• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.481-486
• /
• 2021

Machine learning algorithms adopt criterion function as a key component to measure the quality of their model derived from data. Cluster analysis also uses this function to rate the clustering result. All the criterion functions have in general certain types of favoritism in producing high quality clusters. These clusters are then described by attributes and their values. Category utility and partition utility play an important role in cluster analysis. These are fully analyzed in this research particularly in terms of how they are related to the favoritism in the final results. In this research, several data sets are selected and analyzed to show how different results are induced from these criterion functions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.147-152
• /
• 2016

One of major issues in machine learning that extracts and acquires knowledge implicit in data is to find an appropriate way of representing it. Knowledge can be represented by a number of structures such as networks, trees, lists, and rules. The differences among these exist not only in their structures but also in effectiveness of the models for their problem solving capability. In this paper, we propose partition utility as a criterion function for clustering that can lead to simplification of the model and thus avoid overfitting problem. In addition, a heuristic is proposed as a way to construct balanced hierarchical models.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.3
• /
• pp.426-434
• /
• 2000

This paper deals with a generalized similarity solution for the one-dimensional solidification of ternary or higher-order multicomponent alloys. The present approach not only retains the existing features of binary systems such as temperature- solute coupling, shrinkage-induced flow, solid-liquid property differences, and finite back diffusion, but also is capable of handling a multicomponent alloy without restrictions on the partition coefficient and microsegregation parameter. For an alloy of N-solute species, governing equations in the mushy region reduce to (N+2) nonlinear ordinary differential equations via similarity transformation, which are to be solved along with the closed-form solutions for the solid and liquid regions. A linearized correction scheme adopted in the solution procedure facilitates to determine the solidus and liquidus positions stably. The result for a sample ternary alloy agrees excellently with the numerical prediction as well as the reported similarity solution. Additional calculations are also presented to show the utility of this study. Finally, it is concluded that the present analysis includes the previous analytical approaches as subsets.

• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.4
• /
• pp.355-361
• /
• 2004

The finite element method were used to determine the stress intensity factor of cracked plate. The stress method, displacement method and J Integral are most popular finte element method. ANSYS proposed another a kind of displacement method. In this paper, it was examined that the accuracy and utility of the ANSYS method could believable to determine the stress intensity factors of centered inclined crack. Generally, inclined crack has two portion of stress intensity factors, tensile mode F1 and shear mode F2. For the purpose of increasing the accuracy of stress intensity factors, examined the effect of the numbers of nodes and elements, crack tip element size and number of partition of the crack tip vicinity. It was found that the method proposed by ANSYS is useful and has high accuracy. Accuracy of calculated stress intensity factors was increased by increase of the number of nodes and elements, and at the small size of crack tip elements can get more highly accuracy.

• Journal of the Korean Society of Industry Convergence
• /
• v.12 no.3
• /
• pp.121-128
• /
• 2009

This study is for getting sacrificial service, discussing process of sacrificial rituals and understanding the composition of space in Dong-gok Jaesa. For these things, we're arranged for exact blueprint through actual survey and analyzed the architectural features. Dong-gok Jaesa has features which show centripetal space organization with strong closing sparsely. This is intended for sincerity during ritual which is processed without obstruction. This is a mixed form which is unified both straight dwelling and Jung Dang Hyeop Sil type. And this is for all functions which is necessary for Jaesa architecture in only one building. And this is used with organizing technique for space utility with connection of compartments and various enlargement and partition. Through these things, even though it is not a big Jaesa, it shows that this is Korea traditional composition of space technique according to several purposes.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.299-300
• /
• 2007

Along with the development of imaging sensors, hyperspectral imaging technology is growing rapidly and contributing to many fields of science nowadays. However, the bulky size and complex structure make it difficult to be processed. Focused on in this paper is the clustering utility, implemented in HYVEW, a program involving tools and functions to manipulate with hyperspectral images. The clustering process aims to partition the surface of the imaged area into subregions by grouping the spectra subject to the similarity of spectra.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.302-314
• /
• 2024

