부정 탐지를 위한 이상치 분석 활용방안 연구

김동성(Dongsung Kim),김기태(Kitae Kim),김종우(Jongwoo Kim),박성기(Steve Park) 한국지능정보시스템학회 2014 지능정보연구 Vol.20 No.3

기업 의사 결정 지원을 위하여 거래 데이터를 다양한 관점에서 분석하고 활용하려는 노력과 관심들이 증가하고 있다. 이러한 노력들은 고객 관리나 마케팅에만 국한되는 것이 아니라 부정행위에 대한 감시와 탐지를 목적으로도 다양한 분석 방안들이 연구되고 있다. 부정행위는 기술의 발전을 악용하여 다양한 형태로 진화하고 있으며, 이에 따라 목적에 맞는 부정탐지 방안 연구와 적용을 통하여 탐지 효용의 극대화를 위한 노력의 필요성이 증가하고 있다. 이러한 연구 동향의 일환으로 본 연구에서는 대용량 거래 데이터가 저장·관리되고 있는 국내 최대 농수산물 유통 시장의 2008년부터 2010년까지 상장예외품목의 거래 가격을 분석하여 부정 탐지 규칙을 도출하였으며, 전문가 검증을 통하여 도출 된 규칙의 신뢰성을 확보하였다. 본 연구의 주요 부정거래 분석 방안으로는 정상적인 데이터들은 발생 확률이 높은 반면에 특이한 데이터들의 발생 확률은 낮다고 가정하는 통계적 접근을 통한 이상치 식별 방안을 활용하였다. 이에 따라 부정거래 분석 별로 정의 된 Z-Score 값보다 클 경우 부정거래 탐지 대상이 된다. 다만 상장예외품목 거래의 경우 취급 가능한 중도매인의 수가 제한되어 있으며, 일반적인 상장품목의 거래보다 거래량이 적기 때문에 소수의 이상치가 품목의 평균에 미치는 영향이 크다. 그 예로 다른 소수의 중도매인들이 해당 품목을 정상적인 가격에 거래하였더라도, 특정한 중도매인 한 명이 지나치게 비정상적인 가격에 거래할 경우 모든 거래들이 부정거래로 탐지 될 가능성도 있다. 이러한 문제를 해결하기 위하여 기존의 Z-Score의 개념을 활용하여 수정된 Z-Score(Self-Eliminated Z-Score)를 사용하였다. 또한 부정 유형별 탐지 규칙 관리와 활용을 위한 시스템 프로토타입(prototype) 개발을 수행하였다. 이를 통하여 실제 부정거래 탐지 업무에 적용할 수 있는 효과적인 방안을 제시하였고, 농수산 유통시장의 공정성 및 투명성 확보를 위한 관리·감독의 기능 강화가 가능할 것이다. To support business decision making, interests and efforts to analyze and use transaction data in different perspectives are increasing. Such efforts are not only limited to customer management or marketing, but also used for monitoring and detecting fraud transactions. Fraud transactions are evolving into various patterns by taking advantage of information technology. To reflect the evolution of fraud transactions, there are many efforts on fraud detection methods and advanced application systems in order to improve the accuracy and ease of fraud detection. As a case of fraud detection, this study aims to provide effective fraud detection methods for auction exception agricultural products in the largest Korean agricultural wholesale market. Auction exception products policy exists to complement auction-based trades in agricultural wholesale market. That is, most trades on agricultural products are performed by auction; however, specific products are assigned as auction exception products when total volumes of products are relatively small, the number of wholesalers is small, or there are difficulties for wholesalers to purchase the products. However, auction exception products policy makes several problems on fairness and transparency of transaction, which requires help of fraud detection. In this study, to generate fraud detection rules, real huge agricultural products trade transaction data from 2008 to 2010 in the market are analyzed, which increase more than 1 million transactions and 1 billion US dollar in transaction volume. Agricultural transaction data has unique characteristics such as frequent changes in supply volumes and turbulent time-dependent changes in price. Since this was the first trial to identify fraud transactions in this domain, there was no training data set for supervised learning. So, fraud detection rules are generated using outlier detection approach. We assume that outlier transactions have more possibility of fraud transactions than normal transactions. The outlier transactions are identified to compare daily average unit price, weekly average unit price, and quarterly average unit price of product items. Also quarterly averages unit price of product items of the specific wholesalers are used to identify outlier transactions. The reliability of generated fraud detection rules are confirmed by domain experts. To determine whether a transaction is fraudulent or not, normal distribution and normalized Z-value concept are applied. That is, a unit price of a transaction is transformed to Z-value to calculate the occurrence probability when we approximate the distribution of unit prices to normal distribution. The modified Z-value of the unit price in the transaction is used rather than using the original Z-value of it. The reason is that in the case of auction exception agricultural products, Z-values are influenced by outlier fraud transactions themselves because the number of wholesalers is small. The modified Z-values are called Self-Eliminated Z-scores because they are calculated excluding the unit price of the specific transaction which is subject to check whether it is fraud transaction or not. To show the usefulness of the proposed approach, a prototype of fraud transaction detection system is developed using Delphi. The system consists of five main menus and related submenus. First functionalities of the system is to import transaction databases. Next important functions are to set up fraud detection parameters. By changing fraud detection parameters, system users can control the number of potential fraud transactions. Execution functions provide fraud detection results which are found based on fraud detection parameters. The potential fraud transactions can be viewed on screen or exported as files. The study is an initial trial to identify fraud transactions in Auction Exception Agricultural Products. There are still many remained research topics of the issue. First, the

