Swarm intelligence inspired algorithms have so many profound natural advantages in solving large-scale and distributed problems. This paper systematically analyzes the characteristics of wolves' behaviors such as ...
详细信息
Swarm intelligence inspired algorithms have so many profound natural advantages in solving large-scale and distributed problems. This paper systematically analyzes the characteristics of wolves' behaviors such as cooperative searching, hunting and attacking, and further abstracts those behaviors into four basic ways, that is, wandering, summoning, lurking and besieging, in accordance with the different roles of wolves. Then, we formulate a cluster cooperative rule based on the principle of Dynamic Wolf Head Alternation and Real-time Role Assignment, and propose a fatigue-rendering tactics based on interception strategy in two teams. Finally, the clustering cooperative rule enlightened by the group's behavior is established, and the convergence of the algorithm is proved with the Markov asymptotic convergence theory. Experiments show that the model can effectively guarantee the efficiency of solving large-scale complex optimization problems and the operational effectiveness of distributed cluster cooperative attack problems.
In this paper, we investigate the elastic inverted pendulum with hysteretic nonlinearity (a backlash) in the suspension point. Namely, the problems of stabilization and optimization of such a system are considered. Th...
详细信息
In this paper, we investigate the elastic inverted pendulum with hysteretic nonlinearity (a backlash) in the suspension point. Namely, the problems of stabilization and optimization of such a system are considered. The algorithm (based on the bionic model) which provides the effective procedure for finding of optimal parameters is presented and applied to considered system. The results of numerical simulations, namely the phase portraits and the dynamics of Lyapunov function, are also presented and discussed.
作者：
Wang, ZeyuDeng, YueWuhan Univ
Inst Qual Dev Strategy Macro Qual Management Collaborat Innovat Ctr Hube Wuhan 430072 Peoples R China
The present work aims to optimize the time index of financial engineering to improve the efficiency of financial decision-making. A Back Propagation Neural Network (BPNN) model is designed and optimized by the Ant Col...
详细信息
The present work aims to optimize the time index of financial engineering to improve the efficiency of financial decision-making. A Back Propagation Neural Network (BPNN) model is designed and optimized by the Ant Colony algorithm (ACA) based on the bionic algorithm and Deep Learning (DL). After introducing the basic knowledge of neural networks and bionic algorithms, the advantages and disadvantages of the algorithms are integrated for maximal effects. Besides, ACA optimizes the weights and thresholds in the neural network in complex problems to reduce the relative error, enhance the stability and accuracy, and improve the classification speed of the BPNN model. The experimental results indicate that the classification accuracy of the ACA model is 91.3%, and the area under the receiver operating characteristic curve is 0.867. Moreover, the running time of BPNN based on ACA is 2.5 s, the error is 0.2, and the required number of iteration steps is 36 times, better than the test results of similar algorithms. These results demonstrate that the improved BPNN based on ACA has higher classification efficiency, better efficiency and smaller errors than the traditional BPNN. In terms of financial engineering decision-making, the time index of decision-making has been significantly improved, which is conducive to reducing the decision-making risk of financial institutions and has a positive effect on improving the overall operational efficiency of enterprises.
This study tackles the urgent issue of indoor particulate matter (PM) pollutants, highlighting the critical need for efficient source localization due to its significant health risks. Moving beyond traditional constan...
详细信息
This study tackles the urgent issue of indoor particulate matter (PM) pollutants, highlighting the critical need for efficient source localization due to its significant health risks. Moving beyond traditional constant-rate gas emission research, we explore real-world PM releases using a multirobot system, enabling effective PM source localization in dynamically ventilated environments. Initial data collection on airflow and PM concentrations helps optimize our system for mechanical ventilation challenges. Through 90 experiments across six scenarios, we evaluate the improved whale optimization algorithm (IWOA) and improved particle swarm optimization (IPSO) methods, assessing their ability to identify both constant and variable PM sources and their adaptability to different pollutants. The results show a success rate of 73.3 % for both methods in locating constant PM sources, with IPSO offering a slight edge in efficiency. Moreover, in tasks involving ethanol vapor, the methods exhibited higher success rates, indicating uniform performance across a variety of pollutants. This consistency, alongside the noted variations in success rates, is primarily attributed to the complexities of PM dispersion. Importantly, our study highlights the methods' adaptability to periodic PM sources with variable release rates, maintaining high success without extra localization steps. This research advances indoor air quality management and emphasizes the importance of flexible, effective pollutant control strategies for public health protection.
Inspired by the behaviour of animal populations in nature, we propose a novel exploration algorithm based on Levy flight (LF) and artificial potential field (APF). The agent is extended to the swarm level using the AP...
详细信息
Inspired by the behaviour of animal populations in nature, we propose a novel exploration algorithm based on Levy flight (LF) and artificial potential field (APF). The agent is extended to the swarm level using the APF method through the LF search environment. Virtual leaders generate moving steps to explore the environment through the LF mechanism. To achieve collision-free movement in an unknown constrained environment, a swarm-following mechanism is established, which requires the agents to follow the virtual leader to carry out the LF. The proposed method, combining the advantages of LF and APF which achieve the effect of flocking in an exploration environment, does not rely on complex sensors for environment labelling, memorising, or huge computing power. Agents simply perform elegant and efficient search behaviours as natural creatures adapt to the environment and change formations. The method is especially suitable for the camouflaged flocking exploration environment of bionic robots such as flapping drones. Simulation experiments and real-world experiments on E-puck2 robots were conducted to evaluate the effectiveness of the proposed LF-APF algorithm.
This paper uses a new bionic algorithm in turning of PID *** Paddy Field algorithm (PFA)is operat-ed in the parametric space from the initial scattering of seeds. The number of seeds of every plant depends on the func...
详细信息
ISBN:
(纸本)9781457702686
This paper uses a new bionic algorithm in turning of PID *** Paddy Field algorithm (PFA)is operat-ed in the parametric space from the initial scattering of seeds. The number of seeds of every plant depends on the function val-ue,as the plant,the closest optimal solution,produces the most *** produced seeds also depend on the number of the plant's neighbors,for only a percentage is viable due to ***,the seeds of each plant must be dispersed in or-der to prevent being stuck in local *** thus applied this improved algorithm to design the PID controller of a high-order *** effect of various parameters on the performance of the algorithm was also *** performance is tested with the PID and PSO *** results show that the approach is effective and the designed controller has a better performance of overshoot and settling time.
Ant Colony algorithm is a brand-new bionic simulated evolutionary algorithm, which has been applied to many fields. Multi-objective optimization problems are very important optimization problems. It's hard to opti...
详细信息
Ant Colony algorithm is a brand-new bionic simulated evolutionary algorithm, which has been applied to many fields. Multi-objective optimization problems are very important optimization problems. It's hard to optimized or solved. An improved Ant Colony algorithm to solve Multi-objective optimization problems is introduced. After setting up a set of weight for the parameters, the algorithm uses some ants search in the solution space first in a stochastic way then stimulate the food searching behavior of real ants to guide the search by the pheromone. The new algorithm is explained in details and some simulations show the algorithm is very effective in finding global optimizations.
暂无评论