Distraction Behavior Research Articles

Text and Voice Message Distraction Detection: A Machine Learning Approach Using Vehicle Trajectory Data

Cellphone usage is often considered to be one of the major causes of distracted driving. Similarly, voice messaging is identified as a potential cause of distracted driving but has received limited attention in the literature. Thus, this study aims to develop supervised machine learning (ML) methods to detect distracted driving events caused by texting and voice messaging using vehicle trajectory data. Vehicle trajectory data was collected from 92 participants who drove a simulated network of the Baltimore metropolitan area using a driving simulator. Different key variables were extracted from the data to construct the features for developing the ML methods, including speed, brake usage, throttle, steering velocity, brake light, and offset from the road center. Several methods, including the support vector machine, k-nearest neighbor, decision tree, neural network, and adaptive boosting (AdaBoost), were examined on the data to achieve the best model. In addition, several metrics were used to assess the performance of the ML models, such as accuracy, sensitivity, precision, the Matthews correlation coefficient, and the area under the receiver operating characteristic curve (AUC-ROC). The results indicated that the AdaBoost algorithm had the best yields, with an accuracy of 74.67% and AUC-ROC of 82.5% on the independent test set. The findings of this study can be directly leveraged to develop in-vehicle driver warning systems to alert drivers with respect to distracted behavior, which lead to the reduction of distracted driving events and an improvement in traffic safety.

Examining drivers’ distracted driving behaviour using the extended norm activation model

A driving distraction is any external or internal stimulus that diverts a driver’s attention away from the primary task of safe vehicle operation, potentially increasing the risk of accidents. Drivers often get involved in distractions such as phone calls, text messaging, interacting with in-vehicle technology, roadside advertisements, roadside accident sites, and chatting with passengers, etc. In previous research, the antecedents of distraction behaviour have primarily been investigated through the theory of planned behaviour (TPB). Refraining from distracted driving can be considered a pro-social behaviour and can be modelled using the norm activation model (NAM). Therefore, this study aimed to evaluate the potential of pro-social behaviour in explaining drivers’ distracted driving behaviour using the NAM theory. In addition to the conventional factors of the NAM model – awareness of consequences (AC), ascription of responsibility (AR), and personal norms (PN) – this study presents a novel element that examines how technology can mitigate distractions. The data was collected in Lahore city through a questionnaire survey. The results indicate that AC and AR have positive associations with PN, however, PN has also been found to have a positive association with the distraction behaviour. This study provides insights into the utilisation of the NAM theory to evaluate the potential of altruistic behaviour in preventing individuals from engaging in distracted driving.

Behavioral Problems Amidst Initial Face-to-Face Classes: Intervention of Teachers

This study unfolded the feedback of teachers of Talomo District, Davao City on behavioral problems in learning environments. There were ten (10) teachers who participated in the study. This study made use of a phenomenological approach to extract the ideas of the participants. The participants were purposely selected as representatives from the group of teachers in the same division. The virtual in-depth-interview was employed to gather some information as regards to their respective experiences on behavioral issues in learning environments. Using the thematic analysis, the following themes emerged as pertains to the experiences of the participants: cheating, Inappropriate distracting behavior in class and school attendance issues. The coping mechanisms to address the struggles of kindergarten play-based learning were: developing relationship with students, using praise and reward and graduated discipline system. The educational management insights gained from the experiences of the teachers were primarily focused on implementing schoolwide policies and expectations on student behavior. The principals may be more receptive on the current problems and issues of the teachers. The school heads may implement rules and policies that will set the disciplinary tone of the school. The teachers may continuously adapt coping mechanisms to address issues and be vigilant in finding classroom solutions to their problems.

Reducing Disruptive and Distracting Behaviors in the Classroom: Assessing the Evidence Base.

