• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.1
• /
• pp.86-93
• /
• 2007

A new operation termed competitive generation in the processes of genetic algorithms is proposed for accelerating the optimization speed of genetic algorithms. The competitive generation devised by considering the competition of sperms for fertilization provides a good opportunity for the genetic algorithms to approach global optimum without falling into local optimum. Experimental results with typical problems showed that the genetic algorithms with competitive generation are superior to those without the competitive generation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.10
• /
• pp.819-826
• /
• 2001

Genetic algorithms are becoming more popular because of their relative simplicity and robustness. Genetic algorithms are global search techniques for nonlinear optimization. However, traditional genetic algorithms, though robust, are generally not the most successful optimization algorithm on any particular domain because they are poor at hill-climbing, whereas simulated annealing has the ability of probabilistic hill-climbing. Therefore, hybridizing a genetic algorithm with other algorithms can produce better performance than using the genetic algorithm or other algorithms independently. In this paper, we propose an efficient hybrid optimization algorithm named the adaptive random signal-based learning. Random signal-based learning is similar to the reinforcement learning of neural networks. This paper describes the application of genetic algorithms and simulated annealing to a random signal-based learning in order to generate the parameters and reinforcement signal of the random signal-based learning, respectively. The validity of the proposed algorithm is confirmed by applying it to two different examples.

• Industrial Engineering and Management Systems
• /
• v.10 no.1
• /
• pp.15-23
• /
• 2011

This research considers scheduling problems with jobs which can be divided into sub-jobs and do not required to be processed immediately following one another. Heuristic algorithms considering how to divide jobs are proposed in an attempt to find near-optimal solutions within reasonable run time. The algorithms contain two phases which are executed recursively. Phase 1 of the algorithm determines how jobs should be divided while phase 2 solves the scheduling problem given the sub-jobs established in phase 1. Simulated annealing and genetic algorithms are applied for the two phases and four heuristic algorithms are established. Numerical experiment is conducted to determine the best parameter values for the heuristic algorithms. Examples with different sizes and levels of complexity are generated. Performance of the proposed algorithms is evaluated. It is shown that the proposed algorithms are able to efficiently and effectively solve the considered problems.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.1
• /
• pp.31-36
• /
• 2010

Many clustering algorithms have been used in diverse fields. When we need to group given data set into clusters, many clustering algorithms based on similarity or distance measures are considered. Most clustering works have been based on hierarchical and non-hierarchical clustering algorithms. Generally, for the clustering works, researchers have used clustering algorithms case by case from these algorithms. Also they have to determine proper clustering methods subjectively by their prior knowledge. In this paper, to solve the subjective problem of clustering we make empirical comparisons of popular clustering algorithms which are hierarchical and non hierarchical techniques using Silhouette measure. We use silhouette information to evaluate the clustering results such as the number of clusters and cluster variance. We verify our comparison study by experimental results using data sets from UCI machine learning repository. Therefore we are able to use efficient and objective clustering algorithms.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.420-426
• /
• 1998

Evolutionary algorithms are probabilistic optimization algorithms based on the model of natural evolution. Recently the efforts to improve the performance of evolutionary algorithms have been made extensively. In this paper, we introduce the research for improving the convergence rate and search faculty of evolution algorithms by using reinforcement learning. After providing an introduction to evolution algorithms and reinforcement learning, we present adaptive genetic algorithms, reinforcement genetic programming, and reinforcement evolution strategies which are combined with reinforcement learning. Adaptive genetic algorithms generate mutation probabilities of each locus by interacting with the environment according to reinforcement learning. Reinforcement genetic programming executes crossover and mutation operations based on reinforcement and inhibition mechanism of reinforcement learning. Reinforcement evolution strategies use the variances of fitness occurred by mutation to make the reinforcement signals which estimate and control the step length.

