• International Journal of Highway Engineering
• /
• v.7 no.4 s.26
• /
• pp.151-162
• /
• 2005

Variable Message Sign (VMS), which provides drivers with direct information about state of traffic congestion and for prevent an accident, is the most effective method among the methods of providing information in Advanced Transportation Management System. Currently establishment and the VMS which is operated foundation lets in Guidelines on the use of Variable message sign (a book of the VMS) of 1999 November the Ministry Construction & Transportation, these contents mean main viewpoint on physical part such as message special quality variable (font, character size and line space, word interval) and position mainly among standard about establishment in general. But, it is true that using without effect verification on the character of VMS display and that using mode of stationary-centered. In this paper, it executed significance test to effort verification on the character of VMS display for more practical and effective information transmission based on the driver viewpoint For the researches; develop 3D-Simulation, select characteristics of driver's visual cognition behavior (the conspicuity, the legibility and the comprehensibility), evaluation each issue (day or night, 80km/h or 100km/h). Especially, that used the Eye Marker Recorder to measure of reading-time (legibility) thus, confirmed objectivity and reduce an observational error. The results showed that the conspicuity is Flashing> Stationary>Scroll. The legibility is not deference that Flashing between stationary form. Also the comprehensibility result showed that Flashing> Stationary>Stroll form.

• Information Systems Review
• /
• v.21 no.4
• /
• pp.99-123
• /
• 2019

The software industry is a high value-added industry in the knowledge information age, and its importance is growing as it not only plays a key role in knowledge creation and utilization, but also secures global competitiveness. Among various SW available in today's business environment, Open Source Software(OSS) is rapidly expanding its activity area by not only leading software development, but also integrating with new information technology. Therefore, the purpose of this research is to empirically examine and analyze the effect of factors on the switching behavior to OSS. To accomplish the study's purpose, we suggest the research model based on "Push-Pull-Mooring" framework. This study empirically examines the two categories of antecedents for switching behavior toward OSS. The survey was conducted to employees at various firms that already switched OSS. A total of 268 responses were collected and analyzed by using the structural equational modeling. The results of this study are as follows; first, continuous maintenance cost, vender dependency, functional indifference, and SW resource inefficiency are significantly related to switch to OSS. Second, network-oriented support, testability and strategic flexibility are significantly related to switch to OSS. Finally, the results show that willingness to secures SW competitiveness has a moderating effect on the relationships between push factors and pull factor with exception of improved knowledge, and switch to OSS. The results of this study will contribute to fields related to OSS both theoretically and practically.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.95-108
• /
• 2011

TThis is a study of the personalization method that intelligently adapts the level of clustering considering purchasing index of a customer. In the e-biz era, many companies gather customers' demographic and transactional information such as age, gender, purchasing date and product category. They use this information to predict customer's preferences or purchasing patterns so that they can provide more customized services to their customers. The previous Customer-Segmentation method provides customized services for each customer group. This method clusters a whole customer set into different groups based on their similarity and builds predictive models for the resulting groups. Thus, it can manage the number of predictive models and also provide more data for the customers who do not have enough data to build a good predictive model by using the data of other similar customers. However, this method often fails to provide highly personalized services to each customer, which is especially important to VIP customers. Furthermore, it clusters the customers who already have a considerable amount of data as well as the customers who only have small amount of data, which causes to increase computational cost unnecessarily without significant performance improvement. The other conventional method called 1-to-1 method provides more customized services than the Customer-Segmentation method for each individual customer since the predictive model are built using only the data for the individual customer. This method not only provides highly personalized services but also builds a relatively simple and less costly model that satisfies with each customer. However, the 1-to-1 method has a limitation that it does not produce a good predictive model when a customer has only a few numbers of data. In other words, if a customer has insufficient number of transactional data then the performance rate of this method deteriorate. In order to overcome the limitations of these two conventional methods, we suggested the new method called Intelligent Customer Segmentation method that provides adaptive personalized services according to the customer's purchasing index. The suggested method clusters customers according to their purchasing index, so that the prediction for the less purchasing customers are based on the data in more intensively clustered groups, and for the VIP customers, who already have a considerable amount of data, clustered to a much lesser extent or not clustered at all. The main idea of this method is that applying clustering technique when the number of transactional data of the target customer is less than the predefined criterion data size. In order to find this criterion number, we suggest the algorithm called sliding window correlation analysis in this study. The algorithm purposes to find the transactional data size that the performance of the 1-to-1 method is radically decreased due to the data sparity. After finding this criterion data size, we apply the conventional 1-to-1 method for the customers who have more data than the criterion and apply clustering technique who have less than this amount until they can use at least the predefined criterion amount of data for model building processes. We apply the two conventional methods and the newly suggested method to Neilsen's beverage purchasing data to predict the purchasing amounts of the customers and the purchasing categories. We use two data mining techniques (Support Vector Machine and Linear Regression) and two types of performance measures (MAE and RMSE) in order to predict two dependent variables as aforementioned. The results show that the suggested Intelligent Customer Segmentation method can outperform the conventional 1-to-1 method in many cases and produces the same level of performances compare with the Customer-Segmentation method spending much less computational cost.

