• 한국컴퓨터정보학회논문지
• /
• 제26권4호
• /
• pp.93-103
• /
• 2021

금융당국의 채권추심 가이드라인, 추심업자에 대한 직접적인 관리 감독 수행 등의 노력에도 불구하고 채무자에 대한 불법, 부당한 채권 추심은 지속되고 있다. 이러한 불법, 부당한 채권추심행위를 효과적으로 예방하기 위해서는 비정형데이터 기계학습 등 기술을 활용하여 적은 인력으로도 불법 추심행위에 대한 점검 등에 대한 모니터링을 강화 할 수 있는 방법이 필요하다. 본 연구에서는 대부업체의 추심 녹취 파일을 입수하여 이를 텍스트 데이터로 변환하고 위법, 위규 행위를 판별하는 규칙기반 검출과 SVM(Support Vector Machine) 등 기계학습을 결합한 불법채권추심 분류 모델을 제안하고 기계학습 알고리즘에 따라 얼마나 정확한 식별을 하였는지를 비교해 보았다. 본 연구는 규칙기반 불법 검출과 기계학습을 결합하여 분류에 활용할 경우 기존에 연구된 기계학습만을 적용한 분류모델 보다 정확도가 우수하다는 것을 보여 주었다. 본 연구는 규칙기반 불법검출과 기계학습을 결합하여 불법여부를 분류한 최초의 시도이며 후행연구를 진행하여 모델의 완성도를 높인다면 불법채권 추심행위에 대한 소비자 피해 예방에 크게 기여할 수 있을 것이다.

• 대한간호
• /
• 제33권1호
• /
• pp.52-64
• /
• 1994

Since 1963 when the graduate program in nursing was initiated in Korea, more than 2,000 students enrolled in the program have published their theses or dissertation papers. However, a few of the study papers have been confined one system, which prohibits them from being used as references by others. This research study provides a database for the nursing thesis and dissertation papers published since 1967 in Korea. This allows for those who are interested in nursing to retrieve the information in effective ways. The retrieval networks as follows: 1) The data is sent via PSTN or DACOM NET to Chonrian by Yonsei Nursing Policy Research Institute. 2) Chonrian saves data. 3) Members of Chonrian retrieve the data through PSTN or DACOM NET. The database is comprised of the title of the papers; school; graduate year.

• Communications for Statistical Applications and Methods
• /
• 제27권6호
• /
• pp.589-602
• /
• 2020

The development of smart grids has enabled the easy collection of a large amount of power data. There are some common patterns that make it useful to cluster power consumption patterns when analyzing s power big data. In this paper, clustering analysis is based on distance functions for time series and clustering algorithms to discover patterns for power consumption data. In clustering, we use 10 distance measures to find the clusters that consider the characteristics of time series data. A simulation study is done to compare the distance measures for clustering. Cluster validity measures are also calculated and compared such as error rate, similarity index, Dunn index and silhouette values. Real power consumption data are used for clustering, with five distance measures whose performances are better than others in the simulation.