A Retrospective Clinical Evaluation of an Artificial Intelligence Screening Method for Early Detection of STEMI in the Emergency Department

Kim Dongsung,Hwang Ji Eun,Cho Youngjin,Cho Hyoung-Won,Lee Wonjae,Lee Ji Hyun,Oh Il-Young,Baek Sumin,Lee Eunkyoung,Kim Joonghee 대한의학회 2022 Journal of Korean medical science Vol.37 No.10

Background: Rapid revascularization is the key to better patient outcomes in ST-elevation myocardial infarction (STEMI). Direct activation of cardiac catheterization laboratory (CCL) using artificial intelligence (AI) interpretation of initial electrocardiography (ECG) might help reduce door-to-balloon (D2B) time. To prove that this approach is feasible and beneficial, we assessed the non-inferiority of such a process over conventional evaluation and estimated its clinical benefits, including a reduction in D2B time, medical cost, and 1-year mortality. Methods: This is a single-center retrospective study of emergency department (ED) patients suspected of having STEMI from January 2021 to June 2021. Quantitative ECG (QCG™), a comprehensive cardiovascular evaluation system, was used for screening. The non-inferiority of the AI-driven CCL activation over joint clinical evaluation by emergency physicians and cardiologists was tested using a 5% non-inferiority margin. Results: Eighty patients (STEMI, 54 patients [67.5%]) were analyzed. The area under the curve of QCG score was 0.947. Binned at 50 (binary QCG), the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were 98.1% (95% confidence interval [CI], 94.6%, 100.0%), 76.9% (95% CI, 60.7%, 93.1%), 89.8% (95% CI, 82.1%, 97.5%) and 95.2% (95% CI, 86.1%, 100.0%), respectively. The difference in sensitivity and specificity between binary QCG and the joint clinical decision was 3.7% (95% CI, −3.5%, 10.9%) and 19.2% (95% CI, −4.7%, 43.1%), respectively, confirming the non-inferiority. The estimated median reduction in D2B time, evaluation cost, and the relative risk of 1-year mortality were 11.0 minutes (interquartile range [IQR], 7.3–20.0 minutes), 26,902.2 KRW (22.78 USD) per STEMI patient, and 12.39% (IQR, 7.51–22.54%), respectively. Conclusion: AI-assisted CCL activation using initial ECG is feasible. If such a policy is implemented, it would be reasonable to expect some reduction in D2B time, medical cost, and 1-year mortality.

Study on statistical breakdown delay time in argon gas using a W-band millimeter-wave gyrotron

Kim, Dongsung,Kim, Sung Gug,Sawant, Ashwini,Yu, Dongho,Choe, MunSeok,Choi, EunMi American Institute of Physics 2016 Physics of plasmas Vol.23 No.4

Use of colloidal iron as a tracer to measure the ingestion rates of free-living marine nematodes

Kim, Dongsung,Shirayama, Yoshihisa Springer-Verlag 2010 Journal of oceanography Vol.66 No.2

Mitochondrial Genetic Variation of Pen Shell, Atrina pectinata in Korea and Japan

