Driver's Physiological State Research Articles

Driving Alertness System Using Deep Learning

Abstract: Driver fatigue, a major contributor to road accidents, poses a significant challenge to road safety. Numerous fatal collisions could be prevented by promptly alerting drivers experiencing drowsiness. Several drowsiness detection methods have been developed to monitor driver alertness while driving and issue warnings when attention lapses. These systems employ various techniques to assess drowsiness levels, including extracting key features from facial expressions such as yawning, eye closure, and head movements. Evaluating both the driver's physiological state and vehicle behavior is crucial for identifying signs of drowsiness. This research delves into a comprehensive evaluation of prevalent classification methodologies and a thorough examination of contemporary driver drowsiness detection technologies. The study initially categorizes existing techniques into three broad groups: physiological, vehicular, and behavioral parameter-based approaches. It then provides an extensive review of recognized supervised learning algorithms employed for drowsiness detection. Furthermore, the examination conducts a comparative analysis of the advantages and limitations of various methods.

Carrying a passenger and relaxation before driving: Classification of young drivers' physiological activation.

Drivers are often held responsible for road crashes. Previous research has shown that stressors such as carrying passengers in the vehicle can be a source of accidents for young drivers. To mitigate this problem, this study investigated whether the presence of a passenger behind the wheel can be predicted using machine learning, based on physiological signals. It also addresses the question whether relaxation before driving can positively influence the driver's state and help controlling the potential negative consequences of stressors. Sixty young participants completed a 10‐min driving simulator session, either alone or with a passenger. Before their driving session, participants spent 10 min relaxing or listening to an audiobook. Physiological signals were recorded throughout the experiment. Results show that drivers experience a higher increase in skin conductance when driving with a passenger, which can be predicted with 90%‐accuracy by a k‐nearest neighbors classifier. This might be a possible explanation for increased risk taking in this age group. Besides, the practice of relaxation can be predicted with 80% accuracy using a neural network. According to the statistical analysis, the potential beneficial effect of relaxation did not carry out on the driver's physiological state while driving, although machine learning techniques revealed that participants who exercised relaxation before driving could be recognized with 70% accuracy. Analysis of physiological characteristics after classification revealed several relevant physiological indicators associated with the presence of a passenger and relaxation.

A machine learning pipeline for fuel-economical driving model

PurposeA cost-effective way to achieve fuel economy is to reinforce positive driving behaviour. Driving behaviour can be controlled if drivers can be alerted for behaviour that results in poor fuel economy. Fuel consumption must be tracked and monitored instantaneously rather than tracking average fuel economy for the entire trip duration. A single-step application of machine learning (ML) is not sufficient to model prediction of instantaneous fuel consumption and detection of anomalous fuel economy. The study designs an ML pipeline to track and monitor instantaneous fuel economy and detect anomalies.Design/methodology/approachThis research iteratively applies different variations of a two-step ML pipeline to the driving dataset for hatchback cars. The first step addresses the problem of accurate measurement and prediction of fuel economy using time series driving data, and the second step detects abnormal fuel economy in relation to contextual information. Long short-term memory autoencoder method learns and uses the most salient features of time series data to build a regression model. The contextual anomaly is detected by following two approaches, kernel quantile estimator and one-class support vector machine. The kernel quantile estimator sets dynamic threshold for detecting anomalous behaviour. Any error beyond a threshold is classified as an anomaly. The one-class support vector machine learns training error pattern and applies the model to test data for anomaly detection. The two-step ML pipeline is further modified by replacing long short term memory autoencoder with gated recurrent network autoencoder, and the performance of both models is compared. The speed recommendations and feedback are issued to the driver based on detected anomalies for controlling aggressive behaviour.FindingsA composite long short-term memory autoencoder was compared with gated recurrent unit autoencoder. Both models achieve prediction accuracy within a range of 98%–100% for prediction as a first step. Recall and accuracy metrics for anomaly detection using kernel quantile estimator remains within 98%–100%, whereas the one-class support vector machine approach performs within the range of 99.3%–100%.Research limitations/implicationsThe proposed approach does not consider socio-demographics or physiological information of drivers due to privacy concerns. However, it can be extended to correlate driver's physiological state such as fatigue, sleep and stress to correlate with driving behaviour and fuel economy. The anomaly detection approach here is limited to providing feedback to driver, it can be extended to give contextual feedback to the steering controller or throttle controller. In the future, a controller-based system can be associated with an anomaly detection approach to control the acceleration and braking action of the driver.Practical implicationsThe suggested approach is helpful in monitoring and reinforcing fuel-economical driving behaviour among fleet drivers as per different environmental contexts. It can also be used as a training tool for improving driving efficiency for new drivers. It keeps drivers engaged positively by issuing a relevant warning for significant contextual anomalies and avoids issuing a warning for minor operational errors.Originality/valueThis paper contributes to the existing literature by providing an ML pipeline approach to track and monitor instantaneous fuel economy rather than relying on average fuel economy values. The approach is further extended to detect contextual driving behaviour anomalies and optimises fuel economy. The main contributions for this approach are as follows: (1) a prediction model is applied to fine-grained time series driving data to predict instantaneous fuel consumption. (2) Anomalous fuel economy is detected by comparing prediction error against a threshold and analysing error patterns based on contextual information.

