Stress detection using deep neural networks

A deep learning-based approach for distinguishing different stress levels of human brain using EEG and pulse rate

In today's world, people suffer from many fatal maladies, and stress is one of them. Excessive stress can have deleterious effects on the health, brain, mind, and nervous system of humans. The goal of this paper is to design a deep learningbased human stress level measurement technique using electroencephalogram (EEG), and pulse rate. In this research, EEG signals and pulse rate of healthy subjects are recorded while they solve four different question sets of increasing complexity. It is assumed that the subjects undergo through four different stress levels, i.e., 'no stress', 'low stress', 'medium stress', and 'high stress', while solving these question sets. An attention mechanism-based CNN-TLSTM (convolutional neural network-tanh long short-term memory) model is proposed to detect the mental stress level of a person. An attention layer is incorporated into the designed TLSTM network to increase the classification accuracy of the CNN-TLSTM model. The CNN network is used for the automated extraction of intricate features from the EEG signals and pulse rate. Then TLSTM is used to classify the stress level of a person into four different categories using the CNNextracted features. The obtained average accuracy of the proposed CNN-TLSTM model is 97.86%. Experimentally, it is found that the designed stress level measurement technique is highly effective and outperforms most existing state-of-the-art techniques. In the future, functional Near-Infrared Spectroscopy (fNIRS), ECG, and Galvanic Skin Response (GSR) can be employed with EEG and pulse rate to increase the effectiveness of the designed stress level measurement technique.

ECG and EEG based detection and multilevel classification of stress using machine learning for specified genders: A preliminary study

Mental health, especially stress, plays a crucial role in the quality of life. During different phases (luteal and follicular phases) of the menstrual cycle, women may exhibit different responses to stress from men. This, therefore, may have an impact on the stress detection and classification accuracy of machine learning models if genders are not taken into account. However, this has never been investigated before. In addition, only a handful of stress detection devices are scientifically validated. To this end, this work proposes stress detection and multilevel stress classification models for unspecified and specified genders through ECG and EEG signals. Models for stress detection are achieved through developing and evaluating multiple individual classifiers. On the other hand, the stacking technique is employed to obtain models for multilevel stress classification. ECG and EEG features extracted from 40 subjects (21 females and 19 males) were used to train and validate the models. In the low&high combined stress conditions, RBF-SVM and kNN yielded the highest average classification accuracy for females (79.81%) and males (73.77%), respectively. Combining ECG and EEG, the average classification accuracy increased to at least 87.58% (male, high stress) and up to 92.70% (female, high stress). For multilevel stress classification from ECG and EEG, the accuracy for females was 62.60% and for males was 71.57%. This study shows that the difference in genders influences the classification performance for both the detection and multilevel classification of stress. The developed models can be used for both personal (through ECG) and clinical (through ECG and EEG) stress monitoring, with and without taking genders into account.

Efficient Feature-Selection-Based Stacking Model for Stress Detection Based on Chest Electrodermal Activity

Contemporary advancements in wearable equipment have generated interest in continuously observing stress utilizing various physiological indicators. Early stress detection can improve healthcare by lessening the negative effects of chronic stress. Machine learning (ML) methodologies have been modified for healthcare equipment to monitor user health situations utilizing sufficient user information. Nevertheless, more data are needed to make applying Artificial Intelligence (AI) methodologies in the medical field easier. This research aimed to detect stress using a stacking model based on machine learning algorithms using chest-based features from the Wearable Stress and Affect Detection (WESAD) dataset. We converted this natural dataset into a convenient format for the suggested model by performing data visualization and preprocessing using the RESP feature and feature analysis using the Z-score, SelectKBest feature, the Synthetic Minority Over-Sampling Technique (SMOTE), and normalization. The efficiency of the proposed model was estimated regarding accuracy, precision, recall, and F1-score. The experimental outcome illustrated the efficacy of the proposed stacking technique, achieving 0.99% accuracy. The results revealed that the proposed stacking methodology performed better than traditional methodologies and previous studies.

Deep Learning Models for Stress Analysis in University Students: A Sudoku-Based Study

