• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.133-138
• /
• 2006

Learning with Attribute Value Taxonomies (AVT) has shown that it is possible to construct accurate, compact and robust classifiers from a partially missing dataset (dataset that contains attribute values specified with different level of precision). Yet, in many cases AVTs are generated from experts or people with specialized knowledge in their domain. Unfortunately these user-provided AVTs can be time-consuming to construct and misguided during the AVT building process. Moreover experts are occasionally unavailable to provide an AVT for a particular domain. Against these backgrounds, this paper introduces an AVT generating method called GA-AVT-Learner, which finds a near optimal AVT with a given training dataset using a genetic algorithm. This paper conducted experiments generating AVTs through GA-AVT-Learner with a variety of real world datasets. We compared these AVTs with other types of AVTs such as HAC-AVTs and user-provided AVTs. Through the experiments we have proved that GA-AVT-Learner provides AVTs that yield more accurate and compact classifiers and improve performance in learning missing data.

• The KIPS Transactions:PartD
• /
• v.13D no.5 s.108
• /
• pp.691-698
• /
• 2006

The companies need the enterprise-wide support environment to build the competency to gather VOM(Voice of Market) in the process of preparing and implementing the strategy and to help establishing and managing the business process in order to secure the continuous competitive edge The enterprise-wide support environment to establish, operate, improve and evaluate the business process must be carried out. In this paper we define the method to define process and business rule in order to enable accurate execution of the process. Furthermore, collection and refection of accurate data concerning the competency of individuals, the subjects of the process execution, allows prevention of weakness of the process execution result and is the basis for identifying the areas of improvement. Therefore, high visibility can be attained through the work knowledge and processes presented in rules, and it can help firmly establish the process centered work culture (or system) in the organization by process improvement strictly based on data.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.5
• /
• pp.458-463
• /
• 2005

The total asset management system is used for banks or financial institutions for the management of trusteed assets or own assets and it is divided into three systems: the front-office system, the middle-office system and the back-office system by its business areas and functionalities. This kind of asset management system is a huge and complex system handling large data and various financial products, and requires professional knowledges like accounting, financial product specific knowledge, compliance and regulations, etc. It also performs high level computation for NAV calculation and risk measurement on every day Therefore, it needs absolute stability, extendability and efficiency and should handle the frequent change of regulation and products and connectivity with outdoor institutions. In this paper, we report our successful development of such a system and discuss issues regarding its efficient system design and system construction.

• The KIPS Transactions:PartA
• /
• v.14A no.6
• /
• pp.357-362
• /
• 2007

In distributed systems like cluster systems, in order to get more performance improvement, the initial task placement system precisely estimates and correctly assigns the resource requirement by the process. The resource-based initial job placement scheme needs the prediction of resource usage of a task in order to fit it to the most suitable hosts. However, the wrong prediction of resource usage causes serious performance degradation in dynamic load balancing systems. Therefore, in this paper, to resolve the problem due to the wrong prediction, we propose a new load metric. By the new load metric, the resource-based initial job placement scheme can work without priori knowledge about the type of process. Simulation results show that the dynamic load balancing system using the proposed approach achieves shorter execution times than the conventional approaches.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.12
• /
• pp.391-398
• /
• 2015

This paper devises a performance improvement and evaluation process of circuit minimization algorithms for mentorship education of distinguished informatics gifted secondary students. In the process, students learn that there are several alternative equivalent circuits for a target function and recognize the necessity for formalized circuit minimization methods. Firstly, they come at the concept of circuit minimization principle from Karnaugh Map which is a manual methodology. Secondly, they explore Quine-McCluskey algorithm which is a computational methodology. Quine-McCluskey algorithm's time complexity is high because it uses set operations. To improve the performance of Quine-McCluskey algorithm, we encourage them to adopt a bit-wise data structure instead of integer array for sets. They will eventually see that the performance achievement is about 36%. The ultimate goal of the process is to enlarge gifted students' interest and integrated knowledge about computer science encompassing electronic switches, logic gates, logic circuits, programming languages, data structures and algorithms.

