• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1786-1797
• /
• 2010

Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

• Journal of the Korea Safety Management & Science
• /
• v.7 no.4
• /
• pp.61-71
• /
• 2005

Many researches have been focused on the analysis of industry disasters in order to reduce them. As a similar endeavor, this paper provides a propensity analysis of injured people from various industries using classification and regression tree(CART), a data mining algorithm. The sample for this work was chosen from 25,157data related to various industries during one year ( $2003.2\sim2004.1$ ) at Kangwon-Do in Korea. For the purpose of this paper, eight independent variables (injured date, injured time, injured month, type of Injured person, continuous service period, sex, company size, age)are taken from injured person group. According to the analysis result, it is found that five out of the eight factors that are predicted as significant have salient effects. Factors of season, time/hour, day of the week, or month which disasters happened do not show any significant effect. This paper provides common features of injured people. The provided analysis result will be helpful as a starting point for root cause analysis and reduction of industry disasters and also for development of a guideline of safety management.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.847-859
• /
• 2011

cDNA microarray-based comparative genomic hybridization(CGH) data includes low-intensity spots and thus a statistical strategy is needed to detect subtle differences between different cancer classes. In this study, genes displaying a high frequency of alteration in one of the different classes were selected among the pre-selected genes that show relatively large variations between genes compared to total variations. Utilizing copy-number changes of the selected genes, this study suggests a statistical approach to predict patients' classes with increased performance by pre-classifying patients with similar genetic alteration scores. Two-stage logistic regression model(TLRM) was suggested to pre-classify homogeneous patients and predict patients' classes for cancer prediction; a decision tree(DT) was combined with logistic regression on the set of informative genes. TLRM was constructed in cDNA microarray-based CGH data from the Cancer Metastasis Research Center(CMRC) at Yonsei University; it predicted the patients' clinical diagnoses with perfect matches (except for one patient among the high-risk and low-risk classified patients where the performance of predictions is critical due to the high sensitivity and specificity requirements for clinical treatments. Accuracy validated by leave-one-out cross-validation(LOOCV) was 83.3% while other classification methods of CART and DT performed as comparisons showed worse performances than TLRM.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.3
• /
• pp.262-276
• /
• 2018

Models to predict Leaf Wetness Duration (LWD) were evaluated using the observed meteorological and dew data at the 11 citrus orchards in Jeju, South Korea from 2016 to 2017. The sensitivity and the prediction accuracy were evaluated with four models (i.e., Number of Hours of Relative Humidity (NHRH), Classification And Regression Tree/Stepwise Linear Discriminant (CART/SLD), Penman-Monteith (PM), Deep-learning Neural Network (DNN)). The sensitivity of models was evaluated with rainfall and seasonal changes. When the data in rainy days were excluded from the whole data set, the LWD models had smaller average error (Root Mean Square Error (RMSE) about 1.5hours). The seasonal error of the DNN model had the similar magnitude (RMSE about 3 hours) among all seasons excluding winter. The other models had the greatest error in summer (RMSE about 9.6 hours) and the lowest error in winter (RMSE about 3.3 hours). These models were also evaluated by the statistical error analysis method and the regression analysis method of mean squared deviation. The DNN model had the best performance by statistical error whereas the CART/SLD model had the worst prediction accuracy. The Mean Square Deviation (MSD) is a method of analyzing the linearity of a model with three components: squared bias (SB), nonunity slope (NU), and lack of correlation (LC). Better model performance was determined by lower SB and LC and higher NU. The results of MSD analysis indicated that the DNN model would provide the best performance and followed by the PM, the NHRH and the CART/SLD in order. This result suggested that the machine learning model would be useful to improve the accuracy of agricultural information using meteorological data.

• Korean Journal of Remote Sensing
• /
• v.34 no.1
• /
• pp.141-150
• /
• 2018

Crop type classification is essential for supporting agricultural decisions and resource monitoring. Remote sensing techniques, especially using hyperspectral imagery, have been effective in agricultural applications. Hyperspectral imagery acquires contiguous and narrow spectral bands in a wide range. However, large dimensionality results in unreliable estimates of classifiers and high computational burdens. Therefore, reducing the dimensionality of hyperspectral imagery is necessary. In this study, the Random Forest (RF) classifier was utilized for dimensionality reduction as well as classification purpose. RF is an ensemble-learning algorithm created based on the Classification and Regression Tree (CART), which has gained attention due to its high classification accuracy and fast processing speed. The RF performance for crop classification with airborne hyperspectral imagery was assessed. The study area was the cultivated area in Chogye-myeon, Habcheon-gun, Gyeongsangnam-do, South Korea, where the main crops are garlic, onion, and wheat. Parameter optimization was conducted to maximize the classification accuracy. Then, the dimensionality reduction was conducted based on RF variable importance. The result shows that using the selected bands presents an excellent classification accuracy without using whole datasets. Moreover, a majority of selected bands are concentrated on visible (VIS) region, especially region related to chlorophyll content. Therefore, it can be inferred that the phenological status after the mature stage influences red-edge spectral reflectance.