Due to the phenomenon of "involution" in China, the current generation of college and university students are experiencing escalating levels of stress, both academically and within their families. Extensive research has shown a strong correlation between heightened stress levels and overall well-being decline. Therefore, monitoring students' stress levels is crucial for improving their well-being in educational institutions and at home. Previous studies have primarily focused on recognizing emotions and detecting stress using physiological signals like ECG and EEG. However, these studies often relied on video clips to induce various emotional states, which may not be suitable for university students who already face additional stress to excel academically. In this study, a series of experiments were conducted to evaluate students' stress levels by engaging them in playing Sudoku games under different distracting conditions. The collected physiological signals, including PPG, ECG, and EEG, were analyzed using enhanced models such as LRCN and self-supervised CNN to assess stress levels. The outcomes were compared with participants' self-reported stress levels after the experiments. The findings demonstrate that the enhanced models presented in this study exhibit a high level of proficiency in assessing stress levels. Notably, when subjects were presented with Sudoku-solving tasks accompanied by noisy or discordant audio, the models achieved an impressive accuracy rate of 95.13% and an F1-score of 93.72%. Additionally, when subjects engaged in Sudoku-solving activities with another individual monitoring the process, the models achieved a commendable accuracy rate of 97.76% and an F1-score of 96.67%. Finally, under comforting conditions, the models achieved an exceptional accuracy rate of 98.78% with an F1-score of 95.39%.

Attention Aware Deep Learning Approaches for an Efficient Stress Classification Model

In today's world, stress is a major factor for various diseases in modern societies which affects the day-to-day activities of human beings. The measurement of stress is a contributing factor for governments and societies that impacts the quality of daily lives. The strategy of stress monitoring systems requires an accurate stress classification technique which is identified via the reactions of the body to regulate itself to changes within the environment through mental and emotional responses. Therefore, this research proposed a novel deep learning approach for the stress classification system. In this paper, we presented an Enhanced Long Short-Term Memory(E-LSTM) based on the feature attention mechanism that focuses on determining and categorizing the stress polarity using sequential modeling and word-feature seizing. The proposed approach integrates pre-feature attention in E-LSTM to identify the complicated relationship and extract the keywords through an attention layer for stress classification. This research has been evaluated using a selected dataset accessed from the sixth Korea National Health and Nutrition Examination Survey conducted from 2013 to 2015 (KNHANES VI) to analyze health-related stress data. Statistical performance of the developed approach was analyzed based on the nine features of stress detection, and we compared the effectiveness of the developed approach with other different stress classification approaches. The experimental results shown that the developed approach obtained accuracy, precision, recall and a F1-score of 75.54%, 74.26%, 72.99% and 74.58%, respectively. The feature attention mechanism-based E-LSTM approach demonstrated superior performance in stress detection classification when compared to other classification methods including naïve Bayesian, SVM, deep belief network, and standard LSTM. The results of this study demonstrated the efficiency of the proposed approach in accurately classifying stress detection, particularly in stress monitoring systems where it is expected to be effective for stress prediction.

Global Stress Detection Framework Combining a Reduced Set of HRV Features and Random Forest Model

Approximately 65% of the worldwide adult population has experienced stress, affecting their daily routine at least once in the past year. Stress becomes harmful when it occurs for too long or is continuous (i.e., chronic), interfering with our performance, attention, and concentration. Chronic high stress contributes to major health issues such as heart disease, high blood pressure, diabetes, depression, and anxiety. Several researchers have focused on detecting stress through combining many features with machine/deep learning models. Despite these efforts, our community has not agreed on the number of features to identify stress conditions using wearable devices. In addition, most of the reported studies have been focused on person-specific training and testing. Thanks to our community's broad acceptance of wearable wristband devices, this work investigates a global stress detection model combining eight HRV features with a random forest (RF) algorithm. Whereas the model's performance is evaluated for each individual, the training of the RF model contains instances of all subjects (i.e., global training). We have validated the proposed global stress model using two open-access databases (the WESAD and SWELL databases) and their combination. The eight HRV features with the highest classifying power are selected using the minimum redundancy maximum relevance (mRMR) method, reducing the training time of the global stress platform. The proposed global stress monitoring model identifies person-specific stress events with an accuracy higher than 99% after a global training framework. Future work should be focused on testing this global stress monitoring framework in real-world applications.

Wrist-Based Electrodermal Activity Monitoring for Stress Detection Using Federated Learning

With the most recent developments in wearable technology, the possibility of continually monitoring stress using various physiological factors has attracted much attention. By reducing the detrimental effects of chronic stress, early diagnosis of stress can enhance healthcare. Machine Learning (ML) models are trained for healthcare systems to track health status using adequate user data. Insufficient data is accessible, however, due to privacy concerns, making it challenging to use Artificial Intelligence (AI) models in the medical industry. This research aims to preserve the privacy of patient data while classifying wearable-based electrodermal activities. We propose a Federated Learning (FL) based approach using a Deep Neural Network (DNN) model. For experimentation, we use the Wearable Stress and Affect Detection (WESAD) dataset, which includes five data states: transient, baseline, stress, amusement, and meditation. We transform this raw dataset into a suitable form for the proposed methodology using the Synthetic Minority Oversampling Technique (SMOTE) and min-max normalization pre-processing methods. In the FL-based technique, the DNN algorithm is trained on the dataset individually after receiving model updates from two clients. To decrease the over-fitting effect, every client analyses the results three times. Accuracies, Precision, Recall, F1-scores, and Area Under the Receiver Operating Curve (AUROC) values are evaluated for each client. The experimental result shows the effectiveness of the federated learning-based technique on a DNN, reaching 86.82% accuracy while also providing privacy to the patient's data. Using the FL-based DNN model over a WESAD dataset improves the detection accuracy compared to the previous studies while also providing the privacy of patient data.

