JXJinjian Xiao

Jinjian Xiao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jinjian Xiao has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    How Does the Built Environment Affect Drunk-Driving Crashes? A Spatial Heterogeneity Analysis

    by Shaohua Wang, Jianzhen Liu, Ning Chen, Jinjian Xiao, Panyi Wei

    In this research, 3356 alcohol-related traffic crashes were obtained from blood-alcohol test reports in Tianjin, China. Population density, intersection density, road density, and alcohol outlet densities, including retail density, entertainment density, restaurant density, company density, hotel density, and residential density, were extracted from 2114 traffic analysis zones (TAZs). After a spatial autocorrelation test, the multiple linear regression model (MLR), geographically weighted Poisson regression model (GWPR), and semi-parametric geographically weighted Poisson regression model (SGWPR) were utilized to explore the spatial effects of the aforementioned variables on drunk-driving crash density. The result shows that the SGWPR model based on the adaptive Gaussian function had the smallest AICc value and the best-fitting accuracy. The residential density and the intersection density are global variables, and the others are local variables that have different influences in different regions. Furthermore, we found that the influence of local variables in the economic–technological development area shows significantly different characteristics compared with other districts. Thus, a comprehensive consideration of spatial heterogeneity would be able to improve the effectiveness of the programs formulated to decrease drunk driving crashes.


  • Open Access

    Highway Ramp Radius Effects on Driving Safety Cognition

    by Jinjian Xiao, Yubo Weng, Yingna Xie

    The driving safety cognition formation was effected distinctly by the highway ramp radius. The ramp radius and automobile velocity were adopted to build driving safety cognition formatting model in the highway ramp environment. The fuzzy logic reasoning rules were applied to construct the computing layers of driving safety cognizing formatting neural network. The driving safety cognition experimental samples in the different ramp radius were gained under different experimental automobile velocity. Weights of fuzzy-neural network layers were trained and were to analog compute effects on the driving safety cognitions under different ramp radius with different experimental velocity. The resulting analyzing to prove that the relations between the typical ramp radius and driving safety cognition were calculated accurately. The trained neural network structure of driving safety cognition based on the utilizing fuzzy inferences is helpful to improve driving safety cognitions of the highway ramp under different automobile velocity.

  • Open Access

    Study on the Prediction of Driving Braking Behaviour Based on FPNN

    by Jinjian Xiao, Yubo Weng, Yingna Xie

    The driving braking recognized and predicted was complicated. The driving braking samples of various braking actions were gained, by means of 3 setting of driving braking including braking of automobile in front, roadblocks cutting off in other lane were planed and simulated in the real road environment. Experimental data of driving actions including automobile velocity, braking velocity and sustained action time were acquired by the driving action collecting system. Taking advantage of fuzzy aggregation analysis, the driving braking action sample was unified for the fuzzy probabilistic neural network (FPNN). Under different action groups of braking action information selected from braking action samples, the FPNN network was constructed and trained. The analytical results show that the hit rate is 95.3 % when the training braking action data number is 46. Meanwhile, the results show that the relative fuzzy unified and FPNN is useful with sufficient driving braking action data. The driving FPNN are a valid way for prediction of driving action time.