• Korean Journal of Radiology
• /
• v.24 no.8
• /
• pp.807-820
• /
• 2023

Objective: To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. Materials and Methods: This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1-7 according to acquisition conditions. CT images in groups 2-7 were converted into the target CT style (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. Results: Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2-7 improved after CT conversion (original vs. converted: 0.63 vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists' scores were significantly higher (P < 0.001) and less variable on converted CT. Conclusion: CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.8 no.2
• /
• pp.47-60
• /
• 1975

For the calculation of population parameter and estimation of recruitment of a fish population, an application of multiple regression method was used with some statistical inferences. Then, the differences between the calculated values and the true parameters were discussed. In addition, this method criticized by applying it to the statistical data of a population of bigeye tuna, Thunnus obesus of the Indian Ocean. The method was also applied to the available data of a population of Pacific saury, Cololabis saira, to estimate its recuitments. A stock at t year and t+1 year is, $N_{0,\;t+1}=N_{0,\;t}(1-m_t)-C_t+R_{t+1}$ where $N_0$ is the initial number of fish in a given year; C, number o: fish caught; R, number of recruitment; and M, rate of natural mortality. The foregoing equation is $$\phi_{t+1}=\frac{(1-\varrho^{-z}{t+1})Z_t}{(1-\varrho^{-z}t)Z_{t+1}}-\frac{1-\varrho^{-z}t+1}{Z_{t+1}}\phi_t-a'\frac{1-\varrho^{-z}t+1}{Z_{t+1}}C_t+a'\frac{1-\varrho^{-z}t+1}{Z_{t+1}}R_{t+1}......(1)$$ where $\phi$ is CPUE; a', CPUE $(\phi)$ to average stock $(\bar{N})$ in number; Z, total mortality coefficient; and M, natural mortality coefficient. In the equation (1) , the term $(1-\varrho^{-z}t+1)/Z_{t+1}$s almost constant to the variation of effort (X) there fore coefficients $\phi$ and $C_t$, can be calculated, when R is a constant, by applying the method of multiple regression, where $\phi_{t+1}$ is a dependent variable; $\phi_t$ and $C_t$ are independent variables. The values of Mand a' are calculated from the coefficients of $\phi_t$ and $C_t$; and total mortality coefficient (Z), where Z is a'X+M. By substituting M, a', $Z_t$, and $Z_{t+1}$ to the equation (1) recruitment $(R_{t+1})$ can be calculated. In this precess $\phi$ can be substituted by index of stock in number (N'). This operational procedures of the method of multiple regression can be applicable to the data which satisfy the above assumptions, even though the data were collected from any chosen year with similar recruitments, though it were not collected from the consecutive years. Under the condition of varying effort the data with such variation can be treated effectively by this method. The calculated values of M and a' include some deviation from the population parameters. Therefore, the estimated recruitment (R) is a relative value instead of all absolute one. This method of multiple regression is also applicable to the stock density and yield in weight instead of in number. For the data of the bigeye tuna of the Indian Ocean, the values of estimated recruitment (R) calculated from the parameter which is obtained by the present multiple regression method is proportional with an identical fluctuation pattern to the values of those derived from the parameters M and a', which were calculated by Suda (1970) for the same data. Estimated recruitments of Pacific saury of the eastern coast of Korea were calculated by the present multiple regression method. Not only spring recruitment $(1965\~1974)$ but also fall recruitment $(1964\~1973)$ was found to fluctuate in accordance with the fluctuations of stock densities (CPUE) of the same spring and fall, respectively.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1041-1043
• /
• 1993

