Single-Trial Cognitive Stress Classification Using Portable Wireless Electroencephalography

Could the Suboccipital Release Technique Result in a Generalized Relaxation and Self-Perceived Improvement? A Repeated Measure Study Design

Background: Musculoskeletal disorders such as cervicogenic headaches present with suboccipital muscle hypertonicity and trigger points. One manual therapy intervention commonly used to target the suboccipital muscles is the suboccipital release technique, previously related to positive systemic effects. Therefore, this study aimed to determine the immediate and short-term effects of the Suboccipital Release Technique (SRT) on brainwave activity in a subgroup of healthy individuals. Methods: Data were collected from 37 subjects (20 females and 17 males, with a mean age of 24.5). While supine, the subjects underwent a head hold followed by suboccipital release. A total of four 15 s electroencephalogram (EEG) measurements were taken and a Global Rating of Change Scale was used to assess self-perception. Results: There was a statistically significant difference (p < 0.005) in various band waves under the following electrodes: AF3, F7, F3, FC5, T7, P7, O1, O2, P8, T8, and FC6. An 8-point range in the Global Rating of Change Scores with a mean score of 1.649 (SD = 1.719 and SE = 0.283) supported the hypothesis of a self-perceived benefit from the intervention. Conclusions: The results of this study indicate that the suboccipital release technique significantly affects brain wave activity throughout different brain regions. This change is likely not the result of any placebo effect and correlates highly with the subject's self-perception of a change following the intervention. These findings support the clinical use of the suboccipital release technique when a centralized effect is desired.

Do Audible Sounds during a Lumbar Spine Thrust Manipulation Have an Impact on Brainwave Activity?

BACKGROUND

To manage pain and stiffness of the lumbar spine, thrust manipulation is commonly used. High-velocity, small-amplitude thrust manipulation often elicits audible sounds. What causes this audible sound remains unclear, and its clinical significance has not been shown. This study aimed to identify how audible sound affects brainwave activity following a side-lying right rotatory thrust manipulation in a group of healthy individuals.

METHODS

This was a quasi-experimental repeated measures study design in which 44 subjects completed the study protocol. A portable Bluetooth EEG device was used to capture brainwave activity. The environment was controlled during testing to minimize any factors influencing the acquisition of real-time EEG data. After a short accommodation period, initial brainwaves were measured. Following this, each subject underwent a lumbar 4-5 side-lying right rotatory thrust manipulation, immediately followed by a second brainwave measurement. A third measurement took place one minute later, followed by a fourth one at the three-minute mark.

RESULTS

21 subjects did not experience audible sounds, while 23 subjects experienced audible sounds. Both groups had significant changes measured by the 14 electrodes (p < 0.05). The audible group had more significant changes, which lasted only two minutes.

CONCLUSION

The lack of brainwave response differences between the audible and non-audible groups implies no direct, measurable placebo or beneficial effect from the audible sound. This study could not identify a benefit from the audible sound during an HVLA manipulation of the subjects.

One-Channel Wearable Mental Stress State Monitoring System

Assessments of stress can be performed using physiological signals, such as electroencephalograms (EEGs) and galvanic skin response (GSR). Commercialized systems that are used to detect stress with EEGs require a controlled environment with many channels, which prohibits their daily use. Fortunately, there is a rise in the utilization of wearable devices for stress monitoring, offering more flexibility. In this paper, we developed a wearable monitoring system that integrates both EEGs and GSR. The novelty of our proposed device is that it only requires one channel to acquire both physiological signals. Through sensor fusion, we achieved an improved accuracy, lower cost, and improved ease of use. We tested the proposed system experimentally on twenty human subjects. We estimated the power spectrum of the EEG signals and utilized five machine learning classifiers to differentiate between two levels of mental stress. Furthermore, we investigated the optimum electrode location on the scalp when using only one channel. Our results demonstrate the system's capability to classify two levels of mental stress with a maximum accuracy of 70.3% when using EEGs alone and 84.6% when using fused EEG and GSR data. This paper shows that stress detection is reliable using only one channel on the prefrontal and ventrolateral prefrontal regions of the brain.

The effect of a spinal thrust manipulation's audible pop on brain wave activity: a quasi-experimental repeated measure design

Introduction

High velocity thrust manipulation is commonly used when managing joint dysfunctions. Often, these thrust maneuvers will elicit an audible pop. It has been unclear what conclusively causes this audible sound and its clinical meaningfulness. This study sought to identify the effect of the audible pop on brainwave activity directly following a prone T7 thrust manipulation in asymptomatic/healthy subjects.

