Garbage recycling and collection problem is an interesting problem that researchers are applying swarm intelligence algorithms to solve. Some previous approaches used particle swarm optimization, immune systems and an...
详细信息
ISBN:
(纸本)9781479967117
Garbage recycling and collection problem is an interesting problem that researchers are applying swarm intelligence algorithms to solve. Some previous approaches used particle swarm optimization, immune systems and ant colony optimization algorithms and achieved good results. Ant colony optimization is a well-known swarmintelligence algorithm that is normally used to solve computational problems which can be reduced to finding good paths in graphs. A multi-robotic system can be applied to solve this problem but it will need a control algorithm to accomplish the task. Applying the regular ant colony optimization algorithm to control the multi-robotic system is not a trivial task due to the graph representation needed. This work proposes modifications in the ant colony optimization algorithm that uses grid representation and applies the modified algorithm to solve this problem. The results showed a decrease of one order of magnitude in the number of iterations needed to solve the problem compared to the previous version of the algorithm. Considering the results the proposed algorithm showed to be able to control a multi-robotic system for the chosen problem.
Monitoring modulation type of the detected signal is the most important intermediate step between signal detection and demodulation. The back propagation neural network (BPNN) was widely used in constructing modulated...
详细信息
ISBN:
(纸本)9783037857441
Monitoring modulation type of the detected signal is the most important intermediate step between signal detection and demodulation. The back propagation neural network (BPNN) was widely used in constructing modulated signal classifier in the field of automatic modulation classification (AMC). There are many visible features in the back propagation (BP) algorithm including adaptive learning, the ability of fault tolerant, etc. However, this algorithm has two main disadvantages, such as the slow convergence speed and easily falling into the local minimum. This paper presents a novel modulation classifier using BPNN trained with swarm intelligence algorithms (SIA), for the sake of overcoming these deficiencies. The initial weights and thresholds of BP neural network were optimized by SIA. As the SIA has an excellent global search property, this classifier can consume less training time and improve the automatic modulation type identification rate.
In the paper, we try to provide a comprehensive look on a multi-objective design of radiating, guiding and reflecting structures fabricated both from special materials (semiconductors, high-impedance surfaces) and con...
详细信息
In the paper, we try to provide a comprehensive look on a multi-objective design of radiating, guiding and reflecting structures fabricated both from special materials (semiconductors, high-impedance surfaces) and conventional ones (microwave substrates, fully metallic antennas). Discussions are devoted to the proper selection of the numerical solver used for evaluating partial objectives, to the selection of the domain of analysis, to the proper formulation of the multi-objective function and to the way of computing the Pareto front of optimal solutions (here, we exploit swarm-intelligencealgorithms, evolutionary methods and self-organizing migrating algorithms). The above-described approaches are applied to the design of selected types of microwave antennas, transmission lines and reflectors. Considering obtained results, the paper is concluded by generalizing remarks.
暂无评论