A method for designing wavelet filter banks that are adapted to the given signal is proposed. The method is based on optimising a certain cost function with constraint conditions. Gradient-descent optimisation techniq...
详细信息
A method for designing wavelet filter banks that are adapted to the given signal is proposed. The method is based on optimising a certain cost function with constraint conditions. Gradient-descent optimisation techniques are not adequate for the minimisation of such a cost function. evolutionary programming is used to resolve this difficult optimisation problem. Simulation results are given.
An evolutionary programming (EP)-based CLEAN and particle swarm optimization (PSO)-based CLEAN have better accuracy than the FFT-based CLEAN. EP-and PSO-based CLEAN have a higher computational burden, because they mus...
详细信息
An evolutionary programming (EP)-based CLEAN and particle swarm optimization (PSO)-based CLEAN have better accuracy than the FFT-based CLEAN. EP-and PSO-based CLEAN have a higher computational burden, because they must solve a three-dimensional optimization problem using the stochastic search method. To overcome this problem, we employ gradient descent to the CLEAN algorithm. We then compare the performance of the proposed method with that of the PSO-based CLEAN and the FFT-based CLEAN. Experimental results show that the proposed algorithm is faster and more accurate than conventional methods.(C) 2017 Wiley Periodicals, Inc.
There are growing initiatives to promote renewable energy in Hong Kong, particularly for solar energy. In order to encourage wider application of centralized solar water heating system for high-rise residential buildi...
详细信息
There are growing initiatives to promote renewable energy in Hong Kong, particularly for solar energy. In order to encourage wider application of centralized solar water heating system for high-rise residential buildings, it is important to pursue an optimal design to get significant energy-savings potential. In this regard, system optimization would be useful because it can relate to a number of design variables of the solar water heating system. The objective function is to maximize the year-round energy savings by using the solar heating against the conventional domestic electric heating. For the methodology of optimization, evolutionary programming, one of the paradigms of the evolutionary algorithm, was applied. From the optimization results, it is suggested that the solar collectors can be installed onto the external shading devices as an integrated architectural feature, since the optimal tilt angle is 21 deg and relatively flat. The optimal surface azimuth is southwest 16 deg, instead of due south. For the engineering design, both the optimal values of calorifier storage capacity. and pump flow rate show that the calculations from normal design practice may not achieve an optimal performance.
Computational methods can be used to provide an initial screening or a second opinion in medical settings and may improve the sensitivity and specificity of diagnoses. In the current study, linear discriminant models ...
详细信息
Computational methods can be used to provide an initial screening or a second opinion in medical settings and may improve the sensitivity and specificity of diagnoses. In the current study, linear discriminant models and artificial neural networks are trained to detect breast cancer in suspicious masses using radiographic features and patient age. Results on 139 suspicious breast masses (79 malignant, 60 benign, biopsy proven) indicate that a significant probability of detecting malignancies can be achieved at the risk of a small percentage of false positives. Receiver operating characteristic (ROC) analysis favors the use of linear models, however, a new measure related to the area under the ROC curve (A(Z)) suggests a possible benefit from hybridizing linear and nonlinear classifiers.
This paper presents a workbench to get simple neural classification models based on product evolutionary networks via a prior data preparation at attribute level by means of filter-based feature selection. Therefore, ...
详细信息
This paper presents a workbench to get simple neural classification models based on product evolutionary networks via a prior data preparation at attribute level by means of filter-based feature selection. Therefore, the computation to build the classifier is shorter, compared to a full model without data pre-processing, which is of utmost importance since the evolutionary neural models are stochastic and different classifiers with different seeds are required to get reliable results. Feature selection is one of the most common techniques for pre-processing the data within any kind of learning task. Six filters have been tested to assess the proposal. Fourteen (binary and multi-class) difficult classification data sets from the University of California repository at Irvine have been established as the test bed. An empirical study between the evolutionary neural network models obtained with and without feature selection has been included. The results have been contrasted with nonparametric statistical tests and show that the current proposal improves the test accuracy of the previous models significantly. Moreover, the current proposal is much more efficient than the previous methodology;the time reduction percentage is above 40%, on average. Our approach has also been compared with several classifiers both with and without feature selection in order to illustrate the performance of the different filters considered. Lastly, a statistical analysis for each feature selector has been performed providing a pairwise comparison between machine learning algorithms.
This paper presents two new computationally efficient improved stochastic algorithms for solving Security Constrained Optimal Power Flow (SCOPF) in interconnected power systems. These algorithms are based on the combi...
详细信息
This paper presents two new computationally efficient improved stochastic algorithms for solving Security Constrained Optimal Power Flow (SCOPF) in interconnected power systems. These algorithms are based on the combined application of Fuzzy Logic strategy incorporated in both evolutionary programming (EP) and Tabu Search (TS) algorithms, hence named as Fuzzy Mutated evolutionary programming (FMEP) and Fuzzy Guided Tabu Search (FGTS). The SCOPF calculation determines the schedule power system controls to achieve operation at a desired security level, while minimizing the generator fuel cost. The proposed methods are tested on single area IEEE 30-bus system and interconnected two area systems. The optimal solutions obtained using EP, TS, FMEP and FGTS are compared and analyzed. The analysis reveals that the proposed algorithms are relatively simple, efficient, reliable and suitable for real-time applications. And these algorithms can provide accurate solution with fast convergence and have the potential to be applied to other power engineering problems.
