Article
Chemistry, Analytical
Liping Huang, Zhenghuan Li, Ruikang Luo, Rong Su
Summary: Despite the availability of sensing data in intelligent transportation systems, missing data is still a problem in traffic estimation. Existing studies have mainly focused on randomly missing data and neglected the distinction between missing data links. This paper proposes a general linear model based on probabilistic principal component analysis for imputing non-randomly missing traffic speed data.
Article
Computer Science, Artificial Intelligence
Tao Su, Ying Shi, Jicheng Yu, Changxi Yue, Feng Zhou
Summary: A novel statistical and machine learning-based imputation method is proposed for handling missing values in smart grid data, showing superior performance compared to commonly used methods. The method combines one-dimensional interpolation and linear compensation to capture global and local variations, reducing RMSE by 29.19% and MAE by 44.73% on average, with the best R-2 closest to 1.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Peixiao Wang, Yan Zhang, Tao Hu, Tong Zhang
Summary: This study proposes a dynamic temporal graph neural network model that considers missing values and dynamic spatial relationships for urban traffic flow prediction. The model achieves good prediction results and outperforms existing baselines on a real traffic dataset.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2023)
Article
Construction & Building Technology
Zhi Ma, Chung-Bang Yun, Hua-Ping Wan, Yanbin Shen, Feng Yu, Yaozhi Luo
Summary: This paper presents an anomaly detection algorithm based on PPCA for long-term structural health monitoring systems. By establishing a baseline model and projecting onto principal vectors, anomaly indices are evaluated to detect structural damage, while also capable of handling incomplete data.
STRUCTURAL CONTROL & HEALTH MONITORING
(2021)
Article
Automation & Control Systems
Guohao Song, Jianhua Zhang, Yingshang Ge, Kangyi Zhu, Zhensheng Fu, Luchuan Yu
Summary: A novel tool wear predicting method is proposed in this paper, utilizing a weighted multi-kernel relevance vector machine and integrated radial basis function-based probabilistic kernel principal component analysis for modeling and feature extraction, which significantly improves the accuracy and robustness of the model. Experimental results demonstrate the effectiveness of the method in accurately monitoring tool wear in industrial applications, with strong practical value.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Automation & Control Systems
Wei Fan, Qinqin Zhu, Shaojun Ren, Liang Zhang, Fengqi Si
Summary: This article proposes a multistep dynamic predictive monitoring scheme that can handle measurement noise, and introduces a dynamic index to detect dynamic anomalies.
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2022)
Article
Automation & Control Systems
Alireza Memarian, Santhosh Kumar Varanasi, Biao Huang
Summary: Industrial processes often operate in multiple operating modes, with outputs measured at a slower rate than inputs due to reasons such as sensor failures causing outliers. This paper proposes a mixture robust semisupervised probabilistic principal component regression model to effectively handle these challenges and demonstrates its performance through numerical examples and an experimental case study.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Automation & Control Systems
Jicong Fan, Tommy W. S. Chow, S. Joe Qin
Summary: In this article, a nonlinear method is proposed to handle the missing data problem in industrial processes. The proposed method, called fast incremental nonlinear matrix completion (FINLMC), allows for missing data imputation in both offline modeling and online monitoring stages. The effectiveness of the method is supported by theoretical analysis and experiments, which demonstrate its ability to improve fault detection rate and reduce false alarms in nonlinear processing monitoring with missing data.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Engineering, Electrical & Electronic
Yuchen Shi, Nan Chen
Summary: This paper proposes a novel method to model power generation distribution under various weather conditions, aiming to address the uncertainty in renewable energy generation and showing better performance in short-term modeling.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Qin Lu, Georgios B. Giannakis
Summary: This work introduces a method for inferring node values in networks based on topology information, particularly suitable for multi-relational graphs. The method models stationary graph processes using a Gaussian mixture prior and considers a first-order topology-dependent Gaussian transition prior to handle nonstationary nodal processes. Novel graph-adaptive solvers are obtained through the EM algorithm to reconstruct node features and quantify the contribution of each relation.
IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS
(2021)
Article
Computer Science, Information Systems
Jiandong Bai, Jiawei Zhu, Yujiao Song, Ling Zhao, Zhixiang Hou, Ronghua Du, Haifeng Li
Summary: An A3T-GCN model was proposed to capture global temporal dynamics and spatial correlations in traffic flows. Experimental results demonstrate the effectiveness and robustness of the model in improving prediction accuracy.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Computer Science, Artificial Intelligence
Pei Li, Wenlin Zhang, Chengjun Lu, Rui Zhang, Xuelong Li
Summary: A novel robust kernel principal component analysis method with optimal mean (RKPCA-OM) is proposed to enhance the robustness of KPCA by automatically eliminating the optimal mean. The theoretical proof guarantees the convergence of the algorithm and the obtained optimal subspaces and means. Exhaustive experimental results validate the superiority of the proposed method.
Article
Computer Science, Artificial Intelligence
Bing Yang, Yan Kang, YaoYao Yuan, Xin Huang, Hao Li
Summary: Real-time, accurate and comprehensive traffic flow data is crucial for intelligent transportation systems. This paper introduces a new Spatio-Temporal Learnable Bidirectional Attention Generative Adversarial Networks (ST-LBAGAN) for missing traffic data imputation, which achieved improved performance on the Beijing taxi GPS dataset by optimizing a new objective function.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Biodiversity Conservation
Mu Xia, Kun Jia, Wenwu Zhao, Shiliang Liu, Xiangqin Wei, Bing Wang
Summary: This study utilizes an Ecological Vulnerability Index (EVI) and 17 indicators to analyze the ecological vulnerability threats faced by the Qinghai-Tibetan Plateau over the past 15 years, with results indicating vegetation as the primary driver of ecological vulnerability. Significant variations in ecological vulnerability trends were observed between Tibet Autonomous Region and Qinghai Province.
ECOLOGICAL INDICATORS
(2021)
Article
Engineering, Chemical
Jiaxin Zhang, Wenjia Luo, Yiyang Dai, Yuman Yao
Summary: This article proposes a multivariate statistical process monitoring method for chemical process fault diagnosis. By combining the cycle temporal algorithm with dynamic kernel principal component analysis and multiway dynamic kernel principal component analysis fault detection algorithms, continuous and batch process fault detection is achieved. Additionally, a fault variable identification model based on reconstructed-based contribution is introduced for determining the cause of the fault. Experimental results show that the proposed method has better detection effects compared to other methods, and it accurately locates the root cause of the fault and determines the fault path using the reconstruction-based contribution model.
CHINESE JOURNAL OF CHEMICAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Xinyu Peng, Fei-Yue Wang, Li Li
Summary: This article studies a new data selection method called the "nontypicality sampling scheme" to improve the generalization performance of deep neural networks. The scheme biases the solution towards wider minima, resulting in better performance. Experimental results confirm the effectiveness of the scheme and suggest its potential benefits for various variants of minibatch stochastic gradient descent.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Feng Mao, Zhiheng Li, Li Li
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2023)
Article
Engineering, Electrical & Electronic
Chi Zhang, Zihang Lin, Liheng Xu, Zongliang Li, Wei Tang, Yuehu Liu, Gaofeng Meng, Le Wang, Li Li
Summary: The key procedure of haze image synthesis with adversarial training is to disentangle the style feature involved in haze synthesis from the content feature representing the invariant semantic content. Previous methods failed to achieve complete content-style disentanglement, while this paper proposes a self-supervised style regression model that can suppress the content information in the style feature. The study also demonstrates the impact of synthesized haze data on the generalization ability of vehicle detectors.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Civil
Li Li, Can Zhao, Xiao Wang, Zhiheng Li, Long Chen, Yisheng Lv, Nan-Ning Zheng, Fei-Yue Wang
Summary: This study focuses on improving driving safety of autonomous vehicles by setting up a set of decision rules. Three essential design principles are summarized, and a nine-step communication-decision model is established. The decision rules aim to be ambiguity-free and readily computable to facilitate understanding between human drivers and autonomous vehicles.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Huile Xu, Christos G. Cassandras, Li Li, Yi Zhang
