Article
Automation & Control Systems
Wen Shi, Wei-Neng Chen, Sam Kwong, Jie Zhang, Hua Wang, Tianlong Gu, Huaqiang Yuan, Jun Zhang
Summary: In this article, a group insurance portfolio model is proposed for investment allocation of multiple insurance policies, with a coevolutionary estimation of distribution algorithm (EDA) utilized to solve the problem. The approach decomposes the group insurance portfolio problem into single-insured insurance portfolio problems, and cooperates with a particle swarm optimization algorithm to optimize the allocation proportions for each insured. Experimental results validate the effectiveness of the proposed approach for the group insurance portfolio problem.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Mathematics
Omer Ali, Qamar Abbas, Khalid Mahmood, Ernesto Bautista Thompson, Jon Arambarri, Imran Ashraf
Summary: This study introduces a competitive coevolution process to enhance the capability of Phasor PSO (PPSO) for global optimization problems. Experimental results show that the improved competitive multi-swarm PPSO (ICPPSO) algorithm achieves a dominating performance, with average improvements of 15%, 20%, 30%, and 35% over PPSO and FMPSO.
Article
Energy & Fuels
Hossein Izadi, Morteza Roostaei, Seyed Abolhassan Hosseini, Mohammad Soroush, Mahdi Mahmoudi, Noel Devere-Bennett, Juliana Y. Leung, Vahidoddin Fattahpour
Summary: This paper presents an approach to estimate permeability based on particle size distribution and porosity. By studying the influencing factors and optimizing the coefficients of the correlations, permeability values were successfully predicted, and the applications and novelties of the proposed method were discussed.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Geochemistry & Geophysics
Qin Li, Wei Wang
Summary: The study successfully inverted AVO data in orthotropic media through the combination of PSO and SA, introducing a hybrid SA-PSO algorithm that overcomes local minima and improves global optimization. The proposed method demonstrates stable inversion results with small errors, showing potential for reservoir identification and prediction in anisotropic media.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Multidisciplinary Sciences
Olatunji A. Akinola, Jeffrey O. Agushaka, Absalom E. Ezugwu
Summary: Selecting appropriate feature subsets is an important task in machine learning. This paper presents the BDMO algorithm, a binary version of the dwarf mongoose optimization, to solve the high-dimensional feature selection problem. The experimental results show that the BDMO algorithm outperforms other methods in terms of both performance and stability.
Article
Computer Science, Artificial Intelligence
Claudiu Pozna, Radu-Emil Precup, Erno Horvath, Emil M. Petriu
Summary: This article presents a hybrid metaheuristic optimization algorithm that combines particle filter (PF) and particle swarm optimization (PSO) algorithms. The algorithm is applied to the optimal tuning of proportional-integral-fuzzy controllers for position control of integral-type servo systems, resulting in reduced energy consumption. A comparison with other metaheuristic algorithms is provided at the end of the article.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Automation & Control Systems
An Song, Wei-Neng Chen, Tianlong Gu, Huaqiang Yuan, Sam Kwong, Jun Zhang
Summary: This study proposes a distributed VNE system with historical archives and metaheuristic approaches to address the challenging issue of mapping virtual resources to substrate resources effectively. Experimental results demonstrate that the system can significantly improve embedding performance and scale well in scenarios of different scales.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Energy & Fuels
Leilei Shi, Junhui Gong, Chunjie Zhai
Summary: A hybrid optimization algorithm combining PSO and GA showed improved performance in determining the pyrolysis kinetics of biomass, achieving higher accuracy and population diversity in the process.
Article
Computer Science, Artificial Intelligence
Christian L. Camacho-Villalon, Marco Dorigo, Thomas Stutzle
Summary: This paper proposes the use of automatic design to overcome the limitations of manually designing PSO algorithms. They develop a flexible software framework called PSO-X, which integrates the automatic configuration tool irace to select and configure high-performing PSO algorithms from a large number of algorithm components.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Review
Computer Science, Interdisciplinary Applications
Janmenjoy Nayak, H. Swapnarekha, Bighnaraj Naik, Gaurav Dhiman, S. Vimal
Summary: This article presents an in-depth analysis of the Particle Swarm Optimization (PSO) algorithm and its developments in different application domains. PSO is highly popular due to its simple structure and few algorithmic parameters, and it has shown excellent performance in areas such as networking, robotics, and image segmentation. The paper discusses the evolution of PSO and its improved variants, providing a scope for further development and inspiring researchers and practitioners to find innovative solutions for complex problems in various domains using PSO.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Chemistry, Multidisciplinary
Xueli Shen, Daniel C. Ihenacho
Summary: Particle swarm optimization and differential evolution are two nature-inspired global optimization algorithms used to simplify complex mathematical models and sensitivity methods in gas cyclone design, achieving optimal solutions by minimizing an objective function.
