A System for Automatic Notification and Severity Estimation of Automotive Accidents

Fogue, Manuel; Garrido, Piedad; Martínez, Francisco J.; Cano, Juan-Carlos; Calafate, Carlos T.; Manzoni, Pietro

doi:10.1109/tmc.2013.35

Cited by 64 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to recent literature, driver injury severity can be classified into a few categories such as property damage, possible/evident injury, or disabling injury/fatality [2]. Therefore, modeling accident severity can be addressed as a pattern recognition problem [3], which can be solved by deep learning, statistical techniques and sometimes by physical modelling approaches [4][5][6][7]. In a deep learning model, an input vector is often mapped into an output vector through a set of nonlinear functions.…”

Section: Introductionmentioning

confidence: 99%

Severity Prediction of Traffic Accidents with Recurrent Neural Networks

2017

View full text Add to dashboard Cite

Abstract:In this paper, a deep learning model using a Recurrent Neural Network (RNN) was developed and employed to predict the injury severity of traffic accidents based on 1130 accident records that have occurred on the North-South Expressway (NSE), Malaysia over a six-year period from 2009 to 2015. Compared to traditional Neural Networks (NNs), the RNN method is more effective for sequential data, and is expected to capture temporal correlations among the traffic accident records. Several network architectures and configurations were tested through a systematic grid search to determine an optimal network for predicting the injury severity of traffic accidents. The selected network architecture comprised of a Long-Short Term Memory (LSTM) layer, two fully-connected (dense) layers and a Softmax layer. Next, to avoid over-fitting, the dropout technique with a probability of 0.3 was applied. Further, the network was trained with a Stochastic Gradient Descent (SGD) algorithm (learning rate = 0.01) in the Tensorflow framework. A sensitivity analysis of the RNN model was further conducted to determine these factors' impact on injury severity outcomes. Also, the proposed RNN model was compared with Multilayer Perceptron (MLP) and Bayesian Logistic Regression (BLR) models to understand its advantages and limitations. The results of the comparative analyses showed that the RNN model outperformed the MLP and BLR models. The validation accuracy of the RNN model was 71.77%, whereas the MLP and BLR models achieved 65.48% and 58.30% respectively. The findings of this study indicate that the RNN model, in deep learning frameworks, can be a promising tool for predicting the injury severity of traffic accidents.

show abstract

Section: Introductionmentioning

confidence: 99%

Severity Prediction of Traffic Accidents with Recurrent Neural Networks

2017

View full text Add to dashboard Cite

show abstract

“…It is expected that emergency response time can be reduced by 50% in the countryside and 60% in the urban areas with such a system. Systems for automatic accident detection and recognition have been proposed and prototyped in such as [14][15][16][17] with discussion on future trends in emergency response systems. In principle, eCall only supports voice and simple data transmission.…”

Section: Recent Developmentsmentioning

confidence: 99%

Every Second Counts: Integrating Edge Computing and Service Oriented Architecture for Automatic Emergency Management

Chen¹,

Englund

2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

Emergency management has long been recognized as a social challenge due to the criticality of the response time. In emergency situations such as severe traffic accidents, minimizing the response time, which requires close collaborations between all stakeholders involved and distributed intelligence support, leads to greater survival chance of the injured. However, the current response system is far from efficient, despite the rapid development of information and communication technologies. This paper presents an automated collaboration framework for emergency management that coordinates all stakeholders within the emergency response system and fully automates the rescue process. Applying the concept of multiaccess edge computing architecture, as well as choreography of the service oriented architecture, the system allows seamless coordination between multiple organizations in a distributed way through standard web services. A service choreography is designed to globally model the emergency management process from the time an accident occurs until the rescue is finished. The choreography can be synthesized to generate detailed specification on peer-to-peer interaction logic, and then the specification can be enacted and deployed on cloud infrastructures.

show abstract

“…This forms record information on accidents and their causes in five major parts. The data included information regarding the conditions of x 5 Road defects Lack of safety barriers along the road, poor lighting on roads, road erosion, surface defects, bumps, inadequate traffic road signs [20] x 6 Road geometric characteristic Uphill, straight, downhill, flat [21] x 7 Road surface condition Dry, wet, icy, gravel/sand, slush/mud, standing oil, other [22] x 8 Safety equipment No special safety equipment, air bag, ABS break [20] x 9 Road direction One-way, separated two-way, unseparated two-way [19] x 10 General cause of accident Not looking ahead, sudden opening of the car door, exceeding the speed limit, swerve to the left or right, abrupt change in direction [18] x 11 Type of collision Collision with motorcycle/bicycle, two-vehicle collision, multi-vehicle collision, collision with pedestrian, collision with animal, fixed object collision, overturn, fire/explosion [21] x 12 Type of region Mountain, plain, foothill [23] x 13 Type of shoulder No shoulder, asphalt [10] x 14 Vehicle type Mini bus, bus, pickup, light truck, truck, ambulance, truck with trailer, motorcycle, bicycle, agricultural vehicles, highway const. equipment, fire truck, police car, other [20] x 15 Weather conditions Clear, fog, rain, snow, storm, cloud, dust [22] …”

Section: Data Collectionmentioning

confidence: 99%