Fuzzy logic based Control Theory has gained much interest in the industrial world, thanks to its ability to formalize and solve in a very natural way many problems that are very difficult to quantify at an analytical level. This paper shows a solution for treating membership function inside hardware circuits. The proposed hardware structure optimizes the memoried size by using particular form of the vectorial representation. The process of memorizing fuzzy sets, i.e. their membership function, has always been one of the more problematic issues for the hardware implementation, due to the quite large memory space that is needed. To simplify such an implementation, it is commonly [1,2,8,9,10,11] used to limit the membership functions either to those having triangular or trapezoidal shape, or pre-definite shape. These kinds of functions are able to cover a large spectrum of applications with a limited usage of memory, since they can be memorized by specifying very few parameters ( ight, base, critical points, etc.). This however results in a loss of computational power due to computation on the medium points. A solution to this problem is obtained by discretizing the universe of discourse U, i.e. by fixing a finite number of points and memorizing the value of the membership functions on such points [3,10,14,15]. Such a solution provides a satisfying computational speed, a very high precision of definitions and gives the users the opportunity to choose membership functions of any shape. However, a significant memory waste can as well be registered. It is indeed possible that for each of the given fuzzy sets many elements of the universe of discourse have a membership value equal to zero. It has also been noticed that almost in all cases common points among fuzzy sets, i.e. points with non null membership values are very few. More specifically, in many applications, for each element u of U, there exists at most three fuzzy sets for which the membership value is ot null [3,5,6,7,12,13]. Our proposal is based on such hypotheses. Moreover, we use a technique that even though it does not restrict the shapes of membership functions, it reduces strongly the computational time for the membership values and optimizes the function memorization. In figure 1 it is represented a term set whose characteristics are common for fuzzy controllers and to which we will refer in the following. The above term set has a universe of discourse with 128 elements (so to have a good resolution), 8 fuzzy sets that describe the term set, 32 levels of discretization for the membership values. Clearly, the number of bits necessary for the given specifications are 5 for 32 truth levels, 3 for 8 membership functions and 7 for 128 levels of resolution. The memory depth is given by the dimension of the universe of the discourse (128 in our case) and it will be represented by the memory rows. The length of a world of memory is defined by: Length = nem (dm(m)＋dm(fm) Where: fm is the maximum number of non null values in every element of the universe of the discourse, dm(m) is the dimension of the values of the membership function m, dm(fm) is the dimension of the word to represent the index of the highest membership function. In our case then Length=24. The memory dimension is therefore 128*24 bits. If we had chosen to memorize all values of the membership functions we would have needed to memorize on each memory row the membership value of each element. Fuzzy sets word dimension is 8*5 bits. Therefore, the dimension of the memory would have been 128*40 bits. Coherently with our hypothesis, in fig. 1 each element of universe of the discourse has a non null membership value on at most three fuzzy sets. Focusing on the elements 32,64,96 of the universe of discourse, they will be memorized as follows: The computation of the rule weights is done by comparing those bits that represent the index of the membership function, with the word of the program memor . The output bus of the Program Memory (μCOD), is given as input a comparator (Combinatory Net). If the index is equal to the bus value then one of the non null weight derives from the rule and it is produced as output, otherwise the output is zero (fig. 2). It is clear, that the memory dimension of the antecedent is in this way reduced since only non null values are memorized. Moreover, the time performance of the system is equivalent to the performance of a system using vectorial memorization of all weights. The dimensioning of the word is influenced by some parameters of the input variable. The most important parameter is the maximum number membership functions (nfm) having a non null value in each element of the universe of discourse. From our study in the field of fuzzy system, we see that typically nfm 3 and there are at most 16 membership function. At any rate, such a value can be increased up to the physical dimensional limit of the antecedent memory. A less important role n the optimization process of the word dimension is played by the number of membership functions defined for each linguistic term. The table below shows the request word dimension as a function of such parameters and compares our proposed method with the method of vectorial memorization[10]. Summing up, the characteristics of our method are: Users are not restricted to membership functions with specific shapes. The number of the fuzzy sets and the resolution of the vertical axis have a very small influence in increasing memory space. Weight computations are done by combinatorial network and therefore the time performance of the system is equivalent to the one of the vectorial method. The number of non null membership values on any element of the universe of discourse is limited. Such a constraint is usually non very restrictive since many controllers obtain a good precision with only three non null weights. The method here briefly described has been adopted by our group in the design of an optimized version of the coprocessor described in [10].