APPLIED SCIENCES-BASEL
(2021)
Article
Multidisciplinary Sciences
Pham Vu Hong Son, Nghiep Trinh Nguyen Dang
Summary: The study introduces a hybrid multi-verse optimizer model (hDMVO) that combines the multi-verse optimizer (MVO) and the sine cosine algorithm (SCA) to solve the discrete time-cost trade-off problem (DTCTP). The optimality of the algorithm is evaluated using 23 benchmark test functions, demonstrating its competitiveness with other algorithms. The performance of hDMVO is further evaluated using four benchmark test problems, showing its superiority in time-cost optimization for large-scale and complex projects compared to previous algorithms.
SCIENTIFIC REPORTS
(2023)
Article
Automation & Control Systems
Li Li, Liang Chang, Tianlong Gu, Weiguo Sheng, Wanliang Wang
Summary: This paper introduces a novel multiobjective PSO algorithm named MOPSO/DD, which utilizes the dominant difference norm to tackle MaOPs. Experimental results demonstrate that the algorithm is competitive with state-of-the-art approaches on benchmark problems.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Acoustics
Zhaoxi Li, Dongdong Chen, Chunlong Fei, Di Li, Wei Feng, Yintang Yang
Summary: An optimization strategy for ultrasonic transducer (UT) with multimatching layer was developed to improve performance. Using piezoelectric equivalent circuit model and neural network models, the optimized UT showed excellent performance with high accuracy in measuring thickness.
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Mustafa Seker
Summary: This study evaluates the function parameters of different mathematical models for modeling lightning impulses using an optimization-based curve-fitting method. The results show that this approach can accurately extract various characteristic parameters of lightning impulses and provide an accurate description of artificial lightning current waveforms.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Computer Science, Theory & Methods
Bo Huang, Mengchu Zhou, Xiaoyu Sean Lu, Abdullah Abusorrah
Summary: Resource allocation systems (RASs) are commonly used discrete event systems in the industry, where available resources are allocated to optimize performance criteria. This paper provides a tutorial and comprehensive literature survey on RG-based RSP methods, presenting a framework for RSPs and their PNs, construction methods, scheduling objectives, search strategies, heuristic functions, and future research directions.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Fatemeh Mohammadi Shakiba, S. Mohsen Azizi, Mengchu Zhou, Abdullah Abusorrah
Summary: This paper surveys recent machine learning-based techniques for fault detection, classification, and location estimation in transmission lines. It emphasizes the need for faster and more accurate fault identification tools and introduces various machine learning methodologies and artificial neural networks used in diagnosing transmission line faults.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Engineering, Electrical & Electronic
Hongyu Xie, Dong Zhang, Jun Wang, MengChu Zhou, Zhengcai Cao, Xiaobo Hu, Abdullah Abusorrah
Summary: This research proposes a semidirect multimap monocular SLAM system (SM-SLAM) that combines direct tracking and feature-based map maintenance with point features and line segments. The experimental results show that SM-SLAM can accurately reconstruct a sparse 3D map with geometrical structure information in low-textured environments at a speed of 30-40 Hz.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
ShouGuang Wang, Xin Guo, Oussama Karoui, MengChu Zhou, Dan You, Abdullah Abusorrah
Summary: This study focuses on the deadlock control problem in resource allocation systems using mixed-integer programming and iterative siphon control. It proposes a two-stage deadlock prevention policy, which avoids exhaustive enumeration and reachability analysis.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
SiYa Yao, Qi Kang, MengChu Zhou, Muhyaddin J. Rawa, Aiiad Albeshri
Summary: This article proposes an efficient discriminative manifold distribution alignment (DMDA) approach, which improves feature transferability by aligning both global and local distributions and refines a discriminative model by learning geometrical structures in manifold space. Extensive experiments show that DMDA outperforms other methods in both classification accuracy and time efficiency in domain adaptation tasks.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Chemistry, Multidisciplinary
Xiaoling Wang, Qi Kang, Mengchu Zhou, Zheng Fan, Aiiad Albeshri
Summary: Multi-task optimization (MTO) is a new evolutionary computation paradigm that solves multiple optimization tasks concurrently by utilizing task similarities and historical knowledge. This work proposes the individually guided multi-task optimization (IMTO) framework, which explores each individual to learn from other tasks, selects individuals with higher solving ability, and only inferior individuals learn from other tasks to improve knowledge transfer. The advantage of IMTO over multifactorial evolutionary framework and baseline solvers is verified through benchmark studies.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Yanlu Gong, Quanwang Wu, Mengchu Zhou, Junhao Wen
