• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.139-152
• /
• 2022

Engineering's work area for plants is a technical area that directly affects productivity, performance, and quality throughout the lifecycle from planning, design, construction, operation and disposal. Using the different types of data that occur to make decisions is important not only in the subsequent process but also in terms of cyclical cost reduction. However, there is a lack of systems to manage and analyze these integrated data. In this paper, we developed a knowledge base-based plant engineering analysis platform that can manage and utilize data. The platform provides a knowledge base that preprocesses previously collected engineering data, and provides analysis and visualization to use it as reference data in AI models. Users can perform data analysis through the use of prior technology and accumulated knowledge through the platform and use visualization in decision-support and systematically manage construction that relied only on experience.

• Smart Structures and Systems
• /
• v.31 no.3
• /
• pp.247-257
• /
• 2023

In structural health monitoring of large-scale structures, optimal sensor placement plays an important role because of the high cost of sensors and their supporting instruments, as well as the burden of data transmission and storage. In this study, a vibration sensor placement algorithm based on deep reinforcement learning (DRL) is proposed, which can effectively solve non-convex, high-dimensional, and discrete combinatorial sensor placement optimization problems. An objective function is constructed to estimate the quality of a specific vibration sensor placement scheme according to the modal assurance criterion (MAC). Using this objective function, a DRL-based algorithm is presented to determine the optimal vibration sensor placement scheme. Subsequently, we transform the sensor optimal placement process into a Markov decision process and employ a DRL-based optimization algorithm to maximize the objective function for optimal sensor placement. To illustrate the applicability of the proposed method, two examples are presented: a 10-story braced frame and a sea-crossing bridge model. A comparison study is also performed with a genetic algorithm and particle swarm algorithm. The proposed DRL-based algorithm can effectively solve the discrete combinatorial optimization problem for vibration sensor placements and can produce superior performance compared with the other two existing methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.67-75
• /
• 2023

This paper deals with the operation of air taxis, which is one of the latest innovative technologies aimed at solving the issue of traffic congestion in cities. A key challenge for the successful introduction of the technology and efficient operation is a vertiport location problem. This paper employs a discrete choice model to calculate choice probabilities of transportation modes for each route, taking into account factors such as cost and travel time associated with different modes. Based on this probability, a mathematical formulation to maximize the utilization rate for air taxi is proposed. However, the proposed model is NP-hard, effective and efficient solution methodology is required. Compared to previous studies that simply proposed the optimization models, this study presents a solution methodology using the cross-entropy algorithm and confirms the effectiveness and efficiency of the algorith through numerical experiments. In addition to the academic excellence of the algorithm, it suggests that decision-making that considers actual data and air taxi utilization plans can increase the practial usability.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.57-66
• /
• 2023

Asset valuation of social infrastructure is essential for rational decision-making for efficient management of assets. In addition, it can be an indicator for correctly recognizing assets. In general, Korea applies depreciated replacement cost based on the straight-line method to evaluate asset value, yet this is unsuitable for evaluating actual value because it is depreciated at a constant rate over the useful life period. In order to evaluate the asset value considering the performance of the bridge, the performance index of the bridge is estimated using the Weibull distribution. Using the estimated performance indicators and defect index, a new asset value evaluation method is proposed and compared and analyzed with the existing method. The proposed valuation method can take into account the performance of the bridge, so it is judged to be more objective and reasonable than existing method.

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.561-566
• /
• 2011

In general, the early stage of urban renewal such as preparing a master plan and processing administrative works including planning permission are conducted by local governments in Korea. The local governments need to review the status of projects that are undergone in other local governments' territories. However, no integrated information system to manage information to this end at the level of nation exists in Korea. If the system would be developed, it may support central government to obtain information on required resources at the national level. In addition, local governments can gain guidance on the process and recognize potential problematic situations from others experience. The system should include functions to collect data on project summary, cost and schedule of projects according to local governments. The expected effects from using the information system are as following. First, information generated from project practice become more credible on account of management at the national level. Because the authorized party such as system administrative agents of governments are responsible for collecting and managing data. Second, the unified information system with no regard to the place where projects progresses reduces the efforts for accumulating reference data for aiding local governments decision making by providing appropriate information timely. Also, enhanced information accessibility for stakeholders make the project process clear. Finally, oversight management is enforced with visualization technology adopted in the system, presenting master plan and mass model including information on usage by floors and progressing information graphically. Ultimately, potential challenges can be anticipated by considering records accumulated from other local governments' projects. This paper presents concept, functionalities, and architecture of information system enabling to manage data from individual projects and aggregate those for oversight management for local and central governments. As a part of systems analysis, general requirements of briefing system for governments and necessary data fields to this end are identified.

