• Journal of the Korea Society for Simulation
• /
• v.22 no.3
• /
• pp.55-69
• /
• 2013

Managers are required to adopt and implement the human resource management practice that fit firm's strategy the most, so that optimize overall performance. However, the time and relative resources that any firm has are limited, which demands managers to understand the relative importance of all sorts of HR practice and promote them in an order of their relative importance. This study follows the universal perspective and contingency perspective(according to firm size and strategy type), try to identify the most effective HR practice on performance as well as their relative importance by "CART Ensemble" analysis. The results are as follows. From universal perspective, firms always need to high level of integration between strategy and HR department, decision making participation, autonomy of speed of working, and autonomy of way of working. Contingency perspective also suggested the importance of integration between HRM and strategy. But others are different case by case. This study suggests useful implications for managers.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.4
• /
• pp.71-80
• /
• 1996

This paper presents stabilization and position control of the Inverted-Pendulum system with cart by using Evolution Strategies that is one of the Evolutionary Computation and is effective in searching real number. The control input of the Inverted-Pendulum is the element of chromosome corresponding to the divided space of Inverted-Pendulum state variable x, x, 0, 0 . In general, the larger the length of the chromosome is, the longer the time of evolution to search optimal solution is. So in this paper, we propose a scheme that reduce the state space by half by taking the method, that is, converting only the sign of the control input without obtaining separately for the symmetrical sections of the Inverted-Pendulum to improve the speed of Evolution, and improved the efficiency of the entire system in addition to the improvement of the chromosome's evolution time by carrying out the chromosome's evolutional process by two steps one of which is that cart is positioned near the control point and the other cart is positioned far from that point. We propose another method that is Neural Network-Evolution StrategiedNN-ES) Controller. We verify the effectiveness of the proposed control scheme by computer simulations.

• Safety and Health at Work
• /
• v.8 no.1
• /
• pp.11-18
• /
• 2017

The purpose of this review is to name and describe the important factors of musculoskeletal strain originating from pushing and pulling tasks such as cart handling that are commonly found in industrial contexts. A literature database search was performed using the research platform Web of Science. For a study to be included in this review differences in measured or calculated strain had to be investigated with regard to: (1) cart weight/ load; (2) handle position and design; (3) exerted forces; (4) handling task (push and pull); or (5) task experience. Thirteen studies met the inclusion criteria and proved to be of adequate methodological quality by the standards of the Alberta Heritage Foundation for Medical Research. External load or cart weight proved to be the most influential factor of strain. The ideal handle positions ranged from hip to shoulder height and were dependent on the strain factor that was focused on as well as the handling task. Furthermore, task experience and subsequently handling technique were also key to reducing strain. Workplace settings that regularly involve pushing and pulling should be checked for potential improvements with regards to lower weight of the loaded handling device, handle design, and good practice guidelines to further reduce musculoskeletal disease prevalence.

• Journal of Service Research and Studies
• /
• v.3 no.1
• /
• pp.9-16
• /
• 2013

Data analysis is the universal classification techniques, which requires a lot of effort. It can be easily analyzed to understand the results. Decision tree which is developed by Breiman can be the most representative methods. There are two core contents in decision tree. One of the core content is to divide dimensional space of the independent variables repeatedly, Another is pruning using the data for evaluation. In classification problem, the response variables are categorical variables. It should be repeatedly splitting the dimension of the variable space into a multidimensional rectangular non overlapping share. Where the continuous variables, binary, or a scale of sequences, etc. varies. In this paper, we obtain the coefficients of precision, reproducibility and accuracy of the classification tree to classify and evaluate the performance of the new cases, and through experiments to evaluate.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1385-1395
• /
• 2014

Economic traits of livestock are affected by environmental factors and genetic factors. In addition, it is not affected by one gene, but is affected by interaction of genes. We used a linear regression model in order to adjust environmental factors. And, in order to identify gene-gene interaction effect, we applied data mining techniques such as neural network, logistic regression, CART and C5.0 using five-SNPs (single nucleotide polymorphism) of FASN (fatty acid synthase). We divided total data into training (60%) and testing (40%) data, and applied the model which was designed by training data to testing data. By the comparison of prediction accuracy, C5.0 was identified as the best model. It were selected superior genotype using the decision tree.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.05a
• /
• pp.266-273
• /
• 2005

