Lei Lin

Lei Lin

Auto-generated profile, based on publicly available information

Lei Lin

Department of Civil, Structural and Environmental Engineering, University at Buffalo, The State University of New York, Buffalo, NY 14260, USA

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2015 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
LLLei Lin
Lei Lin
QWQian Wang
Qian Wang
ASAdel W. Sadek
Adel W. Sadek

1 June 2016 in Accident Analysis & Prevention
Verified
Journal Article
Closed access
LLLei Lin
Lei Lin
QWQian Wang
Qian Wang
ASAdel W. Sadek
Adel W. Sadek

1 July 2018 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
LLLei Lin
Lei Lin
JHJohn C. Handley
John C. Handley
YGYiming Gu
Yiming Gu
LZLei Zhu
Lei Zhu
XWXuejin Wen
Xuejin Wen
ASAdel W. Sadek
Adel W. Sadek

1 January 2015 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
LLLei Lin
Lei Lin
MNMing Ni
Ming Ni
QHQing He
Qing He
JGJing Gao
Jing Gao
ASAdel W. Sadek
Adel W. Sadek
Recently, there has been increased interest in quantifying and modeling the impact of inclement weather on transportation system performance. One problem that the majority of research studies on the topic have faced was the great dependence on weather data merely from atmospheric weather stations, which lack information about road surface condition. The emergence of social media platforms, such as Twitter and Facebook, provides a new opportunity to extract more weather-related data from such platforms. This study had two primary objectives: (a) examine whether real-world weather events can be inferred from social media data and (b) determine whether including weather variables extracted from social media data can improve the predictive accuracy of models developed to quantify the impact of inclement weather on freeway traffic speed. To achieve those objectives, weather data, Twitter data, and traffic information were compiled for the Buffalo–Niagara, New York, metropolitan area as a case study. A method called the Twitter Weather Events Observation was then applied to the Twitter data, and the sensitivity and false alarm rate for the method was evaluated against real-world weather data. Then, linear regression models for predicting the impact of inclement weather on freeway speed were developed with and without the Twitter-based weather variables incorporated. The results indicated that Twitter data have a relatively high sensitivity for predicting inclement weather (i.e., snow), especially during the daytime and for areas with significant snowfall. The results also showed that the incorporation of Twitter-based weather variables could help improve the predictive accuracy of the models.

1 January 2014 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
LLLei Lin
Lei Lin
QWQian Wang
Qian Wang
ASAdel W. Sadek
Adel W. Sadek
The field of traffic accident analysis has long been dominated by traditional statistical analysis. With the recent advances in data collection, storage, and archival methods, the size of accident data sets has grown significantly. This result in turn has motivated research on applying data mining and complex network analysis algorithms to traffic accident analysis; the data mining and complex network analysis algorithms are designed specifically to handle data sets with large dimensions. This paper explores the potential for using two such methods–-namely, a modularity-optimizing community detection algorithm and the association rule learning algorithm–-to identify important accident characteristics. As a case study, the algorithms were applied to an accident data set compiled for Interstate 190 in the Buffalo–Niagara, New York, metropolitan area. Specifically, the community detection algorithm was used to cluster the data to reduce the inherent heterogeneity, and then the association rule learning algorithm was applied to each cluster to discern meaningful patterns within each, related particularly to high accident frequency locations (hot spots) and incident clearance time. To demonstrate the benefits of clustering, the association rule algorithm was also applied to the whole data set (before clustering) and the results were compared with those discovered from the clusters. The study results indicated that ( a) the community detection algorithm was quite effective in identifying clusters with discernible characteristics, ( b) clustering helped unveil relationships and accident causative factors that remained hidden when the analysis was performed on the whole data set, and ( c) the association rule learning algorithm yielded useful insight into accident hot spots and incident clearance time along I-190.

1 January 2013 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
LLLei Lin
Lei Lin
QWQian Wang
Qian Wang
ASAdel W. Sadek
Adel W. Sadek
Although several methods for short-term forecasting of traffic volume have recently been developed, the literature lacks studies that focus on how to choose the appropriate prediction method on the basis of the statistical characteristics of the data set. This study first diagnosed the predictability of four traffic volume data sets on the basis of various statistical measures, including (a) complexity analysis methods, such as the delay time and embedding dimension method and the approximate entropy method; (b) nonlinearity analysis methods, such as the time reversibility of surrogate data; and (c) long-range dependency analysis techniques, such as the Hurst exponent. After the data sets were diagnosed, three models for short-term prediction of traffic volume were applied: (a) seasonal autoregressive integrated moving average (SARIMA), (b) k nearest neighbor (k-NN), and (c) support vector regression (SVR). The results from the statistical data diagnosis methods were then correlated to the performance results of the three prediction methods on the four data sets to determine the means for choosing the appropriate prediction method. The results revealed that SVR was more suitable for nonlinear data sets, while SARIMA and k-NN were more appropriate for linear data sets. The data diagnosis results were also used to devise a selection process for the parameters of the prediction models, such as the length of the training data set for SARIMA and SVR, the average number of nearest neighbors for k-NN, and the input vector length for k-NN and SVR.