• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.53-58
• /
• 2023

With the fast development of artificial intelligence day by day, users are demanding explanations about the results of algorithms and want to know what parameters influence the results. In this paper, we propose a model for bankruptcy prediction with interpretability using the SHAP framework. SHAP (SHAPley Additive exPlanations) is framework that gives a visualized result that can be used for explanation and interpretation of machine learning models. As a result, we can describe which features are important for the result of our deep learning model. SHAP framework Force plot result gives us top features which are mainly reflecting overall model score. Even though Fully Connected Neural Networks are a "black box" model, Shapley values help us to alleviate the "black box" problem. FCNNs perform well with complex dataset with more than 60 financial ratios. Combined with SHAP framework, we create an effective model with understandable interpretation. Bankruptcy is a rare event, then we avoid imbalanced dataset problem with the help of SMOTE. SMOTE is one of the oversampling technique that resulting synthetic samples are generated for the minority class. It uses K-nearest neighbors algorithm for line connecting method in order to producing examples. We expect our model results assist financial analysts who are interested in forecasting bankruptcy prediction of companies in detail.

• Korean Journal of Occupational Health Nursing
• /
• v.10 no.1
• /
• pp.24-40
• /
• 2001

This study is to observe the effectiveness of the applied model and to present the improvement plan and directions for development for the case management practical model suitable for the actual condition of Korea Labor Welfare Co. and needs of the industrial injury patients. The concrete purpose of this study is: First, observe the difference of stressor experience and experience degree between the experimental group and the comparative group. Second, observe the difference of stress of the experimental group and the comparative group. Third, find out how the stress affects the support degree and satisfaction degree. Fourth, present the improvement plan of case management model, which can promote the psychosocial rehabilitation of the industrial injury patient based on the research results. The outline of the main research results identified in this study is as follows. The stressors the industrial injury patients perceived are health problems, family matters, the problems concerning hospital recuperation (hospital staff and environmental problems), economical problems, problems of coming back to society, problems with companies, problems with Korea labour Welfare Co. and other problems. And the experience of stressor was prominently lower in experimental group than comparative group in the whole problem, health problem, problems with Korea Labour-Welfare Co. and other problems. The stressor experience degree was conspicuously lower in experimental group in the whole problem experience degree, health problem experience degree, problem with Korea Labour Co. experience degree and other problem experience degree. Besides whether or not the case management is applied is having a prominent affect on the primary factor affecting the stressor experience degree, therefore the patients applied with case management has less stressor than the patient who didn't. The difference of degree of tension experienced by the stressor in both groups, the degree of stress, was not conspicuous in statistics so it shows that the application of case management in this research has not affected the degree of tension. The field which had been the most help was emotional support in help level the experimental group perceived through applying case management about industrial accident patients and recuperation, compensation problem, medical treatment problem, family matters has been helpful in this order. The help level of the whole problem was in higher level than the middle value. The stress factor which affects the case management problem settlement is the whole body of stress. The satisfaction level of help through applying case management was highest in emotional support and family matters, recuperation problem, company problem, compensation problem, and medical treatment problem was the next highest. The satisfaction level of the whole problem was higher than the middle value. The stress factor affecting the satisfaction level of help is the whole body of stress. Therefore to reduce the stress level of industrial accident patients and for them to come back to local societies, we need to reinforce the continuance and responsibility of case management model, increase staff, reinforce the role of counsel and medical treatment, intervene in the patient's plan of leaving the hospital, develop social support system and the need to establish After Care Center.

• Journal of Digital Convergence
• /
• v.12 no.8
• /
• pp.449-458
• /
• 2014

The purpose of this study was to examine and analysis self-help group program performed in community-based home visiting health service. The data was collected public servants from the Home Visiting Health Care Service of 253 public health centers all over the country and was analyzed by SPSS/Win 17.0 program. 43.1% of self-help program was performed and 56.9% was not from year 2007 to 2010. As the years passed, the number of self-help group program was getting increased. The action for activating self-help programs was voluntary participation of clients, enthusiasm of management practitioner, and encouragement about self-help group. Self-help group programs based on public health center are insufficient. Self-help programs should be activated for clients of home visiting health care service. A systematic operating model of self-help group is also needed to develop and apply in consideration of these findings.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.51 no.3
• /
• pp.312-320
• /
• 2015

The 1/5 scale-down model of the Bycatch Reduction Device (BRD) from an Argentinean demersal trawl was tested in a circulating water channel. The BRD is designed to help small Hake (merluza, merluccius hubbsi) to escape from a trawl. It is settled in front of a trawl codend, and is equipped with selection grids that help small fish to escape from the gear and guiding panels that help fish to meet with the grids. Bars of the grids are wires covered by the PVC and other parts of the BRD are made of net. When the velocity was less than 0.65 m/sec (2.81 Kont when translated to real towing speed) which is slow speed compared with real towing speed, position between an upper guiding panel and an upper selection grid were good to help small fish to escape. When the velocity was more than 0.8 m/sec (3.41 Knot when translated to real towing speed) which is similar to and faster than real towing speed, it was considered that small fish may have difficulties in escaping because the gap was not enough between an upper guiding panel and an upper selection grid. The lower selection grid was sat on the bottom of the tank without an angle due to the weight that it carries. Improvements were proposed to position the panels and the grids better.

