• Journal of KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.694-705
• /
• 2010

The mutation operation is the main operation in the evolutionary programming which has been widely used for the optimization of real valued function. In general, the mutation operation utilizes both a probability distribution and its parameter to change values of variables, and the parameter itself is subject to its own mutation operation which requires other parameters. However, since the optimal values of the parameters entirely depend on a given problem, it is rather hard to find an optimal combination of values of parameters when there are many parameters in a problem. To solve this shortcoming at least partly, if not entirely, in this paper, we propose a new mutation operation in which the parameter for the variable mutation is theoretically estimated from the self-adaptive perspective. Since the proposed algorithm estimates the scale parameter of the Cauchy probability distribution for the mutation operation, it has an advantage in that it does not require another mutation operation for the scale parameter. The proposed algorithm was tested against the benchmarking problems. It turned out that, although the relative superiority of the proposed algorithm from the optimal value perspective depended on benchmarking problems, the proposed algorithm outperformed for all benchmarking problems from the perspective of the computational time.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.55-61
• /
• 2020

Genetic Algorithm(GA) is applied to a problem that could not figure out its solution in a straightway. It is called as NP-hard problem. GA requires a high-performance system to be run on since the high-cost operations are needed such as crossover, selection, and mutation. Moreover, the scale of the problem domain is normally huge. That is why the straightway cannot be applied. To reduce the drawback of high-cost requirements, we try to answer if all the operations including mutation are necessary for all cases. In the experiment, we set up two cases of with/without mutation operations and gather the number of generations and the fitness of a solution. The subject in the experiment is Travelling Salesman Problem(TSP), which is one of the popular problems solved by GA. As a result, the cases with mutation operation are not faster and the solution is fitter than the case with mutation operation. From the result, the conclusion is that mutation operation does not always need for a better solution in a faster way.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.85-92
• /
• 2005

In this Paper, we develope an effective web-based learning contents using interactive genetic algorithms with modified mutation operation. In the interactive genetic algorithm, reciprocal exchange mutation is used. But. we modify the mutation operator to improve the learning effects. The new web-based learning contents using interactive genetic algorithm provide the dynamic learning contents providing and real-time test system. Especially, learners can execute the interactive genetic algorithm according to the learners' characters and interests to select the efficient learning environments and contents sequences.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.317-322
• /
• 2002

The major operations of Evolutionary Computation include crossover, mutation, competition and selection. Although selection does not create new individuals like crossover or mutation, a poor selection mechanism may lead to problems such as taking a long time to reach an optimal solution or even not finding it at all. In view of this, this paper proposes a hybrid Evolutionary Programming (EP) algorithm that exhibits a strong capability to move toward the global optimum even when stuck at a local minimum using a synergistic combination of the following three basic ideas. First, a "local selection" technique is used in conjunction with the normal tournament selection to help escape from a local minimum. Second, the mutation step has been improved with respect to the Fast Evolutionary Programming technique previously developed in our research group. Finally, the crossover and mutation operations of the Genetic Algorithm have been added as a parallel independent branch of the search operation of an EP to enhance search diversity.

• Journal of Korean Association for Spatial Structures
• /
• v.5 no.3 s.17
• /
• pp.117-122
• /
• 2005

This paper investigated the optimum design of truss structures based on Genetic Algorithms (GA's). With GA's characteristic of running side by side, the overall optimization and feasible operation, the optimum design model of truss structures was established. Elite models were used to assure that the best units of the previous generation had access to the evolution of current generation. Using of non-uniformity mutation brought the obvious mutation at earlier stage and stable mutation in the later stage; this benefited the convergence of units to the best result. In addition, to avoid GA's drawback of converging to local optimization easily, by the limit value of each variable was changed respectively and the genetic operation was performed two times, so the program could work more efficiently and obtained more precise results. Finally, by simulating evolution process of nature biology of a kind self-organize, self-organize, artificial intelligence, this paper established continuous structural optimization model for ten bars cantilever truss, and obtained satisfactory result of optimum design. This paper further explained that structural optimization is practicable with GA's, and provided the theoretic basis for the GA's optimum design of structural engineering.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.10
• /
• pp.83-92
• /
• 2017