• Journal of Chest Surgery
• /
• v.32 no.3
• /
• pp.224-236
• /
• 1999

Background: To evaluate the short-term effect of dynamic cardiomyoplasty on circulatory function and detect the related factors that can affect it, experimental cardiomyoplasties were performed under the state of normal cardiac function and heart failure. Material and Method: A total of 10 mongrel dogs weighing 20 to 30kg were divided arbitrarily into two groups. Five dogs of group A underwent cardiomyoplasty with latissimus dorsi(LD) muscle mobilization followed by a 2-week vascular delay and 6-week muscle training. Then, hemodynamic studies were conducted. In group B, doxorubicin was given to 5 dogs in an IV dose of 1 mg/kg once a week for 8 weeks to induce chronic heart failure, and simultaneous muscle training was given for preconditioning during this period. Then, cardiomyoplasties were performed and hemodynamic studies were conducted immediately after these cardiomyoplasties in group B. Result: In group A, under the state of normal cardiac function, only mean right atrial pressure significantly increased with the pacer-on(p<0.05) and the left ventricular hemodynamic parameters did not change significantly. However, with pacer-on in group B, cardiac output(CO), rate of left ventricular pressure development(dp/dt), stroke volume(SV), and left ventricular stroke work(SW) increased by 16.7${\pm}$7.2%, 9.3${\pm}$3.2%, 16.8${\pm}$8.6%, and 23.1${\pm}$9.7%, respectively, whereas left ventricular end-diastole pressure(LVEDP) and mean pulmonary capillary wedge pressure(mPCWP) decreased by 32.1${\pm}$4.6% and 17.7${\pm}$9.1%, respectively(p<0.05). In group A, imipramine was infused at the rate of 7.5mg/kg/hour for 34${\pm}$2.6 minutes to induce acute heart failure, which resulted in the reduction of cardiac output by 17.5${\pm}$2.7%, systolic left ventricular pressure by 15.8${\pm}$2.5% and the elevation of left ventricular end-diastole pressure by 54.3${\pm}$15.2%(p<0.05). With pacer-on under this state of acute heart failu e, CO, dp/dt, SV, and SW increased by 4.5${\pm}$1.8% and 3.1${\pm}$1.1%, 5.7${\pm}$3.6%, and 6.9${\pm}$4.4%, respectively, whereas LVEDP decreased by 11.7${\pm}$4.7%(p<0.05). Comparing CO, dp/dt, SV, SW and LVEDP that changed significantly with pacer-on, both under the state of acute and chronic heart failure, augmentation widths of these left ventricular hemodynamic parameters were significantly larger under the state of chronic heart failure(group B) than acute heart failure(group A)(p<0.05). On gross inspection, variable degrees of adhesion and inflammation were present in all 5 dogs of group A, including 2 dogs that showed no muscle contraction. No adhesion and inflammation were, however, present in all 5 dogs of group B, which showed vivid muscle contractions. Considering these differences in gross findings along with the following premise that the acute heart failure state was not statistically different from the chronic one in terms of left ventricular parameters(p>0.05), the larger augmentation effect seen in group B is presumed to be mainly attributed to the viability and contractility of the LD muscle. Conclusion: These results indicate that the positive circulatory augmentation effect of cardiomyoplasty is apparent only under the state of heart failure and the preservation of muscle contractility is important to maximize this effect.

• Asia pacific journal of information systems
• /
• v.22 no.3
• /
• pp.99-124
• /
• 2012