• Journal of the Korean earth science society
• /
• v.29 no.6
• /
• pp.495-505
• /
• 2008

The main purposes of this study are to: (1) to develop astronomy observation program based on a standardized coefficient decision program; and (2) to apply the developed program to after-school or club activities. As a first step, we analyzed activities related to astronomy in the authorized textbooks that are currently adopted in high schools. based on the analysis, we developed an astronomy observation program according to the standardized coefficient decision program, and the program was applied to students' astronomical observations as part of the club activities. Specifically, this program used a 102 mm refracting telescope and digital camera. we took into account the observation site's environment of the urban areas in which many school were located and then developed a the computer program for observation activities. The results of this study are as follows. First, the current astronomical education in schools was based off of the textbooks. Specifically, it was mostly about analyzing the materials and making simulated experiments. Second, most schools participated in this study were located in urban areas where students had more difficulty in observation than in rural areas. Third, an exemplary method was investigated in order to make an astronomical observation efficiently in urban areas with the existing devices. In addition, the standardized coefficient decision program was developed to standardize the magnitude of stars according to the observed value. Finally, based on the students' observations, we found that there was no difference between the magnitude of a star in urban sites and in rural sites. The current astronomical education in schools lacks an activity of practical experiments, and many schools have not good observational sites because they are located in urban areas. However, use of this program makes it possible to collect significant data after a series of standardized corrections. In conclusion, this program not only helps schools to create an active astronomy observation activity in fields, but also promotes students to be more interested in astronomical observation through a series of field-based activities.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.12 no.6
• /
• pp.111-122
• /
• 2017

This study analyzes the current state of entrepreneurship education and start-up foundations by country in order to find ways to improve the domestic entrepreneurial environment and to promote the recognition of desirable entrepreneurship practices. It also investigates the relationship between entrepreneurship, entrepreneurial will, and the level of opportunity-based entrepreneurships, by using data from the 2016 Global Entrepreneurship Trend Report (GETR). First, the results show the urgent need for the expansion of entrepreneurship education in Korea. In the GETR category of 'experience of entrepreneurship education in elementary, middle and high schools', Korea was ranked very low (19th place), among the 20 countries. In the 'college' and 'lifelong entrepreneurship education' categories, it procured a mid-level ranking (15th). While entrepreneurship education for all ages is being promoted globally, entrepreneurship education for middle-aged individuals in Korea is relatively weak. This implies that the expansion of entrepreneurship education to lifelong education and education for employees and retirees is required. Second, the individual's entrepreneurial intention in Korea was 3.8 points, implying a mid-level ranking (15th), and it ranked the lowest in terms of opportunity-based entrepreneurship (20th). In comparison to China (4.55) and the United States (4.01), the entrepreneurial intention of Koreans was found to be low. The level of opportunity-driven entrepreneurship was also found to be very low, compared to China (4.35), Japan (4.04) and the United States (4.59). In general, the proportion of the level in opportunity-driven entrepreneurship, increases from the factor-driven and efficiency-driven, to the innovation-driven type. In Korea, the percentage of entrepreneurial ventures centered around involuntary entrepreneurship and small businesses is high. It is also interpreted that opportunity-based entrepreneurships are low in number because of this high proportion of involuntary start-up and small businesses. Last, the entrepreneurial intention in all types (factor-driven, efficiency-driven, and innovation-driven) was exceptionally high. It has been confirmed that exposure to all entrepreneurship education (elementary, junior high, university, and lifelong education) in innovation-driven countries, greatly increases entrepreneurial intention. In the case of Korea, which is an innovation-driven country, qualitative improvement based on quantitative expansion of entrepreneurship education is expected to be a major driving force for individuals' entrepreneurial intention to obtain a mid-level ranking (15th).

