• ETRI Journal
• /
• v.29 no.5
• /
• pp.697-699
• /
• 2007

Spatiograms are histograms augmented with spatial means and covariances to capture a richer description of the target. We present a particle filtering framework for region-based tracking using spatiograms. Unlike mean shift, the framework allows for non-differentiable similarity measures to compare two spatiograms; we present one such similarity measure, a combination of a recent weighting scheme and histogram intersection. Experimental results show improved performance with the new measure as well as the importance of global spatial information for tracking. The performance of spatiograms is compared with color histograms and several texture histogram methods.

• Communications for Statistical Applications and Methods
• /
• v.6 no.3
• /
• pp.813-820
• /
• 1999

Supprot vector machine(SVM) is a new and very promising regression and classification technique developed by Vapnik and his group at AT&T Bell Laboratories. in this paper we provide a brief overview of SVM for regression. Furthermore we describe Bayesian model selection based on macKay's evidence framework for SVM regression.

• Journal of Korean Society for Geospatial Information Science
• /
• v.9 no.1 s.17
• /
• pp.27-38
• /
• 2001

The GIS construction project using the Digital Map has been progressed actively since the enforcement of NGIS project in 1995. But, the Digital Map actually can't use directly in building GIS because of many defects of the digital map such as geometric features errors(the overshoot/undershoot of line or the opening of polygon), non-topology etc. Many advanced countries in GIS has provided users Framework Data which is generated topology defined spatial relationships and used as a basic data of national geospatial information. In this study, we proposed the definition and the scope of Framework Data as a basemap of the Nation Geospatial Information and studied for the management and construction of the Transportation/Road Framework Data which is a core and basic data among them.

• Bulletin of the Korean Chemical Society
• /
• v.12 no.3
• /
• pp.265-270
• /
• 1991

Theoretical calculations on the stabilization energies of framework atoms in hydrolyses Co(Ⅱ )-exchanged zeolite A were made using some potential energy functions and optimization program. The protons which are produced by hydrolysis of $[Co(H_2O)_n]^{2+}$ ion in large cavity showed a tendency to attack the framework oxygen atom O(1) preferentially, and the oxygen atom O(4) within OH- ion was coordinated at Al atom. The weakness of bonds between T(Si, Al) and oxygen by attack of proton and too large coordination number around small aluminum atom will make the framework of Co(Ⅱ)-exchanged zeolite A more unstable. The stabilization energy of $Co_4Na_4$-A framework (- 361.57 kcal/mol) was less than that of thermally stable zeolite A($Na_{12-}$A: - 419.68 kcal/mol) and greater than that of extremely unstable Ba(Ⅱ)-exchanged zeolite A($Ba_{6-}$A: - 324.01 kcal/mol). All the data of powder X-ray diffraction, infrared and Raman spectroscopy of Co(Ⅱ)-exchanged zeolite A showed the evidence of instability of its framework in agreement with the theoretical calculation. Three different groups of water molecules are found in hydrated Co(Ⅱ )-exchanged zeolite A; W(Ⅰ) group of water molecules having only hydrogen-bonds, W(Ⅱ) group water coordinated to $Na^+$ ion, ans W(Ⅲ) group water coordinated to Co(Ⅱ) ion. The averaged interaction energy of each water group shows the decreasing order of W(Ⅲ)>W(Ⅱ)>W(Ⅰ).

• Journal of applied mathematics & informatics
• /
• v.41 no.5
• /
• pp.1129-1143
• /
• 2023

Social media platforms have become an integral part of our daily lives, and they generate vast amounts of data that can be analyzed for various purposes. However, the quality of the data obtained from social media is often questionable due to factors such as noise, bias, and incompleteness. Enhancing data quality is crucial to ensure the reliability and validity of the results obtained from such data. This paper proposes an enhanced decision-making framework based on Business Decision Management Systems (BDMS) that addresses these challenges by incorporating a data quality enhancement component. The framework includes a backtracking method to improve plan failures and risk-taking abilities and a steep optimized strategy to enhance training plan and resource management, all of which contribute to improving the quality of the data. We examine the efficacy of the proposed framework through research data, which provides evidence of its ability to increase the level of effectiveness and performance by enhancing data quality. Additionally, we demonstrate the reliability of the proposed framework through simulation analysis, which includes true positive analysis, performance analysis, error analysis, and accuracy analysis. This research contributes to the field of business intelligence by providing a framework that addresses critical data quality challenges faced by organizations in decision-making environments.

• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.232-234
• /
• 2005

This paper will produce a practical, accurate method for computing the equipment forced outages rate (FOR) based on 10 years of historical equipment outages data. Also, the location and weather conditions on outages are included. The computed FOR are ranked as 4 groups (presumably high, medium, low & very low) depending on the frequency (up to # times per year) and a consistent framework for transmission reliability performance table is developed based on these groupings. Our intent is to use this framework as guidelines for contingency analysis criteria in system planning / operation departments. The concepts are illustrated on the 2005 KEPCO power system.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.73-86
• /
• 2020

The well-known sentence, "You can't manage what you don't measure" suggests the importance of measurement. The Ministry of National Defense (MND) in Korea is measuring the effort of informatization for various dimensions such as validity, adequacy, and effectiveness using the MND evaluation system to obtain positive and significant effects from informatization. MND views the defense informatization domain as divided into the defense informatization policy, the defense informatization project, and the defense informatization level, which can measure the informatization capability of the MND and the armed forces or organizations. Furthermore, it feels there is some limitation, such as those related to ambiguity and reliability, present in the system. To overcome the limitations in the existing system to evaluate the defense informatization policy, this study proposes a revised evaluation framework for the policy of defense informatization, its indicators, and measurement methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.85-87
• /
• 2018

Motivating by two promising technique of 5G, namely D2D and Edge computing, and the above mentioned problem of the current joint studies, We believe that more study is needed on the benefits of joining these two techniques in a single framework by more precisely taking into account the energy needed to computation, sending data, receiving data and as a result achieving more realistic energy efficiency in 5G cellular networks.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.222-223
• /
• 2018

본 논문에서는 인간과 사물, 서비스 세 가지 분산된 환경 요소에 대해 인간의 명시적 개입 없이 상호 협력적으로 정보 센싱, 네트워킹, 정보 처리 등 지능적인 기능을 제공하는 표준 IoT 플랫폼 기반에 대량의 이벤트에 대한 융합분석이 가능한 CEP(Complex Event Processing) 및 시나리오 기반 자동화된 절차에 따라 대응이 가능한 워크플로우 기술을 적용하여 중요시설감지, 국경감시, 해안감시, 도시안전 분야 등 다양한 분야에 활용이 가능한 지능형 시큐리티 플랫폼을 제안하고자 한다.

• Telecommunications review
• /
• v.24 no.5
• /
• pp.677-691
• /
• 2014

Connectivity is becoming more important keywords recently. For example, many devices are going to be connected to the internet. It is usually called as the IoT(internet of things). Many IoT devices can be evolved as a part of giant system of the world wide web. It is a great opportunity for us, because many new services can have emerged through this paradigm. In this paper, we propose a device virtualization framework for smart home service. The proposed framework connects the many home appliances devices and the internet using a dynamic protocol conversion. After our protocol conversion for device virtualization, our framework provides a RESTful API to access the resources of device through the internet. Therefore, the proposed framework can provide a variety of services, so it also can be developed into the ecosystem for smart home service. The current framework version only supports UPnP enabled devices of the home, but it can easily be extended to many other home middleware solutions. To verify the feasibility of the framework, we have implemented several service scenarios.