Article
Computer Science, Information Systems
Dongqing Zhang, Yucheng Dong, Zhaoxia Guo
Summary: The paper introduces a novel turning point-based offline map matching algorithm, which improves matching accuracy and efficiency by segmenting the entire trajectory into sub-trajectories and selecting the best-matched path from the K-shortest paths. Extensive experiments show that the algorithm outperforms five benchmark algorithms in terms of correctly matched percentages, incorrectly matched percentages, and matching speeds.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Banqiao Chen, Chibiao Ding, Wenjuan Ren, Guangluan Xu
Summary: High-quality digital road maps are essential for location-based services and smart city applications. Generating maps from massive GPS trajectory data poses challenges due to low sampling rates and multi-level disparity problems. The presented GPS trajectory data-based road tracking algorithm, with an active contour-based road centerline refinement algorithm, can produce higher quality maps with fewer zig-zag roads.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Computer Science, Artificial Intelligence
Chuanming Chen, Zhen Ye, Fan Hu, Shan Gong, Liping Sun, Qingying Yu
Summary: This paper introduces a trajectory-clustering method based on road-network-sensitive features, which effectively addresses the issue of similarity metrics among different road-network trajectories. By combining overall vehicle motion trends and road characteristics, the method clusters trajectories more effectively and improves its overall performance.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Engineering, Civil
Qingying Yu, Fan Hu, Zhen Ye, Chuanming Chen, Liping Sun, Yonglong Luo
Summary: Accurately mapping GPS trajectories to the road network is crucial for studying trajectory data applications. This study proposes a novel offline map matching algorithm based on road network topology to address the low efficiency and poor accuracy issues of the selective look-ahead map matching algorithm. The algorithm removes noise points, segments the trajectory data, selects candidate arcs, and matches the segmented data to the road network using error ellipses. Experimental results demonstrate that this algorithm is more efficient and robust for high-frequency trajectories compared to other map matching algorithms.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Dawen Xia, Bingqi Shen, Yongling Zheng, Wenyong Zhang, Dewei Bai, Yang Hu, Huaqing Li
Summary: In this paper, a Bidirectional-A-star-based Ant Colony Optimization (BiA*-ACO) algorithm is proposed to solve the problems of high fuel consumption and severe traffic congestion. Experimental results show that the BiA*-ACO algorithm is at least 47.05% more efficient than the traditional ACO algorithm on small data sets and at least 49.81% more efficient than ACO, Dijkstra, and Bellman-Ford on large GPS trajectory data sets. Furthermore, it reduces the length of the recommended fastest route compared to other algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Xiaohan Wang, Zengyu He, Pei Wang, Xinmeng Zha, Zimin Gong
Summary: Due to limitations of positioning devices, GPS positioning data may have errors compared to actual locations on the map, requiring processing to improve usability. Existing map matching methods have issues with circular road sections, leading to the proposal of a contextual voting map matching method. The effectiveness of this method was verified through experiments.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Chemistry, Analytical
Amal Al-Dawsari, Isra Al-Turaiki, Heba Kurdi
Summary: This paper introduces an online machine learning algorithm IAM for analyzing large amounts of dynamic data in IoT environments. IAM outperforms classic offline classifiers in terms of time and space overheads, and achieves excellent performance in multiple metrics. The experimental results demonstrate the potential and effectiveness of IAM in big data analytics in various areas.
Article
Chemistry, Multidisciplinary
Feng Qu, Wentao Yu, Kui Xiao, Chaofan Liu, Weirong Liu
Summary: This paper proposes a hybrid scheme using mutual learning and adaptive ant colony optimization (MuL-ACO) for trajectory generation and optimization of mobile robots in complex and uneven environments. The proposed scheme utilizes a 2D-H map to describe the uneven environment, and incorporates adaptive ant colony algorithm based on simulated annealing (SA) and mutual learning algorithm to generate collision-free trajectories with high comprehensive quality. Experimental results demonstrate the effectiveness of the proposed scheme in uneven environments.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Ge Cui, Wentao Bian, Xin Wang
Summary: Map matching is a crucial preprocessing step for many GPS trajectory-based applications. The conventional map matching methods based on hidden Markov model can suffer from decreased effectiveness and efficiency in dense road networks. This study proposes a segment-based hidden Markov model method to improve the performance of map matching by segmenting GPS trajectories and searching for candidate road segment sequences.