Digital transformation in organizational health and safety to mitigate Burnout Syndrome

In 2000, the World Health Organization (WHO) identified Burnout Syndrome as an occupational risk factor, affecting an estimated 10% of workers, resulting in lost productivity and increased costs due to sick leave. Some claim that Burnout Syndrome has reached epidemic proportions in workplaces around the world. While signs of burnout are not difficult to identify and palliate, its real impact is not easy to measure, generating a number of risks for companies from possible loss of human talent to decreased productivity and diminished quality of life. Given the complexity of Burnout Syndrome, it must be addressed in a creative, innovative and systematic way; traditional approaches cannot be expected to deliver different results. This paper describes the experience where an innovation challenge was launched to collect creative ideas to identify, prevent or mitigate Burnout Syndrome through the use of technological tools and software. The challenge was endowed with an economic award and its guidelines stated that the proposals must be both creative and feasible from an economic and organizational point of view. A total of twelve creative projects were submitted, including each of them, the analysis, design and management plans, to envision an idea that is feasible and with the appropriate budget, implemented. In this paper, we present a summary of these creative projects and how the IRSST (Instituto Regional de Seguridad y Salud en el Trabajo) experts and leaders in OHS in the Madrid Region (Spain) envision their potential impact on improving the OHS landscape.

An Efficient AP-ANN-Based Multimethod Fusion Model to Detect Stress through EEG Signal Analysis

Stress is a universal emotion that every human experiences daily. Psychologists say stress may lead to heart attack, depression, hypertension, strokes, or even sudden death. Many technical explorations like stress detection through facial expression, speech, text, physical behaviors, etc., were explored, but no consensus has been reached on the best method. The advancement in biomedical engineering yielded a rapid development of electroencephalogram (EEG) signal analysis that has inspired the idea of a multimethod fusion approach for the first time which employs multiple techniques such as discrete wavelet transform (DWT) for de-noising, adaptive synthetic sampling (ADASYN) for class balancing, and affinity propagation (AP) as a stratified sampling model along with the artificial neural network (ANN) as the classifier model for human emotion classification. From the EEG recordings of the DEAP dataset, the artifacts are removed, the signal is decomposed using a DWT, and features are extracted and fused to form the feature vector. As the dataset is high-dimensional, feature selection is done and ADASYN is used to address the imbalance of classes resulting in large-scale data. The innovative idea of the proposed system is to perform sampling using affinity propagation as a stratified sampling-based clustering algorithm as it determines the number of representative samples automatically which makes it superior to the K-Means, K-Medoid, that requires the K-value. Those samples are used as inputs to various classification models, the comparison of the AP-ANN, AP-SVM, and AP-RF is done, and their most important five performance metrics such as accuracy, precision, recall, F1-score, and specificity were compared. From our experiment, the AP-ANN model provides better accuracy of 86.8% and greater precision of 85.7%, a higher F1 score of 84.9%, a recall rate of 84.1%, and a specificity value of 89.2% which altogether provides better results than the other existing algorithms.

Stress Detection from Surface Electromyography using Convolutional Neural Networks

The study of stress and its implications has been the focus of interest in various fields of science. Many automated/semi-automated stress detection systems based on physiological markers have been gaining enormous popularity and importance in recent years. Such non-voluntary physiological features exhibit unique characteristics in terms of reliability, accuracy. Combined with machine learning techniques, they offer a great field of study of stress identification and modelling. In this study, we explore the use of Convolutional Neural Networks (CNN) for stress detection through surface electromyography signals (sEMG) of the trapezius muscle. One of the main advantages of this model is the use of the sEMG signal without computed features, contrary to classical machine learning algorithms. The proposed model achieved good results, with 73% f1-score for a multi-class classification and 82% in a bi-class classification.

