Dataset Information

A hybrid neural network for driving behavior risk prediction based on distracted driving behavior data.

ABSTRACT: Distracted driving behavior is one of the main factors of road accidents. Accurately predicting the risk of driving behavior is of great significance to the active safety of road transportation. The large amount of information collected by the sensors installed on the vehicle can be identified by the algorithm to obtain the distracted driving behavior data, which can be used to predict the driving behavior risk of the vehicle and the area. In this paper, a new neural network named Driving Behavior Risk Prediction Neural Network (DBRPNN) is developed for prediction based on the distracted driving behavior data. The network consists of three modules: the Feature Processing Module, the Memory Module, and the Prediction Module. In this process, attribute data (time in a day, daily driving time, and daily driving mileage) that can reflect external factors and driver statuses, are added to the network to increase the accuracy of the model. We predicted the driving behavior risk of different objects (Vehicle and Area). For the applicability improvement of the model, we further classify the distracted driving behavior categories, and DBRPNN can provide more accurate risk prediction. The results show that compared with traditional models (Classification and Regression Tree, Support Vector Machines, Recurrent Neural Network, and Long Short-Term Memory), DBRPNN has better prediction performance. The method proposed in this paper has been fully verified and may be transplanted into active safety early warning system for more accurate and flexible application.

SUBMITTER: Fu X

PROVIDER: S-EPMC8789134 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Distracted driving attributable to the performance of secondary tasks is a major cause of motor vehicle crashes both among teenagers who are novice drivers and among adults who are experienced drivers. METHODS:We conducted two studies on the relationship between the performance of secondary tasks, including cell-phone use, and the risk of crashes and near-crashes. To facilitate objective assessment, accelerometers, cameras, global positioning systems, and other sensors were installed in the vehicles of 42 newly licensed drivers (16.3 to 17.0 years of age) and 109 adults with more driving experience. RESULTS:During the study periods, 167 crashes and near-crashes among novice drivers and 518 crashes and near-crashes among experienced drivers were identified. The risk of a crash or near-crash among novice drivers increased significantly if they were dialing a cell phone (odds ratio, 8.32; 95% confidence interval [CI], 2.83 to 24.42), reaching for a cell phone (odds ratio, 7.05; 95% CI, 2.64 to 18.83), sending or receiving text messages (odds ratio, 3.87; 95% CI, 1.62 to 9.25), reaching for an object other than a cell phone (odds ratio, 8.00; 95% CI, 3.67 to 17.50), looking at a roadside object (odds ratio, 3.90; 95% CI, 1.72 to 8.81), or eating (odds ratio, 2.99; 95% CI, 1.30 to 6.91). Among experienced drivers, dialing a cell phone was associated with a significantly increased risk of a crash or near-crash (odds ratio, 2.49; 95% CI, 1.38 to 4.54); the risk associated with texting or accessing the Internet was not assessed in this population. The prevalence of high-risk attention to secondary tasks increased over time among novice drivers but not among experienced drivers. CONCLUSIONS:The risk of a crash or near-crash among novice drivers increased with the performance of many secondary tasks, including texting and dialing cell phones. (Funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development and the National Highway Traffic Safety Administration.).

Project description:Motivation:A majority of known genetic variants associated with human-inherited diseases lie in non-coding regions that lack adequate interpretation, making it indispensable to systematically discover functional sites at the whole genome level and precisely decipher their implications in a comprehensive manner. Although computational approaches have been complementing high-throughput biological experiments towards the annotation of the human genome, it still remains a big challenge to accurately annotate regulatory elements in the context of a specific cell type via automatic learning of the DNA sequence code from large-scale sequencing data. Indeed, the development of an accurate and interpretable model to learn the DNA sequence signature and further enable the identification of causative genetic variants has become essential in both genomic and genetic studies. Results:We proposed Deopen, a hybrid framework mainly based on a deep convolutional neural network, to automatically learn the regulatory code of DNA sequences and predict chromatin accessibility. In a series of comparison with existing methods, we show the superior performance of our model in not only the classification of accessible regions against background sequences sampled at random, but also the regression of DNase-seq signals. Besides, we further visualize the convolutional kernels and show the match of identified sequence signatures and known motifs. We finally demonstrate the sensitivity of our model in finding causative noncoding variants in the analysis of a breast cancer dataset. We expect to see wide applications of Deopen with either public or in-house chromatin accessibility data in the annotation of the human genome and the identification of non-coding variants associated with diseases. Availability and implementation:Deopen is freely available at https://github.com/kimmo1019/Deopen. Contact:ruijiang@tsinghua.edu.cn. Supplementary information:Supplementary data are available at Bioinformatics online.

Project description:ObjectivePedestrian-related death rates are increasing in the United States, partly due to increased use of distracting smartphones by pedestrians. Previous research documents high frequency of smartphone use while crossing streets near college campuses and in downtown business districts, but little is known about distracted pedestrian behavior in other urban environments. The current study used observational methods to examine and compare distracted pedestrian behavior in four urban areas - near an urban college campus, in a downtown commercial business district, near middle and high schools, and in entertainment districts - as well as examining whether the occurrence of distraction was associated with unsafe crossing behaviors.MethodsWe observed 112 intersections in 46 downtown, 30 school, 25 entertainment district, and 11 college campus-area intersections. Coders recorded distraction, crossing safety, pedestrian demographics, and traffic volume. Chi-square tests compared pedestrian characteristics by intersection type. Log binomial regressions estimated risk ratios (RRs) and associated 95% confidence intervals (CIs) for associations between pedestrians walking alone and traffic volume with distracted crossing behavior, adjusting for age and gender. Similar models examined risk of unsafe crossing behavior by distraction behavior. All models were stratified by intersection type.ResultsDistraction incidence was highest in campus locations (52.9%) and lowest in entertainment districts (16.2%). Walking alone was associated with a 45% higher risk of distraction (RR 1.45, 95% CI 1.30-1.62), although the increased association was limited to entertainment locations (RR 1.61, 95% CI 1.25-2.08) and was significantly decreased in all other locations. Higher traffic volume was associated with lower risk of distraction in downtown locations (RR 0.69, 95% CI 0.56-0.85) but higher distraction risk in entertainment locations (RR 1.71, 95% CI 1.27-2.31). Associations between distraction and unsafe crossing behaviors were minimal.ConclusionDistracted pedestrian behavior occurs at different rates and in different circumstances, depending on the setting. These results offer valuable data to inform intervention programs that target appropriate populations in appropriate locations.

Dataset Information

A hybrid neural network for driving behavior risk prediction based on distracted driving behavior data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets