• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.10
• /
• pp.103-112
• /
• 1999

Genetic algorithm, which uses principles of natural selection and population genetics, is an efficient method to find out an optimal solution. In conventional genetic algorithms, however, the size of gene pool needs to be increased to insure a convergency. Therefore, many memory spaces and much computation time were needed. Also, since child chromosomes were generated by chromosome crossover and gene mutation, the algorithms have a complex structure. Thus, in this paper, a compact stereo matching algorithm using a population-based incremental learning based on probability vector is proposed to reduce these problems. The PBIL method is modified for matching environment. Since th proposed algorithm uses a probability vector and eliminates gene pool, chromosome crossover, and gene mutation, the matching algorithm is simple and the computation load is considerably reduced. Even though the characteristics of images are changed, stable outputs are obtained without the modification of the matching algorithm.

• Journal of Environmental Impact Assessment
• /
• v.20 no.3
• /
• pp.357-365
• /
• 2011

The QUAL2K has the same basic characteristics as the QUAL2E model, which has been widely used in stream water quality modeling; in QUAL2K, however, various functions are supplemented. The QUAL2Kw model uses a genetic algorithm(GA) for automatic calibration of QUAL2K, and it can search for optimum water quality parameters efficiently using the calculation results of the model. The QUAL2Kw model was applied to the Gangneung Namdaecheon River on the east side of the Korean Peninsula. Because of the effluents from the urban area, the middle and lower parts of the river are more polluted than the upper parts. Moreover, the hydraulic characteristics differ between the lower and upper parts of rivers. Thus, the river reaches were divided into seven parts, auto-calibration for the multiple reaches was performed using the function of the user-defined automatic calibration of the rates worksheets. Because GA parameters affect the optimal solution of the model, the impact of the GA parameters used in QUAL2Kw on the fitness of the model was analyzed. Sensitivity analysis of various factors, such as population size, crossover probability, crossover mode, strategy for mutation and elitism, mutation rate, and reproduction plan, were performed. Using the results of this sensitivity analysis, the optimum GA parameters were selected to achieve the best fitness value.

• Clinical and Experimental Reproductive Medicine
• /
• v.41 no.4
• /
• pp.168-173
• /
• 2014

The purpose of this study is to report a successful twin pregnancy and delivery in a female patient with X-linked dominant incontinentia pigmenti (IP) who underwent assisted reproductive technology followed by preimplantation genetic screening (PGS). A 29-year-old female with IP had a previous history of recurrent spontaneous abortion. A molecular analysis revealed the patient had a de novo mutation, 1308_1309insCCCCTTG(p.Ala438ProfsTer26), in the inhibitor of the kappa B kinase gamma gene located in the Xq28 region. IVF/ICSI and PGS was performed, in which male embryos were sexed using array-based comparative genomic hybridization (aCGH). After IVF/ICSI and PGS using aCGH on seven embryos, two euploid male blastocysts were transferred with a 50% probability of a viable male pregnancy. The dizygotic twin pregnancy was confirmed and the amniocentesis results of each twin were normal with regard to the mutation found in the mother. The patient delivered healthy twin babies during the 37th week of gestation. This case shows the beneficial role of PGS in achieving a successful pregnancy through euploid male embryo gender selection in a woman with X-linked dominant IP with a history of multiple male miscarriages.

• Journal of Korean Society on Water Environment
• /
• v.23 no.5
• /
• pp.697-704
• /
• 2007

This study proposes an integrated technique of Genetic Algorishim (GA) and Geographic Information System (GIS) for designing the water quality monitoring networks. To develop solution scheme of the integrated system, fitness functions are defined by the linear combination of five criteria which stand for the operation objectives of water quality monitoring stations. The criteria include representativeness of a river system, compliance with water quality standards, supervision of water use, surveillance of pollution sources and examination of water quality changes. The fitness level is obtained through calculations of the fitness functions and input data from GIS. To find the most appropriate parameters for the problems, the sensitivity analysis is performed for four parameters such as number of generations, population sizes, probability of crossover, and probability of mutation. Using the parameters resulted from the sensitivity analysis, the developed system proposed 110 water quality monitoring stations in the Nakdong River. This study demonstrates that the integrated technique of GA and GIS can be utilized as a decision supporting tool in optimized design for a water quality monitoring network.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.65-73
• /
• 1997

