG) headset. In this study, we investigated two parameters: (1) placement of the EEG headset and (2) inter-stimulus distance and found that the former significantly improved the information transfer rate (ITR). To analyze EEG, we adopted canonical correlation analysis (CCA) without weight-calibration. The BCI for musical performance realized a high ITR of 37.59 ± 9.86 bits min−1 and a mean accuracy of 88.89 ± 10.09%. The BCI for musical composition obtained an ITR of 14.91 ± 2.87 bits min−1 and a mean accuracy of 95.83 ± 6.97%. The BCI was successfully deployed to the person with severe motor-impairments. She regularly uses it for musical composition at home, demonstrating how BCIs can be translated from laboratories to real-world scenarios.

Improved access to rapid electroencephalography at a community hospital reduces inter‐hospital transfers for suspected non‐convulsive seizures

AbstractObjective. Patients with suspected non‐convulsive seizures are optimally evaluated with EEG. However, limited EEG infrastructure at community hospitals often necessitates transfer for long‐term EEG monitoring (LTM). Novel point‐of‐care EEG systems could expedite management of nonconvulsive seizures and reduce unnecessary transfers. We aimed to describe the impact of rapid access to EEG using a novel EEG device with remote expert interpretation (tele‐EEG) on rates of transfer for LTM.Methods. We retrospectively identified a cohort of patients who underwent Rapid‐EEG (Ceribell Inc., Mountain View, CA) monitoring as part of a new standard‐of‐care at a community hospital. Rapid‐EEGs were initially reviewed on‐site by a community hospital neurologist before transitioning to tele‐EEG review by epileptologists at an affiliated academic hospital. We compared the rate of transfer for LTM after Rapid‐EEG/tele‐EEG implementation to the expected rate if rapid access to EEG was unavailable.Results. Seventy‐four patients underwent a total of 118 Rapid‐EEG studies (10 with seizure, 18 with highly epileptiform patterns, 90 with slow/normal activity). Eighty‐one studies (69%), including 9 of 10 studies that detected seizures, occurred after‐hours when EEG was previously unavailable. Based on historical practice patterns, we estimated that Rapid‐EEG potentially obviated transfer for LTM in 31 of 33 patients (94%); both completed transfers occurred before the transition to tele‐EEG review.Significance. Rapid access to EEG led to the detection of seizures that would otherwise have been missed and reduced inter‐hospital transfers for LTM. We estimate that the reduction in inter‐hospital transportation costs alone would be in excess of $39,000 ($1,274 per patient). Point‐of‐care EEG systems may support a hub‐and‐spoke model for managing non‐convulsive seizures (similar to that utilized in this study and analogous to existing acute stroke infrastructures), with increased EEG capacity at community hospitals and tele‐EEG interpretation by specialists at academic hospitals that can accept transfers for LTM.

English speaking proficiency assessment using speech and electroencephalography signals

<p>In this paper, the English speaking proficiency level of non-native English speakers<br />was automatically estimated as high, medium, or low performance. For this purpose, the speech of 142 non-native English speakers was recorded and electroencephalography (EEG) signals of 58 of them were recorded while speaking in English. Two systems were proposed for estimating the English proficiency level of the speaker; one used 72 audio features, extracted from speech signals, and the other used 112 features extracted from EEG signals. Multi-class support vector machines (SVM) was used for training and testing both systems using a cross-validation strategy. The speech-based system outperformed the EEG system with 68% accuracy on 60 testing audio recordings, compared with 56% accuracy on 30 testing EEG recordings.</p>

Alterations in Cortical Activation among Soccer Athletes with Chronic Ankle Instability during Drop-Jump Landing: A Preliminary Study.

Background: Chronic ankle instability (CAI) is a common peripheral joint injury and there is still no consensus on the mechanisms. It is necessary to investigate electrocortical parameters to provide clinical insight into the functional alterations of brain activity after an ankle sprain, which would greatly affect the implementation of rehabilitation plans. The purpose of this study was to assess cortical activation characteristics during drop-jump landing among soccer athletes with CAI. Methods: A total of 24 participants performed the drop-jump landing task on a force platform while wearing a 64-channel EEG system. The differences of power spectral density (PSD) in theta and alpha (alpha-1 and alpha-2) bands were analyzed between two groups (CAI vs. CON) and between two limbs (injured vs. healthy). Results: CAI participants demonstrated significantly higher theta power at the frontal electrode than that in healthy control individuals (F(1,22) = 7.726, p = 0.011, η2p = 0.260). No difference in parietal alpha-1 and alpha-2 power was found between groups (alpha-1: F(1,22) = 0.297, p = 0.591, η2p = 0.013; alpha-2: F(1,22) = 0.118, p = 0.734, η2p = 0.005). No limb differences were presented for any frequency band in selected cortical areas (alpha-1: F(1,22) = 0.149, p = 0.703, η2p = 0.007; alpha-2: F(1,22) = 0.166, p = 0.688, η2p = 0.007; theta: F(1,22) = 2.256, p = 0.147, η2p = 0.093). Conclusions: Theta power at the frontal cortex was higher in soccer athletes with CAI during drop-jump landing. Differences in cortical activation provided evidence for an altered neural mechanism of postural control among soccer athletes with CAI.

