• Title/Summary/Keyword: Impact model

Search Result 8,260, Processing Time 0.032 seconds

Optimization of Uneven Margin SVM to Solve Class Imbalance in Bankruptcy Prediction (비대칭 마진 SVM 최적화 모델을 이용한 기업부실 예측모형의 범주 불균형 문제 해결)

  • Sung Yim Jo;Myoung Jong Kim
    • Information Systems Review
    • /
    • v.24 no.4
    • /
    • pp.23-40
    • /
    • 2022
  • Although Support Vector Machine(SVM) has been used in various fields such as bankruptcy prediction model, the hyperplane learned by SVM in class imbalance problem can be severely skewed toward minority class and has a negative impact on performance because the area of majority class is expanded while the area of minority class is invaded. This study proposed optimized uneven margin SVM(OPT-UMSVM) combining threshold moving or post scaling method with UMSVM to cope with the limitation of the traditional even margin SVM(EMSVM) in class imbalance problem. OPT-UMSVM readjusted the skewed hyperplane to the majority class and had better generation ability than EMSVM improving the sensitivity of minority class and calculating the optimized performance. To validate OPT-UMSVM, 10-fold cross validations were performed on five sub-datasets with different imbalance ratio values. Empirical results showed two main findings. First, UMSVM had a weak effect on improving the performance of EMSVM in balanced datasets, but it greatly outperformed EMSVM in severely imbalanced datasets. Second, compared to EMSVM and conventional UMSVM, OPT-UMSVM had better performance in both balanced and imbalanced datasets and showed a significant difference performance especially in severely imbalanced datasets.

Estimating the Impact of DMZ Punchbowl Trail as a National Forest Trail on Local Economy using the Regional Input-Output Model (지역산업연관모델을 이용한 국가숲길의 지역경제 파급효과 분석: DMZ펀치볼둘레길을 중심으로)

  • Sugwang Lee;Jae Dong Yang;Jeonghee Lee
    • Journal of Korean Society of Forest Science
    • /
    • v.113 no.2
    • /
    • pp.170-186
    • /
    • 2024
  • This study was conducted to identify the usage characteristics of the DMZ Punchbowl Trail (DPT) as a national forest trail (NFT) and to estimate its ripple effects on the local economy. The objective of this study is to provide policy implications for sustainable operational management. Out of the 500 questionnaires distributed, 215 respondents provided their complete travel itineraries and expenditures. The respondents, mainly aged 50 and above and residing in the Seoul Metropolitan Area, spend 3.5 hours of travel time to the DPT. Together with their families, the respondents typically spend approximately 4 hours for leisurely activities, primarily appreciation of scenic views and relaxation by visiting the "O-yubatgil." Furthermore, they extend their travels to other parts of Gangwon Province, where the DPT is situated. Within Gangwon Province, Yanggu County is the most visited destination. The respondents reported a notably higher average expenditure per visitor compared with the typical local walking tourists. Estimates show that the DPT generates an annual average of KRW 2.1 billion in direct expenditure (based on an average of 10,000 visitors for over five years), KRW 2.8 billion in production, and KRW 1.3 billion in added value, and it has created 40 jobs in Gangwon Province. The results of this study lies in empirically determining the specific economic scale and ripple effects of DPT as an NFT in the major sector, which occupies a significant portion of the Gangwon Province's local economy. The results will be instrumental in validating NFT policies and informing policy making for sustainable forest utilization.

A Case Study of Middle School Students' Abductive Inference during a Geological Field Excursion (야외 지질 학습에서 나타난 중학생들의 귀추적 추론 사례 연구)

