• Korean small business review
• /
• v.41 no.1
• /
• pp.29-51
• /
• 2019

This study investigates how SMEs' (small and medium-sized enterprises) financing strategies affect firm valuation. Given that information asymmetry is engaged in firm valuation in the stock market, investors interpret the meanings of debt financing depending on how SMEs construct the portfolio of financing strategies (retained earnings vs debt financing), thereby making investment decision. Specifically, given that SMEs' debt financing has two meanings in the market signals, called "benefit" and "cost", this study postulates that firm valuation will be differently made by investors, depending on how they interpret the meanings of debt financing under choice competition between retained earnings and debt financing. In this study, we argue that under choice competition, as a SME's debt proportion increases, the "cost" signal outweighes the "benefit" signal, thereby decreasing firm valuation. Moreover, the effect of such signal can be contingent on the SME's characteristics-firm visibility. These ideas are examined using 363 U.S. SMEs ranging from 1971 to 2010. The fixed-effects models estimating Tobin's q show that under choice competition, a SME's debt proportion has a negative impact on firm valuation and that the firm's high visibility mitigates the effect of "cost" signal. In conclusion, this study sheds new light on how investors' interpretations of SMEs' financing strategies affect firm valuation.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.4
• /
• pp.29-39
• /
• 2017

Various electronic warfare situations drive the need to develop an integrated electronic warfare simulator that can perform electronic warfare modeling and simulation on radar threats. In this paper, we analyze the components of a simulation system to reversely model the radar threats that emit electromagnetic signals based on the parameters of the electronic information, and propose a method to gradually maintain the reverse extrapolation model of RF threats. In the experiment, we will evaluate the effectiveness of the incremental model update and also assess the integration method of reverse extrapolation models. The individual model of RF threats are constructed by using decision tree, naive Bayesian classifier, artificial neural network, and clustering algorithms through Euclidean distance and cosine similarity measurement, respectively. Experimental results show that the accuracy of reverse extrapolation models improves, while the size of the threat sample increases. In addition, we use voting, weighted voting, and the Dempster-Shafer algorithm to integrate the results of the five different models of RF threats. As a result, the final decision of reverse extrapolation through the Dempster-Shafer algorithm shows the best performance in its accuracy.

• Design Convergence Study
• /
• v.15 no.6
• /
• pp.195-214
• /
• 2016

Predictive analysis is based on a probabilistic learning algorithm called pattern recognition or machine learning. Therefore, if users want to extract more information from the data, they are required high statistical knowledge. In addition, it is difficult to find out data pattern and characteristics of the data. This study conducted statistical data analyses and visual data analyses to supplement prediction analysis's weakness. Through this study, we could find some implications that haven't been found in the previous studies. First, we could find data pattern when adjust data selection according as splitting criteria for the decision tree method. Second, we could find what type of data included in the final prediction model. We found some implications that haven't been found in the previous studies from the results of statistical and visual analyses. In statistical analysis we found relation among the multivariable and deducted prediction model to predict high box office performance. In visualization analysis we proposed visual analysis method with various interactive functions. Finally through this study we verified final prediction model and suggested analysis method extract variety of information from the data.

• Korea Science and Art Forum
• /
• v.24
• /
• pp.143-157
• /
• 2016

Focusing on the Gwangheemun that have a history of spatial specificity. Gwangheemun increase the value of space in the surrounding area, focused to derive a plan that can be activated. Research method was to analyze the characteristics and advantages and disadvantages of the surrounding space and the associated cultural content through SWOT analysis around the base of Gwangheemun. After considering the potential of the current location of physical characteristics and spatial resources, the possibility Gwangheemun development were mainly fashion and art content for the Space Vitalization in the surrounding area. Fashion and art space of Gwangheemun activated based on the possibility of Gwangheemun cultural meaning and value in the history of the past and the present time presented the main directions and strategic approach. The results of this research suggested Fashion art Hotel in applying urban regeneration methodologies, Cheongguro-16 plan for content development, arts and culture fashion street planning. Through this research, we want to establish the strategic control strategy between the policy decision making structures for the successful development of the fashion arts content.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.129-148
• /
• 2023