Smart driver assistance system using raspberry pi and sensor networks

With the evolution of science and technology, monitoring human reactions and activities have become really easy and smooth. These new technologies have the potential to revolutionize the domain of safety and security in different realms of the society. Surveillance being the key factor of security measures has been elevated to a whole new level with the advancement in signal processing techniques. This paper basically focuses on the implementation of a smart surveillance system using signal processing and embedded tools which is applied in automobiles to ultimately develop the holistic driver assistance system. Earlier methods were based on physiological and analog data, but the present day scenario demands a smarter and digitalized working system so as to employ integrity and compatibility with other smart sub-systems like mobile phones and tablets. Transportation as we all know is one of the key sectors in the society. But the safety and security measures which people implement for their homes is not being employed for their vehicles. Apart from the vehicular anti-theft burglar systems, driver monitoring systems are also crucial to the lives of the driver and the passengers. Hence, this paper consists of three inter-linked modules which are the driver fatigue detection, alcohol content detection and vehicular crash detection along with control to monitor the driver's physiological state that can affect the vehicular control. A variety of input extraction hardware tools and software algorithms have been utilized in a collaborative way to implement this process.

Feasibility study on measurement of a physiological index value with an electrocardiogram tester to evaluate the pavement evenness and driving comfort

The driving comfort, which is mainly determined by the pavement evenness, is one of the most important indexes for evaluating the pavement service condition. Current evaluation indexes for the pavement evenness, such as the international roughness index (IRI), are mainly determined by the vibration acceleration method. However, the driver is at the core in the human-vehicle–road-environment system. Few studies have focused on the physiological state as a response to accelerations induced by pavement unevenness and evaluate the driving comfort on this basis. In this study, the Root Mean Square of the Successive Differences (RMSSD) derived from the driver's heart rate variability (HRV) in the time domain and was selected as an index value for the driver's physiological state. Using an advanced indoor testing platform, the RMSSD values of five drivers were recorded by a KF2 electrocardiogram tester. The relationship between the RMSSD, the driving speed and the IRI underwent detailed analyses. The results of the tests show that the vertical vibration is identical when the drivers are driving on the simulated pavement with the same IRI value; however, the RMSSD values of different drivers were different, i.e., the perception of the same pavement evenness is subjective. Therefore, when evaluating the driving comfort based on the pavement evenness, it is necessary to consider the physiological index. The results obtained in this study have proven the feasibility of measurement of RMSSD value to evaluate the pavement evenness and driving comfort. They are therefore a powerful augmentation of existing evaluation methods and also provide a new reference for further optimization of the pavement surface performance.

