• Title/Summary/Keyword: 독립모형

Search Result 1,017, Processing Time 0.029 seconds

Development of fecal coliform prediction model using random forest method (랜덤포레스트기법을 이용한 분변성대장균 예측모델 개발)

  • Seo, Il Won;Choi, Soo Yeon
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2016.05a
    • /
    • pp.124-124
    • /
    • 2016
  • 하천에서의 분변성대장균은 분변성 오염 정도를 나타내는 지표로서, 이 농도가 높을수록 오염된 하천수와의 접촉을 통한 호흡기, 소화기 및 피부 관련 질병의 발발 확률이 높다고 알려져 있다. 따라서 하천에서의 수영, 수상스키 등과 같은 입수형 친수활동을 할 때, 분변성대장균 농도가 농도 기준 이하인지를 확인하고 이러한 정보를 친수활동에 이용할 필요가 있다. 그러나 분변성대장균의 경우, 현재 자동수질측정망에서 측정되고 있는 다른 수질인자들과는 달리 실시간 측정이 불가능하다고 알려져 있다. 분변성대장균을 측정하는데 있어 최소 18시간 이상이 필요하며, 이러한 분변성대장균 측정 방식은 하천 이용자들이 안전한 친수활동을 영위하는데 있어 적절한 수질 정보를 제공하지 못한다. 그러므로 분변성대장균을 예측하는 모델을 개발하고, 이를 이용하여 실시간 분변성대장균 정보를 생성하여 하천 이용자들에게 제공할 필요가 있다. 본 연구에서는 친수활동이 활발하게 이루어지는 곳 중 하나인 북한강의 대성리 지점에 대해 데이터 기반 모델을 이용하여 분변성대장균을 예측하였다. 데이터 기반 모델은 물리 기반 모델에서 필요한 지형데이터나 비점오염원 등의 초기 오염물의 양에 대한 데이터를 필요로 하지 않고, 대신 독립변수로 사용되는 기상 및 수질데이터를 필요로 한다. 이러한 기상 및 수질데이터는 기존 기상관측소, 수질관측소에서 매일 자동으로 측정되기 때문에 데이터 기반 모델은 물리 기반 모델에 비해 입력데이터를 구성하기가 쉽다는 장점을 지닌다. 이러한 데이터 기반 모델 중 분류 모델은 회귀 모델과 달리 분변성대장균 농도가 일정 수질기준 이상을 넘는지를 바로 예측할 수 있다. 본 연구에서는 분류 모델 중 높은 예측력을 가진다고 알려진 랜덤포레스트(random forest) 기법을 이용하여 분변성대장균 예측 모델을 개발하였다. 분변성대장균 예측 모델은 주어진 기상 및 수질 조건에 대해 분변성대장균이 200 CFU/100ml가 넘는지를 예측하였다. 예측된 분변성대장균이 기준을 넘는 경우를 2등급, 넘지 않는 경우를 1등급으로 명명하였다. 모델을 개발하기 위하여 북한강 대성리 인근 측정소에서 2010년부터 2015년까지 측정된 기상 및 수질데이터를 수집하였다. 수집한 데이터를 훈련 및 검증데이터로 샘플링하였으며, 이 때 샘플링한 데이터가 기존 데이터가 가지고 있던 등급별 비율을 유지하기 위하여 층화샘플링을 하였다. 본 연구에서는 샘플링에 의한 불확실성을 줄이기 위하여 랜덤하게 50번 샘플링된 각각의 훈련데이터에 대해 모델을 개발하였다. 50개의 모델의 검증 결과를 종합한 결과, 전체 예측률은 0.139로 나타났다.

  • PDF

The Effect of Entrepreneurship, Perception of Entrepreneurial Environment and Participation in Government Start-up Support Project on Business Performance (창업자들의 기업가정신과 창업환경인식, 그리고 정부의 창업지원사업 참여정도가 경영성과에 미치는 영향)