Bitcoin is a blockchain technology-based digital currency that has been recognized as a representative cryptocurrency and a financial investment asset. Due to its highly volatile nature, Bitcoin has gained a lot of attention from investors and the public. Based on this popularity, numerous studies have been conducted on price and trend prediction using machine learning and deep learning. This study employed LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks), which have shown potential for predictive performance in the finance domain, to enhance the classification accuracy in Bitcoin price trend prediction. XAI(eXplainable Artificial Intelligence) techniques were applied to the predictive model to enhance its explainability and interpretability by providing a comprehensive explanation of the model. In the empirical experiment, CNN was applied to technical indicators and Google trend data to build a Bitcoin price trend prediction model, and the CNN model using both technical indicators and Google trend data clearly outperformed the other models using neural networks, SVM, and LSTM. Then SHAP(Shapley Additive exPlanations) was applied to the predictive model to obtain explanations about the output values. Important prediction drivers in input variables were extracted through global interpretation, and the interpretation of the predictive model's decision process for each instance was suggested through local interpretation. The results show that our proposed research framework demonstrates both improved classification accuracy and explainability by using CNN, Google trend data, and SHAP.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.35-56
• /
• 2023

With the development of information and communication technology, numerous reviews are continuously posted on websites, which causes information overload problems. Therefore, users face difficulty in exploring reviews for their decision-making. To solve such a problem, many studies on review helpfulness prediction have been actively conducted to provide users with helpful and reliable reviews. Existing studies predict review helpfulness mainly based on the features included in the review. However, such studies disable providing the reason why predicted reviews are helpful. Therefore, this study aims to propose a methodology for applying eXplainable Artificial Intelligence (XAI) techniques in review helpfulness prediction to address such a limitation. This study uses restaurant reviews collected from Yelp.com to compare the prediction performance of six models widely used in previous studies. Next, we propose an explainable review helpfulness prediction model by applying the XAI technique to the model with the best prediction performance. Therefore, the methodology proposed in this study can recommend helpful reviews in the user's purchasing decision-making process and provide the interpretation of why such predicted reviews are helpful.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.131-146
• /
• 2023

Smart card data is widely used in the public transportation field. Despite the inevitability of various errors occur during the data collection and storage; however, smart card data errors have not been extensively studied. This paper investigates inherent errors in boarding and alighting station information in smart card data. A comparison smart card data and bus boarding and alighting survey data for the same time frame shows that boarding station names differ by 6.2% between the two data sets. This indicates that the error rate of smart card data is 6.2% in terms of boarding station information, given that bus boarding and alighting survey data can be considered as ground truth. This paper propose 6-step algorithm for correcting errors in smart card boarding station information, linking them to corresponding information in Bus Information System(BIS) Data. Comparing BIS data and bus boarding and alighting survey data for the same time frame reveals that boarding station names correspond by 98.3% between the two data sets, indicating that BIS data can be used as reliable reference for ground truth. To evaluate its performance, applying the 6-step algorithm proposed in this paper to smart card data set shows that the error rate of boarding station information is reduced from 6.2% to 1.0%, resulting in a 5.2%p improvement in the accuracy of smart card data. It is expected that the proposed algorithm will enhance the process of adjusting bus routes and making decisions related to public transportation infrastructure investments.

• 한국체육학회지인문사회과학편
• /
• v.55 no.6
• /
• pp.661-676
• /
• 2016

The purpose of this study is to draw a systematic access method of career intervention for dance majors. This study conducted Delphi survey and Analytic Hierarchy Process(AHP). As a result of study, 16 elements of career intervention were produced in total 4 areas. Results show that vocational guidance puts emphasis on the understanding of the various vocations, career education on the career planning and goal, career counseling on the macro-narrative to the life and career intervention network on the dance job fair and workshop. In the complex weight of all factors, ratings of weight show that dance vocation guidance and career education are demanded significantly. Results show that expansion of career alternatives, application of diversified dance career development road map to the curriculum, development of test tool and outcome standard, dance educators' systematic career intervention education and systematization of network for career support were suggested as measures for dance career intervention. This study discussed about dynamic reality and systematic access method for dance majors based on theories of Holland(1997), Super(1990), and Savickas(2005).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.43-43
• /
• 2021