• Asia pacific journal of information systems
• /
• v.30 no.2
• /
• pp.397-419
• /
• 2020

Business analytics is a management tool for achieving significant business performance improvements. Many organizations fail to or only partially achieve their business objectives and goals from business analytics. Business analytics adoption is a multi-stage complex activity consisting of evaluation, adoption, and assimilation stages. Several research papers have been published in the field of business analytics, but the research on multi-stage BA adoption is fewer in number. This study contributes to the scant literature on the multi-stage adoption model by identifying the critical themes for evaluation, adoption, and assimilation stages of business analytics. This study uses the thematic content analysis of peer-reviewed published academic papers as a research technique to explore the key themes of business analytics adoption. This study links the critical themes with the popular theoretical foundations: Resource-Based View (RBV), Dynamic Capabilities, Diffusion of Innovations, and Technology-Organizational-Environmental (TOE) framework. The study identifies twelve major factors categorized into three key themes: organizational characteristics, innovation characteristics, and environmental characteristics. The main organizational factors are top management support, organization data environment, centralized analytics structure, perceived cost, employee skills, and data-based decision making culture. The major innovation characteristics are perceived benefits, complexity, and compatibility, and information technology assets. The environmental factors influencing BA adoption stages are competition and industry pressure. A conceptual framework for the multi-stage BA adoption model is proposed in this study. The findings of this study can assist the practicing managers in developing a stage-wise operational strategy for business analytics adoption. Future research can also attempt to validate the conceptual model proposed in this study.

• Journal of Korean Society for Quality Management
• /
• v.52 no.1
• /
• pp.43-56
• /
• 2024

Purpose: The injection molding process, crucial for plastic shaping, encounters difficulties in sustaining product quality when replacing injection machines. Variations in machine types and outputs between different production lines or factories increase the risk of quality deterioration. In response, the study aims to develop a system that optimally adjusts conditions during the replacement of injection machines linked to molds. Methods: Utilizing a dataset of 12 injection process variables and 52 corresponding sensor variables, a predictive model is crafted using Decision Tree, Random Forest, and XGBoost. Model evaluation is conducted using an 80% training data and a 20% test data split. The dependent variable, classified into five characteristics based on temperature and pressure, guides the prediction model. Bayesian optimization, integrated into the selected model, determines optimal values for process variables during the replacement of injection machines. The iterative convergence of sensor prediction values to the optimum range is visually confirmed, aligning them with the target range. Experimental results validate the proposed approach. Results: Post-experiment analysis indicates the superiority of the XGBoost model across all five characteristics, achieving a combined high performance of 0.81 and a Mean Absolute Error (MAE) of 0.77. The study introduces a method for optimizing initial conditions in the injection process during machine replacement, utilizing Bayesian optimization. This streamlined approach reduces both time and costs, thereby enhancing process efficiency. Conclusion: This research contributes practical insights to the optimization literature, offering valuable guidance for industries seeking streamlined and cost-effective methods for machine replacement in injection molding.

• The Korean Journal of Financial Management
• /
• v.21 no.2
• /
• pp.99-123
• /
• 2004

We focus in this study on incremental financing decisions and estimate a logit model for the probability a firm will choose a private placement over a public bond issue. We hypothesize that information asymmetry, financial risk, agent cost, and proprietary information may affect a firm's choice between public debt and private placements. We find that as the size of firm increases, the probability of choosing a private placement declines significantly. The age of the firm, however, is not a significant factor affecting the firm's choice between public and privately-placed bond. The coefficients on the firm's leverage and non-investment grade dummy are significantly positive, meaning firms with high financial risk and credit risk select private placements. The findings regarding agency-related variables, PER and Tobin's Q, are somewhat complex. We find significant evidence that firms with high PER prefer private placements to public bonds, suggesting that borrowers with options to engage in asset substitution or underinvestment are more likely to choose private placements. The coefficient of Tobin's Q is negative, but not significant, which weakly support the hold-up hypothesis. When we construct an interaction term on the Tobin's Q with a non-investment rating dummy, however, the Tobin's Q interaction term becomes positive and significant. Thus, high Tobin's Q firms with a speculative rating are significantly more likely to choose a private placement, regardless of the potential hold-up problems. The ratio of R&D to sales, proxy for proprietary information, is positively significant. This result can be interpreted as evidence in favor of a role for proprietary information in the debt sourcing decision process for these firms.

• Korean Security Journal
• /
• no.50
• /
• pp.209-237
• /
• 2017

Theories on 'opportunity for crime' have utilized CCTV in crime prevention approach, and empirical studies showing crime prevention effects of CCTV have supported expansion of CCTV installation. Particularly, in Korea, the number of CCTV installation had tripled from 2011 to 2015, and governmental policies regarding CCTV have become one of the mainstream social control strategies. Although a couple of empirical studies showed decrease in crime rate due to CCTV installation, there is no study investigating B/C analysis(Benefit vs. cost analysis) of CCTV installation. B/C analysis results will be beneficial for official decision-making of criminal justice policy, and this study is purported to produce such fundamental evidence for policy making procedure. To fulfill this goal, this study collected data on financial information, crime data between 2011 and 2015 across the nation from 232 governmental district offices and the Korean National Police. This study then conducted two different B/C analyses(simple B/C analysis, regression-based B/C analysis). The simple B/C analysis results showed that 1) total costs for CCTV installation in 2014 was 68,626,000,000 won(approximately, US$57,188,333.00, money exchange rate 1200won=US$1), 2) benefits of crime reduction was 90,888,000,000 won(appx. US$75,740,000), and 3) B/C rate was 1.32. The regression-based B/C analysis results showed that 1) B/C rate was 1.52 when only reduced costs of criminal justice processes for crime employed, and 2) B/C rate was 3.62 when overall social costs including reduced costs of criminal justice processes and social benefits, e.g., reduction in costs for managing fear of crime, due to the crime reduction. Based on the results, this study provided policy implications.