• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.27-30
• /
• 2018

의사결정나무를 이용한 토마토 스마트 팜 용 전문가시스템을 설계하여 각 하우스의 주변 환경에 따라 달라지는 요소들에 의해 생성되는 데이터를 사용하여 보다 농민의 결정과 비슷한 의사결정구조를 가진 제어시스템을 구축한다. 현재 스마트 팜의 제어시스템은 지금까지 농민들이 해온 방식과 유사하게 스스로 제어하지 못하였기에 스마트 팜 제어시스템의 의존율은 여전히 높지 못하다. 스마트 팜 내의 센서 값 등 주변 환경을 기준으로 한 환경제어에 농민들의 직접적인 개입이 필수불가결 하다. 그래서 보다 농민의 의사결정과 비슷한 시스템을 만들기 위하여 전문가시스템에 의사결정나무를 접목시킨 제어기를 설계하는 것을 목표로 하였다. 하우스 내의 장비를 제어하기에 앞서 여러 환경요소 중에 가장 직접적인 영향을 미치는 것을 자동으로 선정한 후, 농민들의 의사결정 선정기준을 포함시켜 복합적인제어를 위하여 전문가시스템을 구축한다. 이번 연구는 무거운 툴을 사용하지 않고 데이터를 이용하여 결과를 도출하는 것에 초점을 맞추어 진행하였다. 현재 많은 농장에서 스마트 팜을 이용한 데이터들이 쏟아져 나오고 있고 이것을 농민들이 손쉽고 빠르게 접근하여 직접적인 개입을 줄일 수 있는 방법론에 대한 표준이 될 수 있을 것으로 예상 한다.

• 디지털융복합연구
• /
• 제8권1호
• /
• pp.55-69
• /
• 2010

본 연구는 기업의 윤리정책이 윤리적 의사결정에 행위에 미치는 영향에서 개인특성요인의 조절효과를 분석하는데 초점을 맞추었다. 연구의 대상은 서울 및 수도권에 근무하는 정규직 근로자(n=211)을 대상으로 하였으며, 연구모형을 설정하고 이를 통계적 절차에 의하여 검정하였다. 통계분석에는 신뢰도와 타당도 분석, 상관분석, 분산분석 및 조절회귀분석(MRA)을 실시하였다. 본 연구의 분석결과로 첫째, 조직의 윤리강령이 있고 이를 실행하는 강도가 높을수록, 기업이 추구하는 가치가 높다고 구성원들이 인지하는 정도가 높을수록 윤리적 의사결정에 영향을 미치는 것으로 나타났다. 즉, 기업외적 윤리적 의사결정의 평가 요인보다 내부적 요인에 의해 직접적인 영향을 받고 있음을 것을 시사하며, 기업의 의사결정이 투명하게 이루어지고 이를 조직구성원들에게 인지토록 하는 것이 필요하다. 둘째, 본 연구에서 설정한 조직의 장기비전에 대하여 높은 인지와 내재적인 통제의 위치에 있는 구성원들이 기업의 윤리적 의사결정에 있어 독립변수의 역할을 수행할 뿐만 아니라 조절변수로서의 역할을 수행하고 있음을 알 수 있다. 또한 통제변수로 사용한 많은 변수간의 윤리적 의사결정수준의 차이가 있음을 알 수 있는데 이는 개인특성요인과 관련된 것으로 향후 높은 윤리적 의사결정의 실행을 위해서는 통제변수의 특성을 고려한 차별화된 교육의 실시가 요구된다.

• 한국농공학회논문집
• /
• 제51권6호
• /
• pp.63-68
• /
• 2009

Most of agricultural reservoirs in Korea have no function of flood control except 5% of reservoirs even exposed to natural disaster. In addition, there are increasing needs for the reservoir to guarantee the release of environmental flow to the downstream. Thus, the purpose of this paper is to study the priority decision method for the reservoir redevelopment satisfying both water utilization and flood control. The major scopes of this research are to set up six priority indices and to make needed GIS data for calculating each priority. There is important consideration of obtaining the data or not in deciding the indices. Although the detailed indices is expected to better reflect redevelopment priority but the subjective indices like, 'opinion' and 'landscape' are excluded. From the results, it will enables the six priority indices to really assist in decision redevelopment priority of agricultural reservoirs.