Methods

This was a quasi-experimental repeated measure study design in which 57 subjects completed the study protocol. Brain wave activity was measured with the Emotiv EPOC+, which collects data with a frequency of 128 HZ and has 14 electrodes. Testing was performed in a controlled environment with minimal electrical interference (as measured with a Gauss meter), temperature variance, lighting variance, sound pollution, and other variable changes that could have influenced or interfered with pure EEG data acquisition. After accommodation each subject underwent a prone T7 posterior-anterior thrust manipulation. Immediately after the thrust manipulation the brainwave activity was measured for 10 seconds.

Results

The non-audible group (N = 20) consisted of 55% males, and the audible group (N = 37) consisted of 43% males. The non-audible group EEG data revealed a significant change in brain wave activity under some of the electrodes in the frontal, parietal, and the occipital lobes. In the audible group, there was a significant change in brain wave activity under all electrodes in the frontal lobes, the parietal lobe, and the occipital lobes but not the temporal lobes.

Conclusion

The audible sounds caused by a thoracic high velocity thrust manipulation did not affect the activity in the audible centers in the temporal brain region. The results support the hypothesis that thrust manipulation with or without audible sound results in a generalized relaxation immediately following the manipulation. The absence of a significant difference in brainwave activity in the frontal lobe in this study might indicate that the audible pop does not produce a "placebo" mechanism.

Wireless EEG: A survey of systems and studies

The popular brain monitoring method of electroencephalography (EEG) has seen a surge in commercial attention in recent years, focusing mostly on hardware miniaturization. This has led to a varied landscape of portable EEG devices with wireless capability, allowing them to be used by relatively unconstrained users in real-life conditions outside of the laboratory. The wide availability and relative affordability of these devices provide a low entry threshold for newcomers to the field of EEG research. The large device variety and the at times opaque communication from their manufacturers, however, can make it difficult to obtain an overview of this hardware landscape. Similarly, given the breadth of existing (wireless) EEG knowledge and research, it can be challenging to get started with novel ideas. Therefore, this paper first provides a list of 48 wireless EEG devices along with a number of important-sometimes difficult-to-obtain-features and characteristics to enable their side-by-side comparison, along with a brief introduction to each of these aspects and how they may influence one's decision. Secondly, we have surveyed previous literature and focused on 110 high-impact journal publications making use of wireless EEG, which we categorized by application and analyzed for device used, number of channels, sample size, and participant mobility. Together, these provide a basis for informed decision making with respect to hardware and experimental precedents when considering new, wireless EEG devices and research. At the same time, this paper provides background material and commentary about pitfalls and caveats regarding this increasingly accessible line of research.

Human state anxiety classification framework using EEG signals in response to exposure therapy

Human anxiety is a grave mental health concern that needs to be addressed in the appropriate manner in order to develop a healthy society. In this study, an objective human anxiety assessment framework is developed by using physiological signals of electroencephalography (EEG) and recorded in response to exposure therapy. The EEG signals of twenty-three subjects from an existing database called "A Database for Anxious States which is based on a Psychological Stimulation (DASPS)" are used for anxiety quantification into two and four levels. The EEG signals are pre-processed using appropriate noise filtering techniques to remove unwanted ocular and muscular artifacts. Channel selection is performed to select the significantly different electrodes using statistical analysis techniques for binary and four-level classification of human anxiety, respectively. Features are extracted from the data of selected EEG channels in the frequency domain. Frequency band selection is applied to select the appropriate combination of EEG frequency bands, which in this study are theta and beta bands. Feature selection is applied to the features of the selected EEG frequency bands. Finally, the selected subset of features from the appropriate frequency bands of the statistically significant EEG channels were classified using multiple machine learning algorithms. An accuracy of 94.90% and 92.74% is attained for two and four-level anxiety classification using a random forest classifier with 9 and 10 features, respectively. The proposed state anxiety classification framework outperforms the existing anxiety detection framework in terms of accuracy with a smaller number of features which reduces the computational complexity of the algorithm.

