Yuexuan Wang

Yuexuan Wang


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
31 January 2022 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
ZQZiheng Qi
Ziheng Qi
TWTong Wang
Tong Wang
Jian ChenJian Chen
Jian Chen
DNDeepak Narang
Deepak Narang
YWYuexuan Wang
Yuexuan Wang
HYHuayong Yang
Huayong Yang
Navigation algorithms for autonomous vehicles have become the subject of increasing interest, but most of them heavily rely on expensive high-precision positioning equipment, which hinders autonomous vehicles development. In this paper, we propose a path planning and control framework for autonomous vehicles with low-cost positioning. For the path planning layer, a potential field is constructed by the potential functions of road boundaries, obstacles, and reference waypoints. According to the potential field, a reinforcement learning agent is developed to generate a collision-free path for path tracking. For the control layer, a model predictive control based on vehicle dynamics is designed and a linear terminal constraint is considered. Simulation results show that the proposed algorithm can effectively avoid static and dynamic obstacles. Moreover, compared with traditional methods, the proposed algorithm performs better when the positioning devices are imprecise. Furthermore, the real-time performance can meet the requirements of navigation.

1 January 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
DLDongda Li
Dongda Li
ZGZhaoquan Gu
Zhaoquan Gu
YWYuexuan Wang
Yuexuan Wang
CRChangwei Ren
Changwei Ren
FLFrancis C.M. Lau
Francis C.M. Lau

14 February 2023 in Genome Medicine
Verified
Journal Article
Open access
PDF file
SLShumin Li
Shumin Li
BYBin Yan
Bin Yan
TLThomas K. T. Li
Thomas K. T. Li
JLJianliang Lu
Jianliang Lu
YGYifan Gu
Yifan Gu
RLRuibang Luo
Ruibang Luo
Background: Very low-coverage (0.1 to 1×) whole genome sequencing (WGS) has become a promising and affordable approach to discover genomic variants of human populations for genome-wide association study (GWAS). To support genetic screening using preimplantation genetic testing (PGT) in a large population, the sequencing coverage goes below 0.1× to an ultra-low level. However, the feasibility and effectiveness of ultra-low-coverage WGS (ulcWGS) for GWAS remains undetermined. Methods: We built a pipeline to carry out analysis of ulcWGS data for GWAS. To examine its effectiveness, we benchmarked the accuracy of genotype imputation at the combination of different coverages below 0.1× and sample sizes from 2000 to 16,000, using 17,844 embryo PGT samples with approximately 0.04× average coverage and the standard Chinese sample HG005 with known genotypes. We then applied the imputed genotypes of 1744 transferred embryos who have gestational ages and complete follow-up records to GWAS. Results: The accuracy of genotype imputation under ultra-low coverage can be improved by increasing the sample size and applying a set of filters. From 1744 born embryos, we identified 11 genomic risk loci associated with gestational ages and 166 genes mapped to these loci according to positional, expression quantitative trait locus, and chromatin interaction strategies. Among these mapped genes, CRHBP, ICAM1, and OXTR were more frequently reported as preterm birth related. By joint analysis of gene expression data from previous studies, we constructed interrelationships of mainly CRHBP, ICAM1, PLAGL1, DNMT1, CNTLN, DKK1, and EGR2 with preterm birth, infant disease, and breast cancer. Conclusions: This study not only demonstrates that ulcWGS could achieve relatively high accuracy of adequate genotype imputation and is capable of GWAS, but also provides insights into the associations between gestational age and genetic variations of the fetal embryos from Chinese population.

20 April 2020 in World Wide Web
Verified
Journal Article
Closed access
PDF file
CRChangwei Ren
Changwei Ren
LALixingjian An
Lixingjian An
ZGZhaoquan Gu
Zhaoquan Gu
YWYuexuan Wang
Yuexuan Wang
YGYunjun Gao
Yunjun Gao

23 February 2014 in Journal of Combinatorial Optimization
Verified
Journal Article
Closed access
PDF file
YWYuepeng Wang
Yuepeng Wang
YWYuexuan Wang
Yuexuan Wang
Dongxiao YuDongxiao Yu
Dongxiao Yu
JYJiguo Yu
Jiguo Yu
FLFrancis C Lau
Francis C Lau

18 May 2021 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZFZunlei Feng
Zunlei Feng
ZWZhonghua Wang
Zhonghua Wang
XWXinchao Wang
Xinchao Wang
XZXiuming Zhang
Xiuming Zhang
LCLechao Cheng
Lechao Cheng
MSMingli Song
Mingli Song
The microvascular invasion (MVI) is a major prognostic factor in hepatocellular carcinoma, which is one of the malignant tumors with the highest mortality rate. The diagnosis of MVI needs discovering the vessels that contain hepatocellular carcinoma cells and counting their number in each vessel, which depends heavily on experiences of the doctor, is largely subjective and time-consuming. However, there is no algorithm as yet tailored for the MVI detection from pathological images. This paper collects the first pathological liver image dataset containing $522$ whole slide images with labels of vessels, MVI, and hepatocellular carcinoma grades. The first and essential step for the automatic diagnosis of MVI is the accurate segmentation of vessels. The unique characteristics of pathological liver images, such as super-large size, multi-scale vessel, and blurred vessel edges, make the accurate vessel segmentation challenging. Based on the collected dataset, we propose an Edge-competing Vessel Segmentation Network (EVS-Net), which contains a segmentation network and two edge segmentation discriminators. The segmentation network, combined with an edge-aware self-supervision mechanism, is devised to conduct vessel segmentation with limited labeled patches. Meanwhile, two discriminators are introduced to distinguish whether the segmented vessel and background contain residual features in an adversarial manner. In the training stage, two discriminators are devised to compete for the predicted position of edges. Exhaustive experiments demonstrate that, with only limited labeled patches, EVS-Net achieves a close performance of fully supervised methods, which provides a convenient tool for the pathological liver vessel segmentation. Code is publicly available at https://github.com/wang97zh/EVS-Net.