Article
Computer Science, Artificial Intelligence
Manh Duong Phung, Quang Phuc Ha
Summary: This paper introduces a new algorithm named SPSO for UAV path planning, and demonstrates its superiority over other optimization algorithms in various scenarios through comparative experiments.
APPLIED SOFT COMPUTING
(2021)
Article
Remote Sensing
Zeyuan Ma, Jing Chen
Summary: An adaptive path planning method for UAVs in complex environments is proposed, which utilizes discrete global grid systems and a multi-scale discrete layered grid model, combined with particle swarm optimization algorithm, to address the path planning problem.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Computer Science, Information Systems
Xudong Li, Bin Tian, Shuaidong Hou, Xinxin Li, Yang Li, Chong Liu, Jingmin Li
Summary: An improved particle swarm optimization (PSO) algorithm was proposed to assign paths to three robots in a surface-mounted technology (SMT) machine, addressing the problem of cooperative work among right-angle coordinate robots in spacecraft structural plate mount tasks. The algorithm overcame the early convergence issue of traditional PSO and enhanced global search capability using an inertia weight update strategy and fuzzy control. Additionally, the introduction of genetic algorithm (GA) helped maintain particle diversity during the iterative process and further improved the efficiency of path planning.
Article
Computer Science, Information Systems
Yijun Hu, Jing Wang, Haojin He, Yiqiang Zhang, Shuo Cai, Anlu Xie, Zijun Zheng
Summary: This study integrated differential evolution and particle swarm optimization algorithms to address the autonomous planning of three-dimensional underwater inspection paths for autonomous underwater vehicles (AUVs). The proposed algorithm demonstrated significant improvements in convergence speed, accuracy, and stability under complex scenarios.
Article
Automation & Control Systems
Chen Huang, Xiangbing Zhou, Xiaojuan Ran, Jiamiao Wang, Huayue Chen, Wu Deng
Summary: The ACVDEPSO algorithm is proposed to solve the route planning problem for UAV in complicated environments. It improves the optimization performance by adaptively adjusting parameters, using cylinder vector and different evolution operators. The algorithm converts particle velocity to cylinder vector for path search and automatically selects parameters based on time and fitness values. The challenger based on differential evolution operator reduces the probability of falling into local optimum and accelerates convergence speed.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Lisu Huo, Jianghan Zhu, Zhimeng Li, Manhao Ma
Summary: The study introduces a HDSOS algorithm that combines DE and SOS strategies, with both local and global search capabilities, as well as the introduction of traction function and perturbation strategy to enhance efficiency and robustness, comparative experiments demonstrate its superiority.
Article
Computer Science, Artificial Intelligence
Senthil Kumar Angappamudaliar Palanisamy, Dinesh Selvaraj, Siva Bala Krishnan Ramasamy
Summary: Path planning is a crucial element in mobile robot decision making and control. This research proposes a hybrid optimized path planning model using improved particle swarm optimization and modified whale optimization models, which can achieve the shortest, smoothest, and safest path.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Information Systems
Changsheng Huang, Yanpu Zhao, Mengjie Zhang, Hongyan Yang
Summary: This study proposes an APSO algorithm combining A* and PSO to address the issues in mobile robot path planning. The proposed algorithm optimizes the path planning by utilizing redundant point removal, stochastic inertia weight, and stochastic opposition-based learning strategies. The algorithm is evaluated using a motion time objective function that is more aligned with the actual requirements. Simulation results show that the APSO algorithm reduces the running time of the robot and outperforms other algorithms.
Article
Engineering, Chemical
Qingni Yuan, Ruitong Sun, Xiaoying Du
Summary: This paper proposes an improved particle swarm optimization algorithm based on differential evolution to address the disadvantages of low convergence accuracy and easy maturity in path planning of mobile robots. Adaptive adjustment weights and acceleration coefficients are added to enhance the convergence speed of the traditional particle swarm optimization algorithm. Additionally, adaptive parameters are introduced to control the mutation size and a high-intensity training mode is developed to improve the search precision of the algorithm. Experimental results demonstrate the feasibility and effectiveness of the proposed algorithm in solving mobile robot path-planning problems.