Disruptive and distracting behaviors in the classroom, from off-task to aggressive behaviors, negatively affect academic engagement and achievement and can lead to more serious problems, including mental health conditions and substance use disorders. The goals of this systematic review were to assess the level of evidence, using established rating criteria, for interventions aimed at preventing or reducing disruptive and distracting classroom behaviors; identify program components common to multiple interventions; synthesize the evidence in regard to students from different racial-ethnic groups; and conduct an economic analysis of these interventions. A search of major databases, gray literature, and evidence base registries was conducted to identify studies published between 2008 and 2022. The authors rated interventions as having high, moderate, or low levels of evidence of effectiveness on the basis of the number and rigor of studies with positive outcomes. Of the 27 interventions identified across 65 studies (N=73 articles), six interventions received a high or moderate evidence rating. The Good Behavior Game was the most frequently studied intervention. Many interventions shared similar program components, including behavioral management, classroom management, emotional-cognitive processes, and skills acquisition. Most articles (86%) were focused on elementary school students. The four interventions rated as having high evidence of effectiveness also showed generally positive outcomes in studies conducted in school settings with racial-ethnic diversity. No studies met the criteria for inclusion in an economic analysis. With greater use and more research, interventions focusing on reducing disruptive and distracting behaviors have the potential to promote student well-being and prevent mental health conditions.

An Algorithm for Distracted Driving Recognition Based on Pose Features and an Improved KNN

To reduce safety accidents caused by distracted driving and address issues such as low recognition accuracy and deployment difficulties in current algorithms for distracted behavior detection, this paper proposes an algorithm that utilizes an improved KNN for classifying driver posture features to predict distracted driving behavior. Firstly, the number of channels in the Lightweight OpenPose network is pruned to predict and output the coordinates of key points in the upper body of the driver. Secondly, based on the principles of ergonomics, driving behavior features are modeled, and a set of five-dimensional feature values are obtained through geometric calculations. Finally, considering the relationship between the distance between samples and the number of samples, this paper proposes an adjustable distance-weighted KNN algorithm (ADW-KNN), which is used for classification and prediction. The experimental results show that the proposed algorithm achieved a recognition rate of 94.04% for distracted driving behavior on the public dataset SFD3, with a speed of up to 50FPS, superior to mainstream deep learning algorithms in terms of accuracy and speed. The superiority of ADW-KNN was further verified through experiments on other public datasets.

Safety analysis of pedestrians distracted by mobile phones at street crossings: Field study in Nanjing

The growing public concern over traffic safety hazards caused by pedestrians’ distracted behavior, particularly related to mobile phone usage at pedestrian crossings. Through video recording of pedestrians’ street-crossing behaviors on 12 sidewalks across 9 urban road intersections in Nanjing city, 1778 valid pedestrian samples were collected. The study categorizes mobile phone use during the crossing into five distinct types: no use, voice call, screen gaze, screen gaze with operation, and listening to music with headphones. Then, the effects of gender, age and companion conditions on the mobile phone during the crossing were examined by chi-square tests. Utilizing binomial logistic and Relogit regression models, the study analyzed the impact and safety risks of distraction on crossing behavior. Additionally, a random parameters (RP) logit model with heterogeneity in means was used to investigate the determinants affecting mobile phone usage. Notably, individuals aged 18 to 30 years were identified as the random parameter, while factors such as being under 18 years old, having a companion without interaction, having a companion with interaction, weekdays, sidewalk length, and the total number of other pedestrians were identified as fixed parameters. The study also presented significant variables affecting the probability of mobile phone usage through marginal effects, highlighting the potential safety risks associated with mobile phone usage during street crossing. These findings emphasize the need for heightened pedestrian safety awareness and a reduction in distracted behaviors to enhance overall traffic safety.

