• Journal of Biosystems Engineering
• /
• 제42권2호
• /
• pp.98-103
• /
• 2017

Purpose: Precision agriculture includes determining the right amount of nitrogen for a specific location in the field. This work focused on developing and validating a model using variable rate nitrogen application based on the estimated SPAD value from the ground-based image sensor. Methods: A variable rate N application based on the decision making system was performed using a sensor-based variable rate nitrogen application system. To validate the nitrogen application decision making system based on the SPAD values, the developed N recommendation was compared with another conventional N recommendation. Results: Sensor-based variable rate nitrogen application was performed. The nitrogen deficiency level was measured using the image sensor system. Then, a variable rate application was run using the decision model and real-ti me control. Conclusions: These results would be useful for nitrogen management of corn in the field. The developed nitrogen application decision making system worked well, when considering the SPAD value estimation.

• Journal of the Korean Data and Information Science Society
• /
• 제22권4호
• /
• pp.671-678
• /
• 2011

Data mining searches for interesting relationships among items in a given database. The methods of data mining are decision tree, association rules, clustering, neural network and so on. The decision tree approach is most useful in classification problems and to divide the search space into rectangular regions. Decision tree algorithms are used extensively for data mining in many domains such as retail target marketing, customer classification, etc. When create decision tree model, complicated model by standard of model creation and number of input variable is produced. Specially, there is difficulty in model creation and analysis in case of there are a lot of numbers of input variable. In this study, we study on decision tree using intervening variable. We apply to actuality data to suggest method that remove unnecessary input variable for created model and search the efficiency.

• Asia pacific journal of information systems
• /
• 제10권1호
• /
• pp.1-18
• /
• 2000

One stream of the GDSS(Group Decision Support System) research is to investigate how GDSS affects decision performances of small groups according to task types, support features, meeting facilitation modes and meeting environments. But little study has investigated the effects of group member characteristics on group decision processes and outcomes depending upon whether GDSS is provided or not. To date, most GDSS studies have not controlled group member characteristics(e,g. personality, sex, decision style) in laboratory experiments. However, this study included the decision styles of group members as an independent variable. Therefore, this study investigated how differently members of two different decision styles perceive the use of GDSS in small group meetings through lab experiments. The two decision styles are feeling(F) style and thinking(T) style. We found that the effect of GDSS is a function of individual's decision style only in the communication thoroughness variable. The decision style is a statistically significant factor that can mediate the effects of the group support technology on the perceived communication thoroughness. Specifically, the GDSS is positively related to participants' perception about satisfaction on decision process, goal achievement, communication thoroughness, degree of influence-outward and effort for achieving meeting goals.

• Journal of Families and Better Life
• /
• 제18권2호
• /
• pp.109-123
• /
• 2000

The purpose of this study is to investigate decision making styles task management of urban homemakers. This study focuses on the following aspects: 1) to find out which variables of background variables (ie. age of couple, education of couple, duration of marriage, income, family life cycle, number of children) have effect on decision making styles & task management of urban homemakers. 2) to find out the relationships between decision making styles and task management of urban homemakers. 3) to find out independent influcene of background variables on task management. major findings are as follows; First, it is general tendency that decision making styles were human oriented in urban homemakers. Importance & Urgency of the task, age of homemakers, education of homemakers, family life cycle were significant variables to have influcence on task oriented decision making styles. Importance & urgency of task were variables to have influences on human oriented decision making styl s. Second, the tendency of dealing with task at once is the highest in the task management, on the other hand, the tendency of dealing with task in the next session is the lowest. Income is a variable to influence on dealing with task in delegation to others, education of homemaker is a variable to influence on dealing with task in next session and importance & urgency of the task and the number of children were variables to influence on dealing with task immediately. Third, human oriented decision marking style was a variable to influence on dealing with task in delegation with task in delegation to others, in the next session, and in suspending/ in neglecting. Task oriented decision making style was a variable to influence on dealing with task immediately. Fourth, The urgency of task & income were variables to have direct influence on dealing with task in delegation with task in next session, and the urgency of the task, age & education of homemaker and family life cycle were varia les to direct influence on dealing with the task immediately. The urgency & importance of the task and age of homemaker were variables to have indirect on dealing with the task urgency of task & the number of children were variables to have indirect influence on dealing with the task in suspending/in neglecting through the medium of the human oriented decision making styles.

