• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.4
• /
• pp.13-29
• /
• 2020

Automobiles have long been an essential part of daily life, but the social costs of car traffic accidents exceed 9% of the national budget of Korea. Hence, it is necessary to establish prevention and response system for car traffic accidents. In order to present a model that can classify and predict the degree of injury in car traffic accidents, we used big data analysis techniques of K-nearest neighbor, logistic regression analysis, naive bayes classifier, decision tree, and ensemble algorithm. The performances of the models were analyzed by using the data on the nationwide traffic accidents over the past three years. In particular, considering the difference in the number of data among the respective injury severity levels, we used down-sampling methods for the group with a large number of samples to enhance the accuracy of the classification of the models and then verified the statistical significance of the models using ANOVA.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• Korean Journal of Environment and Ecology
• /
• v.36 no.6
• /
• pp.592-602
• /
• 2022

This study aimed to check habitat distribution and analyze influencing factors by analyzing the mating calls of Auritibicen intermedius inhabiting limited locations in South Korea by applying bioacoustic detection techniques. The study sites were 20 protection areas nationwide. The mating call analysis period was 4 years from 2017 to 2021, excluding 2020. The bioacoustic recording system installed at each study site collected recordings of mating calls every day for 1 minute per hour. Climate data received from the Meteorological Agency, such as temperature, humidity, rainfall, cloudiness, and sunshine, were analyzed. The results of this study identified A. intermedius habitat only in four national parks in the highlands of Gangwon Province (Mt. Seorak, Mt. Odae, Mt. Chiak, and Mt. Taebak) out of 20 study sites. During the four years of study, the mating call period of A. intermedius was between August 5 and September 28, and the duration of the mating call was 31 to 52 days. The temperature analysis during the appearance period of A. intermedius showed that A. intermedius mainly produced mating calls at temperatures between 13.1℃ and 35.3℃, and the average temperature during the circadian cycle of mating calls (09:00 to 16:00) was 24.4 to 24.9℃. The analysis of the circadian cycle of mating calls at four study sites where A. intermedius appeared in 2019 showed that A. intermedius produced mating calls from 06:00 to 16:00 and that they peaked around 11:00 to 12:00. During the appearance period of A. intermedius, four species appeared in common: Hyalessa maculaticollis, Meimuna opalifera, Graptopsaltria nigrofuscata, and Suisha coreana. A logistic regression analysis confirmed that sunlight was the environmental factor affecting the mating call of A. intermedius. Regarding interspecific influence, it was confirmed that A. intermedius exchanged interspecific influence with 4 other common species (H. maculaticollis, M. opalifera, G. nigrofuscata, and S. coreana). The above results confirmed that A. intermedius habitats were limited in the highlands of Gangwon Province highlands in Korea and produced mating calls at a lower temperature compared to other species. These results can be used as basic data for future research on A. intermedius in Korea.

• Journal of Korean Society of Transportation
• /
• v.29 no.3
• /
• pp.73-82
• /
• 2011

Recent advancement in traffic surveillance systems has allowed the researchers to obtain more detailed vehicular movement such as individual vehicle trajectory data. Understanding the characteristics of interactions between leading and following vehicles in the traffic flow stream is a backbone for designing and evaluating more sophisticated traffic and vehicle control strategies. This study proposes a methodology for estimating rear-end crash potential, as a probabilistic measure, in real-time based on the analysis of vehicular movements. The methodology presented in this study consists of three components. The first predicts vehicle position and speed every second using a Kalman filtering technique. The second estimates the probability for the vehicle's trajectory to belong to either 'changing lane' or 'going straight'. A binary logistic regression (BLR) is used to model the lane-changing decision of the subject vehicle. The other component calculates crash probability by employing an exponential decay function that uses time-to-collision (TTC) between the subject vehicle and the front vehicle. The result of this study is expected to be adapted in developing traffic control and information systems, in particular, for crash prevention.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.5810-5818
• /
• 2015

The dissertation presents the portfolio construction method using the score sheet so that general investors can utilize it easily. This study draws the significant variables to contribute the enterprise value and suggests the combined models by applying the single methodology, which private investors can easily utilize. The results of the research can be classified into 2 areas. Firstly, the significantly affecting variables were selected for analyzing the enterprise value. The variables and the method for the enterprise value analysis were studied from the existing researches to choose the optimal variables. The variables were identified by using AHP method and the structure equation method from the investigation of the previous researches. And the critical variables were added extracted from the common denominator of variables which the 3 grue investors used for their investment. The final variables identified are dividend yield, PER, PBR, PCR, EV/EBITDA, ROE, net income, sales growth rate, net current asset, debt ratio, current ratio, rate of operating profits, ratio of operating profit to net sales, ratio of net income to net sales, net profit to total assets, EPS growth rate, inventory turnover ratio, and receivables turnover. Second, the new methodologies for forecasting enterprise value modifying the existing methods were developed. The result of the Logistic regression analysis for forecasting showed that the equation could not be suitable as the accuracy with 91.98%.