Our society has long been talking about necessity for innovation. Since companies in particular need to carry out business innovation in their overall processes, they have attempted to apply many innovation factors on sites and become to pay more attention to their innovation. In order to achieve this goal, companies has applied various information technologies (IT) on sites as a means of innovation, and consequently IT have been greatly developed. It is natural for the field of IT to have faced another revolution which is called cloud computing, which is expected to result in innovative changes in software application via the Internet, data storing, the use of devices, and their operations. As a vehicle of innovation, cloud computing is expected to lead the changes and advancement of our society and the business world. Although many scholars have researched on a variety of topics regarding the innovation via IT, few studies have dealt with the issue of could computing as IT. Thus, the purpose of this paper is to set the variables of innovation attributes based on the previous articles as the characteristic variables and clarify how these variables affect "Performance Expectancy" of companies and the intention of using cloud computing. The result from the analysis of data collected in this study is as follows. The study utilized a research model developed on the innovation diffusion theory to identify influences on the adaptation and spreading IT for cloud computing services. Second, this study summarized the characteristics of cloud computing services as a new concept that introduces innovation at its early stage of adaptation for companies. Third, a theoretical model is provided that relates to the future innovation by suggesting variables for innovation characteristics to adopt cloud computing services. Finally, this study identified the factors affecting expectation and the intention to use the cloud computing service for the companies that consider adopting the cloud computing service. As the parameter and dependent variable respectively, the study deploys the independent variables that are aligned with the characteristics of the cloud computing services based on the innovation diffusion model, and utilizes the expectation for performance and Intention to Use based on the UTAUT theory. Independent variables for the research model include Relative Advantage, Complexity, Compatibility, Cost Saving, Trialability, and Observability. In addition, 'Acceptance for Adaptation' is applied as an adjustment variable to verify the influences on the expected performances from the cloud computing service. The validity of the research model was secured by performing factor analysis and reliability analysis. After confirmatory factor analysis is conducted using AMOS 7.0, the 20 hypotheses are verified through the analysis of the structural equation model, accepting 12 hypotheses among 20. For example, Relative Advantage turned out to have the positive effect both on Individual Performance and on Strategic Performance from the verification of hypothesis, while it showed meaningful correlation to affect Intention to Use directly. This indicates that many articles on the diffusion related Relative Advantage as the most important factor to predict the rate to accept innovation. From the viewpoint of the influence on Performance Expectancy among Compatibility and Cost Saving, Compatibility has the positive effect on both Individual Performance and on Strategic Performance, while it showed meaningful correlation with Intention to Use. However, the topic of the cloud computing service has become a strategic issue for adoption in companies, Cost Saving turns out to affect Individual Performance without a significant influence on Intention to Use. This indicates that companies expect practical performances such as time and cost saving and financial improvements through the adoption of the cloud computing service in the environment of the budget squeezing from the global economic crisis from 2008. Likewise, this positively affects the strategic performance in companies. In terms of effects, Trialability is proved to give no effects on Performance Expectancy. This indicates that the participants of the survey are willing to afford the risk from the high uncertainty caused by innovation, because they positively pursue information about new ideas as innovators and early adopter. In addition, they believe it is unnecessary to test the cloud computing service before the adoption, because there are various types of the cloud computing service. However, Observability positively affected both Individual Performance and Strategic Performance. It also showed meaningful correlation with Intention to Use. From the analysis of the direct effects on Intention to Use by innovative characteristics for the cloud computing service except the parameters, the innovative characteristics for the cloud computing service showed the positive influence on Relative Advantage, Compatibility and Observability while Complexity, Cost saving and the likelihood for the attempt did not affect Intention to Use. While the practical verification that was believed to be the most important factor on Performance Expectancy by characteristics for cloud computing service, Relative Advantage, Compatibility and Observability showed significant correlation with the various causes and effect analysis. Cost Saving showed a significant relation with Strategic Performance in companies, which indicates that the cost to build and operate IT is the burden of the management. Thus, the cloud computing service reflected the expectation as an alternative to reduce the investment and operational cost for IT infrastructure due to the recent economic crisis. The cloud computing service is not pervasive in the business world, but it is rapidly spreading all over the world, because of its inherited merits and benefits. Moreover, results of this research regarding the diffusion innovation are more or less different from those of the existing articles. This seems to be caused by the fact that the cloud computing service has a strong innovative factor that results in a new paradigm shift while most IT that are based on the theory of innovation diffusion are limited to companies and organizations. In addition, the participants in this study are believed to play an important role as innovators and early adapters to introduce the cloud computing service and to have competency to afford higher uncertainty for innovation. In conclusion, the introduction of the cloud computing service is a critical issue in the business world.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.4
• /
• pp.193-216
• /
• 2020

