A Review on Mental Stress Detection Using Wearable Sensors and Machine Learning Techniques

In real-life applications, electroencephalogram (EEG) signals for mental stress recognition require a conventional wearable device. This, in turn, requires an efficient number of EEG channels and an optimal feature set. This study aims to identify an optimal feature subset that can discriminate mental stress states while enhancing the overall classification performance. We extracted multi-domain features within the time domain, frequency domain, time-frequency domain, and network connectivity features to form a prominent feature vector space for stress. We then proposed a hybrid feature selection (FS) method using minimum redundancy maximum relevance with particle swarm optimization and support vector machines (mRMR-PSO-SVM) to select the optimal feature subset. The performance of the proposed method is evaluated and verified using four datasets, namely EDMSS, DEAP, SEED, and EDPMSC. To further consolidate, the effectiveness of the proposed method is compared with that of the state-of-the-art metaheuristic methods. The proposed model significantly reduced the features vector space by an average of 70% compared with the state-of-the-art methods while significantly increasing overall detection performance.

Section: Feature Extractionmentioning

confidence: 99%

“…Frequency Relative powers of [18]: Theta (4-8 Hz) Alpha (8-12 Hz) Sigma (12-15 Hz) Low beta (15-20 Hz)A high beta (20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30).…”

Section: Activitymentioning

confidence: 99%

See 1 more Smart Citation

Enhancing EEG-Based Mental Stress State Recognition Using an Improved Hybrid Feature Selection Algorithm

Hag

Handayani

Altalhi

et al. 2021

“…Observing the activities of SNS and HPA axis, therefore, provides the opportunity to access the health status, including mental state. Short-lasting daily stressors trigger acute stress, and our body is usually resilient to such stress; excessive and/or prolonged stress, however, damages the body, resulting in physiological illnesses (e.g., high blood pressure) and can increase the risk of developing mental problems (e.g., depression) [8]. To prevent the severe mental problems by timely carrying out appropriate stress management, it is critical to objectively monitor the physiological and biochemical signs associated with the SNS and HPA axis and ultimately associated with stress, in a continuous or on-demand manner.…”

Section: Introductionmentioning

confidence: 99%

Wearable Sensing Systems for Monitoring Mental Health

Kang

Chai

2022

Wearable systems for monitoring biological signals have opened the door to personalized healthcare and have advanced a great deal over the past decade with the development of flexible electronics, efficient energy storage, wireless data transmission, and information processing technologies. As there are cumulative understanding of mechanisms underlying the mental processes and increasing desire for lifetime mental wellbeing, various wearable sensors have been devised to monitor the mental status from physiological activities, physical movements, and biochemical profiles in body fluids. This review summarizes the recent progress in wearable healthcare monitoring systems that can be utilized in mental healthcare, especially focusing on the biochemical sensors (i.e., biomarkers associated with mental status, sensing modalities, and device materials) and discussing their promises and challenges.

“…Thus, automated and non-invasive procedures that are mostly based on physiological signals (e.g., electrocardiogram (ECG) electrodermal activity (EDA), the electrical activity of the scalp (EEG)) deem to be more suitable for this kind of applications [ 7 ]. To that end, a variety of machine learning models have been developed to automatically assess stress, based on data that can be collected in an unobtrusive manner [ 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

Real-Time Stress Level Feedback from Raw Ecg Signals for Personalised, Context-Aware Applications Using Lightweight Convolutional Neural Network Architectures

Tzevelekakis

Stefanidi

Margetis

2021

Human stress is intricately linked with mental processes such as decision making. Public protection practitioners, including Law Enforcement Agents (LEAs), are forced to make difficult decisions during high-pressure operations, under strenuous circumstances. In this respect, systems and applications that assist such practitioners to take decisions, are increasingly incorporating user stress level information for their development, adaptation, and evaluation. To that end, our goal is to accurately detect and classify the level of acute, short-term stress, in real time, for the development of personalized, context-aware solutions for LEAs. Deep Neural Networks (DNNs), and in particular Convolutional Neural Networks (CNNs), have been gaining traction in the field of stress analysis, exhibiting promising results. Furthermore, the electrocardiogram (ECG) signals, have also been widely adopted for estimating levels of stress. In this work, we propose two CNN architectures for the stress detection and 3-level (low, moderate, high) stress classification tasks, using ultra short-term raw ECG signals (3 s). One architecture is simple and with a low memory footprint, suitable for running in wearable edge-computing nodes, and the other is able to learn more complex features, having more trainable parameters. The models were trained on the two publicly available stress classification datasets, after applying pre-processing techniques, such as data pruning, down-sampling, and data augmentation, using a sliding window approach. After hyperparameter tuning, using 4-fold cross-validation, the evaluation on the test set demonstrated state-of-the-art accuracy both on the 3- and 2-level stress classification task using the DriveDB dataset, reporting an accuracy of 83.55% and 98.77% respectively.