• Management & Information Systems Review
• /
• v.28 no.3
• /
• pp.1-23
• /
• 2009

Prior bankruptcy studies have established that bankrupt firm's pre-filing financial ratios are different from those of healthy firms or of randomly selected going concerns. However, they may not be sufficiently different from the financial ratios of other firms in financial distress to allow the development of a ratio-based model that predicts bankruptcy with reasonable accuracy. As the result, in the multiple discriminant model, independent variables divided firms into bankrupt firms and healthy firms are retained earnings to total asset, receivable turnover, net income to sales, financial expenses, inventory turnover, owner's equity to total asset, cash flow to current liability, and current asset to current liability. Moreover four variables Retained earnings to total asset, net income to sales, total asset turnover, owner's equity to total asset indicate that these valuables classify bankrupt firms and distress firms. On the other hand, Owner's Equity to borrowed capital, Ordinary income to Net Sales, Operating Income to Total Asset, Total Asset Turnover and Inventory Turnover are selected to predict bankruptcy possibility in the Logistic regression model.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.433-444
• /
• 2022

This study aimed to identify the change trajectories and clusters of Korean women's family values and depression levels, and the factors affecting depression, to use balanced panel data from the 1st to 7th rounds of the Korea Longitudinal Survey of Women and Families(KLSWF). The subjects of this study were 5,048 female panelists who participated in the KLSWF, and LSTM analysis was conducted using Python to divide the clusters of Korean women suffering from depression. In addition, descriptive statistical analysis, ANOVA, multinomial logistic regression analysis, and hierarchical regression analysis were analyzed using SPSS 23.0. Results, It was confirmed that women's depression increased with age, and family values had a significant impact on depression. It was found that the more open the marriage values of women in the married group, the higher the level of depression. The family values trajectory and depression level of the analyzed subjects were not a single pattern, but included four clusters. To prevent depression among Korean women and provide more concrete interventions, a humanities and sociological system that can identify depression groups should be prepared.

• The Journal of Society for e-Business Studies
• /
• v.23 no.3
• /
• pp.207-224
• /
• 2018

In this article, an empirical study was conducted by using public dataset from Lending Club Corporation, the largest online peer-to-peer (P2P) lending in the world. We explore significant predictor variables related to P2P lending default that housing situation, length of employment, average current balance, debt-to-income ratio, loan amount, loan purpose, interest rate, public records, number of finance trades, total credit/credit limit, number of delinquent accounts, number of mortgage accounts, and number of bank card accounts are significant factors to loan funded successful on Lending Club platform. We developed online P2P lending default prediction models using discriminant analysis, logistic regression, neural networks, and decision trees (i.e., CART and C5.0) in order to predict P2P loan default. To verify the feasibility and effectiveness of P2P lending default prediction models, borrower loan data and credit data used in this study. Empirical results indicated that neural networks outperforms other classifiers such as discriminant analysis, logistic regression, CART, and C5.0. Neural networks always outperforms other classifiers in P2P loan default prediction.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.4
• /
• pp.615-627
• /
• 2009

In micro marketing promotion, it is important to know the behavior of customers. In this study we are interested in the forecasting of repurchase of customers from customers' behavior. By analyzing the cosmetic transaction data we derive some variables which play an important role in the knowledge of the customers' behavior and in the modeling of repurchase. As modeling tools we use the decision tree, logistic regression and neural network model. Finally we decide to use the decision tree as a final model since it yields the smallest RASE (root average squared error) and the greatest correct classification rate.

• Journal of Korean Society of Transportation
• /
• v.25 no.3
• /
• pp.99-109
• /
• 2007

Variable message signs (VMS), which are used for providing real-time information on traffic conditions and accident occurrences, are one of the important components of intelligent transportation systems VMS messages need to meet human factor requirements: messages should be readable and understandable while driving. Lab-controlled experiments on VMS messages were conducted to obtain useful data for analyzing drivers' responsive characteristics for VMS messages. Binary logistic regression (BLR) modeling techniques were applied to explore the relationships among drivers' message perceptions, message reading time, and amount of VMS messages. Probabilistic outcomes of the proposed BLR-based perception model could be greatly utilized to design VMS messages considering drivers' legibility performance. The major contribution of this study is to develop invaluable statistical models that can be used in designing VMS messages more effectively from the human factor point of view. The results could be further applied to establish the scheme of VMS message phase and duration.