No abstract is provided for this article.
Multitemporal remote sensing image analysis is very important and thus requires trustable tools to analyze land cover changes. In this chapter, we present nature inspired techniques for flood damage evaluation using multitemporal MODIS data. The primary focus of the proposed approach is to combine the spectral and spatial features for the proper assessment of flood prone regions. Multitemporal MODIS data are analyzed in three stages: before, during, and after flood. Methodology involves two steps: in the first step, image clustering is carried out using the genetic algorithm, particle swarm optimization, and the firefly algorithm to distinguish water regions from nonwater using pixel-based spectral information. Most of the multimodal optimization problems are often solved by these three algorithms quite effectively. Subsequently, these clustered images are segmented using geometric features to extract water-covered regions. From the results obtained, a comprehensive performance evaluation of different algorithms is carried out, which leads to the conclusion that integrating region-based image segmentation along with clustering algorithms proves to be a very efficient tool for flood mapping.
The shunt reactors are important components in the EHV/UHV (Eltra/Ultra High Voltage) power systems used for the voltage regulation issues. One of their important roles is to compensate the reactive power. Typically for such compensation the fixed shunt reactors are used. Alternative concepts introduced recently are the controllable reactors. The controlling effect of orthogonal flux type controllable reactor is achieved by controlling the saturation level of the parts of the magnetic core (saturable reactor). In this paper we present an efficient approach for the simulation of such controllable reactors using Integral Equation Method (IEM). The key information when analyzing this kind of devices are the controllable reluctances. The paper demonstrates usage of IEM for the computation of the inductances as a function of the reluctance changes depending on the saturation levels of the magnetic material. The results are compared with the calculation results obtained by an equivalent magnetic circuit calculation model.
No abstract is provided for this article.
No abstract is provided for this article.
Both data mining and machine learning are becoming popular with many different applications. This chapter introduces some techniques in data mining and machine learning, including clustering, support vector machine, and neural networks. We also discuss their links to nature-inspired algorithms for optimization.
Nature-inspired metaheuristic algorithms, especially those based on swarm intelligence, have attracted much attention in the last ten years. Firefly algorithm appeared in about five years ago, its literature has expanded dramatically with diverse applications. In this paper, we will briefly review the fundamentals of firefly algorithm together with a selection of recent publications. Then, we discuss the optimality associated with balancing exploration and exploitation, which is essential for all metaheuristic algorithms. By comparing with intermittent search strategy, we conclude that metaheuristics such as firefly algorithm are better than the optimal intermittent search strategy. We also analyse algorithms and their implications for higher-dimensional optimization problems.
No abstract is provided for this article.
Unknown
No abstract is provided for this article.
No abstract is provided for this article.
Engineering optimization is typically multiobjective and multidisciplinary with complex constraints, and the solution of such complex problems requires efficient optimization algorithms. Recently, Xin-She Yang proposed a bat-inspired algorithm for solving nonlinear, global optimisation problems. In this paper, we extend this algorithm to solve multiobjective optimisation problems. The proposed multiobjective bat algorithm (MOBA) is first validated against a subset of test functions, and then applied to solve multiobjective design problems such as welded beam design. Simulation results suggest that the proposed algorithm works efficiently.
No abstract is provided for this article.
No abstract is provided for this article.
Crack propagation in concrete structures is a very complicated process, and the distribution of cracks may significantly affect the behaviour of the structures under time‐dependent loading. If enough damage or extensive cracks exist in a structure, strengthening or repair using external carbon fibre‐reinforced polymer (CFRP) reinforcement may be needed. Therefore, an understanding of the influence of the CFRP strengthening system on behaviour is crucial for the proper design of a structural reinforcement strategy. In this paper, we compare three major methods: the discrete crack method, the smeared crack method and the element‐free method. By using these methods to study the fracture pattern of a beam with dapped ends, we can compare the capabilities and efficiencies of the three methods. When modelling the crack formation in reinforced concrete structures, the smeared crack approach gives better results than the discrete model in terms of crack spacing and regularity, however, it does not follow the crack growth well. The element‐free Galerkin method seems to be superior to the other methods in the sense that it deals with the irregular cracks well and is very efficient in saving computing time. The preferred choice of method depends on the type of problem and the solution accuracy required, and this also depends on a certain balance between the accurate tracing of individual cracks and the computing efficiency. In addition, new algorithms are required for the efficient simulations of dynamic crack propagation, especially in the case of pre‐cracked structures strengthened with prestressed CFRPs. Copyright © 2007 John Wiley & Sons, Ltd.
The optimization problems we have discussed so far are mainly single-objective optimization problems. In reality, many optimization problems can have more than one objective, thus we have to deal with multi-objective optimization. This chapter introduces the fundamentals of multi-objective optimization and relevant optimization techniques.
