• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.143-163
• /
• 2016

The demographics of Internet users are the most basic and important sources for target marketing or personalized advertisements on the digital marketing channels which include email, mobile, and social media. However, it gradually has become difficult to collect the demographics of Internet users because their activities are anonymous in many cases. Although the marketing department is able to get the demographics using online or offline surveys, these approaches are very expensive, long processes, and likely to include false statements. Clickstream data is the recording an Internet user leaves behind while visiting websites. As the user clicks anywhere in the webpage, the activity is logged in semi-structured website log files. Such data allows us to see what pages users visited, how long they stayed there, how often they visited, when they usually visited, which site they prefer, what keywords they used to find the site, whether they purchased any, and so forth. For such a reason, some researchers tried to guess the demographics of Internet users by using their clickstream data. They derived various independent variables likely to be correlated to the demographics. The variables include search keyword, frequency and intensity for time, day and month, variety of websites visited, text information for web pages visited, etc. The demographic attributes to predict are also diverse according to the paper, and cover gender, age, job, location, income, education, marital status, presence of children. A variety of data mining methods, such as LSA, SVM, decision tree, neural network, logistic regression, and k-nearest neighbors, were used for prediction model building. However, this research has not yet identified which data mining method is appropriate to predict each demographic variable. Moreover, it is required to review independent variables studied so far and combine them as needed, and evaluate them for building the best prediction model. The objective of this study is to choose clickstream attributes mostly likely to be correlated to the demographics from the results of previous research, and then to identify which data mining method is fitting to predict each demographic attribute. Among the demographic attributes, this paper focus on predicting gender, age, marital status, residence, and job. And from the results of previous research, 64 clickstream attributes are applied to predict the demographic attributes. The overall process of predictive model building is compose of 4 steps. In the first step, we create user profiles which include 64 clickstream attributes and 5 demographic attributes. The second step performs the dimension reduction of clickstream variables to solve the curse of dimensionality and overfitting problem. We utilize three approaches which are based on decision tree, PCA, and cluster analysis. We build alternative predictive models for each demographic variable in the third step. SVM, neural network, and logistic regression are used for modeling. The last step evaluates the alternative models in view of model accuracy and selects the best model. For the experiments, we used clickstream data which represents 5 demographics and 16,962,705 online activities for 5,000 Internet users. IBM SPSS Modeler 17.0 was used for our prediction process, and the 5-fold cross validation was conducted to enhance the reliability of our experiments. As the experimental results, we can verify that there are a specific data mining method well-suited for each demographic variable. For example, age prediction is best performed when using the decision tree based dimension reduction and neural network whereas the prediction of gender and marital status is the most accurate by applying SVM without dimension reduction. We conclude that the online behaviors of the Internet users, captured from the clickstream data analysis, could be well used to predict their demographics, thereby being utilized to the digital marketing.

