Understanding the underlying relationship between pedestrian injury severity outcomes and factors leading to more severe injuries is very important in dealing with the problem of pedestrian safety. To investigate injury severity outcomes, many previous works relied on statistical regression models. There has also been some interest for data mining techniques, in particular for clustering techniques which segment the data into more homogeneous subsets. This research combines these two approaches (data mining and statistical regression methods) to identify the main contributing factors associated with the levels of pedestrian injury severity outcomes. This work relies on the analysis of two unique pedestrian injury severity datasets from the City of New York, US (2002-2006) and the City of Montreal, Canada (2003-2006). General injury severity models were estimated for the whole datasets and for sub-populations obtained through clustering analysis. This paper shows how the segmentation of the accident datasets help to better understand the complex relationship between the injury severity outcomes and the contributing geometric, built environment and socio-demographic factors. While using the same methodology for the two datasets, different techniques were tested. For instance, for New York, latent class with ordered probit method provides the best results. However, for Montreal, the K-means with multinomial logit model is identified as the most appropriate technique. The results show the power of using clustering with regression to provide a complementary and more detailed analysis. Among other results, it was found that pedestrian age, location at intersection, actions prior to accident, driver age, vehicle type, vehicle movement, driver alcohol involvement and lighting conditions have an influence on the likelihood of a fatal crash. Moreover, several features within the built environment are shown to have an effect. Finally, the research provides recommendations for policy makers, traffic engineers, and law enforcement to reduce the severity of pedestrian-vehicle collisions.

A Clustering Regression Approach: A Comprehensive Injury Severity Analysis of Pedestrian-Vehicle Crashes in New York, U.S. and Montreal, Canada

The close combination of internet technology and traditional industrial control system (ICS) is a double-edged sword, which not only improves the accuracy of the control system, but also brings great danger. According to the statistics of the authoritative industrial security incident information database, Repository of Industrial Security Incidents (RISI), as of October 2011, there have been more than 200 attacks on industrial control systems around the world. It is obviously a multi-attribute decision-making (MADM) problem to select the appropriate industrial control system security supplier (ICSSS) for ensuring the safety of ICS. In this paper, the traditional TODIM method is improved and reconstructed in the probabilistic linguistic environment by incorporating the prospect theory (PT) which has received close attention recently. In this new model, the entropy weight method is used to obtain the attribute weight under complete information. And based on the ideas of PT as well as traditional TODIM method, the distortion of decision results caused by the risk attitude and psychological state of decision makers is corrected as far as possible. In my opinion, probabilistic linguistic term set (PLTS) ensures that the model can better cope with the real environment and the complexity and ambiguity of decision makers’ thinking. Finally, the successful application of this new probabilistic linguistic TODIM method based on PT (PT-PL-TODIM method) in the selection of ICSSS proves that the model is practical and is also of great value to the decision-making research related to ICS. Moreover, the comparative analysis between the proposed model and the existing model effectively confirms the reliability of the proposed method. In the future, it is hoped that this method can be successfully applied to more decision-making fields.

PT-TODIM Method for Probabilistic Linguistic MAGDM and Application to Industrial Control System Security Supplier Selection

Power prediction of a wind farm cluster based on spatiotemporal correlations

Benchmarking on railway safety performance using Bayesian inference, decision tree and petri-net techniques based on long-term accidental data sets

Does high risk mean high loss: Evidence from flood disaster in southern China.

Historical data-driven risk assessment of railway dangerous goods transportation system: Comparisons between Entropy Weight Method and Scatter Degree Method

Operational failure analysis of high-speed electric multiple units: A Bayesian network-K2 algorithm-expectation maximization approach

Urban bus accident analysis: based on a Tropos Goal Risk-Accident Framework considering Learning From Incidents process

An accurate short-term passenger flow prediction provides essential data support for Urban Rail Transit (URT) organizations. However, the short-term URT passenger flow data is neither linear nor stationary, which results in the inaccuracy of prediction using only single deep-learning models. In this paper, we proposed a hybrid model that integrates Ensemble Empirical Mode Decomposition (EEMD) and Gated Recurrent Unit (GRU) to achieve faster and better results for short-term passenger flow prediction. The approach contains four steps. First, the EEMD algorithm decomposes passenger flow data into several intrinsic mode functions (IMF) and a residual function. Second, the Spearman and Kendall correlation coefficients were used to examine the IMF components to select components that are highly related to the URT passenger flow. Third, the selected features and historical passenger flow are combined as inputs for the GRU model, respectively. Last, the outputs of each input feature and historical data were synthesized to obtain the result. We used the passenger flow of Xipu, a station of Chengdu Metro Line 2, to demonstrate the method. The experimental results indicate that the proposed EEMD-GRU architecture, compared with benchmark models, achieves superior performance. It can reduce the training time by 26.18% and improve the average accuracy by 29.58%, which shows great validity for large-scale short-term metro passenger flow forecasting.

Zhanru Liu

Papers

Historical data-driven risk assessment of railway dangerous goods transportation system: Comparisons between Entropy Weight Method and Scatter Degree Method

Operational failure analysis of high-speed electric multiple units: A Bayesian network-K2 algorithm-expectation maximization approach

Urban bus accident analysis: based on a Tropos Goal Risk-Accident Framework considering Learning From Incidents process

Ensemble Empirical Mode Decomposition-Based Gated Recurrent Unit Model for Short-Term Metro Passenger Flow Prediction