A Novel Classification Method for a Driver’s Cognitive Stress Level by Transferring Interbeat Intervals of the ECG Signal to Pictures

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.

Section: Discussionmentioning

confidence: 94%

“…On the other hand, instead of using the one-dimensional input of the raw ECG measurements, other approaches transform the signal to two dimensional images that they later feed to 2D CNN models [ 34 , 35 ]. Kang et al.…”

Section: Related Workmentioning

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

“…The abnormal values outside the IBI normal ranges (6–1.2 s) were removed. Then, the descriptive statics were calculated, such as range, minimum, and maximum values, and the time interval of the inter-beat interval was divided into 28 intervals according to the distribution of the inter-beat intervals as discussed in [ 35 ]. Second, a

column vector was created for each inter-beat interval and assigned 1 to the interval in which the inter-beat belongs and 0 for the remaining elements.…”

Section: Proposed Stress Image-based Detection Modelmentioning

confidence: 99%

“…They compared the accuracy of this approach with the ANN method using time-domain features (mean IBI and root mean squared difference of adjacent IBIs (RMSSD), and standard deviation of IBIs (SDNN)). They found that the accuracy of the new approach was more accurate than the ANN method, which has been frequently used in recent researches [ 35 ].…”

Section: Introductionmentioning

confidence: 99%

Stress Classification Using Photoplethysmogram-Based Spatial and Frequency Domain Images

Elzeiny

Qaraqe

2020

Stress is subjective and is manifested differently from one person to another. Thus, the performance of generic classification models that classify stress status is crude. Building a person-specific model leads to a reliable classification, but it requires the collection of new data to train a new model for every individual and needs periodic upgrades because stress is dynamic. In this paper, a new binary classification (called stressed and non-stressed) approach is proposed for a subject’s stress state in which the inter-beat intervals extracted from a photoplethysomogram (PPG) were transferred to spatial images and then to frequency domain images according to the number of consecutive. Then, the convolution neural network (CNN) was used to train and validate the classification accuracy of the person’s stress state. Three types of classification models were built: person-specific models, generic classification models, and calibrated-generic classification models. The average classification accuracies achieved by person-specific models using spatial images and frequency domain images were 99.9%, 100%, and 99.8%, and 99.68%, 98.97%, and 96.4% for the training, validation, and test, respectively. By combining 20% of the samples collected from test subjects into the training data, the calibrated generic models’ accuracy was improved and outperformed the generic performance across both the spatial and frequency domain images. The average classification accuracy of 99.6%, 99.9%, and 88.1%, and 99.2%, 97.4%, and 87.6% were obtained for the training set, validation set, and test set, respectively, using the calibrated generic classification-based method for the series of inter-beat interval (IBI) spatial and frequency domain images. The main contribution of this study is the use of the frequency domain images that are generated from the spatial domain images of the IBI extracted from the PPG signal to classify the stress state of the individual by building person-specific models and calibrated generic models.

“…Active driver status monitoring has been a major research topic for a long time, as it has a significant impact on road safety and accident statistics. Various physiological sensors based on electrocardiogram (ECG) and electroencephalogram (EEG) are nowadays frequently used in numerous studies [ 28 , 29 ].…”

Section: Introductionmentioning

confidence: 99%

Vital Sign Monitoring in Car Seats Based on Electrocardiography, Ballistocardiography and Seismocardiography: A Review

Šidiková

Martínek

Kawala-Sterniuk

et al. 2020

This paper focuses on a thorough summary of vital function measuring methods in vehicles. The focus of this paper is to summarize and compare already existing methods integrated into car seats with the implementation of inter alia capacitive electrocardiogram (cECG), mechanical motion analysis Ballistocardiography (BCG) and Seismocardiography (SCG). In addition, a comprehensive overview of other methods of vital sign monitoring, such as camera-based systems or steering wheel sensors, is also presented in this article. Furthermore, this work contains a very thorough background study on advanced signal processing methods and their potential application for the purpose of vital sign monitoring in cars, which is prone to various disturbances and artifacts occurrence that have to be eliminated.