Towards Driver's State Recognition on Real Driving Conditions (original) (raw)
Related papers
Feature and Sensor Selection for Detection of Driver Stress
Proceedings of the 3rd International Conference on Physiological Computing Systems, 2016
This study presents a real-life application-based feature and sensor relevance analysis for detecting stress in drivers. Using the MIT Database for Stress Recognition in Automobile Drivers, the relevance of various physiological sensor signals and features for distinguishing the driver's state have been analyzed. Features related to heart rate, skin conductivity, electromuscular activity, and respiration have been compared using filter and wrapper selection methods. For distinguishing rest from activity, relevant sensors have been found to be heart rate, skin conductivity, and respiration (giving up to 94.6 ± 1.9 % accuracy). For distinguishing low stress from high stress, relevant sensors have been found to be heart rate and respiration (giving up to 78.1 ± 4.1 % accuracy). In both cases, a multiuser model that requires only a calibration from the user in rest, without prior knowledge of the user's individual stress dynamics, resulted in a different optimal sensor and feature configuration, giving 87.3 ± 2.8 % and 72.1 ± 4.3 % accuracy respectively.
Multimodal Features for Detection of Driver Stress and Fatigue: Review
IEEE Transactions on Intelligent Transportation Systems, 2020
Driver fatigue and stress significantly contribute to higher number of car accidents worldwide. Although, different detection approaches have been already commercialized and used by car producers (and third party companies), research activities in this field are still needed in order to increase the reliability of these alert systems. Also, in the context of automated driving, the driver mental state assessment will be an important part of cars in future. This paper presents state-of-the-art review of different approaches for driver fatigue and stress detection and evaluation. We describe in details various signals (biological, car and video) and derived features used for these tasks and we discuss their relevance and advantages. In order to make this review complete, we also describe different datasets, acquisition systems and experiment scenarios.
Detecting of fatigue states of a car driver
… Data Analysis, 2000
This paper deals with research on fatigue states of car drivers on freeways and similar roads. All experiments are performed on-the-road. The approach is based on the assumption that fatigue indicators can be derived from driver+car system behaviour by measuring and processing appropriate factors. For our experiments we designed an array of devices to measure selected physiological and technical parameters. On the basis of experiments already performed and described in the literature, we selected signals that carry appropriate information about fatigue states of a driver. Two data sets are compared: the first set was obtained from alert drivers, and the second one from provably sleep-deprived drivers. We are trying to calibrate "fatigue states" of the driver through trained rater estimates, and to extract reliable symptoms from the measured signals; we are seeking relations between the symptoms and raters fatigue estimates. The results of experiments already performed indicate that the values of symptoms evolve in cycles, which is essential to take into account during design of classifiers in the future.
Designing an Intelligent System to Detect Stress Levels During Driving
The International Arab Journal of Information Technology, 2022
In addition to the devastating effects of anxiety and stress on the development and exacerbation of the cardiovascular disease, lack of stress control increases drivers' risk of accidents. This paper aims to identify the stress of drivers in various driving situations to warn the driver to control the tense conditions during driving. In order to detect stress while driving, we used the heart signals in the Physionet database. To analyze the conditions of the electrocardiogram (ECG) under various driving situations, linear and non-linear features were used. The characteristics of the RRIs are the only able to identify driver stress in different driving modes relative to rest periods, while the return mapping features, in addition to identifying driver stress while resting, have the ability to identify stress between different driving positions also brought. The results showed that driver's stress level during driving in city 1 and highway 1 with a P-value of 0.028 and also in...
Fatigue State Detection for Tired Persons in Presence of Driving Periods
IEEE Access
Due to the increasing of traffic accidents, there is an urgent need to control and reduce driving mistakes. Driver fatigue or drowsiness is one of these major mistakes. Many algorithms have been developed to address this issue by detecting fatigue and alerting the driver to this dangerous condition. The major problem of the developed algorithms is their detection accuracy, as well as the time required to detect fatigue status and alert the driver. The accuracy and the time represent a critical condition that affects the reduction of traffic accidents. Several datasets have been used in the development of fatigue or drowsy detection techniques. These data are gathered from the deriver's brain Electroencephalogram (EEG) signals or from video streaming recordings of the driver behavior. This paper develops two distinct approaches, the first based on the use of machine learning classifiers and the second depends on the use of deep learning models to produce a high-performance fatigue detection system. The machine learning approach is used to process EEG signals, whereas the deep learning approach is used to process video streams. In machine learning classifiers, Support Vector Machine (SVM) provides up to 98% of detection accuracy, which is the highest accuracy among the other five deployed classifiers. In deep learning models, Convolutional Neural Network (CNN) provides up to 99% detection accuracy, which is the highest accuracy among the other two deployed models. The experimental results demonstrate that the two proposed algorithms provide the highest detection accuracy with the shortest Testing Time (TT) when compared to all other recent and efficient fatigue detection algorithms. INDEX TERMS EEG signals, fatigue detection systems, video streaming, support vector machine, convolutional neural network, testing time.
