• 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.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.2 no.1
• /
• pp.1-17
• /
• 1982

The stream morphological characteristics of a river basin has a close correlation with the hydrological and hydraulic characteristics of the basin. In this study the correlations of flow duration and Hydraulic geometry with the stream morphological characteristics as well as the correlation between flow duration and hydraulic geometry were analyzed bases on the data for the Geum River basin. The purpose of this study was to provide the necessary informations for water utilization projects at ungauged locations along the river course. First of all, the stream morphological characteristics was analyzed based on the Horton's three laws on the morphology of a stream that is, the law of stream number, the law of average stream length and the law of average stream slope. As is the case for majority of the rivers it was found that the Geum River basin was well developed according to the Horton's laws. High correlations were also found between the basin characteristics and the channel characteristics. The flow duration curves obtained with the daily stream flow data of 10~90% frequency of occurences at the five stage gauging stations in the Geum River could, in general, be expressed as an exponential functional relationship. The concept of proportional stream ordering system was employed to describe continuously the longitudinal variation of the stream morphological characteristics, and the mathematical model was formulated for the discharge-frequency-proportional stream order relationship. With the morphological characteristics as a common parameter the relationships with flow duration, drainage area were established in mathematical expressions, respectively.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.4
• /
• pp.71-80
• /
• 2009

Although desire for living without hazardous damages grows these days, threats from natural disasters which we are currently exposed to are quiet different from what we have experienced. To cope with this changing situation, it is necessary to assess the characteristics of the natural disasters. Therefore, the main purpose of this research is to suggest a methodology to estimate the potential property loss and assess the flood risk using a regional regression analysis. Since the flood damage mainly consists of loss of lives and property damages, it is reasonable to express the results of a flood risk assessment with the loss of lives and the property damages that are vulnerable to flood. The regional regression analysis has been commonly used to find relationships between regional characteristics of a watershed and parameters of rainfall-runoff models or probability distribution models. In our research, however, this model is applied to estimate the potential flood damage as follows; 1) a nonlinear model between the flood damage and the hourly rainfall is found in gauged regions which have sufficient damage and rainfall data, and 2) a regression model is developed from the relationship between the coefficients of the nonlinear models and socio-economic indicators in the gauged regions. This method enables us to quantitatively analyze the impact of the regional indicators on the flood damage and to estimate the damage through the application of the regional regression model to ungauged regions which do not have sufficient data. Moreover the flood risk map is developed by Flood Vulnerability Index (FVI) which is equal to the ratio of the estimated flood damage to the total regional property. Comparing the results of this research with Potential Flood Damage (PFD) reported in the Long-term Korea National Water Resources Plan, the exports' mistaken opinions could affect the weighting procedure of PFD, but the proposed approach based on the regional regression would overcome the drawback of PFD. It was found that FVI is highly correlated with the past damage, while PFD does not reflect the regional vulnerabilities.

• Journal of Korea Water Resources Association
• /
• v.56 no.2
• /
• pp.75-89
• /
• 2023

As the Mekong River basin is a nationally shared river, it is difficult to collect precipitation data, and the quantitative and qualitative quality of the data sets differs from country to country, which may increase the uncertainty of hydrological analysis results. Recently, with the development of remote sensing technology, it has become easier to obtain grid-based precipitation products(GPPs), and various hydrological analysis studies have been conducted in unmeasured or large watersheds using GPPs. In this study, rainfall-runoff simulation in the Mekong River basin was conducted using the SWAT model, which is a quasi-distribution model with three satellite GPPs (TRMM, GSMaP, PERSIANN-CDR) and two GPPs (APHRODITE, GPCC). Four water level stations, Luang Prabang, Pakse, Stung Treng, and Kratie, which are major outlets of the main Mekong River, were selected, and the parameters of the SWAT model were calibrated using APHRODITE as an observation value for the period from 2001 to 2011 and runoff simulations were verified for the period form 2012 to 2013. In addition, using the ConvAE, a convolutional neural network model, spatio-temporal correction of original satellite precipitation products was performed, and rainfall-runoff performances were compared before and after correction of satellite precipitation products. The original satellite precipitation products and GPCC showed a quantitatively under- or over-estimated or spatially very different pattern compared to APHPRODITE, whereas, in the case of satellite precipitation prodcuts corrected using ConvAE, spatial correlation was dramatically improved. In the case of runoff simulation, the runoff simulation results using the satellite precipitation products corrected by ConvAE for all the outlets have significantly improved accuracy than the runoff results using original satellite precipitation products. Therefore, the bias correction technique using the ConvAE technique presented in this study can be applied in various hydrological analysis for large watersheds where rain guage network is not dense.

• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.35-55
• /
• 2013

Information technology is a critical resource necessary for any company hoping to support and realize its strategic goals, which contribute to growth promotion and sustainable development. The selection of information technology and its strategic use are imperative for the enhanced performance of every aspect of company management, leading a wide range of companies to have invested continuously in information technology. Despite researchers, managers, and policy makers' keen interest in how information technology contributes to organizational performance, there is uncertainty and debate about the result of information technology investment. In other words, researchers and managers cannot easily identify the independent factors that can impact the investment performance of information technology. This is mainly owing to the fact that many factors, ranging from the internal components of a company, strategies, and external customers, are interconnected with the investment performance of information technology. Using an agent-based simulation technique, this research extracts factors expected to affect investment performance on information technology, simplifies the analyses of their relationship with economic modeling, and examines the performance dependent on changes in the factors. In terms of economic modeling, I expand the model that highlights the way in which product quality moderates the relationship between information technology investments and economic performance (Thatcher and Pingry, 2004) by considering the cost of information technology investment and the demand creation resulting from product quality enhancement. For quality enhancement and its consequences for demand creation, I apply the concept of information quality and decision-maker quality (Raghunathan, 1999). This concept implies that the investment on information technology improves the quality of information, which, in turn, improves decision quality and performance, thus enhancing the level of product or service quality. Additionally, I consider the effect of word of mouth among consumers, which creates new demand for a product or service through the information diffusion effect. This demand creation is analyzed with an agent-based simulation model that is widely used for network analyses. Results show that the investment on information technology enhances the quality of a company's product or service, which indirectly affects the economic performance of that company, particularly with regard to factors such as consumer surplus, company profit, and company productivity. Specifically, when a company makes its initial investment in information technology, the resultant increase in the quality of a company's product or service immediately has a positive effect on consumer surplus, but the investment cost has a negative effect on company productivity and profit. As time goes by, the enhancement of the quality of that company's product or service creates new consumer demand through the information diffusion effect. Finally, the new demand positively affects the company's profit and productivity. In terms of the investment strategy for information technology, this study's results also reveal that the selection of information technology needs to be based on analysis of service and the network effect of customers, and demonstrate that information technology implementation should fit into the company's business strategy. Specifically, if a company seeks the short-term enhancement of company performance, it needs to have a one-shot strategy (making a large investment at one time). On the other hand, if a company seeks a long-term sustainable profit structure, it needs to have a split strategy (making several small investments at different times). The findings from this study make several contributions to the literature. In terms of methodology, the study integrates both economic modeling and simulation technique in order to overcome the limitations of each methodology. It also indicates the mediating effect of product quality on the relationship between information technology and the performance of a company. Finally, it analyzes the effect of information technology investment strategies and information diffusion among consumers on the investment performance of information technology.

• Korean Journal of Social Welfare
• /
• v.64 no.2
• /
• pp.241-271
• /
• 2012

This questionnaire study examined the processes linking bicultural identity to self-positivity derived from taking multiple perspectives that, in turn, affects marital well-being among marriage immigrant women. Data were drawn from 281 marriage immigrant women residing in large cities in Korea including Seoul metropolitan area. Results of covariance structural analyses supported most study hypotheses: As predicted, bicultural identity contributed to self-positivity composed of taking multiple perspectives, self-acceptance and self-regulation, and the self-positivity, in turn, promoted marital well-being, conceptualized as marital satisfaction and marital stability. Bicultural identity also showd a significant direct positive effect on marital well-being. In path analyses conducted with observed variables, Korean cultural identity and home cultural identity both had significant positive effects on multiple perspective taking, through which these identity variables were positively related to self-acceptance and self-regulation. While self-acceptance was, as expected, positively related to marital satisfaction, thus indirectly promoting marital stability, the positive effect of self-regulation on marital stability was not signifiant. Taking multiple perspectives was found to promote marital well-being through encouraging both self-acceptance and consensus with a spouse. The effect of Korean cultural identity on marital well-being was found to be completely mediated by self-acceptance and consensus with a spouse fostered by taking multiple perspectives. In contrast, the effect of home cultural identity on marital well-being was partly mediated by such paths, and home cultural identity also had a positive direct effect on marital satisfaction and a negative direct effect on marital stability, suggesting its effect on marital well-being is complicated. Yet total effects of both types of cultural identity on marital well-being turned out to be positive. These results suggest that bicultural identity, supposed to be a psychological strength among marriage immigrant women, may indeed function as psychological resources that promote positive attitude as well as marital well-being. Finally, implications for multicultural social work practice are discussed.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.2
• /
• pp.125-137
• /
• 2018

