• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.679-683
• /
• 2007

Statistical learning theory by Vapnik consists of support vector machine(SVM), support vector regression(SVR), and support vector clustering(SVC) for classification, regression, and clustering respectively. In this algorithms, SVC is good clustering algorithm using support vectors based on Gaussian kernel function. But, similar to SVM and SVR, SVC needs to determine kernel parameters and regularization constant optimally. In general, the parameters have been determined by the arts of researchers and grid search which is demanded computing time heavily. In this paper, we propose a differential evolution based SVC(DESVC) which combines differential evolution into SVC for efficient selection of kernel parameters and regularization constant. To verify improved performance of our DESVC, we make experiments using the data sets from UCI machine learning repository and simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.161-165
• /
• 2014

In this paper, we proposed the fuzzy prototype pattern classifier. In the proposed classifier, each prototype is defined to describe the related sub-space and the weight value is assigned to the prototype. The weight value assigned to the prototype leads to the change of the boundary surface. In order to define the prototypes, we use Fuzzy C-Means Clustering which is the one of fuzzy clustering methods. In order to optimize the weight values assigned to the prototypes, we use the Differential Evolutionary Algorithm. We use Linear Discriminant Analysis to estimate the coefficients of the polynomial which is the structure of the consequent part of a fuzzy rule. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.2
• /
• pp.183-193
• /
• 2016

Estimation of the stability of an operating tunnel through a back analysis is a difficult concept to analyze. Specially, when a relatively thick lining is constructed as in case of a subsea tunnel, there will be a limit to the use of displacement-based tunnel back analysis because the corresponding displacement is too small. In this study, DEA is adopted for tunnel back analysis and the feasibility of DEA for back analysis is evaluated. It is implemented in the finite difference code FLAC3D using its built-in FISH language. In addition, the stability of a tunnel lining will be evaluated from the development of displacement-based algorithm and its expanded algorithm with conformity of several parameters such as stress measurements.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1A
• /
• pp.9-18
• /
• 2009

This paper introduces the application of DE (Differential Evolutionary) method for the estimation of tensile force of the externally prestressed tendon. The proposed technique, a SI (System Identification) method using the DE algorithm, can make global solution search possible as opposed to classical gradient-based optimization techniques. The numerical tests show that the proposed technique employing DE algorithm is a useful method which can detect the effective nominal diameters as well as estimate the exact tensile forces of the externally prestressed tendon with an estimation error less than 1% although there is no a priori information about the identification variables. In addition, the validity of the proposed technique is experimentally proved using a scale-down model test considering the serviceability state condition without and with the loss of the prestressed force. The test results prove that the technique is a feasible and effective method that can not only estimate the exact tensile forces and detect the effective nominal diameters but also inspect the damping properties of test model irrespective of the loss of the prestressed force. The 2% error of the estimated effective nominal diameter is due to the difference between the real tendon diameter with a wired section and the FE model diameter with a full-section. Finally, The accuracy and superiority of the proposed technique using the DE algorithm are verified through the comparative study with the existing theories.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.5
• /
• pp.389-399
• /
• 2016

Efficiency for estimation of subsea tunnel safety can be increased through reflecting back analysis algorithm to displacement measurements besides other measurement information such as stress, water pressure and ground stiffness degradation. In this study, the finite difference code FLAC3D built-in FISH language is used. In addition, the stability of the tunnel lining will be evaluated from the development of displacement-based algorithm and its expanded algorithm with conformity of several parameters such as stress measurements, water pressure measurements, tunnel lining degradation measurements and ground stiffness degradation measurements. By using additional measurement information to assess the stability of subsea tunnel, it was confirmed that the error rate is reduced to the tunnel back analysis.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.11
• /
• pp.1809-1814
• /
• 2003

Differential evolution (DE) algorithm is presented and applied to global optimization in this research. DE suggested initially fur the solution to Chebychev polynomial fitting problem is similar to genetic algorithm(GA) including crossover, mutation and selection process. However, differential evolution algorithm is simpler than GA because it uses a vector concept in populating process. And DE turns out to be converged faster than CA, since it employs the difference information as pseudo-sensitivity In this paper, a trial vector and its control parameters of DE are examined and unconstrained optimization problems of highly nonlinear multimodal functions are demonstrated. To illustrate the efficiency of DE, convergence rates and robustness of global optimization algorithms are compared with those of simple GA.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.4
• /
• pp.27-35
• /
• 2019

This study confirmed the applicability to the field of geotechnical engineering for relatively complicated space and many target design variables in back analysis. The Sharan's equation and the Blum's method were used for the tunnel field and the retaining wall as a model for the multi-variate problem of geotechnical engineering. Optimization methods are generally divided into a deterministic method and a stochastic method. In this study, Simulated Annealing Method (SA) was selected as a deterministic method and Differential Evolution Algorithm (DEA) and Particle Swarm Optimization Method (PSO) were selected as stochastic methods. The three selected optimization methods were compared by applying a multi-variate model. The problem of deterministic method has been confirmed in the multi-variate back analysis of geotechnical engineering, and the superiority of DEA can be confirmed. DEA showed an average error rate of 3.12% for Sharan's solution and 2.23% for Blum's problem. The iteration number of DEA was confirmed to be smaller than the other two optimization methods. SA was confirmed to be 117.39~167.13 times higher than DEA and PSO was confirmed to be 2.43~6.91 times higher than DEA. Applying a DEA to the multi-variate back analysis of geotechnical problems can be expected to improve computational speed and accuracy.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.18 no.6
• /
• pp.545-556
• /
• 2016

If a back analysis is used in various measurement information for the estimation of an operating subsea tunnel safety, it is possible to obtain the results within efficient error rate. With such a commercial geotechnical analysis program as FLAC3D, back analysis is performed with a DEA which was validated in previous studies. However, there is a problem that is relatively a time-consuming analysis. For this reason, beam-spring model-based FEM solver which takes shorter relative analysis time, was developed by Python language, and then combined with the built-DEA. In order to consider the assessment of safety of an operation tunnel near real-time, a program for longitudinal direction tunnel was developed due to its relative easy development for analysis solver engine.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.2
• /
• pp.195-212
• /
• 2017

When back analysis is used for the assessment of an operating subsea tunnel safety in various measurement information such as stress, water pressure and tunnel lining and ground stiffness degradation, the reliable results within tolerable error rate can be obtained. By utilizing a commercial geotechnical analysis program FLAC3D, back analysis can be performed with a DEA which has already been successfully validated in previous studies. However, relative more time-consumption is the drawback of this approach. For this reason, this study introduced beam-spring model-based on FEM solver which uses less analysis time relatively. Beam-spring program capable of structural analysis of a circular tunnel section was developed by using Python language and combined with the built-DEA. From the measurement datum, expected to estimate the stability of an operation tunnel close to real-time.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.129-135
• /
• 2024

In this paper, we propose a new approach that enhances the continuous optimization performance of the MAP-Elites algorithm. The existing self-referencing MAP-Elites algorithm employed the "DE/rand/1/bin" operator from the differential evolution algorithm, which, due to its lack of rotational invariance, led to a degradation in optimization performance when there were high correlations among variables. The proposed algorithm replaces the "DE/rand/1/bin" operator with the "DE/current-to-rand/1" operator. This operator, possessing rotational invariance, ensures robust performance even in cases where there are high correlations among variables. Experimental results confirm that the proposed algorithm performs better than the comparison algorithms.