• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1306-1325
• /
• 2019

As the world is moving towards digitization, data is generated from various sources at a faster rate. It is getting humungous and is termed as big data. The financial sector is one domain which needs to leverage the big data being generated to identify financial risks, fraudulent activities, and so on. The design of predictive models for such financial big data is imperative for maintaining the health of the country's economics. Financial data has many features such as transaction history, repayment data, purchase data, investment data, and so on. The main problem in predictive algorithm is finding the right subset of representative features from which the predictive model can be constructed for a particular task. This paper proposes a correlation-based method using submodular optimization for selecting the optimum number of features and thereby, reducing the dimensions of the data for faster and better prediction. The important proposition is that the optimal feature subset should contain features having high correlation with the class label, but should not correlate with each other in the subset. Experiments are conducted to understand the effect of the various subsets on different classification algorithms for loan data. The IBM Bluemix BigData platform is used for experimentation along with the Spark notebook. The results indicate that the proposed approach achieves considerable accuracy with optimal subsets in significantly less execution time. The algorithm is also compared with the existing feature selection and extraction algorithms.

• 한국IT서비스학회지
• /
• 제11권4호
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• 지능정보연구
• /
• 제12권4호
• /
• pp.109-126
• /
• 2006

성공적인 고객관계관리(CRM : customer relationship management)를 수행하기 위해서는 효과적인 고객 등급화가 필요하다. 일반적으로 고객등급화는 고객별로 LTV를 산정한 다음 일정한 비율로 고객을 분류하여 등급을 정하는 방법이 사용되어 왔다. 그러나 이러한 방법은 등급간의 이질성을 명확하게 반영하지 못하기 때문에 적지 않은 문제점을 내포하고 있다. 본 논문에서는 Holistic Profit을 이용해서 고객을 등급화 하는 방법을 제시하고, A 생명보험회사의 고객자료을 이용해서 이를 검증하였다. Holistic Profit은 신용대출 승인정책에서 승인임계점수(Cutoff Point) 책정에 활용되고 있는 방법들 중의 하나이다. 요약하면, 본 논문의 목적은 Holistic Profit을 활용하여 보다 효과적이고 과학적인 방법으로 고객 등급화 하는 방법의 개발과 검증에 있다. 본 논문에서 제시된 방법을 사용해서 고객을 등급화 함으로써 기업은 보다 효과적인 고객관계관리(CRM)와 마케팅 활동을 수행할 수 있을 것으로 기대된다.

• Journal of Chest Surgery
• /
• 제55권3호
• /
• pp.233-238
• /
• 2022

Background: This study investigated the distribution of valve incompetence in patients with chronic venous disease (CVD) and its correlation with the clinical category of the clinical, etiological, anatomical, and pathophysiological (CEAP) classification. Methods: In total, 1,386 limbs with clinically suspected CVD were categorized according to the CEAP classification and consecutively underwent duplex ultrasonography between April 2017 and December 2020. Results: There were 362 limbs in male patients and 1,024 limbs in female patients. The limbs were classified as C0s-C1 (608 limbs, 43.8%), C2 (727 limbs, 52.5%), or C3-C6 (51 limbs, 3.7%). The prevalence of saphenous vein incompetence in CEAP C0s-C1 limbs was 43.6%. The saphenofemoral junction (SFJ) was competent in 37% of CEAP C2-C6 limbs. The CEAP C3-C6 category was not correlated with reflux patterns of the saphenous vein system (Cramer's V=0.07), incompetent SFJ (Cramer's V=0.07), deep vein reflux (Cramer's V=0.03), or the distribution of incompetent segments in the great saphenous vein (GSV) (Cramer's V=0.11). Conclusion: Duplex ultrasonography is necessary to formulate a proper treatment plan for limbs categorized as CEAP C0s-C1. The SFJ was competent in more than one-third of CEAP C2-C6 limbs with GSV reflux; as such, flush ligation of the GSV may be unnecessary in these patients. The CEAP C3-C6 category showed no correlations with reflux patterns of the saphenous vein system, SFJ reflux, deep vein reflux, or the distribution of incompetent segments in the GSV.

• 스마트미디어저널
• /
• 제12권5호
• /
• pp.73-80
• /
• 2023

최근 지능형 관제 시스템은 다양한 응용 분야에서 빠르게 발전하고 있으며, 딥러닝, IoT, 클라우드 컴퓨팅 등의 기술이 지능형 관제 시스템에 활용하는 방안이 연구되고 있다. 지능형 관제 시스템에서 중요한 기술은 영상에서 객체를 인식하고 추적하는 것이다. 그러나 기존의 다중 객체 추적 기술은 정확도 및 속도에서 문제점을 가지고 있다. 본 논문에서는 객체 추적의 정확성을 높이고, 객체가 서로 겹쳐있거나 동일한 클래스에 속하는 객체들이 많을 경우에도 빠르고 정확하게 추적 가능한 원샷 아키텍처 기반의 YOLO v5와 YOLO v6을 사용하여 실시간 지능형 관제시스템을 구현하였다. 실험은 YOLO v5와 YOLO v6를 비교하여 평가하였다. 실험결과 YOLO v6 모델이 지능형 관제시스템에 적합한 성능을 보여주고 있다. 실험결과 YOLO v6 모델이 지능형 관제시스템에 적합한 성능을 보여주고 있다.

• 천문학회지
• /
• 제45권2호
• /
• pp.31-38
• /
• 2012

In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.