Feasibility assessment of patient-controlled EEG home-monitoring: More results from the HOMEONE study

ObjectiveThe feasibility phase of the HOME (Home-Monitoing and Education) project aims to show the practical feasibility of Electroencephalography (EEG)home-monitoring using a patient-controlled mobile system. Its objective is to assess the potential diagnostic and therapeutic yields of home-monitoring compared to conventional healthcare. Methods16 office-based practitioners chose 97 patients and recorded standard 20-minute EEGs using conventional recorders. After training, the same patients used a patient-controlled mobile dry electrode EEG system in their home environment. The practitioners in charge and two additional raters assessed all recordings. We conducted inter-rater and intra-rater comparisons between the diagnostic findings. Results89 patients successfully conducted home-monitoring recordings. The intra-rater comparison results for the diagnostic findings of the conventional recordings and the patient-made recordings show a fair Cohen’s kappa value (0.21). Additionally, we documented a change of patient management in 9 cases. ConclusionsThe feasibility of EEG home-monitoring using a patient-controlled device is confirmed. The yield of EEG home-monitoring comprises information that can influence patient management. SignificancePatient-controlled EEG home-monitoring is feasible as part of routine care for neurological outpatients as its technical efficacy and practical feasibility are shown and significantly positive effects on patient management are evidenced.

Electroencephalographic Measurement on Post-stroke Sensory Deficiency in Response to Non-painful Cold Stimulation.

BackgroundReduced elementary somatosensation is common after stroke. However, the measurement of elementary sensation is frequently overlooked in traditional clinical assessments, and has not been evaluated objectively at the cortical level. This study designed a new configuration for the measurement of post-stroke elementary thermal sensation by non-painful cold stimulation (NPCS). The post-stroke cortical responses were then investigated during elementary NPCS on sensory deficiency via electroencephalography (EEG) when compared with unimpaired persons.MethodTwelve individuals with chronic stroke and fifteen unimpaired controls were recruited. A 64-channel EEG system was used to investigate the post-stroke cortical responses objectively during the NPCS. A subjective questionnaire of cold sensory intensity was also administered via a numeric visual analog scale (VAS). Three water samples with different temperatures (i.e., 25, 10, and 0°C) were applied to the skin surface of the ventral forearm for 3 s via glass beaker, with a randomized sequence on either the left or right forearm of a participant. EEG relative spectral power (RSP) and topography were used to evaluate the neural responses toward NPCS with respect to the independent factors of stimulation side and temperature.ResultsFor unimpaired controls, NPCS initiated significant RSP variations, mainly located in the theta band with the highest discriminative resolution on the different temperatures (P < 0.001). For stroke participants, the distribution of significant RSP spread across all EEG frequency bands and the temperature discrimination was lower than that observed in unimpaired participants (P < 0.05). EEG topography showed that the NPCS could activate extensive and bilateral sensory cortical areas after stroke. Significant group differences on RSP intensities were obtained in each EEG band (P < 0.05). Meanwhile, significant asymmetry cortical responses in RSP toward different upper limbs were observed during the NPCS in both unimpaired controls and participants with stroke (P < 0.05). No difference was found between the groups in the VAS ratings of the different temperatures (P > 0.05).ConclusionThe post-stroke cortical responses during NPCS on sensory deficiency were characterized by the wide distribution of representative RSP bands, lowered resolution toward different temperatures, and extensive activated sensory cortical areas.

Medical Technology: A Systematic Review on Medical Devices Utilized for Epilepsy Prediction and Management.