  • Jang, Young-Hye;Jang, In Sung;Kim, Pansoo
    • Asia-Pacific Journal of Business Venturing and Entrepreneurship
    • /
    • v.14 no.5
    • /
    • pp.115-125
    • /
    • 2019
  • This study examined the effects of entrepreneurship and perception of entrepreneurial environment on business performance. In particular, this study analyzed the difference in the effect of each independent variable on the dependent variable by using the government's participation in the start-up support project as a moderate variable. In order to achieve the purpose of this study, the researcher drew the variables corresponding to entrepreneurship and the variables related to entrepreneurship awareness. Innovativeness and risk sensitivity were selected as variables for entrepreneurship, and market environment and product environment were selected as variables for perception of entrepreneurial environment. Based on the above variables the research model was completed including the degree of participation in the government's start-up support project as a moderating variable. The data for the empirical analysis were collected from start-up companies in Daegu in 2018. A total of 601 questionnaires were collected and 399 copies of the data were used in this study after removing the unfaithful answers. The results of the analysis showed that innovation had a negative effect on management performance, and risk sensitivity, market environment, and product environment had a positive effect on management performance. In terms of the moderating effect, in the case of innovation, the higher the participation in government support projects, the lesser the negative effect. Risk sensitivity and product environment showed a strong impact on companies with a lot of government support projects, and the market environment had a strong impact on those who participated less. This study confirmed the importance and necessity of entrepreneurship and perception of entrepreneurial environment that influence the management performance of entrepreneurs. It is also meaningful in that it deals with the practical effects of the government's start-up support project on the start-up performance.

The Effects of Female Labor Force Participation, Family Policies, and Gender Equality on Fertility Rate : Focused on OECD Countries (여성의 경제활동참가율이 출산율에 미치는 영향 : OECD 국가를 대상으로)

  • Hong, Sung-Hee
    • Journal of Family Resource Management and Policy Review
    • /
    • v.25 no.2
    • /
    • pp.41-52
    • /
    • 2021
  • The purpose of this study is to examine how female labor force participation, family policies, and gender equality are related to fertility rate across countries. Multiple measures has been collected from various data sources(such as OECD, UNDP, and WVS) and the panel data set which includes (mostly) OECD countries range from 1990 to 2019 are analyzed. The major findings are as follows. First, based on OECD countries samples, female labor force participation is positively associated with the fertility rate, which implies that women's labor force participation does not lead to a reduction in fertility rate. Second, the length of paternity leave is positively associated with fertility rate whereas the direction is the opposite for the relationship between the length of maternity leave and fertility rate. This is attributed to the possibility that a longer period of maternity leave incurs the a higher opportunity cost of earning income, which leads to a reduced fertility rate. Third, countries with higher gender inequality index tend to have a higher fertility rate. Similarly, countries with higher gender equality value have a lower fertility rate. When the gender equality value is devideed into three sub-categories, education, politics, and employment, the gender equality value in education is the only sub-category which is negatively associated with the fertility rate. This study confirms that female labor force participation may not be a contributing factor in the lowering of fertility rate but instead can be positively associated with the fertility rate. Also, the results show that family policies or gender equality values can be significantly affect fertility rate.

A Research on the Paradigm of Interaction Based on Attributes (인터렉션 속성에 기초한 인터렉션 범식화 연구)

  • Shan, Shu Ya;Pan, Young Hwan
    • Journal of the Korea Convergence Society
    • /
    • v.12 no.5
    • /
    • pp.127-138
    • /
    • 2021
  • The aim of this study is to demonstrate interaction as a describable field and tries to understand interaction from the perspective of attributes, thus building a theoretical to help interactive designer understand this field by common rule, rather than waste huge time and labor cost on iteration. Since the concept of interaction language has been brought out in 2000, there are varies of related academical studies, but all with defect such as proposed theoretical models are built on a non-uniform scale, or the analyzing perspective are mainly based on researcher's personal experience and being too unobjective. The value of this study is the clustered resource of research which mainly based on academical review. It collected 21 papers researched on interaction paradigm or interaction attributes published since 2000, extracting 19 interaction attribute models which contains 174 interaction attributes. Furthermore, these 174 attributes were re-clustered based on a more unified standard scale, and the two theoretical models summarized from it are respectively focuses on interaction control and interaction experience, both of which covered 6 independent attributes. The propose of this theoretical models and the analyzation of the cluster static will contribute on further revealing of the importance of interaction attribute, or the attention interaction attribute has been paid on. Also, in this regard, the interactive designer could reasonably allocate their energy during design process, and the future potential on various direction of interaction design could be discussed.

