• 지능정보연구
• /
• 제18권4호
• /
• pp.79-95
• /
• 2012

금융기관들에서 개발한 신용 대출 상품이 증가함에 따라 사기 거래의 수 또한 급속히 증가하고 있다. 따라서, 재정적 위험을 성공적으로 관리하기 위해 금융기관들은 대출 승인 심사를 강화하고 신용 대출 사기를 사전에 탐지할 수 있는 능력을 증대시켜 나가야 한다. 신용 대출 사기를 탐지하기 위한 분류 모델을 구축하는 과정에서 분류 결과에 따른 유틸리티(즉, 정분류에 따른 이익과 오분류에 따른 비용)는 분류의 정확도보다 더 중요하다. 본 연구는 개인별 유틸리티에 기반하여 신용 대출 사기를 탐지하기 위한 분류 모델을 구축하는 것을 목적으로 하였다. 다양한 실험을 통해, 본 연구에서 제시한 모델이 기회 유틸리티와 현금 흐름의 두 관점 모두에서 개인별 유틸리티에 기반하지 않은 모델보다 더 높은 유틸리티를 제공하며, 평균 유틸리티에 기반한 모델보다 더 정확한 유틸리티를 제공한다는 것을 보였다. 본 연구는 기회 유틸리티와 현금 흐름의 두 관점에서 얻어진 실험 결과를 다양한 측면에서 살펴보았다.

• 한국자원식물학회:학술대회논문집
• /
• 한국자원식물학회 2019년도 추계학술대회
• /
• pp.87-87
• /
• 2019

The consumption of herbal medicine and related products (herbal products) have increased in South Korea. At the same time the quality, safety, and efficacy of herbal products is being raised. Currently, the herbal products are standardized and controlled according to the requirements of the Korean Pharmacopoeia, the National Institute of Health and the Ministry of Public Health and Social Affairs. The validation of herbal products and their medicinal component is important, since many of these herbal products are composed of two or more medicinal plants. However, there are no tools to support the validation process. Interest in deep learning has exploded over the past decade, for herbal medicine using algorithms to achieve herb recognition, symptom related target prediction, and drug repositioning have been reported. In this study, individual images of four herbs (Panax ginseng C.A. Meyer, Atractylodes macrocephala Koidz, Poria cocos Wolf, Glycyrrhiza uralensis Fischer), actually sold in the market, were achieved. Certain image preprocessing steps such as noise reduction and resize were formatted. After the features are optimized, we applied GoogLeNet_Inception v4 model for herb image recognition. Experimental results show that our method achieved test accuracy of 95%. However, there are two limitations in the current study. Firstly, due to the relatively small data collection (100 images), the training loss is much lower than validation loss which possess overfitting problem. Secondly, herbal products are mostly in a mixture, the applied method cannot be reliable to detect a single herb from a mixture. Thus, further large data collection and improved object detection is needed for better classification.

• 대한의용생체공학회:의공학회지
• /
• 제44권6호
• /
• pp.414-427
• /
• 2023

Implantable bioabsorbable combination products undergo inherent degradation and systemic absorption within the physiological environment, thereby streamlining the therapeutic regimen and obviating the imperative for invasive extraction procedures. This inherent property not only enhances patient convenience and therapeutic efficacy but also underpins a paradigm of support characterized by heightened safety parameters. Within the regulatory landscapes of Korea, the United States, and Europe, implantable bioabsorbable combination products are meticulously classified into distinct categories, either as pharmaceutical implants or as implantable medical devices, depending on their primary mode of action. This scholarly investigation systematically examines the regulatory frameworks governing implantable bioabsorbable combination products in South Korea, the United States, and Europe. Notable discrepancies across national jurisdictions emerge concerning regulatory specifics, including terminology, product classification, and product name associated with these products. The conspicuous absence of standardized approval regulations presents a formidable barrier to the commercialization of these advanced medical devices. This academic discourse passionately emphasizes the critical need for formulating and implementing a sophisticated regulatory framework capable of streamlining the product approval process, thereby paving the way for a seamless path to commercializing implantable bioabsorbable combination products.

• 품질경영학회지
• /
• 제48권3호
• /
• pp.421-431
• /
• 2020

Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

• 한국작물학회지
• /
• 제46권1호
• /
• pp.53-56
• /
• 2001

Barley Yellow Dwarf Virus (BYDV), an aphid-borne luteovirus, is a major plant pathogenic disease causing a huge economic loss in the grain production of a wide range of Gramineae species throughout the world. It has been recently reported that BYDV also occurred frequently in wheat field of Korea. Here, we performed to develop the detection and classification methods of BYDV strains that were accomplished by reverse transcription-polymerase chain reaction (RT-PCR). Since there are high variations among BYDV strains, three pairs of primers were designed to detect BYDV strains such as PAV (Vic-PAV and CN-PAV) and MAV (primer A) simultaneously, specifically Vic-PAV(primer B), and MAV (primer C) based on the genomic RNA sequences of BYDV strains previously published. The validity of the primers was confirmed using several BYDV strains obtained from CIMMYT. Though three BYDV strains were able to be detected using primer A, PCR products were not distinguished between two PAV strains. It was possible to separate them with a restriction enzyme, EcoRI, whose restriction site was present in the amplified DNA fragment from Vic-PAV, but not from CN-PAV.