• The KIPS Transactions:PartA
• /
• v.15A no.6
• /
• pp.351-360
• /
• 2008

It seems reasonable to assume that the individualized learning means more than simple teaching-learning method, so the instructional method has attracted a fair amount of attention not only in classroom, but also in the field of a adult education, cooperate education, and so on. In order to have an effect on individualized learning, we need to analyze and measure the learner's characteristic. However it is difficult to represent in quantified form because the conception and category of learner's characteristic is various and extensive. Therefore, in this paper, we propose a quantification method of learner's characteristic, which is limited to learner's cognitive structure and style, and is represented in the light of connectionism, verify the validity. The learner's cognitive structure in this paper was represented, which simplified the learner's cognitive structure. Additionally, the cognitive style in this paper was limited to inertia of knowledge for learner's cognition.

• The KIPS Transactions:PartD
• /
• v.15D no.2
• /
• pp.179-186
• /
• 2008

The converge of location-aware devices, GIS functionalities and the increasing accuracy and availability of positioning technologies pave the way to a range of new types of location-based services. The field of spatiotemporal data mining where relationships are defined by spatial and temporal aspect of data is encountering big challenges since the increased search space of knowledge. Therefore, we aim to propose algorithms for mining spatiotemporal patterns in mobile environment in this paper. Moving patterns are generated utilizing two algorithms called All_MOP and Max_MOP. The first one mines all frequent patterns and the other discovers only maximal frequent patterns. Our proposed approach is able to reduce consuming time through comparison with DFS_MINE algorithm. In addition, our approach is applicable to location-based services such as tourist service, traffic service, and so on.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.27-34
• /
• 2013

Background subtraction is one of the key techniques for automatic video content analysis, especially in the tasks of visual detection and tracking of moving object. In this paper, we present a new sample-based technique for background extraction that provides background image as well as background model. To handle both high-frequency and low-frequency events at the same time, multiple interval background models are adopted. The main innovation concerns the use of a confidence factor to select the best model from the multiple interval background models. To our knowledge, it is the first time that a confidence factor is used for merging several background models in the field of background extraction. Experimental results revealed that our approach based on multiple interval sampling works well in complicated situations containing various speed moving objects with environmental changes.

• Journal of Engineering Education Research
• /
• v.21 no.3
• /
• pp.56-65
• /
• 2018

With rapid advance of technologies including information and communication technologies, jobs are evolving faster than ever. Architectural engineering is no exception in this regard, and the green architectural engineering is emerging fast as a promising new field. In this study, a Delphi study of expert architectural engineers are conducted to find out (1) near future prospects of the field, (2) near future emerging jobs, (3) competencies needed for these jobs, and (4) educational content necessary to build these competencies with regards to the green architectural engineering. Initial Delphi survey consisting of open-ended questions in the above four areas were conducted and came out with 65 items after duplicate removal and semantic refinements. Further refinements via second and third wave of Delphi results into 40 items that the 13 architectural engineering experts may largely agree upon as future prospects with regards to the green architectural engineering. Findings indicate that it is expected that the demand for green architectural engineering and needs for automatic energy control system increase. Also, collaborations with other fields is becoming more and more important in green architectural engineering. The professional work management skills such as knowledge convergence, problem solving, collaboration skills, and creativity linking components from various related areas seem to also be on the increasing need. Near future ready critical skills are found to be the building environment control techniques (thermal, light, sound, and air), the data processing techniques like data mining, energy monitoring, and the control and utilization of environmental analysis software. Experts also agree on new curriculum for green building architecture to be developed with more of converging subjects across disciplines for future ready professional skills and experiences. Major topics to be covered in the near future includes building environment studies, building energy management, energy reduction systems, indoor air quality, global environment and natural phenomena, and machinery and electrical facility. Architectural engineering community should be concerned with building up the competencies identified in this Delphi preparing for fast advancing future.

• Journal of the Korean Society of Earth Science Education
• /
• v.13 no.3
• /
• pp.330-343
• /
• 2020

In this study, STEAM program on the subject of 'atmospheric circulation and surface current' was produced based on data and applied to 106 first-year high school students to analyze its effect and problem-solving processes. This program was organized to collect, refine, visualize, and analyze data and to allow communication processes to proceed based on these results. Using this, the concept of circulation in daily life was expanded from a global perspective to identify problems about circulation around the world. As a result of the application of the program, significant changes were identified in knowledge information processing competency. Also, significant changes were made in terms of convergence and creativity, which are sub categories among STEAM core competencies. It also sought to obtain suggestions for data-based STEAM education by analyzing students' responses in the form of a Text network.