Wind turbine radar clutter seriously affects the detection performance of radar. The effective estimation of micro-motion parameters is an important part of wind turbine radar clutter suppression. Aiming at the proble...
详细信息
ISBN:
(纸本)9781450385886
Wind turbine radar clutter seriously affects the detection performance of radar. The effective estimation of micro-motion parameters is an important part of wind turbine radar clutter suppression. Aiming at the problem of wind turbine radar clutter micro-motion parameters estimation, the micro-motion parameters estimation effectiveness of three swarm-based optimization algorithms, namely Particle swarmoptimization (PSO) algorithm, Artificial Bee Colony (ABC) algorithm and Grey Wolf Optimizer (GWO), is compared in this paper. Firstly, the basic principles of three swarm-based optimization algorithms are introduced. Then the wind turbine radar clutter model is established to determine the micro-motion parameters to be estimated and the steps of micro-motion parameters estimation are given. Finally, the micro-motion parameters estimation results of the three algorithms are compared and analyzed through simulation experiments. The results show that the three swarm-based optimization algorithms can estimate the micro-motion parameters. The GWO has the smallest estimation error, which has the potential value for practical wind turbine radar clutter suppression.
Finding a feasible path for an unmanned aerial vehicle (UAV) in a complex environment is a crucial part of any UAV mission planning system. Many algorithms have been developed to identify optimal or nearly optimal pat...
详细信息
Finding a feasible path for an unmanned aerial vehicle (UAV) in a complex environment is a crucial part of any UAV mission planning system. Many algorithms have been developed to identify optimal or nearly optimal pathways for UAVs;however, the vast majority of those algorithms do not deal with this problem as multiobjective. Therefore, this study is presented to propose a new multiobjective optimization technique, namely the hybrid slime mould algorithm (HSMA), based on hybridizing the slime mould algorithm with a new updating mechanism to strengthen its performance when applied to tackle the multiobjective path planning problem in 3-D space. This algorithm employs Pareto optimality to tradeoff between various objectives. Those objectives include path optimality for minimizing the fuel cost and consumed time to reach the target location, flying away from threats to ensure safe operation, and finally the smooth cost to assess the climbing and turning rates. HSMA was evaluated using six benchmarking scenarios with various difficulty levels and compared to several recently published and well-established algorithms to show its effectiveness for several performance metrics, such as the convergence curve, Wilcoxon rank-sum test, and inverted generational distance metric. The experimental findings expose that HSMA is more effective than all the compared optimizers in terms of all performance metrics. Hence, it is the best alternative for efficiently creating high-quality pathways for UAVs.
The Internet of Things (IoT) shapes an organization of objects that can interface and share information with different devices using sensors, computer programs, and other innovations without human intervention. IoT pr...
详细信息
The Internet of Things (IoT) shapes an organization of objects that can interface and share information with different devices using sensors, computer programs, and other innovations without human intervention. IoT problems deal with massive amounts of data with critical challenges such as complex and dynamic search spaces, multiple objectives and constraints, uncertainty, and noise that require an efficient optimizer to extract valuable insights. Grey wolf optimizer (GWO) is an efficient optimizer stimulated by the hunting mechanism of wolves. The increasing trend of applying GWO shows that although it is a simple algorithm with few control parameters, it effectively solves optimization problems, particularly in various IoT applications. Therefore, this study reviews applying GWO, its variants, and its developments in IoT applications. This systematic review uses the PRISMA methodology, including three fundamental phases: identification, evaluation, and reporting. In the identification phase, the target search problems are defined based on suitable keywords and alternative synonyms, and then 693 documents from 2014 to the end of 2023 are retrieved. The evaluation phase applies three screening steps to assess papers and choose 50 eligible papers for full-text reading. Finally, the reporting phase thoroughly examines and synthesizes the 50 eligible articles to identify key themes related to GWOs in IoT applications. The eligible GWOs are reviewed in the development, commercial, consumer, and industrial categories. The paper visualized the spreading of eligible GWOs according to their publisher, application, journal, and country and then suggested future directions for research.
This paper introduces the comparison of evolutionary and swarm-based optimization algorithms for multilevel color image thresholding problem which is a process used for segmentation of an image into different regions....
详细信息
This paper introduces the comparison of evolutionary and swarm-based optimization algorithms for multilevel color image thresholding problem which is a process used for segmentation of an image into different regions. Thresholding has various applications such as video image compression, geovideo and document processing, particle counting, and object recognition. Evolutionary and swarm-based computation techniques are widely used to reduce the computational complexity of the multilevel thresholding problem. In this study, well-known evolutionary algorithms such as Evolution Strategy, Genetic Algorithm, Differential Evolution, Adaptive Differential Evolution and swarm-basedalgorithms such as Particle swarmoptimization, Artificial Bee Colony, Cuckoo Search and Differential Search Algorithm have been used for solving multilevel thresholding problem. Kapur's entropy is used as the fitness function to be maximized. Experiments are conducted on 20 different test images to compare the algorithms in terms of quality, running CPU times and compression ratios. According to the statistical analysis of objective values, swarmbasedalgorithms are more accurate and robust than evolutionary algorithms in general. However, experimental results exposed that evolutionary algorithms are faster than swarmbasedalgorithms in terms of CPU running times. (C) 2014 Elsevier B.V. All rights reserved.
暂无评论