Article
Computer Science, Information Systems
Yuejun Guo, Anton Bardera, Marta Fort, Rodrigo I. Silveira
Summary: This paper introduces a fast four-step density-based approach for constructing a road network from a set of trajectories. The method produces road networks of comparable or better quality than state-of-the-art methods, with fewer nodes and edges, and is scalable to large inputs through a split-and-merge strategy.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2021)
Article
Automation & Control Systems
Zhiwei Cao, Yichao Zhang, Jihong Guan, Shuigeng Zhou, Guanghui Wen
Summary: The proposed chaotic ant colony optimized (CACO) link prediction algorithm shows significantly higher prediction accuracy and robustness in experiments, outperforming most state-of-the-art algorithms.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Mingqiang Wang, Lei Zhang, Zhiqiang Zhang, Zhenpo Wang
Summary: Efficient trajectory planning for intelligent vehicles in dynamic environments is achieved through a hybrid approach combining sampling-based and numerical optimization-based methods. A risk field model is used to evaluate risks with static and moving obstacles. The sampling-based approach generates collision-free trajectory candidates, considering curve smoothness, collision risk, and travel time. The optimization-based method optimizes the behavior trajectory for safety, vehicle dynamics stability, and driving comfort. Simulation results demonstrate the competency of the proposed framework in generating high-quality trajectories in real-time.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Telecommunications
Zongshan Wang, Hongwei Ding, Bo Li, Liyong Bao, Zhijun Yang, Qianlin Liu
Summary: This paper presents a novel cluster-based routing protocol called EECRAIFA, which optimizes network clustering using Self-Organizing Map neural network and firefly algorithm. It establishes inter-cluster routing using improved ant colony optimization and introduces a polling control mechanism to improve network throughput.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Patricia Gonzalez, Roberto Prado-Rodriguez, Attila Gabor, Julio Saez-Rodriguez, Julio R. Banga, Ramon Doallo
Summary: Understanding the deregulation of cell signaling networks is crucial for studying diseases. Computational models, such as CellNOpt, provide a systematic tool to analyze these complex biochemical networks. In this paper, the use of ant colony optimization is proposed as a novel method to improve the limitations of the existing genetic algorithm in CellNOpt, and its performance is demonstrated in liver cancer therapy research.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Hao Zhu, Jingru Liu, Li Jin, Guoan Zhang
Summary: This paper proposes a software-defined network (SDN) based unicast routing scheme in an urban traffic environment, which uses Dijkstra's algorithm to find a global optimal anchor path, solving the local optimum and network congestion problems of traditional geographic routing protocols in VANET.
Article
Computer Science, Artificial Intelligence
Sheng-Hao Wu, Zhi-Hui Zhan, Kay Chen Tan, Jun Zhang
Summary: This article proposes a novel orthogonal transfer (OT) method enabled by a cross-task mapping (CTM) strategy, which achieves high-quality knowledge transfer among heterogeneous tasks. The OT method handles task dimensionality differences and finds the best combination of different dimensions for high-quality knowledge transfer.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Automation & Control Systems
Xiao-Fang Liu, Jun Zhang, Jun Wang
Summary: This article proposes a cooperative particle swarm optimization algorithm to address challenges faced by cooperative coevolutionary algorithms in large-scale dynamic optimization. By introducing a balanced resource allocation mechanism, the algorithm effectively reacts to environmental changes and optimizes fitness functions with multiple peaks and uneven subproblems. Experimental results demonstrate its competitiveness with state-of-the-art algorithms in terms of objective function values and response efficiency to environmental changes.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Feng-Feng Wei, Wei-Neng Chen, Qing Li, Sang-Woon Jeon, Jun Zhang
Summary: This article defines distributed expensive constrained optimization problems (DECOPs) and proposes a distributed evolutionary constrained optimization algorithm with on-demand evaluation (DEAOE). DEAOE adaptively evolves different constraints in an asynchronous way through on-demand evaluation, improving population convergence and diversity. Experimental results demonstrate that DEAOE outperforms centralized state-of-the-art surrogate-assisted evolutionary algorithms (SAEAs) in terms of performance and efficiency.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Engineering, Civil
Wanyi Zhou, Xiaolin Xiao, Yue-Jiao Gong, Jia Chen, Jun Fang, Naiqiang Tan, Nan Ma, Qun Li, Chai Hua, Sang-Woon Jeon, Jun Zhang
Summary: This study proposes a method of formulating the traffic network as a temporal attributed graph and performing node representation learning on it to address the problem of travel time estimation. The learned representation can jointly exploit dynamic traffic conditions and the topology of the road network, and estimate travel time using a route-based spatio-temporal dependence learning module.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Yue-Jiao Gong, Ting Huang, Yi-Ning Ma, Sang-Woon Jeon, Jun Zhang
Summary: This paper focuses on the multiple-trajectory planning problem for automatic underwater vehicles (AUVs) and proposes a comprehensive model that considers the complexity of underwater environments, efficiency of each trajectory, and diversity among different trajectories. To solve this problem, an ant colony-based trajectory optimizer is developed, incorporating a niching strategy, decayed alarm pheromone measure, and diversified heuristic measure for improved search effectiveness and efficiency. Experimental results demonstrate that the proposed algorithm not only provides multiple AUV trajectories for flexible choice, but also outperforms state-of-the-art algorithms in terms of single trajectory efficiency.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jian-Yu Li, Zhi-Hui Zhan, Jin Xu, Sam Kwong, Jun Zhang