Article
Automation & Control Systems
Adam P. Piotrowski, Jaroslaw J. Napiorkowski, Agnieszka E. Piotrowska
Summary: This paper compares Particle Swarm Optimization and Differential Evolution, two landmark metaheuristics, and finds that the performance of Differential Evolution algorithms is clearly better than Particle Swarm Optimization ones. Despite being more commonly used in the literature, Particle Swarm Optimization algorithms are outperformed by Differential Evolution on single-objective numerical benchmarks and real-world problems. Therefore, there is a need to reconsider the algorithmic philosophy of Particle Swarm Optimization variants to enhance their competitiveness.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Review
Computer Science, Artificial Intelligence
Rafael Crespo Izquierdo, Anselmo Rafael Cukla, Flavio Jose Lorini, Eduardo Andre Perondi
Summary: Among the works related to the planning of manipulator robots' trajectories, this paper proposes an optimization technique for planning the trajectory of a cylindrical manipulator robot with 5 degrees of freedom. The technique considers obstacle deviation and the kinematic characteristics of the manipulator, and uses an algorithm to generate intermediate points and b-spline functions to generate smooth and efficient trajectories. The proposed method ensures collision-free zones and operational limits of the robot.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Lin Zhang, Yingjie Zhang, Yangfan Li
Summary: An improved localized particle swarm optimization algorithm is proposed in this article to address the shortcomings of local minimum, premature, and low efficiency. The algorithm is enhanced in inertia weights, acceleration factors, and localization, increasing diversity to overcome premature and applying the smoothing principle in path planning. Comparative study shows that the proposed algorithm outperforms basic particle swarm optimization and A-star algorithms in terms of path length, running time, path optimal degree, and stability.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Information Systems
Yun Chen, Jinfeng Wu, Chaoshuai He, Si Zhang
Summary: In order to enhance the safety and accuracy of path planning for intelligent warehouse robots, this study proposes a storage shelf model and utilizes Poisson Distribution to simulate the impact of unknown factors, establishing a three-color raster map. By optimizing the pheromone update mechanism considering various factors, including path safety, path length, and turning elements influenced by unknown factors, two separate models based on three-dimensional shelves are simulated, and the planned paths are smoothed and pruned. The simulation results demonstrate that the improved algorithm is capable of designing optimal routes safely and effectively in storage environments affected by unknown factors. The proposed algorithm not only resolves the issues of blind search and deadlock but also outperforms other algorithms, with only 4 iterations compared to 22 and 30 iterations, 3 turns compared to 9 and 7 turns, and a reduced running time of 8.468s compared to 16.974s and 13.754s.
Article
Computer Science, Artificial Intelligence
Lin Xu, Maoyong Cao, Baoye Song
Summary: This paper proposes a new approach for smooth path planning of a mobile robot using a new quartic Bezier transition curve and an improved particle swarm optimization (PSO) algorithm. The quartic Bezier transition curve is constructed to ensure G3 continuity at the joints of the path segments, while the PSO algorithm is used to optimize the smooth path planning problem. Simulation experiments demonstrate the effectiveness and superiority of the proposed approach.