  • Maeng, Seung-Ho;Park, Myeong-Sook;Lee, Jeong-A;Kim, Chan-Jong
    • Journal of The Korean Association For Science Education
    • /
    • v.27 no.9
    • /
    • pp.818-831
    • /
    • 2007
  • Recognizing the importance of abductive inquiry in Earth science, some theoretical approaches that deploy abduction have been researched. And, it is necessary that the abductive inquiry in a geological field excursion as a vivid locale of Earth science inquiry should be researched. We developed a geological field trip based on the abductive learning model, and investigated students' abductive inference, thinking strategies used in those inferences, and the impact of a teacher's pedagogical intervention on students' abductive inference. Results showed that students, during the field excursion, could accomplish abductive inference about rock identification, process of different rock generation, joints generation in metamorpa?ic rocks, and terrains at the field trip area. They also used various thinking strategies in finding appropriate rules to construe the facts observed at outcrops. This means that it is significant for the enhancement of abductive reasoning skills that students experience such inquiries as scientists do. In addition, a teacher's pedagogical interventions didn't ensure the content of students' inference while they helped students perform abductive reasoning and guided their use of specific thinking strategies. Students had found reasoning rules to explain the 01: served facts from their wrong prior knowledge. Therefore, during a geological field excursion, teachers need to provide students with proper background knowledge and information in order that students can reason rues for persuasive abductive inference, and construe the geological features of the field trip area by the establishment of appropriate hypotheses.

Research on Characterizing Urban Color Analysis based on Tourists-Shared Photos and Machine Learning - Focused on Dali City, China - (관광객 공유한 사진 및 머신 러닝을 활용한 도시 색채 특성 분석 연구 - 중국 대리시를 대상으로 -)

  • Yin, Xiaoyan;Jung, Taeyeol
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.52 no.2
    • /
    • pp.39-50
    • /
    • 2024
  • Color is an essential visual element that has a significant impact on the formation of a city's image and people's perceptions. Quantitative analysis of color in urban environments is a complex process that has been difficult to implement in the past. However, with recent rapid advances in Machine Learning, it has become possible to analyze city colors using photos shared by tourists. This study selected Dali City, a popular tourist destination in China, as a case study. Photos of Dali City shared by tourists were collected, and a method to measure large-scale city colors was explored by combining machine learning techniques. Specifically, the DeepLabv3+ model was first applied to perform a semantic segmentation of tourist sharing photos based on the ADE20k dataset, thereby separating artificial elements in the photos. Next, the K-means clustering algorithm was used to extract colors from the artificial elements in Dali City, and an adjacency matrix was constructed to analyze the correlations between the dominant colors. The research results indicate that the main color of the artificial elements in Dali City has the highest percentage of orange-grey. Furthermore, gray tones are often used in combination with other colors. The results indicated that local ethnic and Buddhist cultures influence the color characteristics of artificial elements in Dali City. This research provides a new method of color analysis, and the results not only help Dali City to shape an urban color image that meets the expectations of tourists but also provide reference materials for future urban color planning in Dali City.

Assessment of the Non-point Source Pollution Control Strategies for Water Quality Improvement in the Haeban Stream of West Nakdong River Watershed (서낙동강 유역 해반천의 수질 개선을 위한 비점오염관리대책 효과 분석)

  • Yejin Kim
    • Journal of Wetlands Research
    • /
    • v.26 no.1
    • /
    • pp.1-9
    • /
    • 2024
  • In this study, a HSPF model was developed to simulate runoff and water quality in the Haebancheon watershed, which has a high land area ratio and population density among the West Nakdong River watersheds. Various non-point source pollution control strategies were applied, and the reduction in pollutant loads and the exceedance rate of water quality standards were analyzed. The scenarios included basic road cleaning for reducing pollutant loads, runoff reduction measures considering extensive low-impact development techniques, and inflow reduction measures to mitigate non-point source pollution entering the river. In the first step, practical conditions such as the number of vehicles for road cleaning in Kimhae City were considered, while for the second and third steps, it was assumed that 50% of the applicable land use area was used to be applicable for the LID techniques. As a result of applying all three measures, it was analyzed that the BOD pollutant load could be reduced by 58.28%, T-N by 58.49%, and T-P by 51.56%. Furthermore, the 60th percentile of water quality measurements accumulated over 5 years was set as the target water quality, and a flow-duration curve was constructed. The exceedance rate of the flow-duration curve before and after applying non-point source pollution reduction measures was analyzed. As a result, for BOD, the exceedance rate decreased from 41.57% before applying the measures to 16.32% after, showing a 25.25% reduction in the exceedance rate. For T-N, the exceedance rate decreased significantly from 40.31% before the measures to 22.84% after, and for T-P, it decreased significantly from 62.43% to 27.22%.