• Smart Structures and Systems
• /
• v.30 no.3
• /
• pp.263-271
• /
• 2022

In this paper we present an overview of damage diagnosis algorithms that have been developed over the past two decades using vibration signals obtained from structures. Then, the paper focuses primarily on algorithms that can be used following an extreme event such as a large earthquake to identify structural damage for responding in a timely manner. The algorithms presented in the paper use measurements obtained from accelerometers and gyroscope to identify the occurrence of damage and classify the damage. Example algorithms are presented include those based on autoregressive moving average (ARMA), wavelet energies from wavelet transform and rotation models. The algorithms are illustrated through application of data from test structures such as the ASCE Benchmark structure and laboratory tests of scaled bridge columns and steel frames. The paper concludes by identifying needs for research and development in order for such algorithms to become viable in practice.

• IE interfaces
• /
• v.23 no.2
• /
• pp.164-175
• /
• 2010

In logistics e-marketplaces, brokerage agents intermediate empty vehicles and freights registered by car owners and shippers. In the previous research, we proposed constant periodic/fixed matching algorithms for the logistics brokerage agents with the objective of minimizing the total transportation lead time and the transportation due date tardiness of freights(Jeong, 2004; Jeong, 2007). However, the constant type algorithms cannot consider changes in the balance status of an e-marketplace, i.e. the difference between the numbers of freights and vehicles to wait for matching, because they use non-changing matching periods and amounts. In this paper, we propose variable type algorithms for the logistics brokerage agent, in which the matching periods and amounts are changed continuously by considering the balance status between the freights and vehicles. In order to compare performance of the variable type algorithms to the previous constant type algorithms, we carried out computational experiments on various problem instances. The results show that the variable type algorithms give better performance than the constant type algorithms. We can expect that the logistics brokerage agents can improve their performance by using the proposed variable periodic/fixed matching algorithms.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3864-3877
• /
• 2022

We propose a new approach called PESA (Prioritized replay Evolutionary and Swarm Algorithms) combining prioritized replay of reinforcement learning with hybrid evolutionary algorithms. PESA hybridizes different evolutionary and swarm algorithms such as particle swarm optimization, evolution strategies, simulated annealing, and differential evolution, with a modular approach to account for other algorithms. PESA hybridizes three algorithms by storing their solutions in a shared replay memory, then applying prioritized replay to redistribute data between the integral algorithms in frequent form based on their fitness and priority values, which significantly enhances sample diversity and algorithm exploration. Additionally, greedy replay is used implicitly to improve PESA exploitation close to the end of evolution. PESA features in balancing exploration and exploitation during search and the parallel computing result in an agnostic excellent performance over a wide range of experiments and problems presented in this work. PESA also shows very good scalability with number of processors in solving an expensive problem of optimizing nuclear fuel in nuclear power plants. PESA's competitive performance and modularity over all experiments allow it to join the family of evolutionary algorithms as a new hybrid algorithm; unleashing the power of parallel computing for expensive optimization.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.693-696
• /
• 2021

There are various algorithms in reinforcement learning, and the algorithm used differs depending on the field. Even in games, specific algorithms are used when developing AI (artificial intelligence) using reinforcement learning. Different algorithms have different learning methods, so artificial intelligence is created differently. Therefore, the developer has to choose the appropriate algorithm to implement the AI for the purpose. To do that, the developer needs to know the algorithm's learning method and which algorithms are effective for which AI. Therefore, this paper compares the learning methods of three algorithms, SAC, PPO, and POCA, which are algorithms used to implement game AI. These algorithms are practical to apply to which types of AI implementations.

• 한국정보교육학회:학술대회논문집
• /
• 2004.08a
• /
• pp.236-241
• /
• 2004

Algorithms is defined "step-by-step procedure for accomplishing a task that we wish to complete." Algorithms has much educational values. Already many scholar is making researches about paper-and-pencil algorithms in mathematic education. The purpose of this paper is to propose a study on the direction of teaching algorithms with analysis of algorithms