Accident Risk Prediction based on Heterogeneous Sparse Data

Moosavi, Sobhan; Samavatian, Mohammad Hossein; Parthasarathy, S.; Teodorescu, Radu; Ramnath, Rajiv

doi:10.1145/3347146.3359078

Cited by 112 publications

(59 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…U radu [2] diskutuje se o mogućnosti predviđanja saobraćajnih nesreća u realnom vremenu uz oslonac na različite grupe atributa, gde postoji uticaj svakoga od njih na mogućnost izazivanja nezgode u okvirima drumskog saobraćaja. Korišćeni su podaci koji se odnose na saobraćajne nesreće registrovane na teritoriji Sjedinjenih Američkih Država [2,3]. Rešenja su formirana upotrebom modela zasnovanog na dubokoj neuronskoj mreži.…”

Section: Prethodna Istraživanjaunclassified

Primena Tehnologija Računarstva Visokih Performansi U Istraživanju Bezbednosti Saobraćaja

Vunić¹

2022

Zbornik radova FTN

View full text Add to dashboard Cite

Ovaj rad opisuje postupak primene tehnologija računarstva visokih performansi u analizi faktora koji utiču na stepen ozbiljnosti saobraćajnih nesreća. U radu su navedeni upotrebljene tehnologije i algoritmi mašinskog učenja, skupovi podataka sa kojima je rađeno i primenjena metodologija uz prikazane rezultate istraživanja. Rešenja su implementirana uz pomoć programskog jezika R i sistema za distribuiranu obradu podataka Apache Spark.

show abstract

Section: Prethodna Istraživanjaunclassified

Primena Tehnologija Računarstva Visokih Performansi U Istraživanju Bezbednosti Saobraćaja

Vunić¹

2022

Zbornik radova FTN

View full text Add to dashboard Cite

show abstract

“…Computer vision based [24] techniques are also popular and they exploits the use of real time camera even LiDAR sensor. Use of deep models like autoencoder [25], DNN [26], LSTM [27] etc. are being popular now-a-days due to their capability of extracting the insights from data with different modality.…”

Section: A Literature On Accident Predictionmentioning

confidence: 99%

ARIS: A Real Time Edge Computed Accident Risk Inference System

Ovi

Dey

Roy

et al. 2021

2021 IEEE International Conference on Smart Computing (SMARTCOMP)

View full text Add to dashboard Cite

To deploy an intelligent transport system in urban environment, an effective and real-time accident risk prediction method is required that can help maintain road safety, provide adequate level of medical assistance and transport in case of an emergency. Reducing traffic accidents is an important problem for increasing public safety, so accident analysis and prediction have been a subject of extensive research in recent time. Even if a traffic hazard occurs, a readily deployable structure with an accurate prediction of accident can contribute to better management of rescue resources. But the significant shortcomings of current studies are the use of small-scale datasets with minimal scope, being based on extensive data sets, and not being applicable for real-time purposes. To overcome these challenges, we propose ARIS: a system for real-time traffic accident prediction built on a traffic accident dataset named 'US-Accidents' which covers 49 states of United States, collected from February 2016 to June 2020. Our approach is based on a deep neural network model that utilizes a variety of data characteristics, such as time-sensitive weather data, textual information, and discerning factors. We have tested ARIS against multiple baselines through a comprehensive series of experiments across several major cities of USA, and we have noticed significant improvement during inference especially in detecting accident classes. Additionally, to make our model edge-implementable we have compressed our model using a joint technique of magnitude-based weight pruning and model quantization. We have also demonstrated the inference results along with power consumption profiling after deploying the model on a resource constrained environment that consists of Intel Neural Compute Stick 2 (NCS2) with Raspberry Pi 4B (RPi4). Our investigation and observations indicate major improvements to predict unusual traffic accident event even after model compression and deployment. We have managed to reduce the model size and inference time by ≈ 6x, and ≈ 70 % respectively with insignificant drop in performance. Furthermore, to better understand the importance of each individual type of variables used in our analysis, we have showcased a comprehensive ablation study.

show abstract

“…is section describes the process of constructing a California statewide spatial-temporal traffic accident dataset (CASTA), using two datasets named US accident [48] and California Department of Transportation (Caltrans) Performance Measurement System (PeMS) [49].…”

Section: Datasetmentioning

confidence: 99%

Online Traffic Accident Spatial-Temporal Post-Impact Prediction Model on Highways Based on Spiking Neural Networks

Peng

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Traffic accident management as an approach to improve public security and reduce economic losses has received public attention for a long time, among which traffic accidents post-impact prediction (TAPIP) is one of the most important procedures. However, existing systems and methodologies for TAPIP are insufficient for addressing the problem. The drawbacks include ignoring the recovery process after clearance and failing to make comprehensive prediction in both time and space domain. To this end, we build a 3-stage TAPIP model on highways, using the technology of spiking neural networks (SNNs) and convolutional neural networks (CNNs). By dividing the accident lifetime into two phases, i.e., clean-up phase and recovery phase, the model extracts characteristics in each phase and achieves prediction of spatial-temporal post-impact variables (e.g., clean-up time, recovery time, and accumulative queue length). The framework takes advantage of SNNs to efficiently capture accident spatial-temporal features and CNNs to precisely represent the traffic environment. Integrated with an adaptation and updating mechanism, the whole system works autonomously in an online manner that continues to self-improve during usage. By testing with a new dataset CASTA pertaining to California statewide traffic accidents on highways collected in four years, we prove that the proposed model achieves higher prediction accuracy than other methods (e.g., KNN, shockwave theory, and ANNs). This work is the introduction of SNNs in the traffic accident prediction domain and also a complete description of post-impact in the whole accident lifetime.

show abstract

Accident Risk Prediction based on Heterogeneous Sparse Data

Cited by 112 publications

References 23 publications

Primena Tehnologija Računarstva Visokih Performansi U Istraživanju Bezbednosti Saobraćaja

Primena Tehnologija Računarstva Visokih Performansi U Istraživanju Bezbednosti Saobraćaja

ARIS: A Real Time Edge Computed Accident Risk Inference System

Online Traffic Accident Spatial-Temporal Post-Impact Prediction Model on Highways Based on Spiking Neural Networks

Contact Info

Product

Resources

About