• Asia pacific journal of information systems
• /
• 제18권3호
• /
• pp.123-145
• /
• 2008

Recently, as the information communication technology develops, the discussion regarding the ubiquitous environment is occurring in diverse perspectives. Ubiquitous environment is an environment that could transfer data through networks regardless of the physical space, virtual space, time or location. In order to realize the ubiquitous environment, the Pervasive Sensing technology that enables the recognition of users' data without the border between physical and virtual space is required. In addition, the latest and diversified technologies such as Context-Awareness technology are necessary to construct the context around the user by sharing the data accessed through the Pervasive Sensing technology and linkage technology that is to prevent information loss through the wired, wireless networking and database. Especially, Pervasive Sensing technology is taken as an essential technology that enables user oriented services by recognizing the needs of the users even before the users inquire. There are lots of characteristics of ubiquitous environment through the technologies mentioned above such as ubiquity, abundance of data, mutuality, high information density, individualization and customization. Among them, information density directs the accessible amount and quality of the information and it is stored in bulk with ensured quality through Pervasive Sensing technology. Using this, in the companies, the personalized contents(or information) providing became possible for a target customer. Most of all, there are an increasing number of researches with respect to recommender systems that provide what customers need even when the customers do not explicitly ask something for their needs. Recommender systems are well renowned for its affirmative effect that enlarges the selling opportunities and reduces the searching cost of customers since it finds and provides information according to the customers' traits and preference in advance, in a commerce environment. Recommender systems have proved its usability through several methodologies and experiments conducted upon many different fields from the mid-1990s. Most of the researches related with the recommender systems until now take the products or information of internet or mobile context as its object, but there is not enough research concerned with recommending adequate store to customers in a ubiquitous environment. It is possible to track customers' behaviors in a ubiquitous environment, the same way it is implemented in an online market space even when customers are purchasing in an offline marketplace. Unlike existing internet space, in ubiquitous environment, the interest toward the stores is increasing that provides information according to the traffic line of the customers. In other words, the same product can be purchased in several different stores and the preferred store can be different from the customers by personal preference such as traffic line between stores, location, atmosphere, quality, and price. Krulwich(1997) has developed Lifestyle Finder which recommends a product and a store by using the demographical information and purchasing information generated in the internet commerce. Also, Fano(1998) has created a Shopper's Eye which is an information proving system. The information regarding the closest store from the customers' present location is shown when the customer has sent a to-buy list, Sadeh(2003) developed MyCampus that recommends appropriate information and a store in accordance with the schedule saved in a customers' mobile. Moreover, Keegan and O'Hare(2004) came up with EasiShop that provides the suitable tore information including price, after service, and accessibility after analyzing the to-buy list and the current location of customers. However, Krulwich(1997) does not indicate the characteristics of physical space based on the online commerce context and Keegan and O'Hare(2004) only provides information about store related to a product, while Fano(1998) does not fully consider the relationship between the preference toward the stores and the store itself. The most recent research by Sedah(2003), experimented on campus by suggesting recommender systems that reflect situation and preference information besides the characteristics of the physical space. Yet, there is a potential problem since the researches are based on location and preference information of customers which is connected to the invasion of privacy. The primary beginning point of controversy is an invasion of privacy and individual information in a ubiquitous environment according to researches conducted by Al-Muhtadi(2002), Beresford and Stajano(2003), and Ren(2006). Additionally, individuals want to be left anonymous to protect their own personal information, mentioned in Srivastava(2000). Therefore, in this paper, we suggest a methodology to recommend stores in U-market on the basis of ubiquitous environment not using personal information in order to protect individual information and privacy. The main idea behind our suggested methodology is based on Feature Matrices model (FM model, Shahabi and Banaei-Kashani, 2003) that uses clusters of customers' similar transaction data, which is similar to the Collaborative Filtering. However unlike Collaborative Filtering, this methodology overcomes the problems of personal information and privacy since it is not aware of the customer, exactly who they are, The methodology is compared with single trait model(vector model) such as visitor logs, while looking at the actual improvements of the recommendation when the context information is used. It is not easy to find real U-market data, so we experimented with factual data from a real department store with context information. The recommendation procedure of U-market proposed in this paper is divided into four major phases. First phase is collecting and preprocessing data for analysis of shopping patterns of customers. The traits of shopping patterns are expressed as feature matrices of N dimension. On second phase, the similar shopping patterns are grouped into clusters and the representative pattern of each cluster is derived. The distance between shopping patterns is calculated by Projected Pure Euclidean Distance (Shahabi and Banaei-Kashani, 2003). Third phase finds a representative pattern that is similar to a target customer, and at the same time, the shopping information of the customer is traced and saved dynamically. Fourth, the next store is recommended based on the physical distance between stores of representative patterns and the present location of target customer. In this research, we have evaluated the accuracy of recommendation method based on a factual data derived from a department store. There are technological difficulties of tracking on a real-time basis so we extracted purchasing related information and we added on context information on each transaction. As a result, recommendation based on FM model that applies purchasing and context information is more stable and accurate compared to that of vector model. Additionally, we could find more precise recommendation result as more shopping information is accumulated. Realistically, because of the limitation of ubiquitous environment realization, we were not able to reflect on all different kinds of context but more explicit analysis is expected to be attainable in the future after practical system is embodied.