Epilepsy is a devastating neurological disorder that affects nearly 70 million people worldwide. Epilepsy causes uncontrollable, unprovoked and unpredictable seizures that reduce the quality of life of those afflicted, with 1-9 epileptic patient deaths per 1000 patients occurring annually due to sudden unexpected death in epilepsy (SUDEP). Predicting the onset of seizures and managing them may help patients from harming themselves and may improve their well-being. For a long time, electroencephalography (EEG) devices have been the mainstay for seizure detection and monitoring. This systematic review aimed to elucidate and critically evaluate the latest advancements in medical devices, besides EEG, that have been proposed for the management and prediction of epileptic seizures. A literature search was performed on three databases, PubMed, Scopus and EMBASE. Following title/abstract screening by two independent reviewers, 27 articles were selected for critical analysis in this review. These articles revealed ambulatory, non-invasive and wearable medical devices, such as the in-ear EEG devices; the accelerometer-based devices and the subcutaneous implanted EEG devices might be more acceptable than traditional EEG systems. In addition, extracerebral signalbased devices may be more efficient than EEG-based systems, especially when combined with an intervention trigger. Although further studies may still be required to improve and validate these proposed systems before commercialization, these findings may give hope to epileptic patients, particularly those with refractory epilepsy, to predict and manage their seizures. The use of medical devices for epilepsy may improve patients' independence and quality of life and possibly prevent sudden unexpected death in epilepsy (SUDEP).

Task-Rate-Related Neural Dynamics Using Wireless EEG to Assist Diagnosis and Intervention Planning for Preschoolers with ADHD Exhibiting Heterogeneous Cognitive Proficiency.

This study used a wireless EEG system to investigate neural dynamics in preschoolers with ADHD who exhibited varying cognitive proficiency pertaining to working memory and processing speed abilities. Preschoolers with ADHD exhibiting high cognitive proficiency (ADHD-H, n = 24), those with ADHD exhibiting low cognitive proficiency (ADHD-L, n = 18), and preschoolers with typical development (TD, n = 31) underwent the Conners’ Kiddie Continuous Performance Test and wireless EEG recording under different conditions (rest, slow-rate, and fast-rate task). In the slow-rate task condition, compared with the TD group, the ADHD-H group manifested higher delta and lower beta power in the central region, while the ADHD-L group manifested higher parietal delta power. In the fast-rate task condition, in the parietal region, ADHD-L manifested higher delta power than those in the other two groups (ADHD-H and TD); additionally, ADHD-L manifested higher theta as well as lower alpha and beta power than those with ADHD-H. Unlike those in the TD group, the delta power of both ADHD groups was enhanced in shifting from rest to task conditions. These findings suggest that task-rate-related neural dynamics contain specific neural biomarkers to assist clinical planning for ADHD in preschoolers with heterogeneous cognitive proficiency. The novel wireless EEG system used was convenient and highly suitable for clinical application.

Continuous table tennis is associated with processing in frontal brain areas: an EEG approach

Coordinative challenging exercises in changing environments referred to as open-skill exercises seem to be beneficial on cognitive function. Although electroencephalographic research allows to investigate changes in cortical processing during movement, information about cortical dynamics during open-skill exercise is lacking. Therefore, the present study examines frontal brain activation during table tennis as an open-skill exercise compared to cycling exercise and a cognitive task. 21 healthy young adults conducted three blocks of table tennis, cycling and n-back task. Throughout the experiment, cortical activity was measured using 64-channel EEG system connected to a wireless amplifier. Cortical activity was analyzed calculating theta power (4–7.5 Hz) in frontocentral clusters revealed from independent component analysis. Repeated measures ANOVA was used to identify within subject differences between conditions (table tennis, cycling, n-back; p < .05). ANOVA revealed main-effects of condition on theta power in frontal (p < .01, ηp2 = 0.35) and frontocentral (p < .01, ηp2 = 0.39) brain areas. Post-hoc tests revealed increased theta power in table tennis compared to cycling in frontal brain areas (p < .05, d = 1.42). In frontocentral brain areas, theta power was significant higher in table tennis compared to cycling (p < .01, d = 1.03) and table tennis compared to the cognitive task (p < .01, d = 1.06). Increases in theta power during continuous table tennis may reflect the increased demands in perception and processing of environmental stimuli during open-skill exercise. This study provides important insights that support the beneficial effect of open-skill exercise on brain function and suggest that using open-skill exercise may serve as an intervention to induce activation of the frontal cortex.

Scalp Stimulation Targets for Neurological Conditions-Evidence from Large-Scale Meta-Analyses.