This paper proposes a new method of the structure pruning of dynamic recurrent neural networks (DRNN) using evolutionary computations. In general, evolutionary computations are population-based search methods, therefore it is very useful when several different properties of neural networks need to be optimized. In order to prune the structure of the DRNN in this paper, we used the evolutionary programming that searches the structure and weight of the DRNN and evolution strategies which train the weight of neuron and pruned the net structure. An addition or elimination of the hidden-layer's node of the DRNN is decided by mutation probability. Its strategy is as follows, the node which has mhnimum sum of input weights is eliminated and a node is added by predesignated probability function. In this case, the weight is connected to the other nodes according to the probability in all cases which can in- 11:ract to the other nodes. The proposed pruning scheme is exemplified on the stabilization and position control of the inverted-pendulum system and visual servoing of a robot manipulator and the effc: ctiveness of the proposed method is demonstrated by numerical simulations.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.429-436
• /
• 2005

A simple stereo matching algorithm using population-based incremental learning(PBIL) is proposed in this paper to decrease the general problem of genetic algorithms, such as memory consumption and inefficiency of search. PBIL is a variation of genetic algorithms using stochastic search and competitive teaming based on a probability vector. The structure of PBIL is simpler than that of other genetic algorithm families, such as serial and parallel ones, due to the use of a probability vector. The PBIL strategy is simplified and adapted for stereo matching circumstances. Thus, gene pool, chromosome crossover, and gene mutation we removed, while the evolution rule, that fitter chromosomes should have higher survival probabilities, is preserved. As a result, memory space is decreased, matching rules are simplified and computation cost is reduced. In addition, a scheme controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities, like a result of coarse-to-fine matchers. Because of this scheme, the proposed algorithm can produce a stable disparity map with a small fixed-size window. Finally, an alterative version of the proposed algorithm without using probability vector is also presented for simpler set-ups.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.537-544
• /
• 2020

Advances in detection techniques, such as mutation and obfuscation, are being advanced with the development of malware technology. In the malware detection technology, unknown malware detection technology is important, and a method for Malware Authorship Attribution that detects an unknown malicious code by identifying the author through distributed malware is being studied. In this paper, we try to extract the compiler information affecting the binary-based author identification method and to investigate the sensitivity of feature selection, probability and non-probability models, and optimization to classification efficiency between studies. In the experiment, the feature selection method through information gain and the support vector machine, which is a non-probability model, showed high efficiency. Among the optimization studies, high classification accuracy was obtained through feature selection and model optimization through the proposed framework, and resulted in 48% feature reduction and 53 faster execution speed. Through this study, we can confirm the sensitivity of feature selection, model, and optimization methods to classification efficiency.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.259-262
• /
• 1997

This paper presents a visual servoing of RV-M2 robot manipulators to track and grasp moving object, using pruned dynamic recurrent neural networks(DRNN). The object is stationary in the robot work space and the robot is tracking and grasping the object by using CCD camera mounted on the end-effector. In order to optimize the structure of DRNN, we decide the node whether delete or add, by mutation probability, first in case of delete node, the node which have minimum sum of input weight is actually deleted, and then in case of add node, the weight is connected according to the number of case which added node can reach the other nodes. Using evolutionary programming(EP) that search the struture and weight of the DRNN, and evolution strategies(ES) which train the weight of neuron, we pruned the net structure of DRNN. We applied the DRNN to the Visual Servoing of a robot manipulators to control position and orientation of end-effector, and the validity and effectiveness of the pro osed control scheme will be verified by computer simulations.

• International Journal of Aeronautical and Space Sciences
• /
• v.11 no.3
• /
• pp.227-233
• /
• 2010

In this study, a genetic algorithm was utilized to optimize the stacking sequence of a composite plate subjected to a high velocity impact. The aim is to minimize the maximum backplane displacement of the plate. In the finite element model, we idealized the impactor using solid elements and modeled the composite plate by shell elements to reduce the analysis time. Various tests were carried out to investigate the effect of parameters in the genetic algorithm such as the type of variables, population size, number of discrete variables, and mutation probability.

• IE interfaces
• /
• v.17 no.spc
• /
• pp.28-36
• /
• 2004

The main purpose of this study is to find out the optimal solution of the vehicle routing problem considering heterogeneous vehicle(s), double-trips, and multi depots. This study suggests a mathematical programming model with new numerical formula which considers the amount of delivery and sub-tour elimination and gives optimal solution by using OPL-STUDIO(ILOG). This study also suggests modified genetic algorithm which considers the improvement of the creation method for initial solution, application of demanding point, individual and last learning method in order to find excellent solution, survival probability of infeasible solution for allowance, and floating mutation rate for escaping from local solution. The suggested modified genetic algorithm is compared with optimal solution of the existing problems. We found the better solution rather than the existing genetic algorithm. The suggested modified genetic algorithm is tested by Eilon and Fisher data(Eilon 22, Eilon 23, Eilon 30, Eilon 33, and Fisher 10), respectively.