• 지능정보연구
• /
• 제24권2호
• /
• pp.125-148
• /
• 2018

다양한 스마트 기기 및 관련 서비스의 증가에 따라 텍스트 데이터가 폭발적으로 증가하고 있으며, 이로 인해 방대한 문서로부터 필요한 정보만을 추려내는 작업은 더욱 어려워졌다. 따라서 텍스트 데이터로부터 핵심 내용을 자동으로 요약하여 제공할 수 있는 텍스트 자동 요약 기술이 최근 더욱 주목을 받고 있다. 텍스트 요약 기술은 뉴스 요약 서비스, 개인정보 약관 요약 서비스 등을 통해 현업에서도 이미 활발하게 적용되고 있으며, 학계에서도 문서의 주요 요소를 선별하여 제공하는 추출(Extraction) 접근법과 문서의 요소를 발췌한 뒤 이를 조합하여 새로운 문장을 구성하는 생성(Abstraction) 접근법에 따라 많은 연구가 이루어지고 있다. 하지만 문서의 자동 요약 기술에 비해, 자동으로 요약된 문서의 품질을 평가하는 기술은 상대적으로 많은 진전을 이루지 못하였다. 요약문의 품질 평가를 다룬 기존의 대부분의 연구들은 사람이 수작업으로 요약문을 작성하여 이를 기준 문서(Reference Document)로 삼고, 자동 요약문과 기준 문서와의 유사도를 측정하는 방식으로 수행되었다. 하지만 이러한 방식은 기준 문서의 작성 과정에 막대한 시간과 비용이 소요될 뿐 아니라 요약자의 주관에 의해 평가 결과가 다르게 나타날 수 있다는 한계를 갖는다. 한편 이러한 한계를 극복하기 위한 연구도 일부 수행되었는데, 대표적으로 전문에 대해 차원 축소를 수행하고 이렇게 축소된 전문과 자동 요약문의 유사도를 측정하는 기법이 최근 고안된 바 있다. 이 방식은 원문에서 출현 빈도가 높은 어휘가 요약문에 많이 나타날수록 해당 요약문의 품질이 우수한 것으로 평가하게 된다. 하지만 요약이란 본질적으로 많은 내용을 줄여서 표현하면서도 내용의 누락을 최소화하는 것을 의미하므로, 단순히 빈도수에 기반한 "좋은 요약"이 항상 본질적 의미에서의 "좋은 요약"을 의미한다고 보는 것은 무리가 있다. 요약문 품질 평가의 이러한 기존 연구의 한계를 극복하기 위해, 본 연구에서는 요약의 본질에 기반한 자동 품질 평가 방안을 제안한다. 구체적으로 요약문의 문장 중 서로 중복되는 내용이 얼마나 적은지를 나타내는 요소로 간결성(Succinctness) 개념을 정의하고, 원문의 내용 중 요약문에 포함되지 않은 내용이 얼마나 적은지를 나타내는 요소로 완전성(Completeness)을 정의한다. 본 연구에서는 간결성과 완전성의 개념을 적용한 요약문 품질 자동 평가 방법론을 제안하고, 이를 TripAdvisor 사이트 호텔 리뷰의 요약 및 평가에 적용한 실험 결과를 소개한다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권12호
• /
• pp.1141-1153
• /
• 2010