Article
Computer Science, Artificial Intelligence
Quoc Bao Diep, Thanh Cong Truong, Swagatam Das, Ivan Zelinka
Summary: This article introduces an improved version of the Self-Organizing Migrating Algorithm named iSOMA and evaluates its performance. The iSOMA algorithm shows notable improvements compared to previous versions and achieves excellent results in multiple benchmark tests. Additionally, the article demonstrates the application of iSOMA in drone path planning.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Nianyin Zeng, Han Li, Yonghong Peng
Summary: This study develops a novel deep belief network (DBN) based multi-task learning algorithm for accurate classification of Alzheimer's disease (AD) and mild cognitive impairment (MCI), with a focus on distinguishing progressive MCI (pMCI) from stable MCI (sMCI). The algorithm achieves satisfactory results in six different classification tasks using data from the ADNI dataset, demonstrating its effectiveness and practicality.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Automation & Control Systems
Xi Li, Qiankun Song, Yurong Liu, Fuad E. Alsaadi
Summary: This article presents the Hurwicz model of the zero-sum uncertain differential game with jump based on uncertainty theory. It formulates a dynamic system using an uncertain differential equation that satisfies both the canonical Liu process and V-jump uncertain process. An equilibrium equation for solving the saddle-point of the game is proposed. Furthermore, the article analyzes the game with a linear dynamic system and quadratic objective function. Finally, it describes a resource extraction problem using the theoretical results.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Biology
Peishu Wu, Zidong Wang, Baixun Zheng, Han Li, Fuad E. Alsaadi, Nianyin Zeng
Summary: In this paper, a novel attention-based glioma grading network (AGGN) oriented towards magnetic resonance imaging (MRI) is proposed. The AGGN utilizes a dual-domain attention mechanism to consider both channel and spatial information for weight assignment. It also incorporates multi-branch convolution, pooling, and multi-modal information fusion modules to extract and merge features from different modalities. Experimental results demonstrate the effectiveness, superiority, high generalization ability, and strong robustness of the proposed AGGN compared to other models, even without manually labeled tumor masks, alleviating the reliance on supervised information.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Automation & Control Systems
Shijuan Li, Qiankun Song, Yurong Liu
Summary: This paper investigates the stability of a class of distributed-order nonlinear systems using an event-triggered control method. It first establishes an inequality for the solution of distributed-order nonlinear inequality systems using Laplace transform. Then, by designing a state feedback controller and event-triggered strategy and using Lyapunov stability theory and matrix inequality technique, a sufficient condition for the asymptotic stability of the considered systems is obtained in the form of a linear matrix inequality. Furthermore, a criterion to exclude Zeno behavior in the event-triggered strategy is provided. Finally, the proposed method is verified through a simulation example.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yuqing Zhang, Peishu Wu, Han Li, Yurong Liu, Fuad E. Alsaadi, Nianyin Zeng
Summary: In this paper, a novel dual-pathway-fusion-based sequence-to-sequence learning model (DPF-S2S) is proposed for text recognition in the wild. It focuses on enriching spatial information and extracting high-dimensional representation features to aid decoding. The model incorporates a double alignment module to tackle text misalignment and a global fusion module to enhance recognition accuracy in complicated scenes. Benchmark evaluations on seven datasets demonstrate the superiority of DPF-S2S over other state-of-the-art text recognition methods, showcasing its competitiveness in identifying texts in regular and irregular scenes. Ablation studies further validate the effectiveness of the strategies employed in DPF-S2S.
Article
Biology
Meilin Liu, Zidong Wang, Han Li, Peishu Wu, Fuad E. Alsaadi, Nianyin Zeng
Summary: In this paper, a novel attention augmented Wasserstein generative adversarial network (AA-WGAN) is proposed for fundus retinal vessel segmentation. The proposed AA-WGAN can effectively handle the imperfect data property of segmenting tiny vessels, highlight regions of interests via attention augmented convolution, and suppress useless information through the squeeze-excitation module. The comprehensive evaluation on three datasets confirms the competitiveness of the proposed AA-WGAN, with accuracy of 96.51%, 97.19%, and 96.94% achieved on DRIVE, STARE, and CHASE_DB1 datasets respectively. The effectiveness of important components is validated by ablation study, demonstrating considerable generalization ability of the proposed AA-WGAN.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biology
Tingyi Xie, Zidong Wang, Han Li, Peishu Wu, Huixiang Huang, Hongyi Zhang, Fuad E. Alsaadi, Nianyin Zeng
Summary: In this paper, a novel deep learning-based medical imaging analysis framework named multi-scale efficient network (MEN) is proposed to deal with the insufficient feature learning caused by the imperfect property of imaging data. The proposed method integrates different attention mechanisms to realize sufficient extraction of both detailed features and semantic information. The results show that the proposed method is competitive in accurate COVID-19 recognition and exhibits satisfactory generalization ability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Automation & Control Systems