Neurological disorders are a major source of suffering for patients worldwide. Scalp stimulation methods have been widely applied in treating a number of neurological disorders. Recently, our understanding of pathological mechanisms associated with neurological disorders has been enhanced significantly. Nevertheless, these findings have yet to be well-integrated into scalp stimulation treatments for neurological disorders. In a previous study, we proposed new brain targets for scalp stimulation in the treatment of eight common mental disorders based on the results of a large-scale meta-analyses using Neurosynth. This study aims to extend our previous findings in identifying surface brain targets for seven common neurological disorders: Alzheimer's disease, aphasia, chronic pain, dementia, dyslexia, mild cognitive impairment, and Parkinson's disease, utilizing a similar method. We hidentified seven to eight potential scalp stimulation targets for each disorder and used both 10-20 EEG system and acupuncture points to locate these targets to facilitate its clinical application. The proposed target protocols may facilitate and extend clinical applications of scalp stimulation methods such as transcranial electrical stimulation and scalp acupuncture in the treatment of neurological disorders.

Resting-State Electroencephalography and P300 Evidence: Age-Related Vestibular Loss as a Risk Factor Contributes to Cognitive Decline.

Background:In recent years, there have been several meaningful advances in the understanding of the cognitive effects of vestibular loss. However, there has not yet been an investigation exploring the early biomarkers of preclinical cognitive decline in individuals with age-related vestibular loss.Objective:We aim to explore the “early biomarkers” of preclinical cognitive decline based on altered cortical activity (resting-state electroencephalography (EEG) and P300) with a multichannel EEG system in individuals with age-related vestibular loss.Method:This is a case-control study. A total of 21 patients with age-related vestibular loss (66.50±5.79 years, 13 [62% ] females), 19 patients with cognitive decline (68.42±5.82 years, 13 [68% ] females), and 21 age- and sex-matched healthy controls were recruited. All participants underwent a comprehensive battery of neuropsychological tests, audio-vestibular evaluations, resting-state EEG and P300 recordings.Results:Significant visuo-spatial, executive, and attention hypofunction were observed in the age-related vestibular group, reflected by decreased subscale scores. Reduced gamma functional connectivity between the right cuneus (Brodmann area 19, BA19) and the left superior parietal gyrus (BA7) was observed in both the age-related vestibular group and the cognitive impairment group. Smaller P300 amplitudes were observed in the age-related vestibular group (1.43±3.69μV) and cognitive impairment group (1.15±4.24μV) than in the healthy control group (3.97±2.38μV).Conclusion:Decreased P300 amplitude and functional connectivity between the right BA19 and the left BA7 were “early biomarkers” observed in individuals with age-related vestibular loss; these biomarkers may contribute to visuospatial, executive, and attention hypofunction.

Social touch in the age of computational ethology: Embracing as a multidimensional and complex behaviour

Social affective touch is an important aspect of close relationships in humans. It has been also observed in many non-human primate species. Despite the high relevance of behaviours like embraces for personal wellbeing and mental health, they remain vastly under-investigated in psychology. This may be because psychology often relies on a limited repertoire of behavioural measurements such as error rates and reaction time measurements. These are, however, insufficient to capture the multidimensional complexity of highly interactive dyadic behaviours like embraces. Based on recent advances in computational ethology in animal models, the rapidly emerging field of human computational ethology utilizes an accessible repertoire of machine learning methods to track and quantify complex natural behaviours. We highlight how such techniques can be utilized to investigate social touch and which preliminary conditions, motor aspects and higher-level interactions need to be considered. Ultimately, integration of computational ethology with mobile neuroscience techniques such as ultraportable EEG systems will allow for an ecologically valid investigation of social affective touch in humans that will advance psychological research of emotions.

Implementation of a Four-Class Motor Imagery Brain Computer Interface Using Long Short-Term Memory Neural Network

We have developed multi-channel dry-electrode electroencephalography (EEG) system to implement a brain computer interface (BCI) and discriminate four-class motor imagery signals. The EEG channels recorded from Fz, F3, F4, C3, Cz, C4, P3, and P4 positions, according to the international 10‒20 EEG system, were acquired and wirelessly transmitted to a personal computer. Five subjects were recruited to perform right hand, left hand, right foot, and left foot imagery movements with 60 trials in each movement type. EEG data were segmented into epochs from 0 to 8 s and anchored to time points of imagery movement cues. The segmented EEG epochs were pre-processed using the Morlet wavelet. A long short-term memory (LSTM) neural network with 64 LSTM cells was constructed to discriminate EEG signals recorded from different imagery movements. Among total EEG epochs, 80% were randomly chosen as training data and the rest 20% were used as validation data. The detection accuracy reached 89%.

Noninvasive mobile EEG as a tool for seizure monitoring and management: A systematic review.