Summary: Multi-label learning aims to solve classification problems where instances are associated with a set of labels. This work proposes a novel approach called Self-paced Multi-label Co-Training (SMCT) that leverages the co-training paradigm to train two classifiers iteratively and communicate predictions on unlabeled data. Experimental evaluations demonstrate the competitive performance of SMCT compared to state-of-the-art methods.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Zizhen Zhang, Hong Liu, MengChu Zhou, Jiahai Wang
Summary: This article introduces the traveling salesman problem (TSP) and its dynamic versions (DTSP and DPDP). By improving the attention model, a deep reinforcement learning algorithm is proposed to solve DTSP and DPDP problems. Experimental results show that this method can capture dynamic changes and produce satisfactory solutions in a short time, with over 5% improvements observed in many cases compared to other baseline approaches.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Shangce Gao, MengChu Zhou, Ziqian Wang, Daiki Sugiyama, Jiujun Cheng, Jiahai Wang, Yuki Todo
Summary: This article introduces a single dendritic neuron model (DNM) with nonlinear information processing ability, which is extended to complex-valued domain. Experimental results demonstrate that this complex-valued DNM significantly outperforms real-valued DNM, complex-valued multi-layer perceptron, and other complex-valued neuron models.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Guiyuan Yuan, Jiujun Cheng, MengChu Zhou, Sheng Cheng, Shangce Gao, Changjun Jiang, Abdullah Abusorrah
Summary: Accurately processing dynamic evolution events is extremely challenging for autonomous vehicle groups in an urban scene, as they are affected by manned vehicles, roadside obstacles, traffic lights, and pedestrians. Existing work in this area has focused on highway scenes and cannot be directly applied to urban scenes due to different environmental factors and incomplete dynamic evolution events. In this study, a dynamic evolution method specifically designed for autonomous vehicle groups in urban scenes is proposed, which analyzes the reasons for dynamic evolution, abstracts five dynamic evolution events, and introduces a method to process them. Simulation results demonstrate that the proposed method outperforms the existing highway scene method in terms of connectivity, coupling, timeliness, and evolvability of vehicle groups.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Li Huang, MengChu Zhou, Kuangrong Hao, Hua Han
Summary: This paper proposes a distributed event-driven cooperative strategy for multirobot systems to autonomously patrol moving objects. It defines forward and backward utility functions as evaluation criteria for robots to choose patrol targets, and proposes three event types and a cooperative action considering energy consumption and visiting frequency to improve coordination among robots in their execution processes. Simulation experiments show that the proposed strategy has significant advantages in decreasing the average and maximum unvisited time of moving objects compared to the state-of-the-art. A marine pollution monitoring case is simulated to demonstrate the practicability of this strategy.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Huan Liu, Junqi Zhang, MengChu Zhou
Summary: This paper proposes an adaptive particle swarm optimizer that combines hierarchical learning with variable population to enhance the performance of the PSO algorithm. By introducing a heap-based hierarchy and adjusting the particle's level based on its current fitness, as well as eliminating redundant particles based on the population's evolution state, the swarm's exploratory and exploitative capabilities are improved.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Cybernetics
Yu Xie, Guanjun Liu, Chungang Yan, Changjun Jiang, MengChu Zhou
Summary: This study proposes a new model to extract transactional behaviors of credit card users and learn new transactional behavioral representations for fraud detection. The model utilizes time-aware gates and an attention module to capture long- and short-term transactional habits of users and extract behavioral motive and periodicity from historical transactions.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Guanyu Cai, Lianghua He, MengChu Zhou, Hesham Alhumade, Die Hu
Summary: This article explores the performance of adversarial-training-based unsupervised domain adaptation (UDA) methods with Lipschitz constraints when dealing with complex source and target datasets with large distribution discrepancies. The connection between Lipschitz constraints and the error bound of UDA is analyzed, demonstrating how Lipschitzness reduces the error bound. Experimental results show that considering the sample amount of the target domain, dimension, and batch size is crucial for the effectiveness and stability of UDA. The model performs well on standard benchmarks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
ChengRan Lin, ZhengCai Cao, MengChu Zhou
Summary: This study addresses the extended version of the flexible job-shop problem and proposes a learning-based cuckoo search algorithm to obtain reliable and high-quality schedules. By introducing a sparse autoencoder and a factorization machine, the algorithm achieves promising results. Numerical simulations show that it outperforms traditional methods.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)