Credit unions organized and operated by the members of communities, work-places or groups are co-operative entities where customers act as owners not just transaction partners. The foregoing organizational characteristic of credit unions exerts beneficial effects on their customer relationship, and underscores the need for diversifying their relationship marketing strategies. This study sheds light on the structural relationship of credit unions in terms of principal variables of relationship marketing, i.e. relationship benefits, customer satisfaction and long-term relationship orientation. Specifically, we classify the relationship benefits into three sub-dimensions, i.e. confidence benefits, social benefits and special treatment benefits, and structuralize a causal model involving the customer satisfaction and long-term relationship orientation. From December 26, 2017 to January 26, 2018, A total of 360 questionnaires was collected. Of these, 346 were selected as the final samples, excluding 14, which are difficult to use in statistics. The reliability analysis, exploratory factor analysis, and regression analysis was performed by using the 'SPSS 24.0'. And confirmatory factor analysis, structural equation model analysis was performed by using 'AMOS 24.0'. The findings highlight the following. First, confidence benefits directly impact on the long-term relationship orientation, and indirectly influence the latter by the medium of customer satisfaction. Second, social benefits directly influence the long-term relationship orientation, without exerting any indirect effects on the latter via customer satisfaction. Third, special treatment benefits do not directly impact on the long-term relationship orientation but have indirect effects on the latter by the medium of customer satisfaction. Fourth, customer satisfaction has positive effects on the long-term relationship orientation. The findings suggest credit unions should establish a long-term relationship with their customers by providing them with confidence benefits to earn their trust and confidence, with social benefits to build a relationship of affinity and friendship, and with special treatment benefits to meet their needs in the long, not short and temporary, term.

• Journal of Distribution Research
• /
• v.15 no.1
• /
• pp.1-24
• /
• 2010

I. Introduction The industry of domestic discount store was reorganized with 2 bigs and 1 middle, and then Home Plus took over Home Ever in 2008. In present, Oct, 2008, E-Mart has 118 outlets, Home Plus 112 outlets, and Lotte Mart 60 stores. With total number of 403 outlets, they are getting closer to a saturation point. We know that the industry of discount store has been getting through the mature stage in retail life cycle. There are many efforts to maintain existing customers rather than to get new customers. These competitions in this industry lead firms to acknowledge 'store loyalty' to be the first strategic tool for their sustainable competitiveness. In other words, the strategic goal of discount store is to boost up the repurchase rate of customers throughout increasing store loyalty. If owners of retail shops can figure out main factors for store loyalty, they can easily make more efficient and effective retail strategies which bring about more sales and profits. In this practical sense, there are many papers which are focusing on the antecedents of store loyalty. Many researchers have been inspecting causal relationships between antecedents and store loyalty; store characteristics, store image, atmosphere in store, sales promotion in store, service quality, customer characteristics, crowding, switching cost, trust, satisfaction, commitment, etc., In recent times, many academic researchers and practitioners have been interested in 'dual path model for service loyalty'. There are two paths in store loyalty. First path has an emphasis on symbolic and emotional dimension of service brand, and second path focuses on quality of product and service. We will call the former an extrinsic path and call the latter an intrinsic path. This means that consumers' cognitive path for store loyalty is not single but dual. Existing studies for dual path model are as follows; First, in extrinsic path, some papers in domestic settings show that there is 'store personality-identification-loyalty' path. Second, service quality has an effect on loyalty, which is a behavioral variable, in the mediation of customer satisfaction. But, it's very difficult to find out an empirical paper applied to domestic discount store based on this mediating model. The domestic research for store loyalty concentrates on not only intrinsic path but also extrinsic path. Relatively, an attention for intrinsic path is scarce. And then, we acknowledge that there should be a need for integrating extrinsic and intrinsic path. Also, in terms of retail industry, this study is meaningful because retailers want to achieve their competitiveness by using store loyalty. And so, the purpose of this paper is to integrate and complement two existing paths into one specific model, dual path model. This model includes both intrinsic and extrinsic path for store loyalty. With this research, we would expect to understand the full process of forming customers' store loyalty which had not been clearly explained. In other words, we propose the dual path model for discount store loyalty which has been originated from store personality and service quality. This model is composed of extrinsic path, discount store personality$\rightarrow$store identification$\rightarrow$store loyalty, and intrinsic path, service quality of discount store$\rightarrow$customer satisfaction$\rightarrow$store loyalty. II. Research Model Dual path model integrates intrinsic path and extrinsic path into one specific model. Intrinsic path put an emphasis on quality characteristics and extrinsic path focuses on brand characteristics. Intrinsic path is based on information processing perspective, and extrinsic path emphasizes symbolic and emotional dimension of brand. This model is composed of extrinsic path, discount store personality$\rightarrow$store identification$\rightarrow$store loyalty, and intrinsic path, service quality of discount store$\rightarrow$customer satisfaction$\rightarrow$store loyalty. Hypotheses are as follows; Hypothesis 1: Service quality perceived by customers in discount store has an positive effect on customer satisfaction Hypothesis 2: Store personality perceived by customers in discount store has an positive effect on store identification Hypothesis 3: Customer satisfaction in discount store has an positive effect on store loyalty. Hypothesis 4: Store identification has an positive effect on store loyalty. III. Results and Implications We examined consumers who patronize discount stores for samples of this study. With the structural equation model(SEM) analysis, we empirically tested the validity and fitness of the dual path model for store loyalty in discount stores. As results, the fitness indices of this model were well fitted to data obtained. In an intrinsic path, service quality(SQ) is positively related to customer satisfaction(CS), customer satisfaction(CS) has very significantly positive effect on store loyalty(SL). Also, in an extrinsic path, the store personality(SP) is positively related to store identification(SI), it shows significant effect on store loyalty. Table 1 shows the results as follows; There are some theoretical and practical implications. First, Many studies on discount store loyalty have been executed from various perspectives. But there has been no integrative view on this issue. And so, this research was theoretically designed to integrate various and controversial arguments into one systematic model. We empirically tested dual path model forming store loyalty, and brought up a systematic and integrative framework for future studies. We want to expect creative and aggressive research activities. Second, a few established papers are focused on the relationship between antecedents and store loyalty; store characteristics, atmosphere, sales promotion in store, service quality, trust, commitment, etc., There has been some limits in understanding thoroughly the formation process of store loyalty with a singular path, intrinsic or extrinsic. Beyond these limits in single path, we could propose the new path for store loyalty. This is meaningful. Third, discount store firms make and execute marketing strategies for increasing store loyalty. This research provides real practitioners with reference framework needed for actual strategy formation. Because this paper shows integrated and systematic path for store loyalty. A special feature of this study is to represent 6 sub dimensions of service quality in intrinsic path and 4 sub dimensions of store personality in extrinsic path. Marketers can make more analytic marketing planning with concrete sub dimensions of service quality and store personality. When marketers of discount stores make strategic planning like MPR, Ads, campaign, sales promotion, they can use many items which are more competitive than competitors.

