Da Yang

Da Yang

Auto-generated profile, based on publicly available information

Da Yang

School of Transportation and Logistics, National Engineering Laboratory of Integrated Transportation Big Data Application Technology, National United Engineering Laboratory of Integrated and Intelligent Transportation, Southwest Jiaotong University, No. 999 Piduquxianlu, Chengdu 611756, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 April 2015 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
DYDa Yang
Da Yang
XQXiaoping Qiu
Xiaoping Qiu
DYDan Yu
Dan Yu
RSRuoxiao Sun
Ruoxiao Sun
YPYun Pu
Yun Pu

1 January 2016 in Applied Mathematics and Computation
Verified
Journal Article
Closed access
LLLan Liu
Lan Liu
LZLiling Zhu
Liling Zhu
DYDa Yang
Da Yang

13 March 2013 in The European Physical Journal B
Verified
Journal Article
Closed access
PDF file
DYDa Yang
Da Yang
PJPeter Jin
Peter Jin
YPYun Pu
Yun Pu
BRBin Ran
Bin Ran

6 April 2016 in Journal of Intelligent Transportation Systems
Verified
Journal Article
Closed access
FYFei Yang
Fei Yang
ZYZhenxing Yao
Zhenxing Yao
YCYang Cheng
Yang Cheng
BRBin Ran
Bin Ran
DYDa Yang
Da Yang
Handheld global positioning system (GPS) devices can serve as a new tool to collect an individual's trip information with advantages of low cost, accurate data, and intensive spatial coverage. Various machine learning algorithms have been explored to detected trip train information in previous studies; however, few of them focused on the evaluation and comparison of the performance and applicability of different models. Meanwhile, according to previous studies, car and bus mode detection is a thorny issue due to their similar travel characteristics, and algorithms still need to be well explored and improved to solve this problem. In this article, an innovative method is proposed to detect trip information, including trip modes, mode-changing time and location, and other attributes, from personal trajectory data. The method is a two-step process. A machine learning algorith-based module (including artificial neural network, support vector machine, random forests, and Bayesian network) is firstly used to identify walk, bicycle, and motorized trip modes (bus or car); we thoroughly compared the performance of these four algorithms. Then a second module, using critical points on the GPS trajectories, is further developed to distinguish car and bus mode, incorporated with GIS map information. Field test results show that the proposed machine learning models can all be applied for walk, bicycle, and motorized mode detection with high detection rates exceeding 90%; however, the algorithms work relatively poorly for bus and car mode detection, with results mostly below 75%. The proposed two-step method can greatly improve bus and car mode detection accuracy by 14–30%. As a result, the average mode detection rates for all the four modes are above 90%. Compared with mode detection results by using only the machine learning algorithm, the proposed two-step method has much better performance in both accuracy and consistency.

21 January 2014 in Journal of Shanghai Jiaotong University (Science)
Verified
Journal Article
Closed access
PDF file
DYDa Yang
Da Yang
LZLi-Ling Zhu
Li-Ling Zhu
DYDan Yu
Dan Yu
FYFei Yang
Fei Yang
YPYun Pu
Yun Pu

1 May 2015 in Journal of Computational and Nonlinear Dynamics
Verified
Journal Article
Closed access
PDF file
DYDa Yang
Da Yang
LZLiling Zhu
Liling Zhu
YPYun Pu
Yun Pu
Although traffic flow has attracted a great amount of attention in past decades, few of the studies focused on heterogeneous traffic flow consisting of different types of drivers or vehicles. This paper attempts to investigate the model and stability analysis of the heterogeneous traffic flow, including drivers with different characteristics. The two critical characteristics of drivers, sensitivity and cautiousness, are taken into account, which produce four types of drivers: the sensitive and cautious driver (S-C), the sensitive and incautious driver (S-IC), the insensitive and cautious driver (IS-C), and the insensitive and incautious driver (IS-IC). The homogeneous optimal velocity car-following model is developed into a heterogeneous form to describe the heterogeneous traffic flow, including the four types of drivers. The stability criterion of the heterogeneous traffic flow is derived, which shows that the proportions of the four types of drivers and their stability functions only relating to model parameters are two critical factors to affect the stability. Numerical simulations are also conducted to verify the derived stability condition and further explore the influences of the driver characteristics on the heterogeneous traffic flow. The simulations reveal that the IS-IC drivers are always the most unstable drivers, the S-C drivers are always the most stable drivers, and the stability effects of the IS-C and the S-IC drivers depend on the stationary velocity. The simulations also indicate that a wider extent of the driver heterogeneity can attenuate the traffic wave.