Summary: This study compares the performance of four representative cooperative driving strategies, finding that the Monte Carlo Tree Search-based strategy achieves the best traffic efficiency and fuel consumption performance. Dynamic Resequencing and MCTS strategies both perform well in all metrics. The influence of geometric shape on strategies is more significant than that of arrival rates.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Huile Xu, Wei Xiao, Christos G. Cassandras, Yi Zhang, Li Li
Summary: This paper addresses the problem of safely controlling Connected and Automated Vehicles (CAVs) crossing a signal-free intersection with multiple lanes. A general framework is proposed to convert the multi-lane intersection problem into decentralized optimal control problems for each CAV. By combining optimal control and control barrier functions, the proposed method efficiently tracks feasible unconstrained CAV trajectories while ensuring the satisfaction of all safety constraints.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Yuqing Guo, Danya Yao, Bai Li, Zimin He, Haichuan Gao, Li Li
Summary: This paper investigates the impact of road shoulders and slopes on vehicle trajectory planning and addresses the challenges posed by these impacts to existing planners. A two-stage trajectory planning framework is proposed, which improves the hybrid A* algorithm by incorporating spatially dependent constraints and uses optimization to enhance the smoothness and quality of the trajectory.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xinyu Peng, Jiawei Zhang, Fei-Yue Wang, Li Li
Summary: Deep learning has become the most powerful machine learning tool in the last decade, but the problem of efficiently training deep neural networks remains. The information bottleneck theory suggests that the optimization process consists of fitting and compression phases, and typicality sampling can help accelerate the training of deep networks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Zimin He, Huaxin Pei, Yuqing Guo, Danya Yao, Yi Zhang, Li Li
Summary: This paper investigates cooperative driving strategies at on-ramps and compares the performance of five representative strategies. Simulation results demonstrate that the DP-based, grouping-based, and rule-based strategies exhibit good computation time and traffic efficiency, making them recommended for practical use. The study also reveals that the modified DP-based and rule-based strategies achieve a better trade-off between traffic efficiency and fairness. All compared cooperative driving strategies will be integrated into CAVSim, a simulation platform dedicated to CAVs, for easy access by researchers and the community.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Yuxuan Zhu, Zhiheng Li, Feiyue Wang, Li Li
Summary: By designing an LSTM-VAE based generating model, we are able to generate rational control sequences that can push vehicles toward extreme operating conditions and analyze them through simulation tests.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Engineering, Civil
Feng Mao, Zhiheng Li, Yilun Lin, Li Li
Summary: Recent studies have attempted to apply multi-agent deep reinforcement learning (MARL) for large-scale traffic signal control but have overlooked arterial traffic signal control. This study proposes a multi-agent attention-based soft actor-critic (MASAC) model to address these issues. The MASAC method significantly outperforms existing MARL algorithms and the multiband-based method according to testing results.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Jiawei Zhang, Shen Li, Li Li
Summary: Connected and automated vehicles (CAVs) have the potential to improve traffic safety and efficiency. Cooperative driving, enabled by revolutionary CAVs, can make signalized intersections signal-free and enhance traffic efficiency by organizing CAVs' passing order. However, finding the optimal passing order is a challenging task. In this study, we propose a novel cooperative driving algorithm called AlphaOrder, which combines offline deep learning and online tree searching to find near-optimal passing orders in real-time. AlphaOrder reduces travel delay by over 20% compared to the best-so-far algorithm when there are 40 CAVs.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Long Chen, Yuchen Li, Chao Huang, Bai Li, Yang Xing, Daxin Tian, Li Li, Zhongxu Hu, Xiaoxiang Na, Zixuan Li, Siyu Teng, Chen Lv, Jinjun Wang, Dongpu Cao, Nanning Zheng, Fei-Yue Wang
Summary: Interest in autonomous driving and intelligent vehicles is growing rapidly due to their convenience, safety, and economic benefits. However, existing surveys are limited in scope and lack systematic summaries and future research directions.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Engineering, Civil