A Study on the Determinants of Management Performance of Nonprofit Arts Organization: Focusing on Symphony Orchestras in USA (비영리 공연단체의 경영성과 결정요인에 관한 연구 - 미국오케스트라를 중심으로 -)

  • Park, Sunmi;Choi, Young-jun
    • International Area Studies Review
    • /
    • v.22 no.2
    • /
    • pp.121-138
    • /
    • 2018
  • This study aims to suggest effective management performances of nonprofit arts organizations among competitive environment. To examine the factors which affect the performance of nonprofit performing arts organizations such as external environment, cultural capital, orchestra characters and government grants, this study analyzed the data of 990 tax forms of the US Internal Revenue Service(IRS) of the top 73 symphony orchestras and government sources in USA. Independent variables are measured as sponsorship amount which is the biggest part of orchestras' income, and ticket sales which is profit of inherent business purpose. As a result, the performance of the orchestra is affected positively by the income and influenced by the orchestras' characteristics including age, size, and conductor. Also government grants to the orchestras are essential for organizations to sustain their business. But, there are two different sides on these effects that small to medium groups are influenced by crowding in effect and bigger groups are more likely conducted by business overview. Lastly, cultural capital is no significant relationships to orchestras' management performances. This scope of the study is limited to American symphony orchestras; however, this study is significant in that empirical analysis on nonprofit performing arts organizations from an economic view point and contribute on other nonprofit arts organizations to develop their strategic plan for sustainable business.

A Study on The Effect of Justice of Transaction on Customer Performance in manufacturing Outsourcing. ; The Mediation Effect of Partnership (제조 아웃소싱에서 거래공정성이 고객사의 경영성과에 미치는 영향에 관한 연구 ; 파트너십의 매개효과)

  • Park, Sang-Moon;Kim, Gi-Joong;Hyun, Byung-Hwan
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.20 no.6
    • /
    • pp.228-238
    • /
    • 2019
  • The purpose of this study is to investigate the relationship between transaction justice and customer performance. In this study, data were gathered from questionnaires from customers and suppliers of manufacturing outsourcing service, and reliability, validity, and confirmatory factor analysis (CFA) were conducted and the hypothesis was verified through the structural equation modeling (SEM) analysis. The results of this study are as follows: 1)Transaction justice has a significant positive effect on customer's business performance. Distribution and Interactional justice have a small effect on business performance, but Procedural justice has a significant positive effect. 2)Transaction justice has a positive effect on partnerships. 3)The partnership between the customer and the supplier has a positive effect on the customer's business performance. 4)Partnership has positive effect on customer's management performance through mediating justice. This study is based on the fact that justice acts as a independent variable in the transactional relationship between the customer and the supplier in the manufacturing outsourcing and this is the first case that empirically investigated the effect of the justice on the customer's management performance. In order to effectively cope with a rapidly changing business environment and effectively improve management performance, it is necessary to make efforts to improve justice, especially procedural justice, by utilizing outsourcing effectively in a global competition. In this respect, this study provides important implications for the both academically and practically.

An Analysis of the Effects of Customer Characteristics on Sales of Alley Market Area Using Geographically Weighted Regression (지리가중회귀분석을 이용한 고객특성별 골목상권 매출액 영향 연구)

  • Kang, Hyun Mo;Lee, Sang-Kyeong
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.36 no.6
    • /
    • pp.611-620
    • /
    • 2018
  • With the revitalization of alley market area becoming a major goal of the urban regeneration project, an understanding on customer characteristics that affect the sales of alley market areas is needed. As spatial heterogeneity appears to exist in alley market areas, the use of GWR (Geographically Weighted Regression) is required as an alternative to OLS (Ordinary Least Squares) regression. This study analyzes effects of customer characteristics on sales of 1007 alley market areas in Seoul. Comparing R squared and AICc, results show that GWR is better than OLS regression. According to OLS regression, the ratio of female, the ratio of 40's and 50's, the number of employees, the opening rate of establishment, the density of building and the size of alley market area have positive effects on sales, while the ratio of 20's and 30's, the distance of bus stop and that of subway station have negative effects. As a result of comparing local regression coefficients of geographically weighted regression analysis, the ratio of female customers has the greatest effect on the northwestern region, followed by the southwestern region, the central region and the northeastern region. The ratio of 20's and 30's and that of 40's and 50's effect on the southeastern and northeastern regions, and then the southwestern region. It is expected that this study will help to identify marketing target for each alley market area.