• 한국의료질향상학회지
• /
• 제5권2호
• /
• pp.224-237
• /
• 1998

Background : This is an investigative study to analyse the importance of works perceived by Quality Improvement(QI) Coordinators and to evaluate their current work performances using the questionnaires developed by the investigator. Methods : The data were collected from 37 subjects over two weeks period from Oct. 1 to Oct. 17, 1998 and analysed by the descriptive statistics of SPSS program. The items of questionnaire are consisted of 13 work domains including 73 activities based on Quality Management(QM) Coordinator's job description of National Association for Healthcare Quality:data collection & analysis, communication, monitoring, evaluation, accreditation, tool development, policy development, program development, self development, education & trainning, system design, planning, and consultation & support. Results : 1) Of the performances in 13 work domains, the frequencies of the work performed were accreditation(89%), planning(88%), communication(83%), data collection & analysis(82%), monitoring(76%), policy development(72%), consultation & support (71%), education & trainning(70%), self development(68%), evaluation(63%), tool development(61%), program development(44%) and system design(43%) in order. 2) For the importances (1=not important, 5=very important), the policy development(4.46) scored highest then monitoring(4.42), planning(4.41), education & trainning(4.38), communication(4.35), evaluation(4.34) tool development (4.30), data collection & analysis(4.29), program development(4.22), consultation & support(4.22), accreditation(4.15), self development(4.05) and system design(3.98) in order. 3) There was a difference between the work performance and the perceived importance. The results showed the low performances in policy development, monitoring, education & trainning and evaluation which ranked high by the perceived importance and the high performances in accreditation, data collection & analysis, self development, communication and consultation & support which ranked middle to low by the perceived importance. 4) The reasons for low performances of QI Coordinators were the lack of clear assignment for the responsibility and allowed authority for work to QI Coordinators(30.8%), insufficient member of QI Coordinators(13.9%), lack of hospital director's interest(11.5%), low motivation of QI Coordinators (10.6%) and insufficient knowledge & experience of QI Coordinators (8.8%). Conclusion : Most works were perceived important by QI Coordinators, but there was a difference in the work performance. The works performed over 70% were related with accreditation, data collection & analysis, communication, planning and monitoring, on the other hand under 50% in performances were related with system design, program development, tool development and evaluation.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제4권6호
• /
• pp.261-268
• /
• 2015

음성채팅시스템에서 사용자의 음성 질의는 자동음성인식기를 통하여 텍스트 질의로 변환된다. 만약 자동음성인식기의 1순위 결과가 틀린다면 이 오류는 그대로 음성채팅시스템에 전파된다. 자동음성인식기의 1순위 정밀도를 향상시키기 위하여 본 논문에서는 RankSVM을 이용하여 자동음성인식기의 n개 결과를 재순위화하는 후처리 모델을 제안한다. 채팅시스템을 학습하기 위해서는 대용량의 채팅 문장들이 필요하다. 만약 새로운 채팅 문장들이 학습데이터에 자주 추가되지 않는다면 채팅시스템의 응답은 금방 진부해질 것이다. 이러한 문제를 해결하기 위하여 본 논문에서는 SVM을 이용하여 TV와 영화 시나리오로부터 채팅 문장들을 자동으로 선택하는 데이터 수집 모델을 제안한다. 실험에서 제안된 후처리 모델은 후처리를 하지 않은 모델보다 정확률에서 4.4%, 재현율에서 6.4% 더 좋은 결과를 보였다. 그리고 제안된 데이터 수집 모델은 98.95%의 높은 정확률과 57.14%의 재현율을 보였다.

• 부모자녀건강학회지
• /
• 제14권1호
• /
• pp.28-35
• /
• 2011

Purpose: The aim of this study is to suggest a direction for the development of effective methods for relieving labor pain, by analyzing non-pharmacological interventions through a literature review. Methods: Collection of literature data in this study has been accomplished through theses, reports, and academic data searched on databases of the Research Information Sharing Services (Riss), PubMed, ProQuest, and the National Discovery for Science Leaders (NDSL). Results: Non-pharmacological interventions analyzed as effective in relieving labor pain, in literature published both within and outside of Korea, included: pre-delivery education, Yoga, Doula delivery care, Massage, Music therapy, Aromatherapy, Hypnosis, TENS, Sterilized water injection, and Acupuncture. Conclusion: Several different interventions have been attempted for the relief of labor pain. Since even the same intervention shows different results depending on the research method utilized, critical factors must be acknowledged that compromise the effectiveness of these methods. In addition, study of potential synergy effects of interventions that combine these various methods might also prove to be significant.