본 논문에서는 IPTV 표준화 기구인 ITU-T IPTV FG(Focus Group)에서 제안한 IPTV 참조 모델을 기반으로 라이브 IPTV 방송이 고객에게 전달되는 과정을 네트워크 관점에서 분석하여 각 네트워크 특성에 맞는 멀티캐스트 기법을 적용한 혼합형 오버레이 멀티캐스트 네트워크인 ONLIS(Overlay Multicast Network for Live IPTV Service)를 제안한다. IPTV 방송사 네트워크와 네트워크 서비스 제공자의 백본 네트워크에는 안정적인 스트립 분산과 효율적인 트래픽 관리를 위해 전용 서버 기반의 오버레이 멀티캐스트 네트워크를 적용하고, 종단 사용자가 네트워크에 접속하는 구간인 액세스 네트워크 구간은 P2P 방식 오버레이 네트워크를 구성하여 서버 부하 절감효과를 얻을 수 있다. P2P 기술을 이용하여 라이브 스트림을 전송할 때 해결해야 할 가장 중요한 과제는 전송 지연 단축과 전송 스트림 품질 향상이다. 이 문제를 해결하기 위해 본 논문에서는 P2P 관련 기술을 제시한다. 제안 기술은 서버 기반과 P2P 기반의 혼합형 오버레이 멀티캐스트 네트워크의 장점을 활용한 분산 스트리밍 P2P 트리(DSPT: Distributed Streaming P2P Tree)를 이용한 전송 기법이다. 제안하는 P2P 전송 방식은 전적으로 피어에 스트림 전송을 의존하지 않고 액세스 네트워크의 전용 오버레이 멀티캐스트 전송 장비인 릴레이(Relay)와 협조하는 방식으로, 피어에 장애가 발생하면 즉시 릴레이로부터 스트림 수신을 재개하여 끊김 없는 스트림 서비스를 받을 수 있다. 또한, 하나의 스트림을 여러 서버와 경로를 통해 전송할 수 있는 분산 스트리밍 기법을 적용하여 공급 피어의 전송 대역폭 허용하는 범위 내에서 스트림을 전송하고, 나머지는 로컬 액세스 네트워크의 오버레이 전송 장비로부터 수신하여 P2P 네트워크의 전송 효율성을 향상하였다.