Development of an EEG Headband for Stress Measurement on Driving Simulators

In this paper, we designed from scratch, realized, and characterized a six-channel EEG wearable headband for the measurement of stress-related brain activity during driving. The headband transmits data over WiFi to a laptop, and the rechargeable battery life is 10 h of continuous transmission. The characterization manifested a measurement error of 6 μV in reading EEG channels, and the bandwidth was in the range [0.8, 44] Hz, while the resolution was 50 nV exploiting the oversampling technique. Thanks to the full metrological characterization presented in this paper, we provide important information regarding the accuracy of the sensor because, in the literature, commercial EEG sensors are used even if their accuracy is not provided in the manuals. We set up an experiment using the driving simulator available in our laboratory at the University of Udine; the experiment involved ten volunteers who had to drive in three scenarios: manual, autonomous vehicle with a “gentle” approach, and autonomous vehicle with an “aggressive” approach. The aim of the experiment was to assess how autonomous driving algorithms impact EEG brain activity. To our knowledge, this is the first study to compare different autonomous driving algorithms in terms of drivers’ acceptability by means of EEG signals. The obtained results demonstrated that the estimated power of beta waves (related to stress) is higher in the manual with respect to autonomous driving algorithms, either “gentle” or “aggressive”.

Hybrid classification model for eye state detection using electroencephalogram signals

The electroencephalography (EEG) signal is an essential source of Brain-Computer Interface (BCI) technology implementation. The BCI is nothing but a non-muscle communication medium among the external devices and the brain. The basic concept of BCI is to enable the interaction among the neurological ill patients to others with the help of brain signals. EEG signal classification is an essential requirement for various applications such as motor imagery classification, drug effects diagnosis, emotion classification, seizure prediction/detection, eye state prediction/detection, and so on. Thus, there is a need for an efficient classification model that can deal with the EEG datasets more adequately with better classification accuracy, which will further help in developing the automatic solution for the medical domain. In this paper, we have introduced a hybrid classification model for eye state detection using electroencephalogram (EEG) signals. This hybrid classification model has been evaluated with the other traditional machine learning models, eight classification models (Prepossessed + Hypertuned) and six state-of-the-art methods to assess its appropriateness and correctness. This proposed classification model establishes a machine learning-based hybrid model for the classification of eye state using EEG signals with greater exactness. It is also capable of solving the issue of outlier detection and removal to address the class imbalance problem, which will offer the solution toward building the robotic or smart machine-based solution for social well-being.

Comparative Analysis of Emotion Classification Based on Facial Expression and Physiological Signals Using Deep Learning

This study aimed to classify emotion based on facial expression and physiological signals using deep learning and to compare the analyzed results. We asked 53 subjects to make facial expressions, expressing four types of emotion. Next, the emotion-inducing video was watched for 1 min, and the physiological signals were obtained. We defined four emotions as positive and negative emotions and designed three types of deep-learning models that can classify emotions. Each model used facial expressions and physiological signals as inputs, and a model in which these two types of input were applied simultaneously was also constructed. The accuracy of the model was 81.54% when physiological signals were used, 99.9% when facial expressions were used, and 86.2% when both were used. Constructing a deep-learning model with only facial expressions showed good performance. The results of this study confirm that the best approach for classifying emotion is using only facial expressions rather than data from multiple inputs. However, this is an opinion presented only in terms of accuracy without considering the computational cost, and it is suggested that physiological signals and multiple inputs be used according to the situation and research purpose.

Classification of brain electrophysiological changes in response to colour stimuli

In this study, the classification of ongoing brain activity occurring as a response to colour stimuli was managed and reported. Until now, the classification of the seen colour from brain electrical signals has not been investigated or reported in the related literature. In this study, we aimed to classify EEG brain responses corresponding to blue, green, and red coloured shapes. In addition to the current literature, we focused on ongoing EEG responses instead of using ERP metrics, with visual stimulus-related ERP metrics also compared throughout the study. The feature extraction process was carried out using the Fourier transform to obtain the conventional band power values of the EEG for each stimulus type. Delta, theta, alpha, beta, and gamma-band power values of each one-second period constituted the feature set. In addition to scalp measurements, a second feature set was obtained based on the inverse solution of the EEG waves. Furthermore, we applied one-way ANOVA for the feature selection prior to classification procedures. Four classifiers were implemented using the reduced feature set and the raw one as well. The differences between scalp responses were localized mainly around the temporal and temporoparietal regions. Our ERP-component findings support the fact that additional brain regions among the visual cortex participate in the colour categorization process of the brain. RGB colours were identified using 1 s EEG data. Ensemble-KNN and KNN achieved the highest accuracy values (93%) when used either with scalp spectral features or source space features.