Wristband-Type Driver Vigilance Monitoring System Using Smartwatch

Studies have presented that the driver vigilance level has serious implication in the causation of road accidents. This paper focuses on integrating both the vehicle-based control behavior and physiological state to predict the driver vigilance index which is evaluated by using a smartwatch. The vehicle control behavior can be observed from the steering wheel movement. Our study utilized the smartwatch motion sensors to study the steering wheel behavior. Meanwhile, physiological state of driver reflects the driver capability of safety alert driving which is estimated by photoplethysmogram (PPG) and respiration signals in this paper. The PPG sensor is integrated in a sport wristband with a Bluetooth low energy module, transmitted the PPG signals to smartwatch in real time. The steering angle is derived by the reading from smartwatch built-in accelerometer and gyroscope sensors. On the other hand, the respiration is derived using the PPG peak baseline method. In order to utterly investigate the sleepiness-induced factors, the time, spectral, and phase space domain features are calculated. Considering the smartwatch processing capability, mutual-information technique is applied to designate the ten most descriptive features. Then, the extracted descriptive features are serve as parameters to a classifier to determine the driver aptitude status. The features are analyzed for their correlation with the subjective Koralinska sleepiness scale and through recorded video observations. The experimental results reveal that our system is capable of estimating driver hypervigilance at average of 96.5% accuracy rate by evaluating on both driving behavior and driver physiological state, provided a novel and low-cost implementation.

Effect of Driver's Cognitive Distraction on Driver's Physiological State and Driving Performance

Objective: The aim of this study is to investigate effect of driver's cognitive distraction on driver's physiological state and driving performance, and then to determine parameters appropriate for detecting the cognitive distraction. Background: Driver distraction is a major cause of traffic accidents and poses a serious threat to traffic safety due to ever increasing use of in-vehicle information systems and mobile phones during driving. Cognitive distraction, among four different types of distractions, prevents a driver from processing traffic information correctly and adapting to change in surround vehicle behavior in time. However, the cognitive distraction is more difficult to detect because it normally does not involve significant change in driver behavior. Method: A full-scale driving simulator was used to create virtual driving environment and situations. Participants in the experiment drove the driving simulator in three different conditions: attentive driving with no secondary task, driving and conducting secondary task of adding numbers, and driving and conducting secondary task of conversing with an experimenter. Parameters related with driver's physiological state and driving performance were measured and analyzed for their change. Results: The experiment results show that driver's cognitive distraction, induced by secondary task of addition and conversation during driving, increased driver's cognitive workload, and indeed brought change in driver's physiological state and degraded driving performance. Conclusion: The galvanic skin response, pupil size, steering reversal rate, and driver reaction time are shown to be statistically significant for detecting cognitive distraction. The appropriate combination of these parameters will be used to detect the cognitive distraction and estimate risk of traffic accidents in real-time for a driver distraction warning system.

Assessment of Driver Movements during Prolonged Driving Using Seat Pressure Measurements

Driver's physiological state changes with the increase of driving time. The current study used seat pressure to examine the driver movements (result from driver's physiological state changes) during prolonged driving. Two experiments were conducted in real vehicle and driving simulator, respectively. Ten male participants were divided into two groups to complete the two experiments, respectively. According to the results of the real vehicle experiment, moment center in the seat back and average pressures were found to have significant correlation with time. The results indicated that there were two kinds of movements: (1) participants turned their heads front, their backs became more curving, and their knees rose; (2) participants turned their heads rear, their back angles became larger, and their knees rose. The results of driving simulator experiment proved that the seat pressure was sensitive to movements, and proved that effects of driving movements (result from driving task) on the seat pressure were significant, which indicated the control of redundant movements, including driving movements, was very important in the study. Language: en