• 한국환경교육학회지:환경교육
• /
• 제19권3호
• /
• pp.40-56
• /
• 2006

The purpose of this study is to enhance elementary students' awareness of environment-friendly life and help them to prepare for a better life in the future. To achieve this purpose we examined the effect typical environmental experience-based learning activities, which were based on the local circumstances with high environmental-educational potential, have on the attitudes toward environment-friendly life. This study was carried out on the basis of typical environmental experience-based learning in the small class size. The research group used was composed of one sixth grade elementary school class called Sangroksu, whose total students were 9. The research period lasted from March 2005 to February 2006. To analyze the result of this study, two research methods were applied simultaneously : quantitative research methods and qualitative research methods. Especially statistical analysis in quantitative research methods by self-administrated questionnaire was done with SAS program. Qualitative research methods were analyzed in a cyclic pattern, including the processes of domain analysis, classification analysis, and factor analysis which continued to be associated with data-collecting methods. This research shows the following results. First of all, students have shown meaningful differences after typical environmental experience-based learning activities.(p<.05). Followings are fields of the differences - students‘ interest on the subject, their understanding levels of necessity for basic environmental facilities around us as well as for the kinds of environmental experience-based learning, awareness levels of various environmental problems, consciousness on environment conservation, and the practicing ability of environment - friendly lifestyles. Secondly, We have discovered improvements in the following fields after this study - the knowledge and understanding levels on our environment and human relationships, students' fundamental abilities to work out environmental problems, right ideas and appropriate attitudes on environment protection, the practicing ability of environment-friendly life styles, and their parents' understanding levels on the education related to environment. In conclusion, typical environmental experience-based learning activities have a positive effect on the improvement of elementary school students' environment-friendly life styles.

• 한국환경교육학회지:환경교육
• /
• 제20권1호
• /
• pp.19-27
• /
• 2007

This study was intended to answer the question, 'What kinds of effects will be aroused by experiential learning for environment based on living area?'. Experiential learning for environment was operated to 17 elementary school students in 4th grade in Kyeong-san city. The results were drawn analyzing the mind map for the changes of environmental consciousness before and after learning, and they are as below. First, it had an effect to change the meaning association of the relationship between 'river and me'. Meaning association was 'river-a thing' before experiential learning, but it was developed as 'river-a thing-me' after learning. This means that students expanded understanding of the world that they were belonging and self-spatialization was promoted. The expansion of meaning association would be a start point and a method to promote their segmentation for each student. Second, students could self-directly modify misconception and preconception after experiential learning. It showed that students could find meanings in the world that they were belonging by experiential learning for environment, and misconception obtained by concept learning without actual situation could be revised through the truth recognition in meanings, and student could see what things displayed. Therefore preconception would be corrected. Of course, everything would not be completed by just one time of experiential learning, and consistent experience learning should be operated. Third, experiential learning promoted the change of sensitivity. Students had shallow sensitivity, which appeared in the relation with things, since having learned only inside of class without a direct observation. However their sensitivity could be increased by experiencing specific things. Fourth, there was the change of classification recognition. Students found properties of things with a direct observation. It raised their ability to classify things, and to understand an individual thing in 'a class'.

• 한국컴퓨터정보학회논문지
• /
• 제14권12호
• /
• pp.55-62
• /
• 2009

이 논문에서는 개체를 명확하게 분류하기 어려운 곤충 발자국 영상으로부터 개체를 인식하기 위해서 추출된 특징값 성분들의 기여도를 측정하고, 서로 관계된 기여도에 따라 가중치를 조정하는 퍼지 가중치 결정 방법을 제안한다. 곤충은 몸의 크기가 작아서 발자국은 작은 점의 형태로 나타난다. 그리고 다른 생물체의 발자국과 달리, 규칙적인 형상을 정의하기 어렵고 발자국 데이터와 구분이 분명하지 않는 노이즈와 혼재하기 때문에 개체를 판단하는데 많은 어려움이 있다. 이런 이유로 추출된 곤충 발자국 특징값은 명확하게 구분되는 특징성분 영역과 그렇지 않는 성분을 함께 가지게 된다. 이중 어떤 성분이 다른 성분과 비교하여 다른 클래스와 구분하기에 충분한 변별력을 가질 경우, 개체를 분류하도록 높은 가중치를 할당한다. 산출된 가중치는 퍼지함수에 의해서 출력신호를 결정하고 우세한 출력신호에 의해서 개체를 판단할수 있다. 제안한 기여도 퍼지 가중치 결정 방법을 이용하여 발자국영상의 인식 실험을 수행하고 실험 결과를 제시하였다.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.157-166
• /
• 2020

Automated rebar fabrication, which requires effective information exchange between model designers and fabricators, has brought the integration and interoperability of data from different sources to the notice of both academics and industry practitioners. Industry Foundation Classes (IFC) was one of the most commonly used data formats to represent the semantic information of prefabricated components in buildings, whereas the data format utilized by rebar fabrication machine is BundesVereinigung der Bausoftware (BVBS), which is a numerical data structure exchanging reinforcement information through ASCII encoded files. Seamless transformation between IFC and BVBS empowers the automated rebar fabrication and improve the construction productivity. In order to improve data interoperability between IFC and BVBS, this study presents an IFC extension based on the attributes required by automated rebar fabrication machines with the help of Information Delivery Manual (IDM) and Model View Definition (MVD). IDM is applied to describe and display the information needed for the design, construction and operation of projects, whereas MVD is a subset of IFC schema used to describe the automated rebar fabrication workflow. Firstly, with a rich pool of vocabularies practitioners, OmniClass is used in information exchange between IFC and BVBS, providing a hierarchy classification structure for reinforcing elements. Then, using International Framework for Dictionaries (IFD), the usage of each attribute is defined in a more consistent manner to assist the data mapping process. Besides, in order to address missing information within automated fabrication process, a schematic data mapping diagram has been made to deliver IFC information from BIM models to BVBS format for better data interoperability among different software agents. A case study based on the data mapping will be presented to demonstrate the proposed IFC extension and how it could assist/facilitate the information management.