Sesan강과 Srepok강은 베트남, 캄보디아, 라오스가 공유하는 3S강 유역 (Sesan강, Srepok강, Sekong강)의 일부로 국제 공유하천으로 관리되고 있다. 3S강 유역은 Mekong강의 중요한 지류이며 Mekong강 유역의 상당 부분을 구성한다(Mekong강 유역 면적의 10%, 연간 총 유출량의 20%). 베트남에 속해 있는 Sesan강 유역면적은 11,255km², Srepok강 유역면적은 18,162km²이다. Sesan강과 Srepok강의 상류는 베트남 중부 고원의 긴 산맥에 위치하고 있으며, 하류는 캄보디아에 위치해 있어 상·하류간 긴밀한 협력이 필요하다. Sesan강과 Srepok강 유역은 기후변화에 따른 홍수, 가뭄, 수력발전소 건설로 인한 유출량 변동에 따른 상·하류 분쟁, 사면침식 및 퇴적 등 많은 문제와 도전에 직면할 것으로 예측되고 있다. 본 연구에서는 World Bank의 "Viet Nam Mekong Integrated Water Resources Management (M-IWRM) Project의 일환으로 베트남 정부 차원에서 처음으로 구축한 수자원관리 의사결정지원시스템인 "DSS-2S"를 활용하여, Sesan-Srepok강 유역의 수자원 계획을 수립하였다. DSS-2S는 MIKE Hydro Basin을 기반으로 SWAT모델 등과 연계 하여 구축되었다. DSS-2S는 2S 유역의 모든 주요 하천과 지류를 반영하였으며. 여기에는 17개의 수력발전 댐과 주요 지류에서 용량이 3백만 m³ 이상인 기타 저수지가 포함되었다. 이 보다 작은 용량의 저수지는 대표적인 저수지로 그룹화 되어 반영되었다. 기후변화 및 사회-경제적 발전계획 등을 반영하여, 2030년과 2050년을 목표연도로 생활, 공업, 농업, 관광, 유지용수 등 용수 수요를 추정하였다. 50% 및 85% 빈도의 공급 가능성을 고려하여 물 배분은 물 수요를 충족하고 지하수 개발 최소화를 기준으로 고려되었다. 분석 결과에 의하면 2S강 유역의 총 수자원은 32.2억 m³으로 그중 지표수자원은 29.2억 m³, 안정적으로 이용 가능한 지하수자원은 2.97억 m³으로 분석 되었으며, 지표수와 지하수 연계를 고려하면 전체 2S 강 유역에 물 부족하지는 않으나, 개별 공급 지점을 고려할 때 4월과 5월에 일부 지역에서 물 부족이 나타날 것으로 예측 된다. 장래 물 부족 해결을 위한 대안들을 제시하였으며, 본 성과는 베트남 중앙 정부의 장기수자원 종합계획 수립의 기본 자료로 활용 될 예정이다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.485-492
• /
• 2023

Among the methods to improve traffic congestion by providing real-time traffic information and solving problems like traffic congestion and traffic crashes, private enterprise is implementing policies to lower insurance premiums like compensation for drivers' driving safety scores. Despite the emergence of various incentive policies, a study on the level of incentive payment for safe/eco-friendly driving is insufficient. The research analyzed the satisfactory factors that affect the scale of incentives through questionnaires and the applicable scale of incentives that enable safe/eco-friendly driving using a binary logistic regression model. As a result of analyzing the incentive scale of the appropriate payment amount for each driving score increase, 0.4% of the toll fee was derived when the driving score increased by 20 points, and 0.5% of the toll fee was derived when the driving score increased by 30 points. This study on calculating the appropriate incentive payment scale for driver information sharing and driving score increase will help optimize incentives and prepare system implementation plans.