• 대한지역사회영양학회지
• /
• 제16권2호
• /
• pp.278-293
• /
• 2011

The purpose of this study was to examine the research trend of nutrition for the recent 12 years from 1996 to 2007 by analyzing 734 articles published in the Korean Journal of Community Nutrition. The majority of the articles (61.4%) were classified as survey types in terms of data collection methods. Most of the subjects used in the articles were adults (28.8%), and the subject whose research has been increased at the highest rate was "patients". The most frequent keywords in the title of articles were "nutrient intake" (231times), "food service" (92times), "dietary habits" (69times), and "obesity" (69times). The keywords that have appeared more frequently with the years were "osteoporosis" (450.0%), "menopause" (350.0%) and "dietary attitudes" (208.3%). As for research interests, "nutrient intake" was dominant in the early stage of research while "disease", "dietary habits", "dietary attitudes" and "nutrition education" have increased in recent years. Some of the most common methods of nutrition assessment were "dietary intake" (41.2%), "anthropometric" (34.0%) and "biochemical test" (14.7%). The most common methods of dietary intake were "24-hours recall" (28.6%) and "dietary habits" (23.3%). The results of this study showed some biases in data collection methods, gender of the subjects, and study areas. Moreover, inconsistent terminologies, questionnaire contents, and measures were used for the researches on dietary behaviors, dietary habits, dietary attitudes, which made it difficult to compare their results for each research. Therefore, standardized research methods and terminologies need to be developed regarding dietary practices.

• 동서간호학연구지
• /
• 제30권1호
• /
• pp.10-21
• /
• 2024

Purpose: The purpose of this study are to understand the meaning and essential structure of clinical nurses' experiences of verbal violence and find nursing intervention for them by applying phenomenological research method. Methods: The participants in this study were seven clinical nurses with experience of verbal violence. Data collection were conducted from August 2016 through January 2017 until data saturation. Data analysis was performed through a cyclical process of data collection and analysis by applying Giorgi's phenomenological method. Results: Four categories were identified: A weapon of the mind: the shock of verbal abuse; negative emotions that shake my heart; skepticism about the value and meaning of a job; an unforgettable wound. Conclusions: The results of this study provide a deeper understanding of the pain caused by verbal violence experienced by nurses from their care recipients. These results suggest that nursing interventions for nurses with experience of verbal violence will contribute to resolving the problem.

• 대한간호학회지
• /
• 제43권6호
• /
• pp.801-811
• /
• 2013

Purpose: To investigate changes in Quality of life (QOL) and related factors in patients with thyroid cancer undergoing Radioactive Iodine remnant ablation (RAI). Methods: Data were collected longitudinally 3 times for 6 months (2 weeks post-surgery, post RAI, 3 months post RAI) in a hospital located in Seoul. Questionnaires were used to measure levels of physical symptoms, anxiety, depression, and QOL. Ninety-eight patients with thyroid cancer who had RAI were included in the analysis. Data were analyzed using SPSS (18.0). Results: Findings for the three data collection times respectfully were: mean scores for physical symptoms, 0.53, 1.21 and 0.62, patients with depression, 47%, 36.7% and 37.7%, patients with anxiety, 18.4 %, 19.4% and 20.4%, mean scores for QOL, 7.06, 7.01 and 7.28. QOL score was highest 3 months post RAI (p=.031). In the stepwise multiple regression analysis, depression and fatigue were predicting factors for low QOL at all data collection times. Dysponia was a predicting factor for low QOL post RAI and 3 months post RAI. Conclusion: To increase QOL, it is necessary to provide information in advance regarding physical & psychological symptoms and to develop nursing intervention programs to decrease depression and fatigue.

• 대한기계학회논문집B
• /
• 제31권6호
• /
• pp.522-530
• /
• 2007

The practical studies on the method of particle contamination control for yield enhancement in the cleanroom were carried out. The method of the contamination control was proposed, which are composed of data collection, data analysis, improvement action, verification, and implement control. The partition check method and the composition analysis for data collection and data analysis were respectively used in the main board and the cellular phone module production lines. And these methods were evaluated by the variation of yield loss between before and after improvement action. In case that the partition check method was applied, the critical process step was selected and yield loss reduction through improvement actions was observed. While in case that the composition analysis was applied, the critical sources were selected and yield loss reduction through improvement actions was also investigated. From these results, it is concluded that the partition check and the composition analysis are effective solutions for particle contamination control in the cleanroom production lines.