Xi Li, Qiankun Song, Yurong Liu
Summary: Uncertainty theory in axiomatic mathematics aims to eliminate degrees of belief. This article focuses on the optimal control and non-zero-sum differential game of uncertain delay dynamic systems, using uncertainty theory and the Hurwicz criterion. By employing dynamic programming, the optimality principle is proposed and the optimality equation is formulated to solve the optimal control problem. Additionally, an equilibrium equation is derived to solve the Nash equilibrium in the multi-player non-zero-sum uncertain differential game based on the proposed optimality equation. An example is provided to illustrate the applicability of the results.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Automation & Control Systems
Han Li, Haonan Liu, Chengbo Lan, Yiqi Yin, Peishu Wu, Cheng Yan, Nianyin Zeng
Summary: In this paper, a novel multidisciplinary design optimisation (MDO) algorithm called the decomposition-based switching multi-objective whale optimiser (SMWO/D) is proposed. It utilizes a penalty-Tchebycheff value-based decomposition framework to decouple strongly correlated conflicting objectives and considers different disciplinary demands comprehensively. Two adaptively switchable evolutionary modes are defined to overcome the shortcoming of premature convergence in the complicated multi-modal non-linear decision space and promote a thorough global search with rich learning strategies. The proposed SMWO/D is evaluated on benchmark functions and compared with four popular decomposition-based multi-objective optimisation algorithms (MOAs), demonstrating its competitiveness in terms of comprehensive performance. Additionally, a sensitivity analysis is conducted to determine the best parameter configuration of SMWO/D. Finally, a case study of a real-world turbine disk structural optimisation validates the practicality of SMWO/D in handling multidisciplinary properties and provides valuable experiences in the aero-engine MDO domain.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Engineering, Multidisciplinary
Tengpeng Chen, Fangyan Liu, Lu Sun, Gehan A. J. Amaratunga, Nianyin Zeng
Summary: This paper proposes a robust dynamic state estimation (DSE) method based on maximum correlation entropy, quadratic function, and the cubature Kalman filter to reduce the effects caused by uncertainties in power system DSE. The proposed method demonstrates robustness and estimation precision through simulations on a synchronous generator under different cases.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Minzhi Chen, Guijun Ma, Weibo Liu, Nianyin Zeng, Xin Luo
Summary: Battery degradation has a significant impact on the safety and sustainability of battery management systems. This paper provides an overview of data-driven battery state of health (SOH) estimation technology for BMSs. It reviews state-of-the-art models, feature extraction methods, benchmarks, and publicly-available battery SOH datasets. The study includes experiments and analysis on Toyota & Stanford-MIT battery SOH datasets, highlighting existing challenges and feature trends.
Article
Engineering, Electrical & Electronic
Zhenhua Gan, Peishu Wu, Nianyin Zeng, Fumin Zou, Baoping Xiong, Min Du, Qin Bao, Jinyang Li, Yuankun Bai
Summary: This study proposes a new approach based on cyclic cleaving by DNA walkers for biological signal amplification and quantitative detection. The experimental results show that this method has good linear characteristics and has wide applications in biology, medicine, food, and the environment.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Juan Li, Weimei Chen, Yihao Zhu, Kui Xuan, Han Li, Nianyin Zeng
Summary: In this paper, a novel YOLO-based detection model with deformable convolution network (DCN-YOLOv5) is proposed to address the object detection and behavior tracking problem in the ammonia nitrogen environment. By deforming the receptive field, the proposed model can adapt to the posture change of the object, thereby solving the problem of false and missed detection caused by movement and occlusion. A new multi-object multi-category tracking algorithm (MOMC-Tracking) is also proposed to track and calculate key behavioral characteristics parameters. Experimental results show that the proposed DCN-YOLOv5 model outperforms the typical YOLO series of algorithms in terms of accuracy and convergence speed.
Article
Computer Science, Artificial Intelligence
Jun Tang, Zidong Wang, Hongyi Zhang, Han Li, Peishu Wu, Nianyin Zeng
Summary: This paper proposes a lightweight printed circuit board defects detection model (light-PDD) to overcome the deficiencies of redundant parameters and slow inference speed in existing methods. The light-PDD model follows the overall framework of YOLOv4 with enhancements, using a pruned MobileNetV3 structure for feature extraction. It also incorporates a dual-domain attention mechanism and diverse activation functions to effectively handle the detection of tiny-size PCB defects. The improved cross-stage partial structure is deployed for feature fusion to reduce model complexity. Experimental results demonstrate the superiority of light-PDD in terms of inference speed and detection accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Peishu Wu, Zidong Wang, Han Li, Nianyin Zeng
Summary: This paper proposes a novel knowledge distillation-based pedestrian attribute recognition model, which achieves a highly generalized and robust attribute recognition model by designing a multi-label mixed feature learning network as the student model and combining multiple mechanisms.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
