Search

Public speaking is a common type of social evaluative situation and a significant amount of the population feel uneasy with it. It is of utmost importance to detect public speaking stress so that appropriate action can be taken to minimize its impacts on human health. In this study, a multimodal human stress classification scheme in response to real-life public speaking activity is proposed. Electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG) signals of forty participants are acquired in rest-state and during public speaking activity to divide data into a stressed and non-stressed group. Frequency domain features from EEG and time-domain features from GSR and PPG signals are extracted. The selected set of features from all modalities are fused to classify the stress into two classes. Classification is performed via a leave-one-out cross-validation scheme by using five different classifiers. The highest accuracy of 96.25% is achieved using a support vector machine classifier with radial basis function. Statistical analysis is performed to examine the significance of EEG, GSR, and PPG signals between the two phases of the experiment. Statistical significance is found in certain EEG frequency bands as well as GSR and PPG data recorded before and after public speaking supporting the fact that brain activity, skin conductance, and blood volumetric flow are credible measures of human stress during public speaking activity., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

Stress research is a rapidly emerging area in the field of electroencephalography (EEG) signal processing. The use of EEG as an objective measure for cost effective and personalized stress management becomes important in situations like the nonavailability of mental health facilities. In this study, long-term stress was classified with machine learning algorithms using resting state EEG signal recordings. The labeling for the stress and control groups was performed using two currently accepted clinical practices: (i) the perceived stress scale score and (ii) expert evaluation. The frequency domain features were extracted from five-channel EEG recordings in addition to the frontal and temporal alpha and beta asymmetries. The alpha asymmetry was computed from four channels and used as a feature. Feature selection was also performed to identify statistically significant features for both stress and control groups (via t-test). We found that support vector machine was best suited to classify long-term human stress when used with alpha asymmetry as a feature. It was observed that the expert evaluation-based labeling method had improved the classification accuracy by up to 85.20%. Based on these results, it is concluded that alpha asymmetry may be used as a potential bio-marker for stress classification, when labels are assigned using expert evaluation.

Human stress is a serious health concern, which must be addressed with appropriate actions for a healthy society. This paper presents an experimental study to ascertain the appropriate phase, when electroencephalography (EEG) based data should be recorded for classification of perceived mental stress. The process involves data acquisition, pre-processing, feature extraction and selection, and classification. The stress level of each subject is recorded by using a standard perceived stress scale questionnaire, which is then used to label the EEG data. The data are divided into two (stressed and non-stressed) and three (non-stressed, mildly stressed, and stressed) classes. The EEG data of 28 participants are recorded using a commercially available four channel Muse EEG headband in two phases i.e., pre-activity and post-activity. Five feature groups, which include power spectral density, correlation, differential asymmetry, rational asymmetry, and power spectrum are extracted from five bands of each EEG channel. We propose a new feature selection algorithm, which selects features from appropriate EEG frequency band based on classification accuracy. Three classifiers i.e., support vector machine, the Naive Bayes, and multi-layer perceptron are used to classify stress level of the participants. It is evident from our results that EEG recording during the pre-activity phase is better for classifying the perceived stress. An accuracy of [Formula: see text] and [Formula: see text] is achieved for two- and three-class stress classification, respectively, while utilizing five groups of features from theta band. Our proposed feature selection algorithm is compared with existing algorithms and gives better classification results.

In this paper, we present an experimental study for the classification of perceived human stress using non-invasive physiological signals. These include electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG). We conducted experiments consisting of steps including data acquisition, feature extraction, and perceived human stress classification. The physiological data of 28 participants are acquired in an open eye condition for a duration of three minutes. Four different features are extracted in time domain from EEG, GSR and PPG signals and classification is performed using multiple classifiers including support vector machine, the Naive Bayes, and multi-layer perceptron (MLP). The best classification accuracy of 75% is achieved by using MLP classifier. Our experimental results have shown that our proposed scheme outperforms existing perceived stress classification methods, where no stress inducers are used.