In the last two decades new noninvasive mobile electroencephalography (EEG) solutions have been developed to overcome limitations of conventional clinical EEG and to improve monitoring of patients with long‐term conditions. Despite the availability of mobile innovations, their adoption is still very limited. The aim of this study is to review the current state‐of‐the‐art and highlight the main advantages of adopting noninvasive mobile EEG solutions in clinical trials and research studies of people with epilepsy or suspected seizures. Device characteristics are described, and their evaluation is presented. Two authors independently performed a literature review in accordance with Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) guidelines. A combination of different digital libraries was used (Embase, MEDLINE, Global Health, PsycINFO and https://clinicaltrials.gov/). Twenty‐three full‐text, six conference abstracts, and eight webpages were included, where a total of 14 noninvasive mobile solutions were identified. Published studies demonstrated at different levels how EEG recorded via mobile EEG can be used for visual detection of EEG abnormalities and for the application of automatic‐detection algorithms with acceptable specificity and sensitivity. When the quality of the signal was compared with scalp EEG, many similarities were found in the background activities and power spectrum. Several studies indicated that the experience of patients and health care providers using mobile EEG was positive in different settings. Ongoing trials are focused mostly on improving seizure‐detection accuracy and also on testing and assessing feasibility and acceptability of noninvasive devices in the hospital and at home. This review supports the potential clinical value of noninvasive mobile EEG systems and their advantages in terms of time, technical support, cost, usability, and reliability when applied to seizure detection and management. On the other hand, the limitations of the studies confirmed that future research is needed to provide more evidence regarding feasibility and acceptability in different settings, as well as the data quality and detection accuracy of new noninvasive mobile EEG solutions.

Consumer-Grade Brain Measuring Sensor in People With Long-Term Kratom Consumption

Neurophysiological characteristics of long-term Kratom users have been challenged for identification due to the lack of evidence. Long-term and high Kratom consumption caused concern, particularly in older adults. Thus, the study aims to explore EEG biomarkers in long-term Kratom users (LKU) based on consumer-grade EEG systems. The fifty-two participants were collected EEG using MUSE portable system during resting-state to examine EEG biomarkers with the proposed features: theta/alpha ratio and power variance function (PVF) in theta and alpha bands. The statistical analysis was further carried out to test the existent difference between controls and LKU in various age ranges (≤50 and >50 years of age) and different doses of Kratom consumption (low to high doses and very high dose). Subsequently, the statistical-based EEG biomarkers were extracted and performed classification among four classifiers (Random forest, Support vector machine, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -Nearest Neighbor, and Logistic regression. As a result, the TAR ratio was remarkably different between groups over 50 years of age. Furthermore, TAR and PVF in the alpha band were dominant in those who consumed Kratom at a very high dose and was classified well by support vector machine using the features combination (accuracy at 83.33% ± 10.24, sensitivity at 90.00% ± 10.00, specificity at 75.00% ± 13.44). Our preliminary results concluded that the proposed EEG features were an important EEG biomarker for LKU with a large effect size. This finding led us to the promising aspect of applying machine learning-based EEG biomarkers to screen the overdose of Kratom consumption in the future.

Two-dimensional CNN-based distinction of human emotions from EEG channels selected by multi-objective evolutionary algorithm

In this study we explore how different levels of emotional intensity (Arousal) and pleasantness (Valence) are reflected in electroencephalographic (EEG) signals. We performed the experiments on EEG data of 32 subjects from the DEAP public dataset, where the subjects were stimulated using 60-s videos to elicitate different levels of Arousal/Valence and then self-reported the rating from 1 to 9 using the self-assessment Manikin (SAM). The EEG data was pre-processed and used as input to a convolutional neural network (CNN). First, the 32 EEG channels were used to compute the maximum accuracy level obtainable for each subject as well as for creating a single model using data from all the subjects. The experiment was repeated using one channel at a time, to see if specific channels contain more information to discriminate between low vs high arousal/valence. The results indicate than using one channel the accuracy is lower compared to using all the 32 channels. An optimization process for EEG channel selection is then designed with the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with the objective to obtain optimal channel combinations with high accuracy recognition. The genetic algorithm evaluates all possible combinations using a chromosome representation for all the 32 channels, and the EEG data from each chromosome in the different populations are tested iteratively solving two unconstrained objectives; to maximize classification accuracy and to reduce the number of required EEG channels for the classification process. Best combinations obtained from a Pareto-front suggests that as few as 8–10 channels can fulfill this condition and provide the basis for a lighter design of EEG systems for emotion recognition. In the best case, the results show accuracies of up to 1.00 for low vs high arousal using eight EEG channels, and 1.00 for low vs high valence using only two EEG channels. These results are encouraging for research and healthcare applications that will require automatic emotion recognition with wearable EEG.