Numerical Simulation of the Flood Event Induced Temporally and Spatially Concentrated Rainfall - On August 17, 2017, the Flood Event of Cheonggyecheon (시공간적으로 편중된 강우에 의한 홍수사상 수치모의 - 2017년 8월 17일 청계천 홍수사상을 대상으로)

  • Ahn, Jeonghwan;Jeong, Changsam
    • Journal of Korean Society of Disaster and Security
    • /
    • v.11 no.2
    • /
    • pp.45-52
    • /
    • 2018
  • This study identifies the cause of the accident and presents a new concept for safe urban stream management by numerical simulating the flood event of Cheonggyecheon on August 17, 2017, using rain data measured through a dense weather observation network. In order to simulate water retention in the CSO channel listed as one of the causes of the accident, a reliable urban runoff model(XP-SWMM) was used which can simulate various channel conditions. Rainfall data measured through SK Techx using SK Telecom's cell phone station was used as rain data to simulate the event. The results of numerical simulations show that rainfall measured through AWSs of Korea Meteorological Administration did not cause an accident, but a similar accident occurred under conditions of rainfall measured in SK Techx, which could be estimated more similar to actual phenomena due to high spatial density. This means that the low spatial density rainfall data of AWSs cannot predict the actual phenomenon occurring in Cheonggyecheon and safe river management needs high spatial density weather stations. Also, the results of numerical simulation show that the residual water in the CSO channel directly contributed to the accident.

The Effect of the Entrepreneurial Motivation in Women Entrepreneurs on Entrepreneurial Satisfaction Mediated by Entrepreneurial Orientation and Commitment to Start-up (여성창업자의 창업동기가 기업가지향성과 창업의지를 매개로 창업만족도에 미치는 영향)

  • Lee, Sun Hyup;An, Eun Jae
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.23 no.6
    • /
    • pp.95-112
    • /
    • 2018
  • This study aims to examine their influential relations between the start-up motivation and entrepreneurial satisfaction of women entrepreneurs mediated by entrepreneurial orientation and commitment to start-up. An empirical analysis of the 386 questionnaires collected by the cosmetics store entrepreneurs located in Seoul and Gyeonggi provinces were conducted in this study. Mediator effect use the comparison by correspondence with total effect, direct effect, indirect effect inclusive of characteristic indirect effect. To achieve the research goal, this study were analyzed on the cornerstone of combination of parallel serial mediation models with entrepreneurial orientation and commitment to start-up as mediator variable. The following is the results verified through this study. First, Rewards motivation had the significant positive effects on the entrepreneurial satisfaction in total effects of X on Y and direct effects of X on Y. Second, Achievement motivation had the positive effects on entrepreneurial satisfaction in characteristic indirect effects of X on Y. Third, Environment motivation had the significant positive effects on the entrepreneurial satisfaction in total effects of X on Y and direct effects of X on Y. Fourth, The entrepreneurial orientation and the commitment to start-up between the start-up motivation and entrepreneurial satisfaction in women entrepreneurs had the serial mediation effects. I discussed theoretical and empirical implications with these findings and described the future research.

A Study on the Acceptance Factors of the Introduction of a Smart IoT Technology for Well-being Companion Animal (반려동물 웰빙을 위한 스마트 IoT 기술 도입 수용요인에 관한 연구)

  • Kang, Sung Kwang;Kim, Hoontae;Ji, Yong Gu;Lee, Jeongyoung
    • The Journal of Society for e-Business Studies
    • /
    • v.24 no.2
    • /
    • pp.143-163
    • /
    • 2019
  • The purpose of this study is to identify acceptance factors and influencing factors of respondents' adoption of smart IoT technology to companion animal health based on the integrated technology acceptance model. Based on the previous studies, we constructed the hypotheses by defining the technical factors, social factors, control variables, and mediating variables (UTAUT), and set the hypotheses between the independent variables of each factor and the dependent intention. A research model was designed to verify the relationship between variables. We developed questionnaires on the items and verified them through data collected from 494 people. As a result, product design, quality of service, product performance, and quality service of technological factors had a significant effects on performance expectancy and effort expectancy. However, product safety, product function awareness, and product price did not significantly affect performance expectancy and effort expectancy. Social influence had significant effects on cognitive effect, welfare system, and welfare facilities. In conclusion, the comparative analysis of technical factors and social factors showed that social factors have more significant effects on welfare systems and facilities.