• Journal of the Korean Data and Information Science Society
• /
• 제16권2호
• /
• pp.195-205
• /
• 2005

In decision tree analysis, C4.5 and CART algorithm have some problems of computational complexity and bias on variable selection. But QUEST algorithm solves these problems by dividing the step of variable selection and split point selection. When input variables are continuous, QUEST algorithm uses ANOVA F-test under the assumption of normality and homogeneity of variances. In this paper, we investigate the influence of violation of normality assumption and effect of the transformation of variables in the QUEST algorithm. In the simulation study, we obtained the empirical powers of variable selection and the empirical bias of variable selection after transformation of variables having various type of underlying distributions.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• 제6권9호
• /
• pp.111-124
• /
• 1983

The basic model of decision problem the enterprise is conforonted with includes the following 3 elements ; 1) Elements that can not be controlled by the decision maker : In the thesis elements are named environmental variables, and varied itself according to the change of environmental condition. 2) Elements that can be controlled by the decision maker ; These elements are called decision elements in the thesis and variable according to the event. 3) object of decision making : The degree of achievement to the object is identified by taking various criteria- The index indicating the degree of achievement to the object whatever criterion is applied is called object function in the thesis. It's the fanetion of environmental variable, decision variable and object function. The relation between them brings forth the relation formula that characterize the each problem. The basic types of decision making model use in the thesis are as following ; 1) The problem of decision making under conditions of certainty. 2) The problem of decision making under conditions of risk. 3) The problem of decision making under conditions of uncertainty. 4) The problem of decision making under competitive condition. in general case that the Profit of two decision makers varies, what we regard the decision that make the sum of profit of two men maximum as the best choice for two men has a reasonability in certain case. When the sum of profit two men is zero, by taking toe promise that ail of them art according to the min-max criteria and by extending the object of choice to the mixed strategy. We certify the existance of equilibrium solution and admit them as the best solution of competitive model in general.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• 제32B권6호
• /
• pp.868-875
• /
• 1995

This paper presents a method of constructing the multiple-valued combinational logic systems(MVCLS) by decision diagram. The switching function truth table of MVCLS is transformed into canonical normal form of sum-of-products(SOP) with literals at first. Next, the canonical normal form of SOP is transfered into multiple-valued logic decision diagram(MVLDD). The selecting of variable ordering is very important in this stage. The MVLDDs are quite different from each other according to the variable ordering. Sometimes the inadequate variable ordering produces a very large size of MVLDD means the large size of circuit implementation. An algorithm for generating the proper variable ordering produce minimal MVLDD and an example shows the verity of the algorithm. The circuits are realized with T-gate acceording to the minimal MVLDD.

• Korean Journal of Child Studies
• /
• 제33권6호
• /
• pp.71-84
• /
• 2012

The purpose of this study is to analyze the relationship between decision making abilities young children and their self-directed learning abilities. A survey was carried out using 160 young children in the J region. The collected data were analyzed by Pearson correlation and multiple regression techniques using the SPSS statistics program. The conclusions are as follows : First, decision making abilities in young children exhibited a positive correlation with their self-directed learning abilities. Second, decision making abilities in young children were an influential variable in terms of their self-directed learning abilities. As a result, decision making abilities in young children were an important variable in predicting their self-directed learning abilities.

• Journal of Fisheries and Marine Sciences Education
• /
• 제17권3호
• /
• pp.293-304
• /
• 2005

The purpose of this study is to analyze middle school teachers' perception of their participation in decision-making processes at their schools. 507 middle school teachers in the Pusan metropolitan area were involved in this study through a questionnaire to examine the actual state of participation of teachers in decision-making processes. The results of the above mentioned analyses are as follows: First, the degree of actual participation in the decision-making process for each field in terms of school management is lower than that of expected participation in general. Second, the variable which influences the actual participation the most is seen in the jurisdiction of the related fields. However, as an exception, expertise is the most influential variable on actual participation in terms of teaching activities.

• Journal of Korean Institute of Industrial Engineers
• /
• 제43권1호
• /
• pp.1-11
• /
• 2017

Stochastic resource-constrained project scheduling problem is an extension of resource-constrained project scheduling problem such that activity duration has stochastic nature. In real situation where activity duration is not known until the activity is finished, open-loop based static policies such as activity-based policy and priority-based policy will not well cope with duration variability. Then, a dynamic policy based on closed-loop decision making will be regarded as an alternative toward achievement of minimal makespan. In this study, a dynamic policy designed to select activities to start at each decision time point is illustrated. The performance of static and dynamic policies based on variable neighborhood search is evaluated under the discrete-event simulation environment. Experiments with J120 sets in PSPLIB and several probability distributions of activity duration show that the dynamic policy is superior to static policies. Even when the variability is high, the dynamic policy provides stable and good solutions.