Stress is inevitably experienced by almost every person at some stage of their life. A reliable and accurate measurement of stress can give an estimate of an individual's stress burden. It is necessary to take essential steps to relieve the burden and regain control for better health. Listening to music is a way that can help in breaking the hold of stress. This study examines the effect of music tracks in English and Urdu language on human stress level using brain signals. Twenty-seven subjects including 14 males and 13 females having Urdu as their first language, with ages ranging from 20 to 35 years, voluntarily participated in the study. The electroencephalograph (EEG) signals of the participants are recorded, while listening to different music tracks by using a four-channel MUSE headband. Participants are asked to subjectively report their stress level using the state and trait anxiety questionnaire. The English music tracks used in this study are categorized into four genres i.e., rock, metal, electronic, and rap. The Urdu music tracks consist of five genres i.e., famous, patriotic, melodious, qawali, and ghazal. Five groups of features including absolute power, relative power, coherence, phase lag, and amplitude asymmetry are extracted from the preprocessed EEG signals of four channels and five bands, which are used by the classifier for stress classification. Four classifier algorithms namely sequential minimal optimization, stochastic decent gradient, logistic regression (LR), and multilayer perceptron are used to classify the subject's stress level into two and three classes. It is observed that LR performs well in identifying stress with the highest reported accuracy of 98.76% and 95.06% for two- and three-level classification respectively. For understanding gender, language, and genre related discriminations in stress, a t-test and one-way analysis of variance is used. It is evident from results that English music tracks have more influence on stress level reduction as compared to Urdu music tracks. Among the genres of both languages, a noticeable difference is not found. Moreover, significant difference is found in the scores reported by females as compared to males. This indicates that the stress behavior of females is more sensitive to music as compared to males., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

A study on classification of psychological stress in humans using electroencephalography (EEG) is presented. The stress is classified using a correlation-based feature subset selection method that efficiently reduces the feature vector length. In this study, twenty-eight participants are involved by filling in the perceived stress scale-10 (PSS-10) questionnaire and their EEG is also recorded in closed eye condition to measure the baseline stress. The recorded data is labelled on the basis of the stress level that is indicated by the participant's PSS score. The feature selection method has shown that, among the EEG oscillations, low beta, high beta, and low gamma are the most significant neural oscillations for classifying human stress. The proposed method not only reduces the time to build a classification model but also improves the classification accuracy up to 78.57% using a single channel wearable EEG device.

Electroencephalography (EEG) signals are always accompanied by endogenous and exogenous artifacts. Research carried out in the past few years focused on EEG artifact removal considered EEG signals recorded in a restricted lab environment. Considering the importance of EEG in daily life activities, no definitive approach is presented in removing blink artifacts from non-restricted EEG recordings. In this paper, a new supervised artifact removal method is proposed that classifies EEG chunks having eye movements and then utilizes independent component analysis and discrete wavelet transform to eliminate the ocular artifacts. The EEG data is acquired from 29 subjects in a non-restricted environment where the subject has to watch videos while walking and giving gestures and facial expressions. Thirteen morphological features are extracted from the recorded EEG signals to classify chunks with eye movements. The EEG chunks with eye movements are further processed to remove noise without distorting the morphology of signals. The proposed method is tested for eye movements and shows an improved performance in terms of correlation, mutual information, phase difference, and computational time over unsupervised modified multi-scale sample entropy and kurtosis, and wavelet enhanced independent component analysis based approaches. Moreover, the computed values of statistical parameters including sensitivity and specificity show the robustness of the proposed scheme. [ABSTRACT FROM AUTHOR]

Personality traits are fundamental parameters to characterize an individual’s behavior. Recently physiological signals are used to recognize personality traits in response to emotional videos, but gives good accuracies only for few traits. In this study, personality traits are statistically analyzed and recognized using physiological signals (electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmogram (PPG)) in response to public speaking. The proposed framework consists of data acquisition, pre-processing, feature extraction, feature selection, and classification stages. The subject is labeled into two classes of each personality trait based on the mean value of big five personality trait questionnaire score. The physiological signals of twenty-eight participants are recorded while performing a public speaking task in front of a real audience. These signals are statistically analyzed to examine the behavior of different personality traits. Time domain features from GSR and PPG data and frequency domain features from EEG data are extracted. A wrapper based method for feature selection is applied to select an optimum set of features from each modality, which are then fused for personality trait recognition. An average F1-score of 0.86, 0.96, 0.64, 0.75, and 0.86 is achieved by the proposed framework for openness to experience, extroversion, neuroticism, conscientiousness, and agreeableness traits respectively. It is observed that the personality trait recognition using physiological signals in response to public speaking task outperforms the existing methods. [ABSTRACT FROM AUTHOR]

