• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.285-288
• /
• 2006

Most previous studies on improving the effectiveness of CBR have focused on the similarity function aspect or optimization of case features and their weights. However, according to some of the prior research, finding the optimal k parameter for the k-nearest neighbor (k-NN) is also crucial for improving the performance of the CBR system. Nonetheless, there have been few attempts to optimize the number of neighbors, especially using artificial intelligence (AI) techniques. In this study, we introduce a genetic algorithm (GA) to optimize the number of neighbors that combine, as well as the weight of each feature. The new model is applied to the real-world case of a major telecommunication company in Korea in order to build the prediction model for the customer profitability level. Experimental results show that our GA-optimized CBR approach outperforms other AI techniques for this mulriclass classification problem.

• Bulletin of the Korean Chemical Society
• /
• v.15 no.2
• /
• pp.106-112
• /
• 1994

Six physical properties (molecular weight, heat capacity, side chain weight, side chain volume, standard entropy and partial molar volume) of amino acids, peptides and their derivatives were examined by molecular modeling techniques. The molecular connectivity index, Wiener distance index and ad hoc descriptor are employed as structural parameters to encode information about branching, size, cyclization, unsaturation, heteroatom content and polarizability. This paper examines the correlation of the molecular modeling techique's parameters and the physicochemical properties of amino acids and their derivatives. As a result, calculated values were in agreement with experimental data in the above six physical properties of amino acids, peptides and their derivatives and the molecular connectivity index was superior to the other indices in fitting the calculated data.

• Journal of Magnetics
• /
• v.18 no.3
• /
• pp.331-338
• /
• 2013

We present a few significant advances in methods and concepts of magnetic measurements, aimed both at providing novel routes in the characterization of hard and soft magnetic materials and at improving our basic knowledge of the magnetization process. We discuss, in particular, investigation methods and experimental arrangements that have been developed in recent times for: 1) Hysteresis loop determination in extra-hard magnets by means of Pulsed Field Magnetometry; 2) Broadband observation of domain wall dynamics by highspeed stroboscopical Kerr techniques; 3) Entropy measurements in magnetocaloric materials by calorimetry in magnetic field. While pertaining to somewhat independent fields of investigation, all these measuring techniques have in common a solid approach to the underlying physical phenomenology and have a potential for further developments.

• Journal of the Korean Society of Visualization
• /
• v.17 no.1
• /
• pp.19-25
• /
• 2019

We report a study on the dynamics of the transport of a capsule immersed in a vertical pipe. Techniques to convey objects through liquid flow pipes using a hydraulic mean are used to transport sludge and hazardous materials. For the better understanding of the techniques, we developed a theoretical model to predict the transport speed of a cylindrical capsule in a vertical pipe. The comparison of the model prediction with the experiments shows that our model using the lubrication approximation precisely describes the experimental observations in cases where the gap between the capsule and pipe wall is sufficiently small. Our study suggests parameters to control the falling speed and thus enable an accurate control of the capsule speed in hydraulic transport systems.

• Smart Structures and Systems
• /
• v.22 no.6
• /
• pp.711-725
• /
• 2018

Most of the practical engineering structures exhibit nonlinearity due to nonlinear dynamic characteristics of structural joints, nonlinear boundary conditions and nonlinear material properties. Hence, it is highly desirable to detect and characterize the nonlinearity present in the system in order to assess the true behaviour of the structural system. Further, these identified nonlinear features can be effectively used for damage diagnosis during structural health monitoring. In this paper, we focus on the detection of the nonlinearity present in the system by confining our discussion to only a few selective time-frequency analysis and multivariate analysis based techniques. Both damage induced nonlinearity and inherent structural nonlinearity in healthy systems are considered. The strengths and weakness of various techniques for nonlinear detection are investigated through numerically simulated two different classes of nonlinear problems. These numerical results are complemented with the experimental data to demonstrate its suitability to the practical problems.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.665-675
• /
• 2019

In this paper, we compare and analyze the classification performance of deep learning algorithm Convolutional Neural Network(CNN) ac cording to ensemble generation and combining techniques. We used several CNN models(VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, GoogLeNet) to create 10 ensemble generation combinations and applied 6 combine techniques(average, weighted average, maximum, minimum, median, product) to the optimal combination. Experimental results, DenseNet169-VGG16-GoogLeNet combination in ensemble generation, and the product rule in ensemble combination showed the best performance. Based on this, it was concluded that ensemble in different models of high benchmarking scores is another way to get good results.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.381-382
• /
• 2019

Recently, various search techniques using artificial intelligence techniques have been introduced. It is also possible to use the artificial intelligence to grasp customer propensity. Analyzing the clothes that customers usually wear, it is possible to analyze various colors such as favorite colors, patterns, and fashion styles. In this study, we use artificial intelligence technology to create an application that distinguish between adults and children by combining various factors such as shape, type, color and size of human clothes. Through this, it will be possible to utilize it in a living area where children can be protected in advance by grasping the intrusion of unauthorized adults in the living area where children live mainly. In addition, in the future, we can obtain good results to detect stranger adult person if we apply this experimental result to the detection system using clothing information.

• Journal of Korea Game Society
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2021

In this paper, we considered that recently 3D game characters have been almost alike realistic expression because of a great mathematical computation and efficient techniques on GPU hardware. We presented the rendering technique and analysis for 3D game characters to simulate and render mathematical approach model from recent researches to perform the game engine for the surface reflection of lighting model. We compare our approach with the existing variant rendering techniques here using Open GL shader language on game engine. The experimental result will be provided the view-dependent visual appearance of variant and effective modeling characters for realistic expression using existing methods on the GPU for effective simulations and rendering process. Since there are many operations that are used redundantly while performing mathematical operations, the necessary functions and requirements have been to compute in advance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.31-36
• /
• 2021

RNA sequencing (RNA-Seq) is a technology that facilitates transcriptome analysis using next-generation sequencing (NSG) tools. Information on the quantity and sequences of RNA is vital to relate our genomes to functional protein expression. RNA-Seq data are characterized as being high-dimensional in that the number of variables (i.e., transcripts) far exceeds the number of observations (e.g., experiments). Given the wide range of dimensionality reduction techniques, it is not clear which is best for RNA-Seq data analysis. In this paper, we study the effect of three dimensionality reduction techniques to improve the classification of the RNA-Seq dataset. In particular, we use PCA, SVD, and SOM to obtain a reduced feature space. We built nine classification models for a cancer dataset and compared their performance. Our experimental results indicate that better classification performance is obtained with PCA and SOM. Overall, the combinations PCA+KNN, SOM+RF, and SOM+KNN produce preferred results.

• Nuclear Engineering and Technology
• /
• v.53 no.6
• /
• pp.1731-1735
• /
• 2021

The operation of the nuclear reactor requires accurate and fast methods and techniques for analysing its kinetics. These techniques become even more important when the MOX-fuel is used due to the lower value of delayed neutron fraction 𝛽 for ²³⁹Pu. Based on a Birth-and-Death process review, the mathematical model of thermal reactor core has been proposed different from existing ones. The analytical method for thermal point-reactor parameters evaluation is described within this work. The proposed method is applied for analysis of the unsteady transient processes taking place in a thermal reactor at its start-up or shutdown power change, as well as during small accidental power variation from the rated value. Theoretical determination of MASURCA reactor core reactivity through the analysis of experimental data on neutron time spectra was made.