Purpose: This study proposes a fall detection model based on a top-down deep learning pose estimation model to automatically determine falls of multiple workers in an underground utility tunnel, and evaluates the performance of the proposed model. Method: A model is presented that combines fall discrimination rules with the results inferred from YOLOv8-pose, one of the top-down pose estimation models, and metrics of the model are evaluated for images of standing and falling two or fewer workers in the tunnel. The same process is also conducted for a bottom-up type of pose estimation model (OpenPose). In addition, due to dependency of the falling interference of the models on worker detection by YOLOv8-pose and OpenPose, metrics of the models for fall was not only investigated, but also for person. Result: For worker detection, both YOLOv8-pose and OpenPose models have F1-score of 0.88 and 0.71, respectively. However, for fall detection, the metrics were deteriorated to 0.71 and 0.23. The results of the OpenPose based model were due to partially detected worker body, and detected workers but fail to part them correctly. Conclusion: Use of top-down type of pose estimation models would be more effective way to detect fall of workers in the underground utility tunnel, with respect to joint recognition and partition between workers.

• Journal of Power System Engineering
• /
• v.21 no.6
• /
• pp.40-45
• /
• 2017

The objective of this study is the finite element-transfer stiffness coefficient method, which is the combination of the modeling technique of finite element method and the transfer technique of transfer stiffness coefficient method, is applied in the static analyses of two dimensional curved beam structures. To confirm the effectiveness of the applied method, two computational models are selected and analyzed by using finite element method, finite element-transfer stiffness coefficient method and exact solution. The computational results of the static analyses for two computational models using finite element-transfer stiffness coefficient method are equal to those using finite element method. When the element partition number of curved beam structure is increased, the computational results of the static analyses using both methods approach the exact solution. We confirmed that the finite element-transfer stiffness coefficient method is superior to finite element method when the number of the curved beam elements is increased from the viewpoints of the computational speed and the utility of computer memory.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.5
• /
• pp.288-300
• /
• 2003

Purpose: To obtain regional blood flow and tissue-blood partition coefficient with time-activity curves from ${H_2}^{15}O$ PET, fitting of some parameters in the Kety model is conventionally accomplished by nonlinear least squares (NLS) analysis. However, NLS requires considerable compuation time then is impractical for pixel-by-pixel analysis to generate parametric images of these parameters. In this study, we investigated several fast parameter estimation methods for the parametric image generation and compared their statistical reliability and computational efficiency. Materials and Methods: These methods included linear least squres (LLS), linear weighted least squares (LWLS), linear generalized least squares (GLS), linear generalized weighted least squares (GWLS), weighted Integration (WI), and model-based clustering method (CAKS). ${H_2}^{15}O$ dynamic brain PET with Poisson noise component was simulated using numerical Zubal brain phantom. Error and bias in the estimation of rCBF and partition coefficient, and computation time in various noise environments was estimated and compared. In audition, parametric images from ${H_2}^{15}O$ dynamic brain PET data peformed on 16 healthy volunteers under various physiological conditions was compared to examine the utility of these methods for real human data. Results: These fast algorithms produced parametric images with similar image qualify and statistical reliability. When CAKS and LLS methods were used combinedly, computation time was significantly reduced and less than 30 seconds for $128{\times}128{\times}46$ images on Pentium III processor. Conclusion: Parametric images of rCBF and partition coefficient with good statistical properties can be generated with short computation time which is acceptable in clinical situation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.181-187
• /
• 2020

In this paper, we proposed a register allocation algorithm and resource allocation algorithm in the high level synthesis process for the SoC design synthesis system of high performance vehicles We have analyzed to the operator characteristics and structure of datapath in the most important high-level synthesis. We also introduced the concept of virtual operator for the scheduling of multi-cycle operations. Thus, we demonstrated the complexity to implement a multi-cycle operation of the operator, regardless of the type of operation that can be applied for commonly use in the resources allocation algorithm. The algorithm assigns the functional operators so that the number of connecting signal lines which are repeatedly used between the operators would be minimum. This algorithm provides regional graphs with priority depending on connected structure when the registers are allocated. The registers with connecting structure are allocated to the maximum cluster which is generated by the minimum cluster partition algorithm. Also, it minimize the connecting structure by removing the duplicate inputs for the multiplexor in connecting structure and arranging the inputs for the multiplexor which is connected to the operators. In order to evaluate the scheduling performance of the described algorithm, we demonstrate the utility of the proposed algorithm by executing scheduling on the fifth digital wave filter, a standard bench mark model.