Jiawei Zhang, Cheng Chang, Zimin He, Wenqin Zhong, Danya Yao, Shen Li, Li Li
Summary: This paper introduces CAVSim, a novel microscopic traffic simulator for connected and automated vehicles (CAVs), which addresses the deficiencies of traditional simulators in planning and modeling vehicles and providing standardized algorithms for multi-CAV cooperative driving.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Long Chen, Yuchen Li, Chao Huang, Yang Xing, Daxin Tian, Li Li, Zhongxu Hu, Siyu Teng, Chen Lv, Jinjun Wang, Dongpu Cao, Nanning Zheng, Fei-Yue Wang
Summary: Interest in autonomous driving and intelligent vehicles is rapidly growing due to their convenience, safety, and economic benefits. Existing surveys in this field are limited to specific tasks and lack systematic summaries and future research directions. This article consists of three parts, with the first part being a survey that covers the history, milestones, and future research directions of AD and IVs. The second part reviews the development of control, computing system design, communication, HD maps, testing, and human behaviors in IVs. The third part focuses on the perception and planning sections. The objective of this article is to provide a comprehensive overview of AD and IVs, summarize the latest milestones, and guide beginners in understanding their development. This work is expected to offer valuable insights to researchers and beginners, bridging the gap between the past and future.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Transportation Science & Technology
Yue Zhao, Liujiang Kang, Huijun Sun, Jianjun Wu, Nsabimana Buhigiro
Summary: This study proposes a 2-population 3-strategy evolutionary game model to address the issue of subway network operation extension. The analysis reveals that the rule of maximum total fitness ensures the priority of evolutionary equilibrium strategies, and proper adjustment minutes can enhance the effectiveness of operation extension.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Hongtao Hu, Jiao Mob, Lu Zhen
Summary: This study investigates the challenges of daily storage yard management in marine container terminals considering delayed transshipment of containers. A mixed-integer linear programming model is proposed to minimize various costs associated with transportation and yard management. The improved Benders decomposition algorithm is applied to solve the problem effectively and efficiently.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Zhandong Xu, Yiyang Peng, Guoyuan Li, Anthony Chen, Xiaobo Liu
Summary: This paper studied the impact of range anxiety among electric vehicle drivers on traffic assignment. Two types of range-constrained traffic assignment problems were defined based on discrete or continuous distributed range anxiety. Models and algorithms were proposed to solve the two types of problems. Experimental results showed the superiority of the proposed algorithm and revealed that drivers with heightened range anxiety may cause severe congestion.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Chuanjia Li, Maosi Geng, Yong Chen, Zeen Cai, Zheng Zhu, Xiqun (Michael) Chen
Summary: Understanding spatial-temporal stochasticity in shared mobility is crucial, and this study introduces the Bi-STTNP prediction model that provides probabilistic predictions and uncertainty estimations for ride-sourcing demand, outperforming conventional deep learning methods. The model captures the multivariate spatial-temporal Gaussian distribution of demand and offers comprehensive uncertainty representations.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Benjamin Coifman, Lizhe Li
Summary: This paper develops a partial trajectory method for aligning views from successive fixed cameras in order to ensure high fidelity with the actual vehicle movements. The method operates on the output of vehicle tracking to provide direct feedback and improve alignment quality. Experimental results show that this method can enhance accuracy and increase the number of vehicles in the dataset.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Mohsen Dastpak, Fausto Errico, Ola Jabali, Federico Malucelli
Summary: This article discusses the problem of an Electric Vehicle (EV) finding the shortest route from an origin to a destination and proposes a problem model that considers the occupancy indicator information of charging stations. A Markov Decision Process formulation is presented to optimize the EV routing and charging policy. A reoptimization algorithm is developed to establish the sequence of charging station visits and charging amounts based on system updates. Results from a comprehensive computational study show that the proposed method significantly reduces waiting times and total trip duration.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