Kim, Dongsung,Rho, Hyun Soo,Jung, Jongwoo The Korean Society of Systematic Zoology 2017 Animal Systematics, Evolution and Diversity Vol.33 No.3

In the northwestern Pacific region, the pen shell (Atrina pectinata) is a widely distributed bivalve and economically important in fisheries. Recently, stock of this species has been greatly reduced due to overexploitation and marine pollution, which arouses interest in conservation. Studies on genetic and taxonomic entities of pen shells have not been tried in Korea, which makes difficult to take measures for effective conservation of this marine resource. In this study, we investigated mitochondrial genetic polymorphism of pen shells collected from 4 locations in Korea and Japan using cytochrome c oxidase I (COI) gene sequences. A total of 39 haplotypes were identified among 86 individuals of pen shell. Although only 5 haplotypes were shared, no significant genetic differentiation was observed between Korean and Japanese populations. These results suggest that pen shell populations of these regions share an ancestral population which might have experienced expansion during the Pleistocene, but gene flow must have been highly restricted after expansion.

Mitochondrial Genetic Variation of Pen Shell, Atrina pectinata in Korea and Japan

Dongsung Kim,Hyun Soo Rho,Jongwoo Jung 한국동물분류학회 2017 Animal Systematics, Evolution and Diversity Vol.33 No.3

In the northwestern Pacific region, the pen shell (Atrina pectinata) is a widely distributed bivalve and economically important in fisheries. Recently, stock of this species has been greatly reduced due to overexploitation and marine pollution, which arouses interest in conservation. Studies on genetic and taxonomic entities of pen shells have not been tried in Korea, which makes difficult to take measures for effective conservation of this marine resource. In this study, we investigated mitochondrial genetic polymorphism of pen shells collected from 4 locations in Korea and Japan using cytochrome c oxidase I (COI) gene sequences. A total of 39 haplotypes were identified among 86 individuals of pen shell. Although only 5 haplotypes were shared, no significant genetic differentiation was observed between Korean and Japanese populations. These results suggest that pen shell populations of these regions share an ancestral population which might have experienced expansion during the Pleistocene, but gene flow must have been highly restricted after expansion.

High-Throughput Screening for Novel Inhibitors of Protein-Tyrosine Phosphatase-1B

Kim WonBae,Lee Inki,Son MiWon,Jung MiYoung,Shin ChangYell,Kim DongSung,Kim SoonHoe,Yoo MooHi 大韓藥學會 2002 大韓藥學會 總會 및 學術大會 Vol.2002 No.2

Discourse Structure and Syntax-Semantics Interface

Dongsung Kim 담화·인지언어학회 2003 담화·인지언어학회 학술대회 발표논문집 Vol.- No.-

DA 11004, a synthetic IDPc inhibitor, inhibits the high fat high sucrose diet-induced obesity in C57BL/6 mice

Kim WonBae,Jeong MiYoung,Shin ChangYell,Sohn JinBup,Lee InKi,Son Miwon,Bae CheolJun,Byun JongSoo,Kim DongSung,Huh TaeLin,Yoo Moohi,Kim SoonHae 大韓藥學會 2003 大韓藥學會 總會 및 學術大會 Vol.2003 No.1

딥러닝 기반 단어 임베딩을 적용한 사진 자막 영작문 채점 시스템

김동성 ( Kim Dongsung ) 대한언어학회 2021 언어학 Vol.29 No.2

Since human grading of English writing requires substantial resources, many researchers in the area of Computer-Assisted Language Learning (CALL) have been focusing on automatic scoring systems based on natural language processing systems, machine learning, and other automatic processing mechanisms. English Testing Services (ETS) announced several automatic scoring systems for English writing. In this paper, we suggest using a deep learning based automatic scoring system for an English caption writing test. Our method involves using a sentence similarity measurement, which compares different levels of answer sentences with user writing input. We chose different word embedding types (Word2Vec, Word Mover‘s Distance (WMD), Bidirectional Encoder Representations from Transformers (BERT)) and Abstract Meaning Representation (AMR), a linguistic model for comparing semantic differences between two sentences based on semantic representation. Scoring systems should not only satisfy the requirements of complicated scoring rubrics but also meet the conditions of a language proficiency test. Our results show that BERT outperforms three competitive models in predicting accurate scoring levels and also shows the characteristics of the criterion reference which could theoretically express the standards of a language proficiency test.