Lei Gao

Lei Gao

Auto-generated profile, based on publicly available information

Lei Gao

The Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
1 August 2019 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
LGLei Gao
Lei Gao
XLXingquan Liu
Xingquan Liu
YLYu Liu
Yu Liu
PWPu Wang
Pu Wang
MDMin Deng
Min Deng
HLHaifeng Li
Haifeng Li

6 March 2024 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
LGLei Gao
Lei Gao
HHHaozhe Huang
Haozhe Huang
JYJianhong Ye
Jianhong Ye
DWDaoge Wang
Daoge Wang

5 July 2023 in Transportation
Verified
Journal Article
Closed access
PDF file
DWDaoge Wang
Daoge Wang
JYJianhong Ye
Jianhong Ye
BYBin Yu
Bin Yu
PJPeng Jing
Peng Jing
LGLei Gao
Lei Gao

1 September 2011
Verified
Conference Paper
Closed access
BZBin Zhang
Bin Zhang
JYJiahai Yang
Jiahai Yang
JWJianping Wu
Jianping Wu
DQDonghong Qin
Donghong Qin
LGLei Gao
Lei Gao
In this paper, we present a statistical analysis of six traffic features based on entropy and distinct feature number at the packet level, and we find that, although these traffic features are unstable and show seasonal patterns like traffic volume for a long period, they are stable and consistent with Gaussian distribution in a short time period. However, this equilibrium property will be violated by some anomalies. Based on this observation, we propose a Multi-dimensional Clustering method for Short-time scale Traffic(MCST) to classify abnormal and normal traffic. We compare our new method to the well known wavelet technique. The detection result on synthetic anomaly traffic shows MCST can better detect the low-rate attacks than wavelet-based method, and detection result on real traffic demonstrates that MCST can detect more anomalies with low false alarm rate.

25 February 2024 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
JYJianhong Ye
Jianhong Ye
YHYifan Hu
Yifan Hu
LGLei Gao
Lei Gao
Transportation demand models and traffic simulations, particularly in the realm of innovative activity-based models, necessitate comprehensive demographic-activity-travel data. Although cell phone data holds the potential to provide detailed insights into activity-travel patterns, transportation planners often resort to aggregate data, constrained by limited socio-demographic attributes because of stringent privacy protection policies. This creates a significant challenge: how to reconstruct detailed traveler profiles from such aggregate data. In this paper, we propose a novel data-driven integration framework, DATG, based on improved Markov and XGBoost classification models, with which we are able to reconstruct travelers with diverse socio-demographic attributes as well as their one-day activity-travel information. We test our model on a real cell phone data set and validate the proposed model by relying on travel survey data. Our framework is able to provide fundamental data support for agent-based models, activity-based models, and transportation planning.