Wen Cui

Wen Cui

Auto-generated profile, based on publicly available information

Wen Cui

Luoyang Institute of Science and Technology, Luoyang, 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
23 November 2023 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
KHKunkun Hao
Kunkun Hao
WCWen Cui
Wen Cui
YLYonggang Luo
Yonggang Luo
LXLecheng Xie
Lecheng Xie
YBYuqiao Bai
Yuqiao Bai
ZYZijiang Yang
Zijiang Yang
Evaluating the decision-making system is indispensable in developing autonomous vehicles, while realistic and challenging safety-critical test scenarios play a crucial role. Obtaining these scenarios is non-trivial, thanks to the long-tailed distribution, sparsity, and rarity in real-world data sets. To tackle this problem, in this paper, we introduce a natural adversarial scenario generation solution using naturalistic human driving priors and reinforcement learning techniques. By doing this, we can obtain large-scale test scenarios that are both diverse and realistic. Specifically, we build a simulation environment that mimics natural traffic interaction scenarios. Informed by this environment, we implement a two-stage procedure. The first stage incorporates conventional rule-based models, e.g., IDM (Intelligent Driver Model) and MOBIL (Minimizing Overall Braking Induced by Lane changes) model, to coarsely and discretely capture and calibrate key control parameters from the real-world dataset. Next, we leverage GAIL (Generative Adversarial Imitation Learning) to represent driver behaviors continuously. The derived GAIL can be further used to design a PPO (Proximal Policy Optimization)-based actor-critic network framework to fine-tune the reward function, and then optimize our natural adversarial scenario generation solution. Extensive experiments have been conducted in two popular datasets, NGSIM and INTERACTION. Essential traffic parameters were measured in comparison with the baseline model, e.g., the collision rate, accelerations, steering, and the number of lane changes. Our findings demonstrate that the proposed model can generate realistic safety-critical test scenarios covering both naturalness and adversariality with an advanced 44% efficiency gain over the baseline model, which can be a cornerstone for the development of autonomous vehicles.

10 May 2017 in Journal of Educational Computing Research
Verified
Journal Article
Closed access
Nianfeng ShiNianfeng Shi
Nianfeng Shi
WCWen Cui
Wen Cui
PZPing Zhang
Ping Zhang
XSXiming Sun
Ximing Sun
This research applies the roles of variables to the novice programmers in the C language programming. The results are evaluated using the Structure of Observed Learning Outcomes (SOLO) taxonomy. The participants were divided into an experimental group and a control group. The students from the control group learned programming in the traditional case-based teaching method. The students in the experimental group learned programming by applying the role-based approach to the case-based teaching method. For the purposes of determining the effects of the role-based teaching, the SOLO taxonomy was used to evaluate the results of the participants’ final paper–pencil test. The SOLO level of the code reading and code writing was graded according to the SOLO categories for program comprehension and construction. Data analyses show that (a) there was a higher level of performance and cognitive ability in the experimental group, (b) there were some positive and significant correlations between student’s final examination scores and their SOLO level of the code reading and code writing, and (c) the SOLO level of the code writing and code reading was significantly related. These results suggest that the role of variable is effective on improving novice programming.

17 February 2021 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
WCWen Cui
Wen Cui
CLChen Liu
Chen Liu
WYWenjun Yang
Wenjun Yang
LCLin Cai
Lin Cai
Internet-of-Things (IoT) is emerging, while the spectrum is at a premium. To enhance spectrum efficiency, a promising solution is Non-Orthogonal Multiple Access (NOMA) that enables users to communicate with the same resource at the same time, while decoding the superimposed signal at the receiver. Existing NOMA technologies, however, rely on strict power control to decode the superimposed signal, infeasible for heterogeneous and low-cost IoT devices. In contrast, we propose I-Talk, a new NOMA scheme that is designed for IoT and can decode the superimposed signals from two transmitters without power control. Importantly, considering the IoT systems in the wild, both the hardware imperfections and mobility are unavoidable, which can cause severe signal variations, resulting in an unreliable decoding performance. To solve this problem, we design a synthesis channel coefficient to track all signal offsets caused by the hardware imperfection. Meanwhile, we propose a diversity transmission and smart combining scheme to achieve high reliable decoding performance. To demonstrate the feasibility of this new NOMA approach in practical systems, we implement I-Talk with USRP devices and the experimental results illustrate that I-Talk achieves a one-order lower bit-error-rate and a 1.47× higher throughput gain than the state-of-the-art superimposed signal decoding scheme.