A Study on the Effect of Public Libraries' ESG Management on Its Perception, User Satisfaction, and the User's Intention to Revisit (공공도서관의 ESG경영이 도서관 인식, 이용자 만족도 및 재이용 의도에 미치는 영향)

  • Mi Ok Jeong
    • Journal of the Korean Society for Library and Information Science
    • /
    • v.58 no.1
    • /
    • pp.303-328
    • /
    • 2024
  • In this study, we designed and verified a research model in order to determine whether ESG management for public libraries affects the perception of libraries, user satisfaction, and the intention to revisit. A survey was conducted among the users of six public libraries in the Gyeonggi region and 25 libraries in Seoul, and 247 valid responses from the survey were analyzed. The analysis revealed that the environment and society factors of ESG management had a positive effect on the perception of libraries and user satisfaction. It also showed that the libraries' perception had a positive impact on user satisfaction and the intention to revisit, and user satisfaction showed a positive correlation for the intention to revisit. From the analysis, we can infer that the effects of ESG management were reflected in everyday life via public libraries as ESG management of the public libraries influenced the perception of libraries, user satisfaction, and the intention to revisit. We confirmed that users showed the intention to revisit if the library provides positive and sincere satisfaction through ESG management, due to public libraries having ethical and moral significance to users. We have also put forward practical marketing strategies and identified areas for enhancement that can prove beneficial to public libraries.

The Relationship Between Entrepreneurial Competency and Entrepreneurial Intention of SME Workers: Focusing on the Mediating Effect of Start-Up Efficacy and Start-Up Mentor (중소기업 종사자의 창업역량과 창업의도 간의 영향 관계: 창업효능감과 창업멘토링의 매개효과 중심으로)

  • Oun Ju Lee
    • Asia-Pacific Journal of Business Venturing and Entrepreneurship
    • /
    • v.18 no.6
    • /
    • pp.201-214
    • /
    • 2023
  • This study attempted to analyze the impact of individual entrepreneurial capabilities on entrepreneurial intention targeting small and medium-sized business employees, and sought to confirm the mediating effect of entrepreneurial efficacy and entrepreneurial mentoring between entrepreneurial capabilities and entrepreneurial intention. The sub-variables of entrepreneurship competency were analyzed separately into creativity, problem solving, communication, and marketing. 368 questionnaires collected from employees at small and medium-sized manufacturing companies located across the country were used for empirical analysis. A parallel dual mediation model with no causal relationship between parameters was used for empirical analysis using SPSS v26.0 and PROCESS macro v4.2. As a result of the analysis, first, among the start-up competencies, creativity, communication, and marketing were confirmed to have a significant positive (+) effect on start-up efficacy. Second, among the start-up competencies, creativity, communication, and marketing were tested to have a significant positive influence on start-up mentoring. Third, both startup efficacy and startup mentoring were found to have a significant positive influence on startup intention. Fourth, among start-up capabilities, creativity and marketing were confirmed to have a significant positive (+) effect on start-up intention. Fifth, startup efficacy and startup mentoring were found to have a mediating effect on startup intention except for problem solving among startup competencies. As a result, it was confirmed that in order to strengthen the intention to start a business among small and medium-sized business employees, start-up efficacy and start-up mentoring are important factors, and that marketing and creativity have an important influence among individual start-up capabilities, so education and prior preparation for these are necessary. As follow-up research, it will be necessary to apply multivariate models, analyze time series data, research considering external environmental factors, and test the difference between start-up capabilities and performance considering detailed population characteristics.

