• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.49-63
• /
• 2003

This paper proposes and implements a tool for the development of efficient and reliable expert system. In the expert system the inference is executed, based on the knowledges stored in the knowledge base of specific domain. To acquire the reliable results of inference, the expert system requires the facilities which can access the various kinds of knowledge and maintain the consistency and accuracy of knowledge. In this context this paper implemented the knowledge management system which maintains the consistency and accuracy of knowledge, adding selectively the knowledges without error to the knowledge base by verifying their error before the knowledges are added to the knowledge base. At the same time this paper made the expert system call and use the procedural knowledge and the declarative knowledge in the data base so that it might use the various kinds of knowledge in the process of inference.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.99-104
• /
• 2003

In this research, we proposed the mechanism to develop self evolving expert systems (SEES) based on data mining (DM), fuzzy neural networks (FNN), and relational database (RDB)-driven forward/backward inference engine. Most former researchers tried to develop a text-oriented knowledge base (KB) and inference engine (IE). However, thy have some limitations such as 1) automatic rule extraction, 2) manipulation of ambiguousness in knowledge, 3) expandability of knowledge base, and 4) speed of inference. To overcome these limitations, many of researchers had tried to develop an automatic knowledge extraction and refining mechanisms. As a result, the adaptability of the expert systems was improved. Nonetheless, they didn't suggest a hybrid and generalized solution to develop self-evolving expert systems. To this purpose, in this study, we propose an automatic knowledge acquisition and composite inference mechanism based on DM, FNN, and RDB-driven inference. Our proposed mechanism has five advantages empirically. First, it could extract and reduce the specific domain knowledge from incomplete database by using data mining algorithm. Second, our proposed mechanism could manipulate the ambiguousness in knowledge by using fuzzy membership functions. Third, it could construct the relational knowledge base and expand the knowledge base unlimitedly with RDBMS (relational database management systems). Fourth, our proposed hybrid data mining mechanism can reflect both association rule-based logical inference and complicate fuzzy logic. Fifth, RDB-driven forward and backward inference is faster than the traditional text-oriented inference.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.511-518
• /
• 2022

Supervised learning based on deep learning has made a leap forward in various application fields. However, many supervised learning methods work under the common assumption that training and test data are extracted from the same distribution. If it deviates from this constraint, the deep learning network trained in the training domain is highly likely to deteriorate rapidly in the test domain due to the distribution difference between domains. Domain adaptation is a methodology of transfer learning that trains a deep learning network to make successful inferences in a label-poor test domain (i.e., target domain) based on learned knowledge of a labeled-rich training domain (i.e., source domain). In particular, the unsupervised domain adaptation technique deals with the domain adaptation problem by assuming that only image data without labels in the target domain can be accessed. In this paper, we explore the unsupervised domain adaptation techniques.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.1222-1229
• /
• 1993

An advanced design environment , which is based on adaptive and knowledge -based finite elements (INTELMESH), has been developed. Unlike other approaches, INTEMMESH incorporates the information about the object geometry as well as the boundary and loading conditions to generate an ${\alpha}$-priori finite element mesh which is more refined around the critical regions of the problem domain. INTEMMESH is designed for planar domains and axisymmetric 3-D structures of elasticity and heat transfer subjected to mechanical and thermal loading . It intelligently identifies the critical regions/points in the problem domain and utilize the new concepts of substructuring and wave propagation to choose the proper mesh size for them. INTEMMESH generates well-shaped triangular elements by applying trangulartion and Laplacian smoothing procedures. The adaptive analysis involves the intial finite elements analyze and an efficient ${\alpha}$-posteriori error analysis involves the initial finite element anal sis and an efficient ${\alpha}$-posteriori error analysis and estimation . Once a problem is defined , the system automatically builds a finite element model and analyzes the problem though automatic iterative process until the error reaches a desired level. It has been shown that the proposed approach which initiates the process with an ${\alpha}$-priori, and near optimum mesh of the object , converges to the desired accuracy in less time and at less cost. Such an advanced design/analysis environment will provide the capability for rapid product development and reducing the design cycle time and cost.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.21 no.4
• /
• pp.477-489
• /
• 2015