Data mining techniques enable us to generate useful information for decision support from the data sources which are generated and accumulated in the process of routine organizational management activities. College administration system is a typical example that produces a warehouse of student records as each and every student enters a college and undertakes the curricular and extracurricular activities. So far, these data have been utilized to a very limited student service purposes, such as issuance of transcripts, graduation evaluation, GPA calculation, etc. In this paper, we utilize Holland career search test results, TOEIC score, course work list, and GPA score as the input for data mining and generation the student advisory information. Factor analysis, AHP(Analytic Hierarchy Process), artificial neural net, and CART(Classification And Regression Tree) techniques are deployed in the data mining process. Since these data mining techniques are very powerful in processing and discovering useful knowledge and information from large scale student databases, we can expect a highly sophisticated student advisory knowledge and services which may not be obtained with the human student advice experts.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.93-100
• /
• 2010

Trip generation is the first step in the conventional four-step model and has great effects on overall demand forecasting, so accuracy really matters at this stage. A linear regression model is widely used as a current trip generation model for such plans as urban transportation and SOC facilities, assuming that the relationship between each socio-economic index and trip generation stays linear. But when rapid urban development or an urban planning structure has changed, socio-economic index data for trip estimation may be lacking to bring many errors in estimated trip. Hence, instead of assuming that a socio-economic index widely used for a general purpose, this study aims to develop a new trip generation model by type based on the market separation for the variables to reflect the characteristics of various zones. The study considered the various characteristics (land use, socio-economic) of zones to enhance the forecasting accuracy of a trip generation model, the first-step in forecasting transportation demands. For a market separation methodology to improve forecasting accuracy, data mining (CART) on the basis of trip generation was used along with a regression analysis. Findings of the study indicated as follows : First, the analysis of zone characteristics using the CART analysis showed that trip production was under the influence of socio-economic factors (men-women relative proportion, age group (22 to 29)), while trip attraction was affected by land use factors (the relative proportion of business facilities) and the socio-economic factor (the relative proportion of third industry workers). Second, model development by type showed as a result that trip generation coefficients revealed 0.977 to 0.987 (trip/person) for "production" 0.692 to 3.256 (trip/person) for "attraction", which brought the necessity for type classifications. Third, a measured verification was conducted, where "production" and "attraction" showed a higher suitability than the existing model. The trip generation model by type developed in this study, therefore, turned out to be superior to the existing one.

• Journal of Korean Society of Transportation
• /
• v.28 no.6
• /
• pp.147-158
• /
• 2010

Studies on the distribution of traffic demands have been proceeding by providing traffic information for reducing greenhouse gases and reinforcing the road's competitiveness in the transport section, however, since it is preferentially required the extensive studies on the driver's behavior changing routes and its influence factors, this study has been developed a discriminant model for changing routes considering driving conditions including traffic conditions of roads and driver's preferences for information media. It is divided into three groups depending on driving conditions in group classification with the CART analysis, which is statistically meaningful. And, elements of the driving conditions and the preferred media affecting the change of paths are classified into statistical meaningful groups through the CHAID analysis, and the major factors affecting the change of paths are examined. Finally, the extent that driving conditions and preferred media affect a route change is examined through a discriminant analysis, and it is developed a discriminant model equation to predict a route change. As a result of building the discriminant model equation, it is shown that driving conditions affect a route change much more, the entire discriminant hit ratio is derived as 64.2%, and this discriminant equation shows high discriminant ability more than a certain degree.

• Journal of Intelligence and Information Systems
• /
• v.11 no.3
• /
• pp.83-101
• /
• 2005

Customer retention is one of the major issues in life insurance industry, in which competition is increasingly fierce. There are many things for the life insurers to do many things to retain the customers. One of those things is to make sure to keep in touch with all customers. When an insurance-planner resigned, his/her customers must be taken care of by some planner-assistants. This article outlines the design of Contact Scheduling System (CSS) that supports planner-assistants for contacting the customers. Planner-assistants are unable to share the resigned insurance-planner's experience and knowledge regarding the customer relationship management. The CSS developed by employing both Classification And Regression Tree (CART) technique and Sequential Pattern Mining (SPM) technique has a two-stage process. In the first stage, it segments the customers into eight groups by CART model. Then it generates contact scheduling information consisting of contact-purpose, contact-interval and contact-channel, according to the segment's typical contact pattern. Contact-purpose is derived by schedule-driven, event-driven, or business-rule-driven. Schedule-driven contact is determined by SPM model. In the operation of CSS in a realistic situation, it shows a practicality in supporting planner-assistants to keep in touch with the customers efficiently and effectively.

• 한국ITS학회:학술대회논문집
• /
• 2008.11a
• /
• pp.1-7
• /
• 2008