• 제어로봇시스템학회논문지
• /
• 제20권4호
• /
• pp.463-467
• /
• 2014

High precision machining technology has become one of the most important parts in the development of a precision machine. Such a machine requires high precision positioning as well as high speed on a large workspace. For machining systems having high precision positioning with a long stroke, it is necessary to examine the repeatability of the reference position decision. Though ball-screw driven linear stages equipped with linear scale have high precision feed drivers and a long stroke, they have some limitations for reference position decisions if they have not been equipped with an accurate home sensor. This study is performed to experimentally examine the repeatability for home position decision of a photo micro sensor as a home switch of a ball-screw driven linear stage by using a capacitance probe.

• 제어로봇시스템학회논문지
• /
• 제22권4호
• /
• pp.271-275
• /
• 2016

For machining systems like the motor driven linear stage which have high precision positioning with a long stroke, it is necessary to examine the repeatability of the reference position decision. Though piezo (PZT) actuator driven linear stages have high precision feed drivers and a short stroke, they have some limitations for reference position decisions if they have not been equipped with an accurate home sensor. This study was performed to examine the repeatability for home position decision of a EE-SX671 photo sensor as a home switch by using piezo actuator driven linear stages and capacitance probe.

• 대한전기학회논문지
• /
• 제33권10호
• /
• pp.381-386
• /
• 1984

This paper deals with the microcomputer realization of EMG pattern recognition system which provides identification of motion commands from the EMG signals for the on-line control of a prosthetic arm. A probabilistic model of pattern is formulated in the feature space of integral absolute value(IAV) to describe the relation between a motion command and the location of corresponding pattern. This model enables the derivation of sample density function of a command in the feature space of IAV. Classification is caried out through the multiclass sequential decision process, where the decision rule and the stopping rule of the process are designed by using the simple mathematical formulas defined as the likelihood probability and the decision measure, respectively. Some floating point algorithms such as addition, multiplication, division, square root and exponential function are developed for calculating the probability density functions and the decision measure. Only six primitive motions and one no motion are incorporated in this paper.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권11호
• /
• pp.2254-2271
• /
• 2011

Access control in dynamic environments needs the ability to provide more access opportunities of information to users, while also ensuring protection information from malicious users. Trust and risk are essential factors and can be combined together in access control decision-making to meet the above requirement. In this paper, we propose the combination of the trust and risk in access control to balance information accessibility and protection. Access control decision is made on the basis of trustworthiness of users and risk value of permissions. We use potential relations between users and relations between permissions in access control. Our approach not only provides more access opportunities for trustworthy users in accessing permissions, but also enforces traditional access control constraints such as Chinese Wall policy and Separation of Duty (SoD) of Role-Based Access Control (RBAC) model in an effective way.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.368-368
• /
• 2000

In this paper, we present forecasting ozone concentration with decision support system. Since the mechanism of ozone concentration is highly complex, nonlinear, and nonstationary, modeling of ozone prediction system has many problems and results of prediction are not good performance so far. Forecasting ozone concentration with decision support system is acquired to information from human knowledge and experiment data. Fuzzy clustering method uses the acquisition and dynamic polynomial neural network gives us a good performance for ozone prediction with ability of superior data approximation and self-organization.

• 한국환경과학회지
• /
• 제25권2호
• /
• pp.191-216
• /
• 2016

Since prolonged exposure to elevated ozone ($O_3$) concentrations is known to be harmful to human health, appropriate control strategies for ozone are needed for the non-attainment area such as Seoul, Korea. The goal of this research is to assess factors linked with the 1-hour ozone exceedance through a decision tree model. Since ozone is a secondary pollutant, lag times between ozone and explanatory variables for ozone formation are taken into account in the model to improve the accuracy of the simulation. Results show that while ozone concentrations of the previous day and $NO_2$ concentrations in the morning are major drivers for ozone exceedances in the early afternoon, meteorology plays more important role for ozone exceedances in the late afternoon. Results also show that a selection of lag times between ozone and explanatory variables affect the accuracy of predicting 1-hour ozone exceedances. The result analyzed in this study can be used for developing control strategies of ozone in Seoul, Korea.

• Management Science and Financial Engineering
• /
• 제13권2호
• /
• pp.1-27
• /
• 2007

This paper presents a fuzzy-goal programming(FGP) approach for Bi-Level Linear Multiple Objective Decision Making(BLL-MODM) problem in a large hierarchical decision making and planning organization. The proposed approach combines the attractive features of both fuzzy set theory and goal programming(GP) for MODM problem. The GP problem has been developed by fixing the weights and aspiration levels for generating pareto-optimal(satisfactory) solution at each level for BLL-MODM problem. The higher level decision maker(HLDM) provides the preferred values of decision vector under his control and bounds of his objective function to direct the lower level decision maker(LLDM) to search for his solution in the right direction. Illustrative numerical example is provided to demonstrate the proposed approach.