Three stage classification framework with ranking scheme for distracted driver detection using heuristic-assisted strategy

In recent days, the number of road accidents are greatly increased in world wide. The people around the world died due to the rapid road crush. The driver behavior must be detected to neglect the occurrence of road accidents. In this work, the three stage deep learning-based techniques are developed to detect the distracted driver action. The developed model is implemented in three phase to detect the distracted behavior of the driver during the driving process. In the first stage, the images are gathered from standard public resources regarding various drivers while driving. Next, the deep features retrieved using VGG16 and Inception and Xception networks. Then, the weighted fusedfusion is done by gathered features, where the weight parameter is optimized through the Adaptive Gradient-based Optimizer (AGBO) algorithm. Further, the driver behavior classification is done through a Deep Belief Network (DBN) with Radial Basis Functions Neural Networks (RBF), where the hyperparameters of DBN and RBF are optimized through the same AGBO algorithm. Finally, the first set of classified outcomes is attained from the images. In the second stage, the gathered images are fed to the feature extraction stage, where the texture features and motion features are gathered from the images. These collected features are fed to the same optimized DBN with RBF and the second set of classified outcomes with human behaviors has been attained.In the third stage, the gathered image fralgoriom the dataset is fed to the PCA for extracting the features. The gathered features are given to the same optimized DBN with the RBF classifier to get the classified outcome. Later, the classified outcomes from the three stages are fed to the ranking procedure for detecting the distracted driver action. When considering the evaluation indices, the suggested distracted driver prediction model attains 97.67% of accuracy, 97.68% of sensitivity, 97.67% of specificity, and 97.55% of precision value. Thus, the performance of the developed model in the distracted driver prediction is enhanced than the existing approaches.

A Novel Driver Distraction Behavior Detection Method Based on Self-Supervised Learning With Masked Image Modeling

A Novel Driver Distraction Behavior Detection Method Based on Self-Supervised Learning With Masked Image Modeling

CDCL-VRE: An ensemble deep learning-based model for distracted driver behavior detection

Millions of traffic accidents occur worldwide each year, resulting in tens of thousands of deaths. The primary cause is the distracted behavior of drivers during the driving process. If the distracted behaviors of drivers during driving can be detected and recognized in time, drivers can regulate their driving and the goal of reducing the number of traffic fatalities can be achieved. A deep learning model is proposed to detect driver distractions in this paper. The model can identify ten behaviors including one normal driving behavior and nine distracted driving behaviors. The proposed model consists of two modules. In the first module, the cross-domain complementary learning (CDCL) algorithm is used to detect driver body parts in the input images, which reduces the impact of environmental factors in vehicles on the convolutional neural network. Then the output images of the first module are sent to the second module. The Resnet50 and Vanilla networks are ensembled in the second module, and then the driver behavior can be classified. The ensemble architecture used in the second module can reduce the sensitivity of only a single network on the data, and then the detection accuracy can be improved. Through the experiments, it can be seen that the proposed model in this paper can achieve an average accuracy of 99.0%.

A Driving Risk Assessment Framework Considering Driver’s Fatigue State and Distraction Behavior

A Driving Risk Assessment Framework Considering Driver’s Fatigue State and Distraction Behavior

Driver Distraction Behavior Detection Framework Based on the DWPose Model, Kalman Filtering, and Multi-Transformer

Driver Distraction Behavior Detection Framework Based on the DWPose Model, Kalman Filtering, and Multi-Transformer

An Improved Distraction Behavior Detection Algorithm Based on YOLOv5

An Improved Distraction Behavior Detection Algorithm Based on YOLOv5

Driver Distraction Behavior Recognition for Autonomous Driving: Approaches, Datasets and Challenges

Driver Distraction Behavior Recognition for Autonomous Driving: Approaches, Datasets and Challenges

Design and Analysis of Unlocking Student Emotions: Enhancing E-Learning with Facial Emotion Detection

Abstract: In all forms of learning, students are required to make the most of the time allotted to them during instruction. They will pay close attention to the material being taught to them. Students' performance will rise as a result. In order to provide a framework for the future, we are attempting to ascertain the feelings and behaviors of the students participating in an online course as well as to examine their distracted behavior. This study on students' tendency toward distraction can assist teachers in monitoring these students and providing assistance to those who choose to improvise their performances. To investigate the distracted behavior of students during virtual classes, one must possess knowledge in image processing, machine learning, and deep learning techniques.

