• Environmental Engineering Research
• /
• v.25 no.4
• /
• pp.545-553
• /
• 2020

Rainfall-Runoff modeling plays a crucial role in various aspects of water resource management. It helps significantly in resolving the issues related to flood control, protection of agricultural lands, etc. Various Machine learning and statistical-based algorithms have been used for this purpose. These techniques resulted in outcomes with an acceptable rate of success. One of the pertinent machine learning algorithms namely Adaptive Neuro Fuzzy Inference System (ANFIS) has been reported to be a very effective tool for the purpose. However, the computational complexity of ANFIS is a major hindrance in its application. In this paper, we resolved this problem of ANFIS by incorporating one of the evolutionary algorithms known as Particle Swarm Optimization (PSO) which was used in estimating the parameters pertaining to ANFIS. The results of the modified ANFIS were found to be satisfactory. The performance of this modified ANFIS is then compared with conventional ANFIS and another popular statistical modeling technique namely ARIMA model with respect to the forecasting of runoff. In the present investigation, it was found that proposed PSO-ANFIS performed better than ARIMA and conventional ANFIS with respect to the prediction accuracy of runoff.

• Journal of KSNVE
• /
• v.3 no.4
• /
• pp.341-352
• /
• 1993

Although a frequency analysis by FFT algorithm has been widely used in the vibration community, this approach has somewhat limited features when an analysist want to see the details of frequency trends because FFT shows only energy contents along frequencies. So the concept of instantaneous frequency that represents the dominant frequency component at each time needs to be introduced. In this paper, to get the instantaneous frequency, two methods are used. Methods using Hilbert transform and evolutionary spectrum are those. One of the problems of estimating instantaneous frequency using Hilbert transform is that it is normally very sensitive to signal to noise ratio(SNR) because of the differentiation. Moving window is applied on the estimation of instantaneous frequency, and instantaneous frequency histogram are used to handle this problem and proved to be very effective. Computer simulations for various signals have been done to understand the characteristics of instantaneous frequency. The usefulness of signal analysis using instantaneous frequency was tested by three simple experiments, which were engine experiment, beam experiment, and car door experiment. The instantaneous frequency analysis is found to be a useful technique to analyze the signals that have time varying frequencies.

• Journal of Korea Game Society
• /
• v.11 no.2
• /
• pp.19-28
• /
• 2011

Level design is one of the important factors in tower defense game development. The difficulty of tower defense game depends on its wave design. In general, it requires a lot of manual labor to generate well-balanced waves with fun. In this paper, we propose a new automated wave generation system by using a genetic algorithm. With our system, a game designer can easily generate an optimized wave by designating the difficulty level in the initial stage of game design. Our system can be useful in reducing the trial-errors in the initial level design process of tower defense game development.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.4
• /
• pp.13-21
• /
• 2009

Game level design is one of the important parts in the commercial game development. Because of its complexity in combining game components, game design work could be classified into a non-linear problem. In this paper, we propose a new automated game level design system by using genetic algorithms. With our system, a game designer easily generates an optimized game level by designating the key parameters m the initial stage of game design. Our system can be useful in reducing the trial-errors in the initial game level design process.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.12
• /
• pp.1748-1755
• /
• 2015

A linear regression is widely used for prediction problem, but it is hard to manage an irregular nature of nonlinear system. Although nonlinear regression methods have been adopted, most of them are only fit to low and limited structure problem with small number of independent variables. However, real-world problem, such as weather prediction required complex nonlinear regression with large number of variables. GP(Genetic Programming) based evolutionary nonlinear regression method is an efficient approach to attach the challenging problem. This paper introduces the improvement of an GP based nonlinear regression method using ADF(Automatically Defined Function). It is believed ADFs allow the evolution of modular solutions and, consequently, improve the performance of the GP technique. The suggested ADF based GP nonlinear regression methods are compared with UM, MLR, and previous GP method for 3 days prediction of wind speed using MOS(Model Output Statistics) for partial South Korean regions. The UM and KLAPS data of 2007-2009, 2011-2013 years are used for experimentation.

