To detect salient ground targets precisely and rapidly during aerial reconnaissance, this paper describes a novel object recognition method based on the feature selection of a biologically inspired model and biogeogra...
详细信息
To detect salient ground targets precisely and rapidly during aerial reconnaissance, this paper describes a novel object recognition method based on the feature selection of a biologically inspired model and biogeography-based optimization. As a promising approach to object recognition, the biologically inspired model is a hierarchical system of building an increasingly complex and invariant feature representation, which closely follows the process of object recognition in the visual cortex. These scale-and position-tolerant features are constructed by alternating between a template-matching and a maximum-pooling operation. Because of the many patches extracted in the standard biologically inspired model, the random mechanism may extract patches from irrelevant parts of an image and consume a lot of time. In this work, a feature selection method is proposed based on a new population-based evolutionary algorithm called biogeography-based optimization to choose the proper set of patches with high accuracy of classification and recognition. A support vector machine classifier is used for evaluation of the fitness function in biogeography-based optimization and to calculate the recognition rate in testing. A series of experiments are conducted, and the comparative results demonstrate the feasibility and effectiveness of the approach.
A binary-coupled dipole approximation (BCDA) is described for designing metal nanoparticles with nonperiodic structures in one, two, and three dimensions. This method can be used to simulate the variation of near-and ...
详细信息
A binary-coupled dipole approximation (BCDA) is described for designing metal nanoparticles with nonperiodic structures in one, two, and three dimensions. This method can be used to simulate the variation of near-and far-field properties through the interactions of metal nanoparticles. An advantage of this method is in its combination with the binary particle swarm optimization (BPSO) algorithm to find the best array of nanoparticles from all possible arrays. The BPSO algorithm has been used to design an array of plasmonic nanospheres to achieve maximum absorption, scattering, and extinction coefficient spectra. In BPSO, a swarm consists of a matrix with binary entries controlling the presence ('1') or the absence ('0') of nanospheres in the array. This approach is useful in optical applications such as solar cells, biosensors, and plasmonic nanoantennae, and optical cloaking.
High-dimensional design-optimization problems involving complex and time-consuming solvers present computational challenges and are expensive to execute. Even though surrogate models can replace these expensive proble...
详细信息
High-dimensional design-optimization problems involving complex and time-consuming solvers present computational challenges and are expensive to execute. Even though surrogate models can replace these expensive problems with simpler models, the initial design of experiment for constructing these models effectively is still exponential to the dimension of the problem. Traditional screening methods in optimization reduce the dimension of the problem by discarding variables, which is undesirable. In this paper, a latent variable model called generative topographic mapping is proposed to reduce the dimension of the problem so as to facilitate an optimization search in a low-dimensional space without removing any variables from the design problem. The method works by transforming high-dimensional data to be embedded on a low-dimensional manifold. It is demonstrated on a two-dimensional Branin function subjected to nonlinear constraints and then applied to real engineering constrained optimization problems of an aircraft wing design and an aircraft compressor rotor. The model developed in this work proved to be more effective in dealing with constrained optimization problems by effectively learning the constraint boundary, hence finding feasible best designs when compared to other surrogate models like kriging.
This article presents a novel method to optimize the sensitivity and robustness of MEMS vibratory gyroscopes with the help of a 3-DOF MEMS vibratory gyroscope with a 2-DOF-sense mode, which enables adjusting an adapti...
详细信息
This article presents a novel method to optimize the sensitivity and robustness of MEMS vibratory gyroscopes with the help of a 3-DOF MEMS vibratory gyroscope with a 2-DOF-sense mode, which enables adjusting an adaptive trade-off between the precision and robustness for their different desirable importance ratios and a broadband range of frequency response. In this approach, a nonlinear optimization problem is defined in order to maximize both sensitivity and robustness. The design variables are spring constants and the operating frequency, the objective function is obtained regarding both sensitivity and robustness with weighting factors, and both equality and inequality constraint are defined based on the problem. To solve the problem, the Sequential Quadratic Programming (SQP) is applied and the optimized values of design variables, sensitivity and robustness are derived. Changing the weighting factors for the sensitivity and robustness, results in the adjustable values of the vibratory system parameters for different bands of frequency response. A comparison is made among a fully coupled gyroscope with no adjustment capability, an adjustable and fully coupled gyroscope, and an adjustable and broadband gyroscope. Then, they are simulated with different weighting factors. Comparing the results shows the superiority of the proposed adjustable as well as broadband gyroscope. (C) 2013 Elsevier B.V. All rights reserved.
In this article, we consider how to automatically create pleasing photo collages created by placing a set of images on a limited canvas area. The task is formulated as an optimization problem. Differently from existin...