• Journal of Cadastre & Land InformatiX
• /
• v.45 no.1
• /
• pp.225-240
• /
• 2015

The effect of passing pedestrians'characteristics on locational goodwill was empirically modeled and tested. The theoretical basis for the study was central place theory, bid rent and, agglomeration theory, and demand externality theory. The data included information on goodwill, retail rents and passing pedestrians' characteristics in 100 retail trade areas in Seoul. The empirical model was tested with the sample of 1,307 retail units in Seoul, South Korea. The data set was analyzed with the Classification and Regression Tree software. As the results, using the regression tree method, the variables does affect locational goodwill in the each retail trade area were the volume of pedestrians around 2:00 pm on weekdays, volume of pedestrians around 4:00 pm on weekdays, and volume of pedestrians around 8:00 pm on weekdays. In summary, not only the economic base in the retail trade area but also the volume of passing pedestrians should be considered to determine the locational goodwill.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.7-8
• /
• 2019

지속적인 건축물의 노화와 개발지 부족은 현존하는 건축물의 재건축 및 활용 가능 용지에 신규 건축행위를 유도한다. 서울에서는 근 5년간 25,000여 건의 신축이 발생하였으며, 이에 대한 신규 정책 등 다양한 지원 체계가 활성화되고 있다. 본 연구에서는 2011년부터 2015년까지 발생한 필지별 건축행위 데이터와 추가적 43개의 변수를 활용하여 신규 건축행위가 발생하는 필지에 대한 예측 모델을 구축하고자 한다. 요인도출 기계학습 방식인 의사결정트리 (Decision Tree) 중 CART(Classification And Regression Tree)를 활용하여 신규 건축 예측 모델을 구축하였으며, 86.28%의 정확도와 4개의 주요 신규 건축행위 발생 요인을 도출하였다.

• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.921-932
• /
• 2015

This study analyzed military personnel survivability in regards to offensive operations according to the scientific military training data of a reinforced infantry battalion. Scientific battle training was conducted at the Korea Combat Training Center (KCTC) training facility and utilized scientific military training equipment that included MILES and the main exercise control system. The training audience freely engaged an OPFOR who is an expert at tactics and weapon systems. It provides a statistical analysis of data in regards to state-of-the-art military training because the scientific battle training system saves and utilizes all training zone data for analysis and after action review as well as offers training control during the training period. The methodologies used the Cox PH modeling (which does not require parametric distribution assumptions) and decision tree modeling for survival data such as CART, GUIDE, and CTREE for richer and easier interpretation. The variables that violate the PH assumption were stratified and analyzed. Since the Cox PH model result was not easy to interpret the period of service, additional interpretation was attempted through univariate local regression. CART, GUIDE, and CTREE formed different tree models which allow for various interpretations.

• Journal of the Korea Society for Simulation
• /
• v.23 no.1
• /
• pp.21-31
• /
• 2014

In this article, data mining simulation is applied to find a proper approach and results of analysis for study of variables related to organization. Also, turnover intention and organizational commitment are used as target (dependent) variables in this simulation. Classification and regression tree (CART) with ensemble methods are used in this study for simulation. Human capital corporate panel data of Korea Research Institute for Vocation Education & Training (KRIVET) is used. The panel data is collected in 2005, 2007, and 2009. Organizational commitment variables are analyzed with combined measure variables which are created after investigation of reliability and single dimensionality for multiple-item measurement details. The results of this study are as follows. First, major determinants of turnover intention are trust, communication, and talent management-oriented trend. Second, the main determining factors for organizational commitment are trust, the number of years worked, innovation, communication. CART with ensemble methods has two ensemble CART methods which are CART with Bagging and CART with Arcing. Comparing two methods, CART with Arcing (Arc-x4) extracted scenarios with very high coefficients of determination. In this study, a scenario with maximum coefficient of determinant and minimum error is obtained and practical implications are presented. Using one of data mining methods, CART with ensemble method. Also, the limitation and future research are discussed.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.17 no.2
• /
• pp.131-140
• /
• 2004

It really needs fuzzy decision making of integrity assessment considering about both durability and load carrying capacity for maintenance and administration, such as repairing and reinforcing. This thesis shows efficient models about reinforced concrete structure using CART-ANFIS. It compares and analyzes decision trees parts of expert system, using the theory of fuzzy, and applying damage & diagnosis at reinforced concrete structure and decision trees of integrity assessment using established artificial neural. Decided the theory of reinforcement design for recovery of durability at damaged concrete ＆ the theory of reinforcement design for increasing load carrying capacity keep stability of damage and detection. It is more efficient maintenance and administration at reinforced concrete for using integrity assessment model of this study and can carry out predicting cost of life cycle.