• Genomics & Informatics
• /
• v.11 no.4
• /
• pp.272-276
• /
• 2013

Sequence analysis of the 16S rRNA gene has been widely used for the classification of microorganisms. However, we have been unable to clearly identify five Flavobacterium species isolated from a freshwater by using the gene as a single marker, because the evolutionary history is incomplete and the pace of DNA substitutions is relatively rapid in the bacteria. In this study, we tried to classify Flavobacterium species through multilocus sequence analysis (MLSA), which is a practical and reliable technique for the identification or classification of bacteria. The five Flavobacterium species isolated from freshwater and 37 other strains were classified based on six housekeeping genes: gyrB, dnaK, tuf, murG, atpA, and glyA. The genes were amplified by PCR and subjected to DNA sequencing. Based on the combined DNA sequence (4,412 bp) of the six housekeeping genes, we analyzed the phylogenetic relationship among the Flavobacterium species. The results indicated that MLSA, based on the six housekeeping genes, is a trustworthy method for the identification of closely related Flavobacterium species.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3126-3145
• /
• 2014

Cloud computing is a computing paradigm in which users can rent computing resources from service providers according to their requirements. A spot instance in cloud computing helps a user to obtain resources at a lower cost. However, a crucial weakness of spot instances is that the resources can be unreliable anytime due to the fluctuation of instance prices, resulting in increasing the failure time of users' job. In this paper, we propose a Genetic Algorithm (GA)-based workflow scheduling scheme that can find the optimal task size of each instance in a spot instance-based cloud computing environment without increasing users' budgets. Our scheme reduces total task execution time even if an out-of-bid situation occurs in an instance. The simulation results, based on a before-and-after GA comparison, reveal that our scheme achieves performance improvements in terms of reducing the task execution time on average by 7.06%. Additionally, the cost in our scheme is similar to that when GA is not applied. Therefore, our scheme can achieve better performance than the existing scheme, by optimizing the task size allocated to each available instance throughout the evolutionary process of GA.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.677-682
• /
• 2006

Multi-domain design is difficult because such systems tend to be complex and include a mixtures of electrical, mechanical, hydraulic, and thermal components. To design an optimal system, unified and automated procedure with efficient search technique is required. This paper introduces design method for multi-domain system to obtain design solutions automatically, combining bond graph which is domain independent modeling tool and genetic programming which is well recognized as a powerful tool for open-ended search. The suggested design methodology has been applied for design of electric fitter, electric printer drive, and and pump system as a proof of concept for this approach.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.5 s.143
• /
• pp.534-541
• /
• 2005

Until now, Korean shipyards have accumulated a great amount of data. But they do not have appropriate tools to utilize the data in practical works. Engineering data contains experts' experience and know-how in its own. It is very useful to extract knowledge or information from the accumulated existing data by using data mining technique This paper treats an evolutionary computation based on genetic programming (GP), which can be one of the components to realize data mining. The paper deals with linear models of GP for the regression or approximation problem when given learning samples are not sufficient. The linear model, which is a function of unknown parameters, is built through extracting all possible base functions from the standard GP tree by utilizing the symbolic processing algorithm. In addition to a standard linear model consisting of mathematic functions, one variant form of a linear model, which can be built using low order Taylor series and can be converted into the standard form of a polynomial, is considered in this paper. The suggested model can be utilized as a designing tool to predict design parameters with small accumulated data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.265-267
• /
• 2019

In this paper, we propose a method to automatically generate gray images similar to existing images using genetic algorithms. We have proposed two techniques for gene modeling, which is the most important design element to apply genetic algorithm to real field problems. Experiments were performed on two different sizes of gray images using each of the proposed techniques. Experimental results show that there is a large difference in the evolutionary performance of each technique in gene modeling for image generation. Therefore, it can be understood that gene modeling should be carefully decided in order to generate an image similar to the existing image in the future, or to learn quickly and naturally to generate an image synthesized from different images.