• 한국대기환경학회지
• /
• 제33권4호
• /
• pp.377-392
• /
• 2017

A set of BFM (Brute Force Method) simulations with the CMAQ (Community Multiscale Air Quality) model were conducted in order to estimate self-contributions and conversion rates of PPM (Primary $PM_{2.5}$), $NO_x$, $SO_2$, $NH_3$, and VOC emissions to $PM_{2.5}$ concentrations over the SMA (Seoul Metropolitan Area). CAPSS (Clean Air Policy Support System) 2013 EI (emissions inventory) from the NIER (National Institute of Environmental Research) was used for the base and sensitivity simulations. SCCs (Source Classification Codes) in the EI were utilized to group the emissions into area, mobile, and point source categories. PPM and $PM_{2.5}$ precursor emissions from each source category were reduced by 50%. In turn, air quality was simulated with CMAQ during January, April, July, and October in 2014 for the BFM runs. In this study, seasonal variations of SMA $PM_{2.5}$ self-sensitivities to PPM, $SO_2$, and $NH_3$ emissions can be observed even when the seasonal emission rates are almost identical. For example, when the mobile PPM emissions from the SMA were 634 TPM (Tons Per Month) and 603 TPM in January and July, self-contributions of the emissions to monthly mean $PM_{2.5}$ were $2.7{\mu}g/m^3$ and $1.3{\mu}g/m^3$ for the months, respectively. Similarly, while $NH_3$ emissions from area sources were 4,169 TPM and 3,951 TPM in January and July, the self-contributions to monthly mean $PM_{2.5}$ for the months were $2.0{\mu}g/m^3$ and $4.4{\mu}g/m^3$, respectively. Meanwhile, emission-to-$PM_{2.5}$ conversion rates of precursors vary among source categories. For instance, the annual mean conversion rates of the SMA mobile, area, and point sources were 19.3, 10.8, and $6.6{\mu}g/m^3/10^6TPY$ for $SO_2$ emissions while those rates for PPM emissions were 268.6, 207.7, and 181.5 (${\mu}g/m^3/10^6TPY$), respectively, over the region. The results demonstrate that SMA $PM_{2.5}$ responses to the same amount of reduction in precursor emissions differ for source categories and in time (e.g. seasons), which is important when the cost-benefit analysis is conducted during air quality improvement planning. On the other hand, annual mean $PM_{2.5}$ sensitivities to the SMA $NO_x$ emissions remains still negative even after a 50% reduction in emission category which implies that more aggressive $NO_x$ reductions are required for the SMA to overcome '$NO_x$ disbenefit' under the base condition.

• Tuberculosis and Respiratory Diseases
• /
• 제67권2호
• /
• pp.88-94
• /
• 2009

Background: From November 2006, The national health insurance system in the Republic of Korea began to cover prescribed long-term oxygen therapy (LTOT) in patients with chronic respiratory insufficiency. This study examined the current status of LTOT after national health insurance coverage. Methods: Between November 1, 2006 and June 30, 2008, the medical records of patients who were prescribed LTOT by chest physicians were reviewed. The data was collected from 13 university hospitals. Results: 197 patients (131 male and 66 female) were prescribed LTOT. The mean age was 64.3${\pm}$13.0 years. The most common underlying disease was chronic obstructive pulmonary disease (n=103, 52.3%). Chest physicians prescribed LTOT using arterial blood gas analysis or a pulse oxymeter (74.6%), symptoms (14%), or a pulmonary function test (11.2%). The mean oxygen flow rate was 1.56${\pm}$0.68 L/min at rest, 2.08${\pm}$0.91 L/min during exercise or 1.51${\pm}$0.75 L/min during sleep. Most patients (98.3%) used oxygen concentrators. Only 19% of patients used ambulatory oxygen supplies. The oxygen saturation before and after LTOT was 83.18${\pm}$10.48% and 91.64${\pm}$7.1%, respectively. After LTOT, dyspnea improved in 81.2% of patients. The mean duration of LTOT was 16.85${\pm}$6.71 hours/day. The rental cost for the oxygen concentrator and related electricity charges were 48,414${\pm}$15,618 won/month and 40,352${\pm}$36,815 won/month, respectively. Approximately 75% of patients had a regular visit by the company. 5.8% of patients had personal pulse oxymetry. 54.9% of patients had their oxygen saturation checked on each visit hospital. 8% of patients were current smokers. The most common complaint with LTOT was the limitation of daily activity (53%). The most common complaint with oxygen concentrators was noise (41%). Conclusion: The patients showed good compliance with LTOT. However, only a few patients used an ambulatory oxygen device or had their oxygen saturation measured.