  • PDF

Effectiveness of a Clinical Pathway for Breast Cancer Patients Undergoing Surgical Operation on Clinical Outcomes and Costs

  • Jeong Hyun Park;Danbee Kang;Seok Jin Nam;Jeong Eon Lee;Seok Won Kim;Jonghan Yu;Byung Joo Chae;Se Kyung Lee;Jai Min Ryu;Yeon Hee Park;Mangyeong Lee;Juhee Cho
    • Quality Improvement in Health Care
    • /
    • v.30 no.1
    • /
    • pp.120-131
    • /
    • 2024
  • Purpose: This study aimed to evaluate the impact of implementing a clinical pathways (CPs) on the clinical outcomes and costs of patients undergoing breast cancer surgery. Methods: This retrospective cohort study included patients who were newly diagnosed with primary breast cancer at the Samsung Medical Center between 2014 and 2019 (N=8482; 2931 patients in the pre-path and 5551 patients in the post-path). Clinical outcomes included reoperation during hospitalization, readmission, and emergency room visits within 30 days of discharge. The cost data for each unit were obtained from an activity-based management accounting system. We performed an interrupted time series analysis. Results: The post-path period showed a significantly shorter hospital length of stay (LOS) than the pre-path period (6.3 days in pre-path vs. 5.0 days in post-path; -1.3 days' difference; p=.001), and fewer reoperations during hospitalization and within 30 days after discharge than the pre-path period. After adjusting for inflation rates and relative value scores, the model demonstrated savings of $146 per patient in the post-path for total costs, and $537 per patient for patient out-of-pocket costs (p=.001). Conclusion: CPs can help reduce costs without compromising the quality of care by reducing the number of reoperations, readmissions, and complications.

Perception Survey for Demonstration Service using Drones (드론을 활용한 실증 서비스에 대한 인식 조사)

  • Jina Ok;Soonduck Yoo;Hyojin Jung
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.24 no.1
    • /
    • pp.125-132
    • /
    • 2024
  • The purpose of this study is to discover a drone utilization model tailored to local characteristics, propose directions for building a drone demonstration city based on demand surveys for drone activation, and suggest ways to utilize and support a drone application system. First, according to the survey results, there was a high understanding of and necessity for drone demonstration projects, particularly in addressing urban issues, which were deemed to have a significant impact. Second, based on the analysis of priorities and short- and long-term approaches, disaster-related tasks were evaluated as a priority, requiring an approach through medium- to long-term strategies. Third, it was noted that budgetary considerations emerged as the most critical issue during project implementation. Practitioners and experts expressed willingness to actively introduce drone-based technologies into their work when budget and technology were ready. Budgetary constraints were identified as the most significant obstacle to proper implementation, emphasizing the need for resolution. Fourth, the necessity of demand surveys during project development was identified in certain areas. Demand surveys were deemed essential for drone-based demonstration city construction, and a survey indicated that public leadership in this regard was also necessary. Fifth, concerning approaches in specific areas, the field of safety and disaster management was highlighted as the most crucial for application.

Analysis of Flow Velocity in the Channel according to the Type of Revetments Blocks Using 3D Numerical Model (3차원 수치모델을 활용한 호안 블록 형상에 따른 하도 내 유속 분석)

  • Dong Hyun Kim;Su-Hyun Yang;Sung Sik Joo;Seung Oh Lee
    • Journal of Korean Society of Disaster and Security
    • /
    • v.16 no.4
    • /
    • pp.9-18
    • /
    • 2023
  • Climate change affects the safety of river revetments, especially those associated with external flooding. Research on slope reinforcement has been actively conducted to enhance revetment safety. Recently, technologies for producing embankment blocks using recycled materials have been developed. However, it is essential to analyze the impact of block shapes on the flow characteristics of exclusion zones for revetment safety. Therefore, this study investigates the influence of revetment block shapes on the hydraulic characteristics of revetment surfaces through 3D numerical simulations. Three block shapes were proposed, and numerical analyses were performed by installing the blocks in an idealized river channel. FLOW-3D was used for the 3D numerical simulations, and the variations in maximum flow velocity, bed velocity beneath the revetment, and maximum shear stress were analyzed based on the shapes of the revetment blocks. The results indicate that for irregularly sized and spaced revetment blocks, such as the natural stone-type vegetation block (Block A), when connected to the revetment in an irregular manner, the changes in flow velocity in the revetment installation zone are more significant than those for Blocks B and C. It is anticipated that considering the topographical characteristics of rivers in the future will enable the design of revetment blocks with practical applicability in the field.