A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data

Bao, Jie; Liu, Pan; Ukkusuri, Satish V.

doi:10.1016/j.aap.2018.10.015

Cited by 213 publications

(83 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatiotemporal patterns can be mined from Big Data (social media, phone locations, bus lines and traffic zones) collected within cities and used to better understand our urban settings and broader patterns such as human mobility and accessibility (Pappalardo and Simini 2018). This is true also for population dynamics (Liu et al 2018a), crash indices (Bao et al 2019), poverty distribution (Njuguna and McSharry 2017), segregation based on environment, gender, racial/ethnic and socioeconomic aspects (Park and Kwan 2017), patterns of social activities for policy development (Fu et al 2018), and the stability of urban human convergence and divergence patterns (Fang et al 2017). For crime reduction and public safety, Big Data (such as surveillance videos) have been used to improve data service sustainability and to analyze crime patterns based on city to city distance and connectivity (Kotevska et al 2017).…”

Section: Big Spatiotemporal Data Analytics In Actionmentioning

confidence: 99%

“…Big spatiotemporal data analysis now draws on new analytical frameworks. For example, deep learning can be expanded to a spatiotemporal framework for different scales of problems in space and time in the recognition of citywide crash patterns (Bao, Liu, and Ukkusuri 2019). The integration of cyber-physical systems requires new frameworks and models to provide integrated management, collaborative observation, scalable processing/fusion and intelligent services (Zhang et al, 2018).…”

Section: Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Big Spatiotemporal Data Analytics: a research and innovation frontier

Yang

Clarke

Shekhar

et al. 2019

International Journal of Geographical Information Science

View full text Add to dashboard Cite

Section: Big Spatiotemporal Data Analytics In Actionmentioning

confidence: 99%

Section: Future Directionsmentioning

confidence: 99%

Big Spatiotemporal Data Analytics: a research and innovation frontier

Yang

Clarke

Shekhar

et al. 2019

International Journal of Geographical Information Science

View full text Add to dashboard Cite

“…Traffic collisions that happen on urban roads not only severely threaten property and human life, but also negatively affect urban traffic and Sustainability 2019, 11,4739 2 of 14 bring inconvenience to citizens. Uncovering the spatio-temporal distribution of traffic collisions and detecting areas of high risk may help promote the efficiency of traffic resource allocation and practical efforts to ensure public road safety [4,5].…”

Section: Introductionmentioning

confidence: 99%

“…A number of factors have been widely used to estimate the occurrence of traffic collisions at the micro-level, such as vehicle speed [6][7][8][9] and/or vehicle exposure [4,5,10,11], the geometric and physical characteristics of roads [12,13], and land use types [14,15]. For instance, a study by Shirazinejad et al found that the collision rate increased when the speed limit on expressways rose from 70 mph to 75 mph [9].…”

Section: Introductionmentioning

confidence: 99%

Investigating the Potential of Using POI and Nighttime Light Data to Map Urban Road Safety at the Micro-Level: A Case in Shanghai, China

et al. 2019

View full text Add to dashboard Cite

The way in which the occurrence of urban traffic collisions can be conveniently and precisely predicted plays an important role in traffic safety management, which can help ensure urban sustainability. Point of interest (POI) and nighttime light (NTL) data have always been used for characterizing human activities and built environments. By using a district of Shanghai as the study area, this research employed the two types of urban sensing data to map vehicle-pedestrian and vehicle-vehicle collision risks at the micro-level by road type with random forest regression (RFR) models. First, the Network Kernel Density Estimation (NKDE) algorithm was used to generate the traffic collision density surface. Next, by establishing a set of RFR models, the observed density surface was modeled with POI and NTL variables, based on different road types and periods of the day. Finally, the accuracy of the models and the predicted outcomes were analyzed. The results show that the two datasets have great potential for mapping vehicle-pedestrian and vehicle-vehicle collision risks, but they should be carefully utilized for different types of roads and collision types. First, POI and NTL data are not applicable to the modeling of traffic collisions that happen on expressways. Second, the two types of sensing data are quite suitable for estimating the occurrence of traffic collisions on arterial and secondary trunk roads. Third, while the two datasets are capable of predicting vehicle-pedestrian collision risks on branch roads, their ability to predict vehicle safety on branch roads is limited.

show abstract

“…Zhang, Xie, & Li, 2012), generalized estimating equation models (Zha, Li, Zhang, & Gao, 2011), Tobit regression models (Anastasopoulos, Mannering, Shankar, & Haddock, 2012), simulation models (Kuang, Qu, & Wang, 2014), multivariate models (Barua, El-Basyouny, & Islam, 2016;Caliendo, De Guglielmo, & Guida, 2013), Bayesian models (W. Cheng, Gill, Sakrani, Dasu, & Zhou, 2017;Guadamuz-Flores & Aguero-Valverde, 2017;Zeng & Huang, 2014), neural network models (Chong, Abraham, & Paprzycki, 2004;H. Ye, Xu, & Lord, 2018), and spatiotemporal deep learning approaches (Bao, Liu, & Ukkusuri, 2019). Ye, Xu, & Lord, 2018), and spatiotemporal deep learning approaches (Bao, Liu, & Ukkusuri, 2019).…”

mentioning

confidence: 99%

An ensemble machine learning‐based modeling framework for analysis of traffic crash frequency

Zhang

Waller

Jiang

2019

Computer aided Civil Eng

View full text Add to dashboard Cite

This study is, to our knowledge, the first in the literature to introduce a modeling framework for analyzing traffic crash frequency based on a series of ensemble machine learning (EML) methods. The main objectives of this study are fourfold: (a) to design a systematic EML‐based framework for crash frequency analysis, (b) to comprehensively compare the performance in analyzing crash frequency by different optimized EML models, (c) to identify significant contributors to crash frequency, and (d) to propose the approach to construct schemes to reduce traffic crashes. To achieve the research goal, the Highway Safety Information System database that includes records of over 1.5 million crashes is employed for model estimation and validation. We first optimize the EML models for crash analysis via the k‐fold cross‐training, including the two averaging methods of random forest and extremely randomized trees, and the two boosting methods of adaptive boosting and gradient tree boosting. Then, we assess the behavior of the optimized models, and conduct a sensitivity test to validate the stability of model performance. Furthermore, we evaluate the relative importance of features to crash frequency by using the Gini diversity index. The results indicate that the two averaging EML models can achieve desirable performance in crash frequency analysis, which outperform the two boosting EML models, in terms of predictive accuracy, generalization ability, and stability. From the results, we explore new insights into the significance of contributors to crash occurrence. Finally, we present the approach of safety improvements for transport facilities.

show abstract

A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data

Cited by 213 publications

References 27 publications

Big Spatiotemporal Data Analytics: a research and innovation frontier

Big Spatiotemporal Data Analytics: a research and innovation frontier

Investigating the Potential of Using POI and Nighttime Light Data to Map Urban Road Safety at the Micro-Level: A Case in Shanghai, China

An ensemble machine learning‐based modeling framework for analysis of traffic crash frequency

Contact Info

Product

Resources

About