Emotion-Driven Analysis and Control of Human-Robot Interactions in Collaborative Applications

The utilization of robotic systems has been increasing in the last decade. This increase has been derived by the evolvement in the computational capabilities, communication systems, and the information systems of the manufacturing systems which is reflected in the concept of Industry 4.0. Furthermore, the robotics systems are continuously required to address new challenges in the industrial and manufacturing domain, like keeping humans in the loop, among other challenges. Briefly, the keeping humans in the loop concept focuses on closing the gap between humans and machines by introducing a safe and trustworthy environment for the human workers to work side by side with robots and machines. It aims at increasing the engagement of the human as the automation level increases rather than replacing the human, which can be nearly impossible in some applications. Consequently, the collaborative robots (Cobots) have been created to allow physical interaction with the human worker. However, these cobots still lack of recognizing the human emotional state. In this regard, this paper presents an approach for adapting cobot parameters to the emotional state of the human worker. The approach utilizes the Electroencephalography (EEG) technology for digitizing and understanding the human emotional state. Afterwards, the parameters of the cobot are instantly adjusted to keep the human emotional state in a desirable range which increases the confidence and the trust between the human and the cobot. In addition, the paper includes a review on technologies and methods for emotional sensing and recognition. Finally, this approach is tested on an ABB YuMi cobot with commercially available EEG headset.

EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities

Emotions are fundamental for human beings and play an important role in human cognition. Emotion is commonly associated with logical decision making, perception, human interaction, and to a certain extent, human intelligence itself. With the growing interest of the research community towards establishing some meaningful "emotional" interactions between humans and computers, the need for reliable and deployable solutions for the identification of human emotional states is required. Recent developments in using electroencephalography (EEG) for emotion recognition have garnered strong interest from the research community as the latest developments in consumer-grade wearable EEG solutions can provide a cheap, portable, and simple solution for identifying emotions. Since the last comprehensive review was conducted back from the years 2009 to 2016, this paper will update on the current progress of emotion recognition using EEG signals from 2016 to 2019. The focus on this state-of-the-art review focuses on the elements of emotion stimuli type and presentation approach, study size, EEG hardware, machine learning classifiers, and classification approach. From this state-of-the-art review, we suggest several future research opportunities including proposing a different approach in presenting the stimuli in the form of virtual reality (VR). To this end, an additional section devoted specifically to reviewing only VR studies within this research domain is presented as the motivation for this proposed new approach using VR as the stimuli presentation device. This review paper is intended to be useful for the research community working on emotion recognition using EEG signals as well as for those who are venturing into this field of research.

Modified Support Vector Machine for Detecting Stress Level Using EEG Signals

Stress is categorized as a condition of mental strain or pressure approaches because of upsetting or requesting conditions. There are various sources of stress initiation. Researchers consider human cerebrum as the primary wellspring of stress. To study how each individual encounters stress in different forms, researchers conduct surveys and monitor it. The paper presents the fusion of 5 algorithms to enhance the accuracy for detection of mental stress using EEG signals. The Whale Optimization Algorithm has been modified to select the optimal kernel in the SVM classifier for stress detection. An integrated set of algorithms (NLM, DCT, and MBPSO) has been used for preprocessing, feature extraction, and selection. The proposed algorithm has been tested on EEG signals collected from 14 subjects to identify the stress level. The proposed approach was validated using accuracy, sensitivity, specificity, and F1 score with values of 96.36%, 96.84%, 90.8%, and 97.96% and was found to be better than the existing ones. The algorithm may be useful to psychiatrists and health consultants for diagnosing the stress level.

Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network

Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

Alpha and beta cortical activity during guitar playing: task complexity and audiovisual stimulus analysis

PURPOSE

Some studies have explored the relationship between music and cortical activities; however, there are just few studies investigating guitar performance associated with different sensory stimuli. Our aim was to evaluate alpha and beta activity during guitar playing.

MATERIALS AND METHOD

Twenty healthy right-handed people participated in this study. Cortical activity was measured by electroencephalogram (EEG) during rest and 4 tasks (1: easy music with an auditory stimulus; 2: easy music with an audiovisual stimulus; 3: complex music with an auditory stimulus; 4: complex music with an audiovisual stimulus). The peak frequency (PF), median frequency (MF) and root mean square (RMS) of alpha and beta EEG signals were assessed.

RESULTS

A higher alpha PF at the T3-P3 was observed, and this difference was higher between rest and task 3, rest and task 4, tasks 1 and 3, and tasks 1 and 4. For beta waves, a higher PF was observed at C4-P4 and a higher RMS at C3-C4 and O1-O2. At C4-P4, differences between rest and tasks 2 and 4 were observed. The RMS of beta waves at C3-C4 presented differences between rest and task 3 and at O1-O2 between rest and task 2 and 4.