Due to the recent mid- to long-term slump and falling growth rates in the global economy, interest in organizational structures that create new products or services as a new alternative to survive and develop in an opaque environment both internally and externally, and enhance organizational sustainability through changes in production methods and business innovation is increasing day by day. In this atmosphere, we agree that the growth of small and medium-sized venture companies has a significant impact on the national economy, and various efforts are being made to enhance the technological innovation capabilities of the members so that these small and medium-sized venture companies can enhance and sustain their performance. The purpose of this study is also to investigate how the technological innovation capabilities of small and medium-sized venture companies correlate with the performance of knowledge management and to analyze the role of network capabilities to organize the strategic activities of enterprise to obtain the resources and organizational capabilities to be used for value creation from external networks. In other words, research was conducted on the impact of technological innovation capabilities of small and medium venture companies on knowledge management performance by using network capabilities as parameters. Therefore, in this study, we would like to verify the hypothesis that innovation capabilities will have a positive impact on knowledge management performance by using network capabilities of small and medium venture companies. Economic activities based on technological innovation capabilities should respond quickly to new changes in an environment where uncertainty has increased, and lead to macro-economic growth and development as well as overcoming long-term economic downturns so that they can become the nation's new growth engine as well as sustainable growth and survival of the organization. In addition, this study was conducted by setting the most important knowledge management performance within the organization as a dependent variable. As a result, R&D and learning capabilities among technological innovation capabilities have no impact on financial performance. In contrast, it was shown that corporate innovation activities have a positive impact on both financial and non-financial performance. The fact that non-financial factors such as quality and productivity improvement are identified in the management of small and medium-sized venture companies utilizing their technological innovation capabilities is contrary to a number of studies by those corporate innovation activities affect financial performance during prior research. The reason for this result is that research companies have been out of start-up companies for more than seven years, but sales are less than 10 billion won, and unlike start-up companies, R&D and learning capabilities have more positive effects on intangible non-financial performance than financial performance. Corporate innovation activities have been shown to have a positive (+) impact on both financial and non-financial performance, while R&D and learning capabilities have a positive (+) impact on financial performance by parameters of network capability. Corporate innovation activities have been shown to have no impact on both financial and non-financial performance, and R&D and learning capabilities have no impact on non-financial performance. It could be seen that the parameter effects of network competency are limited to when R&D and learning competencies are derived from quantitative financial performance. It could be seen that the parameter effects of network competency are limited to when R&D and learning competencies are derived from quantitative financial performance.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of Soil and Groundwater Environment
• /
• v.13 no.1
• /
• pp.77-91
• /
• 2008

In this study, we developed a technique of applying DRASTIC, which is the most widely used tool for estimation of groundwater vulnerability to the aqueous phase contaminant infiltrated from the surface, and a groundwater flow model jointly to assess groundwater contamination potential. The developed technique is then applied to Buyeo-eup area in Buyeo-gun, Chungcheongnam-do, Korea. The input thematic data of a depth to water required in DRASTIC model is known to be the most sensitive to the output while only a few observations at a few time schedules are generally available. To overcome this practical shortcoming, both steady-state and transient groundwater level distributions are simulated using a finite difference numerical model, MODFLOW. In the application for the assessment of groundwater vulnerability, it is found that the vulnerability results from the numerical simulation of a groundwater level is much more practical compared to cokriging methods. Those advantages are, first, the results from the simulation enable a practitioner to see the temporally comprehensive vulnerabilities. The second merit of the technique is that the method considers wide variety of engaging data such as field-observed hydrogeologic parameters as well as geographic relief. The depth to water generated through geostatistical methods in the conventional method is unable to incorporate temporally variable data, that is, the seasonal variation of a recharge rate. As a result, we found that the vulnerability out of both the geostatistical method and the steady-state groundwater flow simulation are in similar patterns. By applying the transient simulation results to DRASTIC model, we also found that the vulnerability shows sharp seasonal variation due to the change of groundwater recharge. The change of the vulnerability is found to be most peculiar during summer with the highest recharge rate and winter with the lowest. Our research indicates that numerical modeling can be a useful tool for temporal as well as spatial interpolation of the depth to water when the number of the observed data is inadequate for the vulnerability assessments through the conventional techniques.