Cognitive Electronic Jamming Decision-Making Method Based on Improved Q -Learning Algorithm

In this paper, a cognitive electronic jamming decision-making method based on improved Q -learning is proposed to improve the efficiency of radar jamming decision-making. First, the method adopts the simulated annealing (SA) algorithm’s Metropolis criterion to enhance the exploration strategy, balancing the contradictory relationship between exploration and utilization in the algorithm to avoid falling into local optima. At the same time, the idea of stochastic gradient descent with warm restarts (SGDR) is introduced to improve the learning rate of the algorithm, which reduces the oscillation and improves convergence speed at the later stage of the algorithm iteration. Then, a cognitive electronic jamming decision-making model is constructed, and the improved Q -learning algorithm’s specific steps are given. The simulation experiment takes a multifunctional radar as an example to analyze the influence of exploration strategy and learning rate on decision-making performance. The results reveal that compared with the traditional Q -learning algorithm, the improved Q -learning algorithm proposed in this paper can fully explore and efficiently utilize and converge the results to a better solution at a faster speed. The number of iterations can be reduced to more than 50%, which proves the feasibility and effectiveness of the method applied to cognitive electronic jamming decision-making.

An Improved Hybrid Algorithm Based on Biogeography/Complex and Metropolis for Many-Objective Optimization

It is extremely important to maintain balance between convergence and diversity for many-objective evolutionary algorithms. Usually, original BBO algorithm can guarantee convergence to the optimal solution given enough generations, and the Biogeography/Complex (BBO/Complex) algorithm uses within-subsystem migration and cross-subsystem migration to preserve the convergence and diversity of the population. However, as the number of objectives increases, the performance of the algorithm decreases significantly. In this paper, a novel method to solve the many-objective optimization is called Hmp/BBO (Hybrid Metropolis Biogeography/Complex Based Optimization). The new decomposition method is adopted and the PBI function is put in place to improve the performance of the solution. On the within-subsystem migration the inferior migrated islands will not be chosen unless they pass the Metropolis criterion. With this restriction, a uniform distribution Pareto set can be obtained. In addition, through the above-mentioned method, algorithm running time is kept effectively. Experimental results on benchmark functions demonstrate the superiority of the proposed algorithm in comparison with five state-of-the-art designs in terms of both solutions to convergence and diversity.

Analysis of host-pathogen interactions via clustering, statistical analysis, and data visualization

Infectious diseases are caused by a variety of agents: viruses, bacteria, parasites, or even proteins. Using existing state-of-the-art methods and tools I developed myself, I studied aspects of infectious agents. To find the most conserved and diverse regions of influenza A proteins, I found clusters of extremely conserved or diverse residues. Because traditional methods of clustering proved ineffective for diverse regions, I developed a Metropolis Criterion Monte Carlo (MMC) clustering algorithm to discover clusters of extremely diverse regions. In addition to viruses, I studied pathogenic bacterial proteins known as effectors. Using an in-house prediction method, Preffector, I generated predicted effectors for 14 bacteria and created a database and webserver to hold relevant information: BacPaC. BacPaC uses intuitive visualizations and script-generated profile pages to display relevant data about the predicted effectors. Finally, I applied structural modeling and docking techniques to soybean proteins that are known to incur resistance to nematodes. For each of these studies, I used clustering, data analysis, and data visualization to better understand infectious agents.

Hybridizing Invasive Weed Optimization and Simulated Annealing Algorithm for High-Dimensional Function Optimization

We herein propose an efficient algorithm (called IWOSA herein after) hybridizing invasive weed optimization (IWO for short) with the simulated annealing (SA) algorithm. The IWO is a new algorithm proposed to solve actual practical problems, which imitates the invasive behavior of weeds in nature. In the further research IWO algorithm did not show its efficiency in high-dimensional problems, and lacked directivity in the process of IWOSA iterations. To deal with this problem, we employed IWO to provide diversity to explore solution and Metropolis criterion of SA to provide more precise guidance, and tried to improve accuracy and convergence speed by these steps. To test the proposed algorithm, we compared IWOSA with original IWO through high-dimensional optimization benchmark functions. The computational results showed the efficiency of our algorithm.

A Particle Swarm Optimization Algorithm Based on Simulated Annealing

The passage aims at solving the problems resulted from the optimized process of Particle Swarm Optimization (PSO), which might reduce the population diversity, cause the algorithm to convergence too early, etc. A whole new mutable simulated annealing particle swarm optimization is proposed based on the combine of the simulated annealing mechanism and mutation. This new algorithm substitutes the Metropolis criterion in the simulated annealing mechanism for mutagenic factors in the process of mutation, which both ensures the diversity of the particle swarm, and ameliorates the quality of the swarm, so that this algorithm would convergence to the global optimum. According to the result of simulated analysis, this hybrid algorithm maintains the simplicity of the particle swarm optimization, improves its capability of global optimization, and finally accelerates the convergence and enhances the precision of this algorithm.

A Metropolis Criterion Based Fuzzy Q-Learning Flow Controller for High-Speed Networks

For the congestion problems in high-speed networks, a Metropolis criterion based fuzzy Q-learning flow controller is proposed. Because of the uncertainties and highly time-varying, it is not easy to accurately obtain the complete information. In this case, the Q-learning, which is independent of mathematic model, and prior-knowledge, has good performance. The fuzzy inference and Metropolis criterion are introduced in order to facilitate generalization in large state space and balance exploration and exploitation in action selection individually. Simulation results show that the controller can learn to take the best action to regulate source flow with the features of high throughput and low packet loss ratio, and can avoid the occurrence of congestion effectively.