Happy work: Improving enterprise human resource management by predicting workers' stress using deep learning

Recently, workers in most enterprises suffer from excessive occupational stress in the workplace, which negatively affects workers’ productivity, safety, and health. To deal with stress in workers, it is vital for the human resource management (HRM) department to manage stress effectively, bridging the gap between management and stressed employees. To manage stress effectively, the first step is to predict workers’ stress and detect the factors causing stress among workers. Existing methods often rely on the stress assessment questionnaire, which may not be effective to predict workers’ stress, due to 1) the difficulty of collecting the questionnaire data, and 2) the bias brought by workers’ subjectivity when completing the questionnaires. In this paper, we aim to address this issue and accurately predict workers’ stress status based on Deep Learning (DL) approach. We develop two stress prediction models (i.e., stress classification model and stress regression model) and correspondingly design two neural network architectures. We train these two stress prediction models based on workers’ data (e.g., salary, working time, KPI). By conducting experiments over two real-world datasets: ESI and HAJP, we validate that our proposed deep learning-based approach can effectively predict workers’ stress status with 71.2% accuracy in the classification model and 11.1 prediction loss in the regression model. By accurately predicting workers’ stress status with our method, the HRM of enterprises can be improved.

Exploring Unsupervised Machine Learning Classification Methods for Physiological Stress Detection

Over the past decade, there has been a significant development in wearable health technologies for diagnosis and monitoring, including application to stress monitoring. Most of the wearable stress monitoring systems are built on a supervised learning classification algorithm. These systems rely on the collection of sensor and reference data during the development phase. One of the most challenging tasks in physiological or pathological stress monitoring is the labeling of the physiological signals collected during an experiment. Commonly, different types of self-reporting questionnaires are used to label the perceived stress instances. These questionnaires only capture stress levels at a specific point in time. Moreover, self-reporting is subjective and prone to inaccuracies. This paper explores the potential feasibility of unsupervised learning clustering classifiers such as Affinity Propagation, Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH), K-mean, Mini-Batch K-mean, Mean Shift, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Ordering Points To Identify the Clustering Structure (OPTICS) for implementation in stress monitoring wearable devices. Traditional supervised machine learning (linear, ensembles, trees, and neighboring models) classifiers require hand-crafted features and labels while on the other hand, the unsupervised classifier does not require any labels of perceived stress levels and performs classification based on clustering algorithms. The classification results of unsupervised machine learning classifiers are found comparable to supervised machine learning classifiers on two publicly available datasets. The analysis and results of this comparative study demonstrate the potential of unsupervised learning for the development of non-invasive, continuous, and robust detection and monitoring of physiological and pathological stress.

Optimized electroencephalogram and functional near-infrared spectroscopy-based mental workload detection method for practical applications

Background

Mental workload is a critical consideration in complex man–machine systems design. Among various mental workload detection techniques, multimodal detection techniques integrating electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals have attracted considerable attention. However, existing EEG–fNIRS-based mental workload detection methods have certain defects, such as complex signal acquisition channels and low detection accuracy, which restrict their practical application.

Methods

The signal acquisition configuration was optimized by analyzing the feature importance in mental workload recognition model and a more accurate and convenient EEG–fNIRS-based mental workload detection method was constructed. A classical Multi-Task Attribute Battery (MATB) task was conducted with 20 participating volunteers. Subjective scale data, 64-channel EEG data, and two-channel fNIRS data were collected.

Results

A higher number of EEG channels correspond to higher detection accuracy. However, there is no obvious improvement in accuracy once the number of EEG channels reaches 26, with a four-level mental workload detection accuracy of 76.25 ± 5.21%. Partial results of physiological analysis verify the results of previous studies, such as that the θ power of EEG and concentration of O₂Hb in the prefrontal region increase while the concentration of HHb decreases with task difficulty. It was further observed, for the first time, that the energy of each band of EEG signals was significantly different in the occipital lobe region, and the power of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta_{1}$$\end{document}β1 and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta_{2}$$\end{document}β2 bands in the occipital region increased significantly with task difficulty. The changing range and the mean amplitude of O₂Hb in high-difficulty tasks were significantly higher compared with those in low-difficulty tasks.

Conclusions

The channel configuration of EEG–fNIRS-based mental workload detection was optimized to 26 EEG channels and two frontal fNIRS channels. A four-level mental workload detection accuracy of 76.25 ± 5.21% was obtained, which is higher than previously reported results. The proposed configuration can promote the application of mental workload detection technology in military, driving, and other complex human–computer interaction systems.

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.

Informatics and machine learning methods for health applications

The 2020 International Conference on Intelligent Biology and Medicine (ICIBM 2020) provided a multidisciplinary forum for computational scientists and experimental biologists to share recent advances on all aspects of intelligent computing, informatics and data science in biology and medicine. ICIBM 2020 was held as a virtual conference on August 9-10, 2020, including four live sessions with forty-one oral presentations over video conferencing. In this special issue, ten high-quality manuscripts were selected after peer-review from seventy-five submissions to represent the medical informatics and decision making aspect of the conference. In this editorial, we briefly summarize these ten selected manuscripts.