• Journal of Korea Water Resources Association
• /
• v.41 no.11
• /
• pp.1107-1121
• /
• 2008

The simple equation of GIUH are frequently used in many researches instead of the derived equation of GIUH. However it is still unknown whether the simple equation of GIUH is adaptable for estimating IUHs for basins with various geomorphologic conditions. To verify the applicability of the simple equation of GIUH, in this research, four basins which were Bangrim, Sanganmi, Museong, and Byeongcheon were selected and each basin was assumed as the third and fourth stream order basin according to variable resolutions. After than, IUHs were estimated using the derived and simple equations of GIUH. Eight to sixteen hydrographs were estimated from the each IUH, compared with observed graphs. In case of that the basin is assumed as a third order stream, the derived equation underestimated the peak flows while the simple equation overestimated them. When the basin is assumed as a fourth order stream, the simple equation generally overestimated the peak flows whereas the derived equation produced peak flows good agreement with the observed peak flow. Moreover, the simple equation showed various deviations in accuracy whereas the derived equation produced stable results. Based on the fact found from this research, it can be concluded that the derived equation of GIUH brings better results than the simple equation of GIUH to estimate IUHs for ungauged basins.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.397-406
• /
• 2016

This study structurally analyzes the relations between children's pet attachment, empathy ability, and prosociality. The results are used to investigate the relations between pet attachment and empathy ability, which have recently emerged as important variables that affect children's prosociality. Data were collected about pet attachment, empathy ability, and prosociality from 209 elementary students in Daejeon who had experience with raising pets. SPSS 22.0 software was used for descriptive statistical analysis, correlation analysis, and reliability analysis, and AMOS 22.0 was used for confirmatory factor analysis and to examine the structural equation model. According to the analyses, children's pet attachment did not affect their prosociality but did influence their empathy ability. Children's empathy ability affected their prosociality and had a mediating effect on the relation between their pet attachment and prosociality. The results indicate that children's pet attachment and empathy ability are essential factors that influence prosociality. To improve prosociality, efforts should be made increase pet attachment and empathy ability. The study results can be used as a theoretical and practical fundamental basis for plans to improve children's pet attachment, empathy ability, and prosociality.