• 지능정보연구
• /
• 제24권2호
• /
• pp.243-264
• /
• 2018

현재 전세계 배터리 시장은 이차전지 개발에 박차를 가하고 있는 실정이지만, 실제로 소비되는 배터리 중 가격 대비 성능이 좋고 재충전을 통해 다시 재사용이 가능한 납축전지(이차전지)의 소비가 광범위하게 이루어지고 있다. 하지만 납축전지는 복합적 셀(cell)을 묶어 하나의 배터리를 구성하여 활용하는 배터리의 특성상 하나의 셀에서 열화가 발생하면 전체 배터리의 손상을 가져와 열화가 빨리 진행되는 문제가 존재한다. 이를 극복하기 위해 본 연구는 기계학습을 통한 배터리 상태 데이터를 학습하여 배터리 열화를 예측할 수 있는 모델을 개발하고자 한다. 이를 위해 실제 현장에서 배터리 상태를 지속적으로 모니터링 할 수 있는 센서를 골프장 카트에 부착하여 실시간으로 배터리 상태 데이터를 수집하고, 수집한 데이터를 이용하여 기계학습 기법을 적용한 분석을 통해 열화 전조 현상에 대한 예측 모델을 개발하였다. 총 16,883개의 샘플을 분석 데이터로 사용하였으며, 예측 모델을 만들기 위한 알고리즘으로 의사결정나무, 로지스틱, 베이지언, 배깅, 부스팅, RandomForest를 사용하였다. 실험 결과, 의사결정나무를 기본 알고리즘으로 사용한 배깅 모델이 89.3923%이 가장 높은 적중률을 보이는 것으로 나타났다. 본 연구는 날씨와 운전습관 등 배터리 열화에 영향을 줄 수 있는 추가적인 변수들을 고려하지 못했다는 한계점이 있으나, 이는 향후 연구에서 다루고자 한다. 본 연구에서 제안하는 배터리 열화 예측 모델은 배터리 열화의 전조현상을 사전에 예측함으로써 배터리 관리를 효율적으로 수행하고 이에 따른 비용을 획기적으로 줄일 수 있을 것으로 기대한다.

• 한국조경학회지
• /
• 제42권3호
• /
• pp.1-12
• /
• 2014

도시의 공원녹지는 지역 주민들의 신체활동과 건강증진을 위해서 중요한 역할을 담당할 수 있기 때문에, 본 연구에서는 공원녹지의 다양한 특성과 신체활동 및 건강증진 목적의 공원녹지 이용의 상호관련성을 분석하고자 한다. 설문조사는 경상남도 창원시에 거주하는 541명의 주민들을 대상으로 공원녹지의 이용패턴과 주관적인 근린환경 인식을 파악하기 위해서 실시하였다. 사례지역에 대한 공원녹지의 접근성과 물리적 근린환경에 대한 공간정보를 구축하기 위해서 지리정보시스템(GIS)을 이용하였다. 다중회귀분석은 공원녹지의 특성과 신체활동 목적의 공원녹지 이용횟수, 자가인식 건강수준, 그리고 체질량지수(BMI)와의 상호관련성을 규명하기 위해 수행하였다. 거주지로부터 200m 이내에 분포하는 공원녹지의 출입구와 공원의 개수, 집 주변에서 운동하는 사람을 많이 볼 수 있거나, 저렴하게 이용할 수 있는 운동시설이 많다고 느낄수록 신체활동의 증가에 긍정적인 영향을 미치는 것으로 나타났다. 집 주변 공원녹지까지의 거리가 가깝고, 공원녹지의 개수가 많고, 면적이 넓을수록, 보행이 편리할수록, 공동주거지역의 비율이 높을수록 자가인식 건강수준(perceived health level)에 긍정적인 영향을 미치는 것으로 나타났다. 거주지로부터 400m 이내에 분포하는 공원녹지의 개수, 보행환경의 안전성, 공동주거지역의 비율, 도로비율, 교차로 밀도 등이 BMI와 상호관련성이 있는 것으로 나타났다. 독립변수인 공원녹지의 특성과 종속변수인 신체활동 목적의 공원녹지 이용횟수 및 자가인식 건강수준 사이의 다중회귀분석 결과, 유의수준 10% 이내에서 의미가 있는 회귀모형이 도출되었다. 본 연구는 공원녹지와 근린환경의 특성이 지역주민들의 신체활동과 건강에 미치는 영향을 규명함으로써, 향후 신체활동 목적의 공원녹지의 이용을 증진하고 비만을 감소시키기 위한 목적의 조경계획을 수립하는데 활용 가능할 것이다.