详细信息
In this article, we consider how to automatically create pleasing photo collages created by placing a set of images on a limited canvas area. The task is formulated as an optimization problem. Differently from existing state-of-the-art approaches, we here exploit subjective experiments to model and learn pleasantness from user preferences. To this end, we design an experimental framework for the identification of the criteria that need to be taken into account to generate a pleasing photo collage. Five different thematic photo datasets are used to create collages using state-of-the-art criteria. A first subjective experiment where several subjects evaluated the collages, emphasizes that different criteria are involved in the subjective definition of pleasantness. We then identify new global and local criteria and design algorithms to quantify them. The relative importance of these criteria are automatically learned by exploiting the user preferences, and new collages are generated. To validate our framework, we performed several psycho-visual experiments involving different users. The results shows that the proposed framework allows to learn a novel computational model which effectively encodes an inter-user definition of pleasantness. The learned definition of pleasantness generalizes well to new photo datasets of different themes and sizes not used in the learning. Moreover, compared with two state-of-the-art approaches, the collages created using our framework are preferred by the majority of the users.
Recent progress in computer science and stringent requirements of the design of "greener" buildings put forwards the research and applications of simulation-based optimization methods in the building sector....
详细信息
Recent progress in computer science and stringent requirements of the design of "greener" buildings put forwards the research and applications of simulation-based optimization methods in the building sector. This paper provides an overview on this subject, aiming at clarifying recent advances and outlining potential challenges and obstacles in building design optimization. Key discussions are focused on handling discontinuous multi-modal building optimization problems, the performance and selection of optimization algorithms, multi-objective optimization, the application of surrogate models, optimization under uncertainty and the propagation of optimization techniques into real-world design challenges. This paper also gives bibliographic information on the issues of simulation programs, optimization tools, efficiency of optimization methods, and trends in optimization studies. The review indicates that future researches should be oriented towards improving the efficiency of search techniques and approximation methods (surrogate models) for large-scale building optimization problems;and reducing time and effort for such activities. Further effort is also required to quantify the robustness in optimal solutions so as to improve building performance stability. (C) 2013 Elsevier Ltd. All rights reserved.
Reactive power optimization of power system is an effective means to ensure the safe and stable operation of the system, as well as an important measure to reduce the net loss and improve the voltage quality. Optimiza...
详细信息
Reactive power optimization of power system is an effective means to ensure the safe and stable operation of the system, as well as an important measure to reduce the net loss and improve the voltage quality. optimization algorithm on simulating the fisher fishing(SFOA) is a new proposed intelligent algorithm based on fisherman fishing behavior. In this paper, it is applied to solve the problem of reactive power optimization and tested in the IEEE 30-, 57-, 118-bus test system. The simulation results show that the algorithm has better global search capability, and improves the economy of the system operation effectively. Therefore, the algorithm is effective and feasible.
An experimental verification of a damage detection process using novel optimization techniques such as modified real coded genetic algorithms and swarm-based algorithms is presented. Here, the objective function is de...
详细信息
An experimental verification of a damage detection process using novel optimization techniques such as modified real coded genetic algorithms and swarm-based algorithms is presented. Here, the objective function is defined as the sum of differences of the modal frequencies between intact and stiffness damaged state, which has to be minimized to identify the damage location and its severity in the process of model updating. In addition to the structural or damage variables such as the mass or stiffness of the numerical model, the profiles of modal frequency shifts are also damage-sensitive features. The iterative process that uses the proposed population-based optimization algorithms successfully identifies the local mass change of a test structure by updating the damage variables to fit the modal data of test structures such as a cantilevered beam and multibay truss frame. Copyright (c) 2011 John Wiley & Sons, Ltd.
In this paper, Takagi-Sugeno fuzzy classification system (T-S FCS) using particle swarm optimization (PSO) and support vector machine (SVM) for parameters optimization is proposed. The T-S FCS is constructed by fuzzy ...
详细信息
ISBN:
(纸本)9781479970056
In this paper, Takagi-Sugeno fuzzy classification system (T-S FCS) using particle swarm optimization (PSO) and support vector machine (SVM) for parameters optimization is proposed. The T-S FCS is constructed by fuzzy if-then rules whose consequents are linear state equations. The antecedents of T-S FCS are determined by the fuzzy membership of the input feature vectors. The prespecified values during the antecedent construction process are further optimized by using PSO. Consequent parameters in T-S FCS are learned through SVM. The proposed T-S FCS is able to minimize the effect of uncertainties, reduce the influence of artificial factors and give the system better generalization performance, which inherits the benefits of T-S fuzzy system, PSO and SVM. For demonstration, T-S FCS is used as a classifier in gender recognition. Comparisons with other mainstream classifiers, the advantages of the proposed T-S FCS are verified by experimental results.
暂无评论