Cell phone distraction behavior of young pedestrians: evidence from China

Cell phone use while walking escalates pedestrian safety risks, particularly among students, given their heavy reliance on these devices. Psychological factors wield significant influence on individual behavior, particularly among adolescents who navigate a blend of rational and social-reactive pathways in decision-making. Therefore, this paper employs the Prototype Willingness Model (PWM) to scrutinize psychological determinants of students’ cell phone use while walking, drawing on data from 368 valid samples. Structural equation modeling (SEM) dissects the impact of psychological constructs on this behavior, highlighting the significance of both the social response and reasoning pathways within PWM. The study comprehensively analyzes direct, indirect, and overall effects of exogenous variables on behavioral intention and behavior.

Driver distraction detection using semi-supervised lightweight vision transformer

The continuously increasing number of traffic accidents necessitates addressing distracted driving, which is responsible for numerous fatalities. Enhancing driver behavior recognition, particularly through developing a highly reliable Advanced Driver Assistance System (ADAS), holds substantial potential for cultivating safer transportation systems. Inspired by the success of Convolutional Neural Networks (CNNs), various networks have been proposed to enhance the detection accuracy of distracting behaviors. However, existing models have too many parameters and rely heavily on extensive labeled data, leading to time-consuming labeling and large models. To address these limitations, we propose a distracted behavior detection method based on a lightweight vision transformer trained using pseudo-label-based semi-supervised learning to learn discriminative representations from labeled and unlabeled data while ensuring a small model and speedy inference. Specifically, we create strong and weak augmented versions of the input minibatch and employ a hybrid lightweight transformer model in a teacher-student network. Pseudo-labels are generated from the teacher's predictions on weakly augmented data. The student model aligns with these labels on strongly augmented input, with teacher parameters evolving through exponential moving average. Our method presents a real-time, accurate solution for distracted driver detection, with the potential to significantly enhance road safety by reducing accidents. The effectiveness of the proposed approach is demonstrated through a comparative evaluation against alternative fully-supervised and semi-supervised methods. Furthermore, our method is evaluated in naturalistic driving settings with varying lighting and complex backgrounds. Experiments conducted on two publicly available driver distraction detection datasets show that our method outperforms current state-of-the-art approaches.

Distraction-level recognition based on stacking ensemble learning for IVIS secondary tasks

Driver distraction-level recognition while performing secondary tasks in full-touch in-vehicle information systems (FTIVISs) is essential for the harmonious co-driving of human and intelligent vehicle systems. However, there has been little research on this topic. To respond to this issue, this paper proposes a distraction-level recognition framework with a combination of semi-supervised learning, unsupervised learning, and supervised learning. First, unsupervised learning and semi-supervised is used to divide the collected unlabeled samples of driving distraction behavior into three categories of distraction levels: high, medium, and low. Second, the factors influencing the distraction level are explored through a mixed model analysis. Finally, a stacking-based ensemble learning model is proposed to recognize the driver distraction level by supervised learning, with the influencing factors of the distraction level used as model input parameters. To improve the recognition performance of the stacking model, four heterogeneous classifiers selected as the base classifiers, and principal component analysis (PCA) is introduced in the base classifier layer, which improves the ability of the meta-classifier to process raw features based on overfitting resistance. We conducted a real road experiment under different road and FTIVIS task conditions, and the proposed model performed better than traditional machine learning models. In addition, the model exhibited the greatest advantage when the deep neural network (DNN) algorithm was used as the meta-classifier of the model, with a recognition accuracy of 92.5%. The study findings are significant for developing a human–machine co-driving control strategy and improving vehicle driving safety.

Older Drivers Reduced Engagement in Distracting Behaviors Over a Six-Year Period: Findings From the Candrive Longitudinal Study.