The problem addressed in this paper is the detection of drowsiness based on signals acquired using non-invasive and wearable sensors. A combination of signals from electroencephalography (EEG) electrodes, accelerometer, and gyroscope is acquired through a commercially available off-the-shelf headband to achieve this goal. The aim is to substitute the use of intrusive sensors and cameras by extracting both physiological and behavioral features for drowsiness detection using a lightweight wearable headband. A dataset is acquired from 50 volunteers using the MUSE headband for both fresh and drowsy behavior in the resting state, where subjects stare at a slow moving object on a screen and no external stimuli is used. The drowsy state is induced by sleep deprivation. The data are labeled subjectively using the Karolinska sleepiness scale. Complementary features extracted from spectral signals, head movement, and blink analysis are combined to form a feature vector for classifiers to improve the robustness and detection accuracy of the system. The implemented system is validated on the data collected in fresh and drowsy states using a leave-one-out cross-subject and 25% hold-out level testing. A detection accuracy of 92% is achieved using selected features and a linear support vector machine classifier. The results show that the accuracy of drowsiness detection is improved by using a hybrid feature vector acquired from data using multiple sensors. [ABSTRACT FROM AUTHOR]

The success and wider adaptability of smart phones has given a new dimension to the gaming industry. Due to the wide spectrum of video games, the success of a particular game depends on how efficiently it is able to capture the end users' attention. This leads to the need to analyse the cognitive aspects of the end user, that is the game player, during game play. A direct window to see how an end user responds to a stimuli is to look at their brain activity. In this study, electroencephalography (EEG) is used to record human brain activity during game play. A commercially available EEG headset is used for this purpose giving fourteen channels of recorded EEG brain activity. The aim is to classify a player as expert or novice using the brain activity as the player indulges in the game play. Three different machine learning classifiers have been used to train and test the system. Among the classifiers, naive Bayes has outperformed others with an accuracy of 88%, when data from all fourteen EEG channels are used. Furthermore, the activity observed on electrodes is statistically analysed and mapped for brain visualizations. The analysis has shown that out of the available fourteen channels, only four channels in the frontal and occipital brain regions show significant activity. Features of these four channels are then used, and the performance parameters of the four-channel classification are compared to the results of the fourteen-channel classification. It has been observed that support vector machine and the naive Bayes give good classification accuracy and processing time, well suited for real-time applications. [ABSTRACT FROM AUTHOR]

Human emotion recognition using brain signals is an active research topic in the field of affective computing. Music is considered as a powerful tool for arousing emotions in human beings. This study recognized happy, sad, love and anger emotions in response to audio music tracks from electronic, rap, metal, rock and hiphop genres. Participants were asked to listen to audio music tracks of 1 min for each genre in a noise free environment. The main objectives of this study were to determine the effect of different genres of music on human emotions and indicating age group that is more responsive to music. Thirty men and women of three different age groups (15–25 years, 26–35 years and 36–50 years) underwent through the experiment that also included self reported emotional state after listening to each type of music. Features from three different domains i.e., time, frequency and wavelet were extracted from recorded EEG signals, which were further used by the classifier to recognize human emotions. It has been evident from results that MLP gives best accuracy to recognize human emotion in response to audio music tracks using hybrid features of brain signals. It is also observed that rock and rap genres generated happy and sad emotions respectively in subjects under study. The brain signals of age group (26–35 years) gave best emotion recognition accuracy in accordance to the self reported emotions. [ABSTRACT FROM AUTHOR]

• Personalized video summarization framework based on human emotions is proposed. • A new dataset of EEG signals for video summarization purpose is created. • Six different emotions are detected using EEG signals while watching video. • High accuracy and low error rate is achieved by proposed summarization technique. Video summaries produced by low level features are unaware of the viewer's requirements and result in a semantic gap. Video content evokes certain emotions in a viewer, which can be measured and act as a strong source of information to generate summaries meeting viewer's expectation. In this paper, we propose a personalized video summarization framework that classifies viewer's emotion based on electroencephalography (EEG) signals, while watching a video to extract keyframes. Features are extracted from recorded EEG signals in time, frequency and wavelet domain to classify viewer's emotions. Those frames are selected as keyframes from the video, where different emotions of viewer are evoked. Experiments are performed on 50 viewers and 50 video sequences to validate the effectiveness and efficiency of the proposed framework. It is evident from the results that the proposed method generates summaries with high precision, recall, F-measure, accuracy, and low error, hence reducing the semantic gap. [ABSTRACT FROM AUTHOR]