• 가정∙방문간호학회지
• /
• 제6권
• /
• pp.33-45
• /
• 1999

The purpose of this study was to develop a basic framework and criteria for evaluation of quality care provided to patients with the attributes of disease in the home care nursing field, and to provide measurement tools for home health care in the future. The study design was a developmental study for evaluation of hospital-based HCN(home care nursing) in Korea. The study process was as follows: a home care nursing study team of College of Nursing. Yonsei University reviewed the nursing records of 47 patients who were enrolled at Yonsei University Medical Center Home Care Center in March, 1995. Twenty-five patients were insured at that time, were selected from 47 patients receiving home care service for study feasibility with six disease groups; Caesarean Section (C/S), simple nephrectomy, Liver cirrhosis(LC), chronic obstructive pulmonary disease(COPD), Lung cancer or cerebrovascular accident(CVA). In this study, the following items were selected : First step : Preliminary study 1. Criteria and items were selected on the basis of related literature on each disease area. 2. Items were identified by home care nurses. 3. A physician in charge reviewed the criteria and content of selected items. 4. Items were revised through preliminary study offered to both HCN patients and discharged patients from the home care center. Second step : Pretest 1. To verify the content of the items, a pretest was conducted with 18 patients of which there were three patients in each of the six selected disease groups. Third step : Test of reliability and validity of tools 1. Using the collected data from 25 patients with either cis, Simple nephrectomy, LC, COPD, Lung cancer, or CVA. the final items were revised through a panel discussion among experts in medical care who were researchers, doctors, or nurses. 2. Reliability and validity of the completed tool were verified with both inpatients and HCN patients in each of field for researches. The study results are as follows: 1. Standard for discharge with HCN referral The referral standard for home care, which included criteria for discharge with HCN referral and criteria leaving the hospital were established. These were developed through content analysis from the results of an open-ended questionnaire to related doctors concerning characteristic for discharge with HCN referral for each of the disease groups. The final criteria was decided by discussion among the researchers. 2. Instrument for measurement of health statusPatient health status was measured pre and post home care by direct observation and interview with an open-ended questionnaire which consisted of 61 items based on Gorden's nursing diagnosis classification. These included seven items on health knowledge and health management, eight items on nutrition and metabolism, three items on elimination, five items on activity and exercise, seven items on perception and cognition, three items on sleep and rest, three items on self-perception, three items on role and interpersonal relations, five items on sexuality and reproduction, five items on coping and stress, four items on value and religion, three items on family. and three items on facilities and environment. 3. Instrument for measurement of self-care The instrument for self-care measurement was classified with scales according to the attributes of the disease. Each scale measured understanding level and practice level by a Yes or No scale. Understanding level was measured by interview but practice level was measured by both observation and interview. Items for self-care measurement included 14 for patients with a CVA, five for women who had a cis, ten for patients with lung cancer, 12 for patients with COPD, five for patients with a simple nephrectomy, and 11 for patients with LC. 4. Record for follow-up management This included (1) OPD visit sheet, (2) ER visit form, (3) complications problem form, (4) readmission sheet. and (5) visit note for others medical centers which included visit date, reason for visit, patient name, caregivers, sex, age, time and cost required for visit, and traffic expenses, that is, there were open-end items that investigated OPD visits, emergency room visits, the problem and solution of complications, readmissions and visits to other medical institution to measure health problems and expenditures during the follow up period. 5. Instrument to measure patients satisfaction The satisfaction measurement instrument by Reisseer(1975) was referred to for the development of a tool to measure patient home care satisfaction. The instrument was an open-ended questionnaire which consisted of 11 domains; treatment, nursing care, information, time consumption, accessibility, rapidity, treatment skill, service relevance, attitude, satisfaction factors, dissatisfaction factors, overall satisfaction about nursing care, and others. In conclusion, Five evaluation instruments were developed for home care nursing. These were (1)standard for discharge with HCN referral. (2)instrument for measurement of health status, (3)instrument for measurement of self-care. (4)record for follow-up management, and (5)instrument to measure patient satisfaction. Also, the five instruments can be used to evaluate the effectiveness of the service to assure quality. Further research is needed to increase the reliability and validity of instrument through a community-based HCN evaluation.