Reconnaissance is performed gathering information from a series of scanning probes where the objective is to identify attributes of target hosts. Network reconnaissance of IP addresses and ports is prerequisite to various cyber attacks. In order to increase the attacker's workload and to break the attack kill chain, a few proactive techniques based on the network-based moving target defense (NMTD) paradigm, referred to as IP address mutation/randomization, have been presented. However, there are no commercial or trial systems deployed in real networks. In this paper, we propose a threat model and the request for requirements for developing NMTD techniques. For this purpose, we first examine the challenging problems in the NMTD mechanisms that were proposed for the legacy TCP/IP network. Secondly, we present a threat model in terms of attacker's intelligence, the intended information scope, and the attacker's location. Lastly, we provide seven basic requirements to develop an NMTD mechanism for the legacy TCP/IP network: 1) end-host address mutation, 2) post tracking, 3) address mutation unit, 4) service transparency, 5) name and address access, 6) adaptive defense, and 7) controller operation. We believe that this paper gives some insight into how to design and implement a new NMTD mechanism that would be deployable in real network.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.12
• /
• pp.573-580
• /
• 2017

Deep Neural Network (DNN) is a large layered neural network which is consisted of a number of layers of non-linear units. Deep Learning which represented as DNN has been applied very successfully in various applications. However, many issues in DNN have been identified through past researches. Among these issues, generalization is the most well-known problem. A Recent study, Dropout, successfully addressed this problem. Also, Dropout plays a role as noise, and so it helps to learn robust feature during learning in DNN such as Denoising AutoEncoder. However, because of a large computations required in Dropout, training takes a lot of time. Since Dropout keeps changing an inter-layer representation during the training session, the learning rates should be small, which makes training time longer. In this paper, using mutation operation, we reduce computation and improve generalization performance compared with Dropout. Also, we experimented proposed method to compare with Dropout method and showed that our method is superior to the Dropout one.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.12C
• /
• pp.1215-1227
• /
• 2002

This paper presents a genetic algorithmic approach to shortest path (SP) routing problem. Variable-length chromosomes (strings) and their genes (parameters) have been used for encoding the problem. The crossover operation that exchanges partial chromosomes (partial-routes) at positionally independent crossing sites and the mutation operation maintain the genetic diversity of the population. The proposed algorithm can cure all the infeasible chromosomes with a simple repair function. Crossover and mutation together provide a search capability that results in improved quality of solution and enhanced rate of convergence. Computer simulations show that the proposed algorithm exhibits a much better quality of solution (route optimality) and a much higher rate of convergence than other algorithms. The results are relatively independent of problem types (network sizes and topologies) for almost all source-destination pairs.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1202-1211
• /
• 2018

In this paper, induction machine operation efficiency and torque is improved using Machine Learning based Gene Optimization (ML-GO) Technique is introduced. Optimized Genetic Algorithm (OGA) is used to select the optimal induction machine data. In OGA, selection, crossover and mutation process is carried out to find the optimal electrical machine data for induction machine design. Initially, many number of induction machine data are given as input for OGA. Then, fitness value is calculated for all induction machine data to find whether the criterion is satisfied or not through fitness function (i.e., objective function such as starting to full load torque ratio, rotor current, power factor and maximum flux density of stator and rotor teeth). When the criterion is not satisfied, annealed selection approach in OGA is used to move the selection criteria from exploration to exploitation to attain the optimal solution (i.e., efficient machine data). After the selection process, two point crossovers is carried out to select two crossover points within a chromosomes (i.e., design variables) and then swaps two parent's chromosomes for producing two new offspring. Finally, Adaptive Levy Mutation is used in OGA to select any value in random manner and gets mutated to obtain the optimal value. This process gets iterated till finding the optimal value for induction machine design. Experimental evaluation of ML-GO technique is carried out with performance metrics such as torque, rotor current, induction machine operation efficiency and rotor power factor compared to the state-of-the-art works.

• Genomics & Informatics
• /
• v.12 no.4
• /
• pp.289-292
• /
• 2014

Next-generation sequencing (NGS) is widely used to identify the causative mutations underlying diverse human diseases, including cancers, which can be useful for discovering the diagnostic and therapeutic targets. Currently, a number of single-nucleotide variant (SNV)-calling algorithms are available; however, there is no tool for visualizing the recurrent and phenotype-specific mutations for general researchers. In this study, in order to support defining the recurrent mutations or phenotype-specific mutations from NGS data of a group of cancers with diverse phenotypes, we aimed to develop a user-friendly tool, named mutation arranger for defining phenotype-related SNV (MAP). MAP is a user-friendly program with multiple functions that supports the determination of recurrent or phenotype-specific mutations and provides graphic illustration images to the users. Its operation environment, the Microsoft Windows environment, enables more researchers who cannot operate Linux to define clinically meaningful mutations with NGS data from cancer cohorts.