Summary: This article proposes a novel estimation of distribution algorithm (EDA), named surrogate-assisted hybrid-model EDA (SHEDA), for efficient hyperparameters optimization. The algorithm design includes hybrid-model EDA, orthogonal initialization strategy, and surrogate-assisted multi-level evaluation method. Experimental results show that SHEDA is very effective and efficient for hyperparameters optimization on widely used classification benchmark problems.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Junna Zhang, Degang Chen, Qiang Yang, Yiqiao Wang, Dong Liu, Sang-Woon Jeon, Jun Zhang
Summary: This paper proposes a novel differential evolution framework called proximity ranking-based multimodal differential evolution (PRMDE) for multimodal optimization. Through the cooperative cooperation among three main mechanisms, PRMDE is capable of locating multiple global optima simultaneously. Experimental results show that PRMDE is effective and achieves competitive or even better optimization performance than several representative methods.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Dong Liu, Hao He, Qiang Yang, Yiqiao Wang, Sang-Woon Jeon, Jun Zhang
Summary: This paper proposes a simple and effective mutation scheme named DE/current-to-rwrand/1 to enhance the optimization ability of differential evolution (DE) in solving complex optimization problems. The proposed mutation strategy, called function value ranking aware differential evolution (FVRADE), balances high diversity and fast convergence of the population. Experimental results demonstrate that FVRADE outperforms several state-of-the-art methods and shows promise in solving real-world optimization problems.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Qiang Yang, Gong-Wei Song, Xu-Dong Gao, Zhen-Yu Lu, Sang-Woon Jeon, Jun Zhang
Summary: High-dimensional optimization problems are becoming increasingly difficult due to interacting variables. This paper presents a random elite ensemble learning swarm optimizer (REELSO) inspired by human observational learning theory to effectively tackle such problems. REELSO partitions the swarm into elite and non-elite groups, allowing non-elite particles to observe and learn from elite particles, promoting convergence and maintaining swarm diversity. Experimental results demonstrate that REELSO performs competitively or even outperforms state-of-the-art approaches for high-dimensional optimization.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Information Systems
En Zhang, Zihao Nie, Qiang Yang, Yiqiao Wang, Dong Liu, Sang-Woon Jeon, Jun Zhang
Summary: Facing complex large-scale optimization problems, most existing optimization algorithms lose their effectiveness. In order to effectively solve this type of problem, we propose a heterogeneous cognitive learning particle swarm optimization algorithm (HCLPSO). Unlike most particle swarm optimization algorithms, HCLPSO partitions particles into superior and inferior categories based on their fitness and treats them differently. With the collaboration of two learning mechanisms, HCLPSO can effectively explore the search space and exploit the found optimal zones to find optimal solutions.
INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Xiao-Fang Liu, Yongchun Fang, Zhi-Hui Zhan, Jun Zhang
Summary: Cooperative heterogeneous multirobot systems have been gaining attention recently for executing complex tasks using multiple heterogeneous robots. Allocating these robots to cooperative tasks is a significant optimization problem, and existing methods are not sufficient to address it. This study proposes a multiobjective model and a strength learning particle swarm optimization (SLPSO) to optimize multiple objectives. Experimental results demonstrate that SLPSO outperforms existing algorithms in terms of inverted generational distance and hypervolume metrics.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Feng-Feng Wei, Wei-Neng Chen, Wentao Mao, Xiao-Min Hu, Jun Zhang
Summary: This article proposes an efficient two-stage surrogate-assisted differential evolution (eToSA-DE) algorithm to handle expensive inequality constraints. The algorithm trains a surrogate model for the degree of constraint violation, with the type of surrogate changing during the evolution process. Both types of surrogates are constructed using individuals selected by the boundary training data selection strategy. A feasible exploration strategy is devised to search for promising areas. Extensive experiments demonstrate that the proposed method can achieve satisfactory optimization results and significantly improve the efficiency of the algorithm.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Xiao-Fang Liu, Jun Zhang, Jun Wang
Summary: This article presents a cooperative differential evolution algorithm with an attention-based prediction strategy for dynamic multiobjective optimization. Multiple populations are used to optimize multiple objectives and find subparts of the Pareto front. The algorithm achieves a balanced approximation of the Pareto front and adapts to changes in the environment by using a new attention-based prediction strategy. Experimental results demonstrate the superiority of the proposed method to state-of-the-art algorithms.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Tan-Lin Xiao, Qiang Yang, Xu-Dong Gao, Zhen-Yu Lu, Yuan-Yuan Ma, Sang-Woon Jeon, Jun Zhang
Summary: Different from previous studies, this paper uses large-scale swarm optimizers to optimize the path planning of UAV, resulting in a subtler and smoother path. The variation encoding scheme effectively avoids repetitive anchor points and optimizes a large number of anchor points. Experimental results show that SDLSO achieves the best performance when cooperating with the devised encoding scheme.
PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2023
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Xudong Gao, Wenjie Cao, Qiang Yang, Jun Zhang
Summary: Maximum power transfer efficiency is a crucial technical issue in wireless power systems. This paper proposes a maximum efficiency design scheme based on particle swarm optimization, which searches for the maximum efficiency point of the wireless power transfer system by adjusting the parameters of the impedance matching network. The proposed scheme improves the system efficiency by 0.6%.
2023 15TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE, ICACI
(2023)