• 의료법학
• /
• 제18권2호
• /
• pp.163-194
• /
• 2017

관상동맥 질환은 2017년 고령사회로 진입한 우리나라에서 앞으로 더 많은 관심을 가질 것이다. 고령화가 될수록 고혈압, 당뇨 등 복합적인 질환이 합병되어 혈관상태도 상대적으로 더 나빠져 관상동맥 질환에 걸릴 가능성이 높기 때문이다. 심혈관 질병은 심장외과와 심장내과와의 긴밀한 협진이 필요하다. 따라서 협심증이나 심근경색증환자를 먼저 진료하게 되어 있는 우리나라의 임상현장에서 객관적인 심장내과 의사의 치료방침에 대한 판단은 매우 중요하다. 최근 심장내과의 비수술적 중재술이 발전하고 있지만 무리한 스텐트 시술로 의료사고도 발생하고 있다. 특히 관상동맥 3개혈관이 모두 막힌 삼중혈관이거나 석회화가 심해 혈관 상태가 좋지 않은 경우가 문제이다. 또한 심장외과 의사가 없는 병원에서 무리하게 경피적관상동맥중재술을 실시하다가 응급상황이 발생할 경우 관상동맥이식술 등 외과적 대처가 어려운 경우가 종종 발생한다. 최근 2년간 한국소비자원(소비자분쟁조정위원회) 의료분쟁 조정결정 8사례를 분석한 결과, 심장 중재술을 시행한 병원 중 심장외과 의사가 상주한 곳은 2곳으로 확인됐다. 8사례 모두 심장내과 진료 후 풍선확장술 및 스텐트 삽입한 경우로 7명이 사망했고 이중 5명은 시술 당일에 사망했다. 8사례 중에 3중혈관 환자는 5건이고, 나머지도 석회화가 심하거나 완전폐쇄로 혈관상태가 좋지 않은 상태였다. 2017년 심장내과 스텐트 시술 건수 조사 보고에 의하면 3개 이하 약물 방출 스텐트 시술이 98%로 보고됐다. 2015년 스텐트 시술 건수가 38,922건으로 약800건(2%)은 스텐트가 4개 이상 사용된 것으로 추정된다. 무리한 스텐트 시술로 마지막 여명에 급사함으로써 신변정리 기회상실은 물론 여명단축에 따른 손해로서 '지도 설명의무' 책임을 물어 전 손해에 대한 배상을 신중하게 고려할 필요가 있다. 최근 심평원 보험적용 스텐트 시술 개수 제한규제가 없어지면서 무리한 시술과 심장외과 의사 확충에 대한 문제가 있다. '다학제통합진료' 같은 병원차원의 해결방안은 물론 필수요원에 해당하는 심장외과를 공무원으로 확충하는 등 국가차원의 해결방안이 요구된다.

• Asia pacific journal of information systems
• /
• 제19권2호
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.