This paper investigates the applicability and effectiveness of modern heuristic techniques for solving SVC placement problem. Specifically, Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and evolutionary PS...
详细信息
This paper investigates the applicability and effectiveness of modern heuristic techniques for solving SVC placement problem. Specifically, Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and evolutionary PSO (EPSO) have been developed and successfully applied to find the optimal placement of SVC devices. The main objective of the proposed problem is to find the optimal number and sizes of the SVC devices to be installed in order to enhance the load margin when contingencies happen. SVC installation cost and load margin deviation are subject to be minimized. The proposed approaches have been successfully tested on IEEE 14 and 57 buses systems and a comparative study is illustrated. To evaluate the capability of the proposed techniques to solve large scale problems, they are also applied to a large scale mixed-integer nonlinear reactive power planning problem. Results of the application to IEEE 14 bus test system prove the feasibility of the proposed approaches and outperformance of PSO based techniques over GA.
In restructured environment, various transactions such as firm bilateral and multilateral transactions are taking place. An analysis is made on effects of transactions on Generation Expansion Planning (GEP). Some of t...
详细信息
In restructured environment, various transactions such as firm bilateral and multilateral transactions are taking place. An analysis is made on effects of transactions on Generation Expansion Planning (GEP). Some of the metaheuristic techniques such as Genetic Algorithm (GA), Differential Evolution (DE), evolutionary programming (EP), evolutionary Strategy (ES), Particle Swarm Optimization (PSO), Tabu Search (TS), Simulated Annealing (SA), and Hybrid Approach (HA) are applied to solve the Transactions-GEP problem with the support of AC-Optimal Power Flow (OPF) for the modified IEEE-30 bus test system with 6-years planning horizon. The original GEP problem is modified using the proposed methods i) Virtual Mapping Procedure (VMP), and ii) Penalty Factor Approach (PFA), to improve the effectiveness of the Metaheuristic techniques. Further, Intelligent Initial Population Generation (IIPG) and 'Store and Retrieve approach' are introduced in the solution techniques to reduce the computational time. PFA is used to convert the constrained problem into an unconstrained one. The results of the metaheuristic techniques are compared and validated with that of Dynamic programming (DP). The performances of each metaheuristic technique were compared in terms of their Success Rate (SR), Average Number of Generations (ANG), the error percentage and the mean execution time. The effects of various transactions on GEP are also analyzed.
evolutionary programs are capable of finding good solutions to difficult optimization problems. previous analysis of their convergence properties has normally assumed the strategy parameters are kept constant, althoug...
详细信息
evolutionary programs are capable of finding good solutions to difficult optimization problems. previous analysis of their convergence properties has normally assumed the strategy parameters are kept constant, although in practice these parameters are dynamically altered. In this paper, we propose a modified version of the 1/5-success rule for self-adaptation in evolution strategies (ES). Formal proofs of the long-term behavior produced by our self-adaptation method are included. Both elitist and non-elitist ES variants are analyzed. Preliminary tests indicate an ES with our modified self-adaptation method compares favorably to both a non-adapted ES and a 1/5-success rule adapted ES.
C.M. Breneman and M. Rhem [Journal of Computational Chemistry, 18 (1997) 182], recently published data sets containing electronic van der Waals surface property descriptors and the experimental HPLC capacity factors u...
详细信息
C.M. Breneman and M. Rhem [Journal of Computational Chemistry, 18 (1997) 182], recently published data sets containing electronic van der Waals surface property descriptors and the experimental HPLC capacity factors using either ODS or CPK columns for a series of compounds. This study uses one of these data sets (the HPLC ODS column capacity factors [log(k')]) in a Quantitative Structure/Property analysis. The chosen data set contains 22 molecules with 118 descriptors each. Two simple prescreening methods are examined to determine if they can properly reduce the number of descriptors. One method is found to fail, while the other is used to reduce the number of descriptors to111. Three different computational methods are used to generate 5-descriptor, linear relationships with this reduced data set. The first, and fastest method uses a series of 1-dimensional fits to the capacity factors and residual errors. The second method uses an evolutionary programming (EP) paradigm to choose all five descriptors and the third is a complete search over all sets of five descriptors. This paper outlines each of these computational methods and presents their accuracy and CPU requirements. Though the EP method does outperform the stepwise fit, it initially fails to find the best relationships, A close examination of the terms present in the 100 best relationships shows why this data set is not amenable to a QSPR generation technique that uses either a Genetic Algorithm or evolutionary programming. By allowing the EP program to retain relationships with an incorrect number of descriptors, it is able to find the best overall 5-descriptor, linear relationship. (C) 1999 Elsevier Science B.V. All rights reserved.
暂无评论