• Journal of Korean Academy of Nursing
• /
• v.34 no.6
• /
• pp.954-963
• /
• 2004

Purpose: This study was designed to identify the variables affecting male adolescents' sexual intercourse through a comprehensive analysis of individual and environmental factors. Method: The subjects of this descriptive survey on causal relations were 462 subjects enrolled in liberal and vocational high schools selected on a convenience sampling basis. The data collected from May-July 2002 was put to logistic regression analysis to build a forecast model. Findings: 1) Individual factors such as school record, experience seeking, non-inhibition and sexual permissiveness, 2) family factors such as parental living arrangement, 3) school factors such as career tract and 4) peer factors such as having a boy/girl friend were identified as significant variables forecasting sexual intercourse. Conclusion and Recommendation: The theoretical model built on the basis of the major findings of this study will hopefully help promote a wholesome youth culture related to sexual intercourse. It is recommended that a program be developed that can help control the variables identified in this study along with a follow-up study to verify the model.

• Journal of Korean Society for Quality Management
• /
• v.32 no.3
• /
• pp.198-215
• /
• 2004

Technology competitiveness evaluates environmental and engineered technology and process at both the scientific and market levels. There are increasing concerns to measure the effects of the technology variables on the potential market feasibility levels. However, there are very little empirical analysis studies on that issue. This study investigates the impacts of technology variables on the levels of market feasibility based on 230 data obtained from Korea Technology Transfer Center. As various statistical analysis, the canonical discriminant model, logit discriminant model and classification model were used and their results were compared. This study results showed that major technology variables had very significant relations to discriminate high and low categories of market feasibility. Finally, this study will help building management strategies to level up the potential market performance and also help financial Institutions to decide funds needed for small-sized technology firms.

• Structural Monitoring and Maintenance
• /
• v.7 no.1
• /
• pp.59-67
• /
• 2020

This study aims to develop the fuzzy risk assessment model of the debris flow to verify the accuracy of risk assessment in order to help related organizations reduce losses caused by landslides. In this study, actual cases of landslides that occurred are utilized as the database. The established models help us assess the occurrence of debris flows using computed indicators, and to verify the model errors. In addition, comparisons are made between the models to determine the best one to use in practical applications. The results prove that the risk assessment model systems are quite suitable for debris flow risk assessment. The reproduction consequences of highlight point discovery are shown in highlight guide coordinating toward discover steady and coordinating component focuses and effectively identified utilizing these two systems, by examining the variety in the distinguished highlights and the element coordinating.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.221-227
• /
• 2021

An early warning system was developed to help identify stock status as early as possible. For performance to improve, there needs to be a feature to predict the amount of stock that must be provided and a feature to estimate when to buy goods. This research was conducted to improve the inventory early warning system and optimize the Reminder Block's performance in minimum stock settings. The models used in this study are the single exponential smoothing (SES) method for prediction and the economic order quantity (EOQ) model for determining the quantity. The research was conducted by analyzing the Reminder Block in the early warning system, identifying data needs, and implementing the SES and EOQ mathematical models into the Reminder Block. This research proposes a new Reminder Block that has been added to the SES and EOQ models. It is hoped that this study will help in obtaining accurate information about the time and quantity of repurchases for efficient inventory management.

• Journal of the Korean Society of Systems Engineering
• /
• v.17 no.2
• /
• pp.91-97
• /
• 2021

User interface for cancer classification system is a software application with clinician's friendly tools and functions to diagnose cancer from pathology images. Pathology evolved from manual diagnosis to computer-aided diagnosis with the help of Artificial Intelligence tools and algorithms. In this paper, we explained each block of the project life cycle for the implementation of automated breast cancer classification software using AI and machine learning algorithms to classify normal and invasive breast histology images. The system was designed to help the pathologists in an automatic and efficient diagnosis of breast cancer. To design the classification model, Hematoxylin and Eosin (H&E) stained breast histology images were obtained from the ICIAR Breast Cancer challenge. These images are stain normalized to minimize the error that can occur during model training due to pathological stains. The normalized dataset was fed into the ResNet-34 for the classification of normal and invasive breast cancer images. ResNet-34 gave 94% accuracy, 93% F Score, 95% of model Recall, and 91% precision.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.744-747
• /
• 2005

The AEC (Architecture/Engineering/Construction) industry is facing a competitive world after it entered into the 21^st century. Due to improper planning and scheduling, the construction projects face severe delays in completion. Most of the present day construction organisations operate in multiple project environments where more than one projects are to be managed simultaneously. But the advantages of planning and scheduling as multiple projects have not been utilized by these organisations. Change in multi-project planning and scheduling is inevitable and often frequent, therefore the traditional planning and scheduling approaches are no more feasible in scheduling multiple construction projects. The traditional scheduling tools like CPM and PERT do not offer any help in scheduling in a resource-constrained environment. This necessitated a detailed study to model the environment realistically and to make the allocation of limited resources flexible and efficient. This paper delineates about the proactive model which will help the project managers for scheduling the multiple construction projects.