Baltes and Baltes' "selective optimization with compensation" model is pertinent to driving but evidence about the use of compensation using longitudinal designs is scarce. Therefore, we sought to determine if older drivers reduced their engagement in distracting behaviors while driving, over a 6-year period. We used data captured over several annual assessments from a cohort of 583 drivers aged 70 and older to determine if their engagement in 12 distracting behaviors (e.g., listening to the radio, talking with passengers) declined over time. We adjusted our multivariable model for several potential confounders of the association between our outcome variable and time. Overall, and after adjustment for potential confounders, the participants reduced their engagement in distracting behaviors over the study period (odds ratio [OR] = 0.96, 95% confidence interval [CI] = 0.95-0.97). Baseline age was negatively associated with engagement in distracting behaviors (OR = 0.95, 95% CI = 0.94-0.96). Men engaged in more distracting behaviors than women (OR = 1.15, 95% CI = 1.03-1.27), as did participants living in the largest urban centers compared to participants living in the smallest areas (OR = 1.21, 95% CI = 1.04-1.41). The number of kilometers driven per year (for every 10,000 km) was positively associated with the proportion of distracting behaviors drivers engaged in (OR = 1.13, 95% CI = 1.08-1.19). Drivers in our cohort reduced their engagement in distracting behaviors over the study period. This suggests that older drivers adjust their driving over time, which aligns with age-related theories and models about compensation.

Did COVID-19 mandates influence driver distraction Behaviors? A case study in New Jersey

The global pandemic, Coronavirus (COVID), impacts almost everything, and human driving behavior is no exception. Since its breakdown in March 2020, transportation researchers have pondered on this matter to investigate the impact of COVID on drivers' travel behavior. Most of these studies are self-reported surveys, 'before and during' crash analyses, and short-duration observational studies. With a wider scope from an observational lens, we aim to investigate the impact of COVID-19 on drivers' distraction behaviors from an extensive observational database of distracted driving in New Jersey. A moving observational vehicle equipped with mounted cameras was utilized to collect the drivers' behavior across the high crash corridors and important highways in New Jersey. Samples collected during the COVID mandates and the post-COVID period were analyzed to assess the impact of COVID on drivers' distraction behavior at various temporal setups and roadway geometry. The results indicate a significant increase in cellphone use, eating, and fidgeting/grooming during the post-COVID period. However, behaviors like radio/reaching objects and talking to passengers decreased significantly after COVID. Utilizing the Mann-Whitney U test, this study conducted significance tests to identify the impacts of various temporal and geometric roadway features on each distraction type. Summer season, toll roads and roads with no signal had reduced distraction during the post-COVID compared to the COVID period. Both COVID and post-COVID period showed significant patterns of change of driver behavior within the temporal variables and road geometry. This research's findings would enable comprehension of human behavioral change for COVID mandates.

Influence of distracted driving of online car-hailing drivers on overall driving performance

The distraction affects driving performance and induces serious safety issues. To better understand distracted driving, this study examines the influence of distracted driving on overall driving performance. This paper analyzes the distraction behavior (mobile phone use, entertainment activities, and passenger interference) under three driving tasks. The statistical results show that viewing or sending messages is common during driving. Smoking, phone calls, and talking to passengers are evident in cruising, ride request and drop-off, respectively. Then, overall driving performance is proposed based on velocity, longitudinal acceleration (longacc) and yaw_rate. It is divided into three categories, high, medium, and low, by k-means algorithms. The average speed increases from low to high performance; however, the longacc and yaw_rate decrease. Finally, the influence of distracted driving on overall driving performance is analyzed using C4.5 algorithm. The result shows that when time is peak, the probability of high performance (HP) is higher than off-peak. The possibility of HP increases with the increase of duration; the number of, talking to passengers, listening to music or radio, eating; the duration of, viewing or sending messages, phone calls; but reduces with the increase of the number of phone calls. These findings provide theoretical support for driving performance evaluation.