• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2008

This paper resents the spatial electric load forecasting algorithm using the multiple regression analysis method which is enhanced from the algorithm of the DISPLAN(Distribution Information System PLAN). In order to improve the accuracy of the spatial electrical load forecasting, input variables are selected for GRDP(Gross Regional Domestic Product), the local population and the electrical load sales of the past year. Tests are performed to analyze the accuracy of the proposed method for Gyeong-San City, Gu-Mi City, Gim-Cheon City and Yeong-Ju City of North Gyeongsang Province. Test results show that the overall accuracy of the proposed method is improved the percentage error 11.2[%] over 12[%] of the DISPLAN. Specially, the accuracy is enhanced a lot in the case of high variability of input variables. The proposed method will be used to forecast local electric loads for the optimal investment of distribution systems.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.91-105
• /
• 1999

Spatial data integration using multiple geo-based data sets has been regarded as one of the primary GIS application issues. As for this issue, several integration schemes have been developed as the perspectives of mathematical geology or geo-mathematics. However, research-based approaches for statistical/quantitative assessments between integrated layer and input layers are not fully considered yet. Related to this niche point, in this study, spatial data integration using multiple geoscientific data sets by known integration algorithms was primarily performed. For spatial integration by using raster-based GIS functionality, geological, geochemical, geophysical data sets, DEM-driven data sets and remotely sensed imagery data sets from the Ogdong area were utilized for geological thematic mapping related by mineral potential mapping. In addition, statistical/quantitative information extraction with respective to relationships among used data sets and/or between each data set and integrated layer was carried out, with the scope of multiple data fusion and schematic statistical assessment methodology. As for the spatial integration scheme, certainty factor (CF) estimation and principal component analysis (PCA) were applied. However, this study was not aimed at direct comparison of both methodologies; whereas, for the statistical/quantitative assessment between integrated layer and input layers, some statistical methodologies based on contingency table were focused. Especially, for the bias reduction, jackknife technique was also applied in PCA-based spatial integration. Through the statistic analyses with respect to the integration information in this case study, new information for relationships of integrated layer and input layers was extracted. In addition, influence effects of input data sets with respect to integrated layer were assessed. This kind of approach provides a decision-making information in the viewpoint of GIS and is also exploratory data analysis in conjunction with GIS and geoscientific application, especially handing spatial integration or data fusion with complex variable data sets.

• International Journal of Highway Engineering
• /
• v.11 no.4
• /
• pp.41-47
• /
• 2009

This study deals with the side-swipe accidents of 4-legged signalized intersections in Cheongju. The objectives are to analyze the characteristics of the accidents and to develop the related models. In pursuing the above, this study gives particular emphasis to finding the appropriate methodology to modelling. The main results are as follows. First, injuries were analyzed to be twice than property-only accidents in the side-swipe accidents. The accidents were evaluated to occur more in inside-intersection. Also, the accidents were analyzed to be almost the auto-related accidents and to be occurred by the unsafely-driving activity. Second, multiple linear regression models were evaluated to be more statistically significant than multiple non-linear. The most fitted models were analyzed to be the models with the number of accidents as the dependent variable. The factors of side-swipe accidents analyzed in this study were ADT, area of intersection, right-turn-only-lane, number of pedestrian crossings, limited speed of main road, maximum grade and number of signal phase.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.245-258
• /
• 2016

This paper aims to present the way to bring about significant results through performance improvement of learning algorithm in the research applying to machine learning. Research papers showing the results from machine learning methods were collected as data for this case study. In addition, suitable machine learning methods for each field were selected and suggested in this paper. As a result, SVM for engineering, decision-making tree algorithm for medical science, and SVM for other fields showed their efficiency in terms of their frequent use cases and classification/prediction. By analyzing cases of machine learning application, general characterization of application plans is drawn. Machine learning application has three steps: (1) data collection; (2) data learning through algorithm; and (3) significance test on algorithm. Performance is improved in each step by combining algorithm. Ways of performance improvement are classified as multiple machine learning structure modeling, $+{\alpha}$ machine learning structure modeling, and so forth.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.1
• /
• pp.103-110
• /
• 1998

In case of traditional Rule-Based Reasoning(RBR) and Case-Based Reasoning(CBR), although knowledge is reasoned either by one of them or by the integration of RBR and CBR, there is a problem that much time should be consumed by numerous rules and cases. In order to improve this time-consuming problem, in this paper, a new type of reasoning technique, which is a kind of integration of reduced RB and CB, is to be introduced. Such a new type of reasoning uses Rough Set, by which we can represent multi-meaning and/or random knowledge easily. In Rough Set, solution is to be obtained by its own complementary rules, using the process of RB and CB into equivalence class by the classification and approximation of Rough Set. and then using reduced RB and CB through the integrated reasoning.