CONCLUSION

The action observation of audiovisual stimuli while playing guitar can increase beta wave activity in the somatosensory and motor cortexes; and increase in the alpha activity in the somatosensory and auditory cortexes and increase in the beta activity in the bilateral visual cortexes during complex music execution, regardless of the stimulus type received. Abbreviations: bpm: beats per minute; C: central; EEG: electroencephalogram; F: frontal; Hz: hertz; LABCOM: Laboratory of Motor Control and Biomechanics; MD: mean difference; MF: median frequency; O: occipital; P: parietal; PF: peak frequency; R: rest; RMS: root mean square; T: temporal; T1: task 1; T2: task 2; T3: task 3; T4: task 4; UFTM: Federal University of Triângulo Mineiro.

Dynamic Changes in EEG Power Spectral Densities During NIH-Toolbox Flanker, Dimensional Change Card Sort Test and Episodic Memory Tests in Young Adults

Much is known about electroencephalograph (EEG) patterns during sleep, but until recently, it was difficult to study EEG patterns during conscious, awake behavior. Technological advances such as powerful wireless EEG systems have led to a renewed interest in EEG as a clinical and research tool for studying real-time changes in the brain. We report here the first normative study of EEG activity while healthy young adults completed a series of cognitive tests recently published by the National Institutes of Health Toolbox Cognitive Battery (NIH-TCB), a commonly-used standardized measure of cognition primarily used in clinical populations. In this preliminary study using a wireless EEG system, we examined power spectral density (PSD) in four EEG frequency bands. During baseline and cognitive testing, PSD activity for the lower frequency bands (theta and alpha) was greater, relative to the higher frequency bands (beta and gamma), suggesting participants were relaxed and mentally alert. Alpha, beta and gamma activity was increased during a memory test compared to two other, less demanding executive function tests. Gamma activity was also inversely correlated with performance on the memory test, consistent with the neural efficiency hypothesis which proposes that better cognitive performance may link with lower cortical energy consumption. In summary, our study suggests that cognitive performance is related to the dynamics of EEG activity in a normative young adult population.

Predicting Depression, Anxiety, and Stress Levels from Videos Using the Facial Action Coding System

We present the first study in the literature that has aimed to determine Depression Anxiety Stress Scale (DASS) levels by analyzing facial expressions using Facial Action Coding System (FACS) by means of a unique noninvasive architecture on three layers designed to offer high accuracy and fast convergence: in the first layer, Active Appearance Models (AAM) and a set of multiclass Support Vector Machines (SVM) are used for Action Unit (AU) classification; in the second layer, a matrix is built containing the AUs' intensity levels; and in the third layer, an optimal feedforward neural network (FFNN) analyzes the matrix from the second layer in a pattern recognition task, predicting the DASS levels. We obtained 87.2% accuracy for depression, 77.9% for anxiety, and 90.2% for stress. The average prediction time was 64 s, and the architecture could be used in real time, allowing health practitioners to evaluate the evolution of DASS levels over time. The architecture could discriminate with 93% accuracy between healthy subjects and those affected by Major Depressive Disorder (MDD) or Post-traumatic Stress Disorder (PTSD), and 85% for Generalized Anxiety Disorder (GAD). For the first time in the literature, we determined a set of correlations between DASS, induced emotions, and FACS, which led to an increase in accuracy of 5%. When tested on AVEC 2014 and ANUStressDB, the method offered 5% higher accuracy, sensitivity, and specificity compared to other state-of-the-art methods.

Characterization of Industry 4.0 Lean Management Problem-Solving Behavioral Patterns Using EEG Sensors and Deep Learning

Industry 4.0 leaders solve problems all of the time. Successful problem-solving behavioral pattern choice determines organizational and personal success, therefore a proper understanding of the problem-solving-related neurological dynamics is sure to help increase business performance. The purpose of this paper is two-fold: first, to discover relevant neurological characteristics of problem-solving behavioral patterns, and second, to conduct a characterization of two problem-solving behavioral patterns with the aid of deep-learning architectures. This is done by combining electroencephalographic non-invasive sensors that capture process owners' brain activity signals and a deep-learning soft sensor that performs an accurate characterization of such signals with an accuracy rate of over 99% in the presented case-study dataset. As a result, the deep-learning characterization of lean management (LM) problem-solving behavioral patterns is expected to help Industry 4.0 leaders in their choice of adequate manufacturing systems and their related problem-solving methods in their future pursuit of strategic organizational goals.