• 동아시아경상학회지
• /
• 제10권3호
• /
• pp.51-61
• /
• 2022

Purpose - The purpose of this study is to establish the government's logistics policy by calculating the logistics cost of the company and grasping the management status, to reduce the logistics cost of the related companies and to provide basic statistical data necessary for the management strategy. This work examines some associations between reasons for reducing corporate logistics costs (RCLC) and corporate classification such as industry and sales size. Research design, data, and methodology - The survey was conducted in 2018 for 2,000 companies based on the business of mining, manufacturing and wholesale and retail industries since 2010. The survey population is 94,976, of which 92,708 are small and medium enterprises and 2,268 are large corporations. The association among factors may be statistically and visually explored by using chi-squared test and correspondence analysis. Result - This study reveals the association between reasons for RCLC and corporate classification and properties and closeness that exist between the categories of each factor can be mined. Conclusion - As a task to reduce logistics costs of industrial products, expansion and operation of joint logistics business, establishment of cooperative logistics network, and establishment of ordinance on support for smart distribution logistics can be proposed.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.82-84
• /
• 2021

스마트 공장 구축사업을 통해 생산 설비로부터 전력, 진동, 압력, 온도 등의 센서 데이터가 수집되고 있으며 데이터 분석을 통해 예지보전, 불량예측, 이상탐지 등의 서비스 개발이 진행되고 있다. 일반적으로 제조데이터의 경우 정상과 비정상 데이터의 불균형이 극심하여 이상탐지 서비스가 선호되고 있다. 본 논문에서는 이상탐지 서비스 개발의 전단계로 제조데이터의 특징 데이터 추출을 위해 FFT 방법을 사용하였으며, 이를 통해 생산되는 제품을 분류해보고 그 결과를 확인하였다. 즉, 제품별 대표 패턴을 FFT 변환 후 상관계수를 계산하여 제품분류가 가능한지 확인하였다.

• 품질경영학회지
• /
• 제17권2호
• /
• pp.64-69
• /
• 1989

This paper aims at analyzing the process capability and at determining an optimal condition by experimental designs using the 2-way classification with repitition in order to maintain lower Nacl content and to refine both of a very small quantity of fatty acid and various magnetic ions in the glycerin to use ion exchange resin treatment process. An optimal condition of each level combination in both of passing temperature of cation exchange resin($A_1$, $A_2$, $A_3$) and of anion exchange resin($B_1$, $B_2$, $B_3$) is $A_3B_3$. The process capability index is improved from 0.63 to 1.40 and is interpreted as a desirable state. This analysis of process capability by experimental designs will contribute to improving productivity and quality of products.

• 보험의학회지
• /
• 제32권1호
• /
• pp.21-27
• /
• 2013

In case of neoplasm claims, it is important to make a decision of differentiating malignant and benign. In Korean insurance market, there are many insurance products that cover cancer. In the insurance claims adjustment, differentiation between malignant and benign is according to histologic findings. However there are many neoplasms of bad clinical course in spite of benign histopathologic classification. In this article; astrocytoma, thymoma, gastrointestinal stromal tumor, colonic intramucosal carcinoma, gastric high grade adenoma/dysplasia, carcinoid tumor, MALT lymphoma, revision of Korean Classification of Disease-6th edition, and bladder tumors are reviewed in terms of differentiation between malignant and benign in the insurance claims. It may be helpful for claims staff to review important neoplasms in terms of differentiation between malignant and benign.

• ETRI Journal
• /
• 제31권1호
• /
• pp.10-20
• /
• 2009

In this paper, a video broadcasting system between a home-server-type device and a mobile device is proposed. The home-server-type device can automatically extract semantic information from video contents, such as news, a soccer match, and a baseball game. The indexing results are utilized to convert the original video contents to a digested or arranged format. From the mobile device, a user can make recording requests to the home-server-type devices and can then watch and navigate recorded video contents in a digested form. The novelty of this study is the actual implementation of the proposed system by combining the actual IT environment that is available with indexing algorithms. The implementation of the system is demonstrated along with experimental results of the automatic video indexing algorithms. The overall performance of the developed system is compared with existing state-of-the-art personal video recording products.