• Fire Science and Engineering
• /
• v.21 no.2 s.66
• /
• pp.42-47
• /
• 2007

This paper presents the development of a case-based system for an electrical fire cause diagnosis system using the entity relation database. The relation database which provides a very simple but powerful way of representing data is widely used. The system focused on database construction and cause diagnosis can diagnose the causes of electrical fires easily and efficiently. In order to store and access to the information concerned with electrical fires, the key index items which identify electrical fires uniquely are derived out. The case-based system consists of a case which contains information from the past fires. The case-based system could present the cause of a newly occurred fire to be diagnosed by searching the case-based database for reasonable matching. The case-based system has not only searching functions with multiple attributes by using the collected various information(such as fire evidence, structure, and weather of a fire scene) but also more improved diagnosis functions which can be easily used for the electrical fire cause diagnosis system.

• Journal of The Korean Association For Science Education
• /
• v.35 no.2
• /
• pp.231-245
• /
• 2015

Flipped learning can be used as an innovative teaching method in science education. This study analyzes video clip produced by pre-service elementary school teachers for flipped learning and explore strategies to organize effective visualization. The pre-service elementary school teachers focused on providing information on macroscopic natural phenomenon using concrete case selection strategy for earth science class. They used marker and spatial transformation elements effectively, but their efforts to link the elements to the experience of students were not sufficient. In addition, it was very rare to put the contents into simplified drawing or provide extreme cases to enhance the imagery of students. In addition, it is necessary to provide specific case of multi-modal and link the material to the experience of students closely through familiar cases or analogical model to establish an effective visual teaching material. It may also be needed to present simplified drawing for enhancing imagery and provide extreme cases to make students have an opportunity to infer a new situation.

• Design Convergence Study
• /
• v.16 no.5
• /
• pp.125-140
• /
• 2017

This study explores potential capability of a machine learning approach for monitoring urban morphology based on an evident case study. The case study conveys year 2006 investigations on interpreting urban morphology of Boston Main Streets by applying a machine learning approach. From the lesson of the precedent study, in 2016, another field research and interview was conducted to compare changes in urban situation, data commons culture, and technology innovation during the decade. This paper describes open possibilities to advance urban monitoring for morphological changes. Most of all, a multi-participatory data platform enables managing urban data system in real time. Second, collaboration with machines with artificial intelligence can intervene the framework of the urban management system as well as transform it through new demands of innovative industries. Recently, urban regeneration became a dominant urban planning strategy in Korean, therefore, urban monitoring is on demand. It is timely important to correspond to in-situ problems based on empirical research.

• Journal of Korean Library and Information Science Society
• /
• v.44 no.1
• /
• pp.385-408
• /
• 2013

The purpose of this study is to build the tax ontology which can be used to manage imposables by the state or local governments. In this, the tax and related concepts were analyzed and then concept hierarchy i.e., taxonomies were formed. Especially, in the concept hierarchy, after multiple inherits were decomposed as 'primitive concepts' and then Rector's 'methodology of ontology implementation normalization', in which defined concepts were recombined, was used. The methodology employed was that the tax system, which was entangled with the direct taxes, local taxes, and property taxes that has multiple-inherits, was expressed explicitly and logically. After that, automatic classification was carried out through the inference engine, consistency was verified. Finally, some practical cases of ontology created were enumerated.

• Journal of Korea Technology Innovation Society
• /
• v.19 no.2
• /
• pp.254-279
• /
• 2016

Recently, with the conversion towards knowledge-based economy era, the importance of the evaluation for patent valuation has been growing rapidly because technology transactions are increasing with the purpose of practically utilizing R&D outcomes such as technology commercialization and technology transfer. Nevertheless, there is a lack of research on determinants of patent valuation by analyzing technology transactions due to the difficulty of collecting data in practice. Hence, to suggest quantitative determinants for the patent valuation which could be applied to scoring methods, 15 patent valuation models domestically and overseas are analysed in order to assure the objectiveness for subjective results from qualitative methods such as expert surveys, comparison assessment, etc. Through this analysis, the important 6 common determinants are drawn and patent information is matched which can be used as proxy variables of individual determinant factors by advanced researches. In addition, to validate whether the model proposed has a statistically meaningful effect, total 517 technology transactions are collected from both public and private technology transaction offices and analysed by multiple regression analysis, which led to significant patent determinant factors in deciding its value. As a result, it is herein presented that patent connectivity(number of literature cited) and commercialization stage in market influence significantly on patent valuation. The meaning of this study is in that it suggests the significant quantitative determinants of patent valuation based on the technology transactions data in practice, and if research results by industry are systematically verified through seamless collection of transaction data and their monitoring, we would propose the customized patent valuation model by industry which is applicable for both strategic planning of patent registration and achievement assessment of research projects (with representative patents).