• Korean Journal of Cognitive Science
• /
• v.20 no.2
• /
• pp.125-154
• /
• 2009

This paper describes the possibility of human physiological data, especially brain-wave activity, to detect cognitive overload, a phenomenon that may occur while learner uses an e-learning system. If it is found that cognitive overload to be detectable, providing appropriate feedback to learners may be possible. To illustrate the possibility, while engaging in cognitive activities, cognitive load levels were measured by EEG (electroencephalogram) to seek detection of cognitive overload. The task given to learner was a computerized listening and recall test designed to measure working memory capacity, and the test had four progressively increasing degrees of difficulty. Eight male, right-handed, university students were asked to answer 4 sets of tests and each test took from 61 seconds to 198 seconds. A correction ratio was then calculated and EEG results analyzed. The correction ratio of listening and recall tests were 84.5%, 90.6%, 62.5% and 56.3% respectively, and the degree of difficulty had statistical significance. The data highlighted learner cognitive overload on test level of 3 and 4, the higher level tests. Second, the SEF-95% value was greater on test3 and 4 than on tests 1 and 2 indicating that tests 3 and 4 imposed greater cognitive load on participants. Third, the relative power of EEG gamma wave rapidly increased on the 3rd and $4^{th}$ test, and signals from channel F3, F4, C4, F7, and F8 showed statistically significance. These five channels are surrounding the brain's Broca area, and from a brain mapping analysis it was found that F8, right-half of the brain area, was activated relative to the degree of difficulty. Lastly, cross relation analysis showed greater increasing in synchronization at test3 and $4^{th}$ at test1 and 2. From these findings, it is possible to measure brain cognitive load level and cognitive over load via brain activity, which may provide atimely feedback scheme for e-learning systems.

• Spatial Information Research
• /
• v.6 no.2
• /
• pp.133-152
• /
• 1998

This article considers the experimental foundations of geographical phenomena for the distribution of lodging houses and the development of lodging Information Systems in Shin-Chon Area. This system allows the rural students to find their lodging houses conveniently. We examine the geographical reality of lodging houses in Shin-chon area and explores the lodging information system, reflecting how students select the lodging houses. Criteria for selection of lodging houses are travel time to school, interior facilities, rent fee, members, owners of lodging houses, which are collected by field swvey. The lodging information system is built in integration of Visual Basic with spatial data which are created in Mapinfo and Arcview through MapObject, component GIS software. This system provide query tools to efficiently investigate data as well as interactive map display. Also it displays the characteristics of a selected lodging houses using the identify tool on the map.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.16 no.4
• /
• pp.115-133
• /
• 2021

This study examines the concept and related technologies of the 4th industrial revolution that has been mixed so far and examines the socio-economic changes and influences resulting from it, and the cases of responding to the 4th industrial revolution in major countries. Based on this, by deriving SWOT factors and calculating the importance of each factor for Korean venture companies to prepare for the forth industrial revolution, it was intended to help the government and policymakers in suggesting directions for establishing related policies. Furthermore, the purpose of this study was to suggest a direction for securing global competitiveness to Korean venture entrepreneurs and to help with basic and systematic analysis for further academic in-depth research. For this study, a total of 21 items derived through extensive literature research and data research to understand what are the necessary competency factors for internal and external environmental changes in order for Korean venture companies to have global competitiveness in the era of the 4th Industrial Revolution. After reviewing SWOT factors by three expert groups and confirming them through Delphi survey, the importance of each item was analyzed by using AHP, a systematic decision-making technique. As a result of the analysis, it was shown that Strength(48%), Opportunity(25%), Threat(16%), Weakness(11%) were considered important in order. In terms of sub-items, 'quick and flexible commercialization capability', 'platform/big data/non-face-to-face service activation', and 'ICT infrastructure and it's utilization' were shown to be of the comparatively high importance. On the other hand, in the lower three items, 'macro-economic stability and social infrastructure', 'difficulty in entering overseas markets due to global protectionism', and 'absolutely inferior in foreign investment' were found to have low priority. As a result of the correlation verification by item to see differences in opinions by industry, academia, and policy expert groups, there was no significant difference of opinion, as industry and academic experts showed a high correlation and industry experts and policy experts showed a moderate correlation. The correlation between the academic and policy experts was not statistically significant (p<0.01), so it was analyzed that there was a difference of opinion on importance. This was due to the fact that policy experts highly valued 'quick and flexible commercialization', which are strengths, and 'excellent educational system and high-quality manpower' and 'creation of new markets' which are opportunity items, while academic experts placed great importance on 'support part of government policy', which are strengths. The implication of this study is that in order for Korean venture companies to secure competitiveness in the field of the 4th industrial revolution, it is necessary to have a policy that preferentially supports the relevant items of strengths and opportunity factors. The difference in the details of strength factors and opportunity factors, which shows a high level of variability, suggests that it is necessary to actively review it and reflect it in the policy.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.