Purpose: The purpose of this study was to develop an instrument to assess emergency room nurses' knowledge and performance of triage nursing. Methods: The instrument was developed through the stages of conceptual construction, item development, and validity and reliability testing. For the validity and reliability testing, data collected from 48 emergency room nurses using questionnaires was analyzed through descriptive statistics, factor analysis, and reliability coefficients. Results: The knowledge part consisted of 30 items in nine areas, and its reliability was low (KR-20 =0.50). The correct-answer rate was 71.8%. The performance section derived from the factor analysis was composed of two factors with nine items in the triage domain and three factors with 12 items in the non triage domain. The explanatory powers of these factors for the domains were 66.1% and 70.4%, respectively. The overall reliability (Cronbach's ${\alpha}$) was .95, and the reliabilities for the two domains were .88 and .91, respectively. The nurses' mean performance level was 3.2(${\pm}0.45$). Conclusion: The specific contents of the triage nursing work were identified from the developed scale; further research is necessary to in order to develop a scale capable of higher reliability and validity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.976-990
• /
• 2020

The k-means algorithm is widely used in academia and industry due to easy and simple implementation, enabling fast learning for complex datasets. However, k-means struggles to classify datasets without prior knowledge of specific domains. We proposed the repulsive k-means (RK-means) algorithm in a previous study to improve the k-means algorithm, using the repulsive force concept, which allows deleting unnecessary cluster centroids. Accordingly, the RK-means enables to classifying of a dataset without domain knowledge. However, three main problems remain. The RK-means algorithm includes a cluster repulsive force offset, for clusters confined in other clusters, which can cause cluster locking; we were unable to prove RK-means provided optimal convergence in the previous study; and RK-means shown better performance only normalize term and weight. Therefore, this paper proposes the advanced RK-means (ARK-means) algorithm to resolve the RK-means problems. We establish an initialization strategy for deploying cluster centroids and define a metric for the ARK-means algorithm. Finally, we redefine the mass and normalize terms to close to the general dataset. We show ARK-means feasibility experimentally using blob and iris datasets. Experiment results verify the proposed ARK-means algorithm provides better performance than k-means, k'-means, and RK-means.

• Korean Journal of Computational Design and Engineering
• /
• v.18 no.5
• /
• pp.309-320
• /
• 2013

Augmented reality (AR) is considered to be an excellent user interface to a 3D information space embedded within physical reality. For this reason, it has been applied to various applications such as design, medical service, interaction, and collaboration. However, there is no formal way of analyzing the research trend and evolution of augmented reality. This paper identifies the research trend and change in augmented reality (AR) via co-citation analysis. The co-citation analysis provides how the AR research has evolved, who are main contributors, and which papers suggest essential and influencing impact. To systematically analyze the cocitation, we have retrieved 1,145 papers from the Web of Science and applied a scientomertric analysis using CiteSpace. Based on the co-citation analysis of authors and documents, it is possible to analyze the evolution of augmented reality, key authors and papers, and breakthroughs. We have also compared the proposed approach with survey papers written by experts so that the result of the co-citation analysis can compromise the qualitative result done by experts, and thus it can provide a different view and insight for visualizing the research on augmented reality.

• Journal of the Korean Society for information Management
• /
• v.17 no.3
• /
• pp.45-70
• /
• 2000

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.802-805
• /
• 2002

In the three-dimensional domain image expressed with two-dimensional slice images, such as fMRI images and multi-slice CT images, we propose the three-dimensional domain automatic segmentation for the purpose of extracting region. In this paper, we segmented each domain from the fMRI images of the head of people and monkey. We used the neural network "Pulse-Coupled Neural Network" which is one of the models of visual cortex of the brain based on the knowledge from neurophysiology as the technique. By using this technique, we can segment the region without any learning. Then, we reported the result of division of each domain and extraction to the fMRI slice images of human's head using "three-dimensional Pulse-Coupled Neural Network" which is arranged and created the neuron in the shape of a three-dimensional lattice.

• BMB Reports
• /
• v.53 no.8
• /
• pp.413-418
• /
• 2020

ANKHD1 (ankyrin repeat and KH domain containing 1) is a large protein characterized by the presence of multiple ankyrin repeats and a K-homology domain. Ankyrin repeat domains consist of widely existing protein motifs in nature, they mediate protein-protein interactions and regulate fundamental biological processes, while the KH domain binds to RNA or ssDNA and is associated with transcriptional and translational regulation. In recent years, studies containing relevant information on ANKHD1 in cancer biology and its clinical relevance, as well as the increasing complexity of signaling networks in which this protein acts, have been reported. Among the signaling pathways of interest in oncology regulated by ANKHD1 are Hippo signaling, JAK/STAT, and STMN1. The scope of the present review is to survey the current knowledge and highlight future perspectives for ANKHD1 in the malignant phenotype of cancer cells, exploring biological, functional, and clinical reports of this protein in cancer.