Assessment Of Driving Stress Through SVM And KNN Classifiers On Multi-Domain Physiological Data
2022 IEEE 21st Mediterranean Electrotechnical Conference (MELECON)
We propose an objective stress assessment method based on the extraction of features from physiological time series and their classification using Support Vector Machine and K-Nearest Neighbors algorithms. For this purpose, we used an open dataset consisting of multiparametric physiological signals (electrocardiogram, electromyogram, galvanic skin response and breath signal) obtained during the execution of a driving route within the city of Boston with restful, highway and city driving periods indicative of three different stress states. To predict the driver stress level, 21 features were extracted from 122 chunks of raw signals and were subsequently managed by classification algorithms. Our analysis showed a prediction accuracy of 98.4% when all features were used, decreasing when signals from specific physiological systems were not considered. Our results highlighted that multidomain data acquisition by wearable sensors combined with appropriate classification models may represent a promising strategy to detect drivers' stress status in an unobtrusive and objective way that can in perspective be applicable in several other fields such as in the clinics.
Ijca Proceedings on National Conference on Innovative Paradigms in Engineering and Technology, 2012
This paper describes a Prediction of driver-fatigue monitor. It uses remotely located charge-coupled-device cameras equipped with active infrared illuminators to acquire video images of the driver. Various visual cues that typically characterize the level of alertness of a person are extracted in real time and systematically combined to infer the fatigue level of the driver. The visual cues employed characterize eyelid movement, gaze movement, head movement, and facial expression. A probabilistic model is developed to model human fatigue and to predict fatigue based on the visual cues obtained. The simultaneous use of multiple visual cues and their systematic combination yields a much more robust and accurate fatigue characterization than using a single visual cue. This system was validated under real-life fatigue conditions with human subjects of different ethnic backgrounds, genders, and ages; with/without glasses; and under different illumination conditions. It was found to be reasonably robust, reliable, and accurate in fatigue characterization.
Supervised Learning Techniques for Stress Detection in Car Drivers
Advances in Science, Technology and Engineering Systems Journal
In this paper we propose the application of supervised learning techniques to recognize stress situations in drivers by analyzing their Skin Potential Response (SPR) and the Electrocardiogram (ECG). A sensing device is used to acquire the SPR from both hands of the drivers, and the ECG from their chest. We also consider a motion artifact removal algorithm that allows the generation of a single cleaned SPR signal, starting from the two SPR signals, which could be characterized by artifacts due to vibrations or movements of the hands on the wheel. From both the cleaned SPR and the ECG signals we compute some statistical features that are used as input to six Machine Learning Algorithms for stress or non-stress episodes classification. The SPR and ECG signals are also used as input to Deep Learning Algorithms, thus allowing us to compare the performance of the different classifiers. The experiments have been carried out in a firm specialized in developing professional car driving simulators. In particular, a dynamic driving simulator has been used, with subjects driving along a straight road affected by some unanticipated stress-evoking events, located at different positions. We obtain an accuracy of 88.13% in stress recognition using a Long Short-Term Memory (LSTM) network.
A survey on driver drowsiness detection using physiological, vehicular, and behavioral approaches
Bulletin of Electrical Engineering and Informatics , 2022
Drowsiness is a significant reason for street mishaps and has huge ramifications for driver safety. A few lethal mishaps can be prohibited if the sleepy drivers are cautioned in time. There are a number of tiredness identification strategies that screen the drivers' languor state while driving and caution unfocused drivers. Highlights may be gathered from outward appearances (e.g., yawning and eyes and head movement) to determine the degree of laziness. This paper presents a holistic investigation of current strategies for driver laziness discovery and gives an exploration of widelyused characterization procedures. We begin by organizing the current procedures into three categories: behavior, vehicular, and physiological boundaries-based procedures. Then, we survey top directed learning methods utilized for laziness discovery. Next, we examine the advantages and disadvantages of the various techniques. A similar examination indicated that none of these strategies is entirely precise. However, physiological boundaries-based procedures produce more exact outcomes than other types of procedures. Their non-intrusive nature may be decreased through utilizing remote sensors on various elements including the driver's body, driver's seat, seat covers, and steering wheel.
Frontiers in Neuroscience, 2018
Drivers' hazardous physical and mental states (e.g., distraction, fatigue, stress, and high workload) have a major effect on driving performance and strongly contribute to 25-50% of all traffic accidents. They are caused by numerous factors, such as cell phone use or lack of sleep. However, while significant research has been done on detecting hazardous states, most studies have not tried to identify the causes of the hazardous states. Such information would be very useful, as it would allow intelligent vehicles to better respond to a detected hazardous state. Thus, this study examined whether the cause of a driver's hazardous state can be automatically identified using a combination of driver characteristics, vehicle kinematics, and physiological measures. Twenty-one healthy participants took part in four 45-min sessions of simulated driving, of which they were mildly sleep-deprived for two sessions. Within each session, there were eight different scenarios with different weather (sunny or snowy), traffic density and cell phone usage (with or without cell phone). During each scenario, four physiological (respiration, electrocardiogram, skin conductance, and body temperature) and eight vehicle kinematics measures were monitored. Additionally, three self-reported driver characteristics were obtained: personality, stress level, and mood. Three feature sets were formed based on driver characteristics, vehicle kinematics, and physiological signals. All possible combinations of the three feature sets were used to classify sleep deprivation (drowsy vs. alert), traffic density (low vs. high), cell phone use, and weather conditions (foggy/snowy vs. sunny) with highest accuracies of 98.8%, 91.4%, 82.3%, and 71.5%, respectively. Vehicle kinematics were most useful for classification of weather and traffic density while physiology and driver characteristics were useful for classification of sleep deprivation and cell phone use. Furthermore, a second classification scheme was tested that also incorporates information about whether or not other causes of hazardous states are present, though this did not result in higher classification accuracy. In the future, these classifiers could be used to identify both the presence and cause of a driver's hazardous state, which could serve as the basis for more intelligent intervention systems.