• Korean Business Review
• /
• v.21 no.2
• /
• pp.137-170
• /
• 2008

This study is presenting the logistics strategy in the international logistics markets which makes competition and corporation among north-east Asian countries to establishing the multi-pass Eurasian railroads. The countries located in north-east area of Eurasia like China, Japan, Russia and Korea are paying higher costs and disutility to the transportations and communications due to repeated conflicts and confrontations causes from the politic problems. They are being used surface transportation for most of all logistics between Europe and Asia except special merchandises because of characteristic of cargo to be air, the Silk Road remains vestige only which was main logistic passage to this area since BC. So far the Trans-Siberian Railway is being used by Russia mostly as north of Eurasian transport because of difficulties of service. The Trans-China Railway built in 1992 is not accomplishing as a international logistic passages. It is expected to take a long lead time because of characteristic of resource development and poor logistic infrastructure to the countries like Uzbekistan, double landlocked country, Mongolia and Azerbaijan, the countries do not be adjacent to the sea, even they have great economic jump-up plans through the development of their own resources. The Shanghai Cooperation Organization(SCO) start to sail officially in 2001 is constructed with China, Russia, Tadzhikistan, Kyrgyzstan, Kazakhstan and Uzbekistan as regular members of 6 countries and Mongolia, India, Pakistan, Afghanistan and Iran as observers 5 countries. It is started as a military alliance to protect terror, but now, it is expended to cooperate with the traffic, transportation, trade and share of energies. The Russia is doing their best to activate TSR as a government target to developnorth area equivalently, and economic develop of far-east Siberia. And also it is agreed provisionally to improve and repair of rail road between Nahjin and Hassan to connect TSR and TKR( Trans-Korea Railroad) by Russia, North Korea and South Korea with Russian's aggressive efforts. The development plan of this area is over lapped with GTI(Greater Tumen Initiative) promoted by UNDP, and is a cooperated project by 5 countries of South Korea, Mongolia, China, Russia and North Korea, subject to review the appropriation of energy, tour, environment, rail road connection between Mongolia and China and establishing a ferry route to north-east Asia. It is Japanese situation to pay attention to Russia and China even they have been supplying large-scope of infrastructure in Mongol area without any charges, target to get East Asia Main Rail Road to connect Mongolia and Zalubino of Russia. In case of the program for the Denuclearization of North Korea is not creeping, it will be accelerated to connect the TKR and TSR, TKR and TCR by somehow attending United States, including developing program promoted by UN ESCAP. As the result, Korean peninsular will continue the central role of competition and cooperation as in the past, now and future of north-east Asia, as of geographical-economics and geographical-politics whether it is requested or not wanted by neighbor countries.

• The Korean Journal of Air & Space Law and Policy
• /
• v.35 no.2
• /
• pp.247-280
• /
• 2020

For customs-free and liberalization on the trade of aircraft parts, the WTO Agreement on Trade in Civil Aircraft was separately concluded as plurilateral trade agreement at the time of launching WTO in 1995, and currently 33 countries including the United States and the EU are acceded but Korea does not. Major details of the Agreement on Trade in Civil Aircraft include product coverage, the elimination of customs duties and other charges, the prohibition of government-directed procurement of civil aircraft, the application of the Agreement on Subsides and Countervailing Measures, and the consultation on issues related to this Agreement and dispute resolution. Article 89 paragraph 6 of the current Customs Act was newly established on December 31, 2018, and the tariff reduction rate for imports of aircraft parts will be reduced in stages from May 2019 and the tariff reduction system will be abolished in 2026. Accordingly, looking at the impact of the Agreement on Trade in Civil Aircraft on the aviation industry, first, as for the impact on the air transport industry, an tariff allotment of the domestic air transport industry is expected to reach about 160 billion won a year from 2026, and upon acceding to the Agreement on Trade in Civil Aircraft, the domestic air transport industry will be able to import aircraft parts at no tariff, so it will not have to pay 3 to 8 percent import duties. Second, as for the impact on the aviation MRO industry, if the tariff reduction system for aircraft parts is phased out or abolished in stages, overseas outsourcing costs in the engine maintenance and parts maintenance are expected to increase, and upon acceding to the Agreement on Trade in Civil Aircraft, the aviation MRO industry will be able to import aircraft parts at no tariff, so it will reduce overseas outsourcing costs. If the author proposes a policy direction for the trade liberalization of aircraft parts to ensure competitiveness of the aviation industry, first, as for the tariff reduction by the use of FTA, in order to be favored with the tariff reduction by the use of FTA, it is necessary to secure the certificate of origin from foreign traders in the United States and the EU, and to revise the provisions of Korea-Singapore and Korea-EU FTA. Second, as for the push of acceding to the Agreement on Trade in Civil Aircraft, it would be resonable to push the acceding to Agreement on Trade in Civil Aircraft for customs-free on the trade of aircraft parts, as the tariff reduction method by the use of FTA has limits. Third, as for the improvement of the tariff reduction system for aircraft parts under the Customs Act, it is expected that there will take a considerable amount of time until the acceding to the Agreement on Trade in Civil Aircraft, so separate improvement measures are needed to continue the tariff reduction system of aircraft parts under Article 89 paragraph 6 of the Customs Act. In conclusion, Korea should accede to the WTO Agreement on Trade in Civil Aircraft to create an environment in which our aviation industry can compete fairly with foreign aviation industries and ensure competitiveness by achieving customs-free and liberalization on the trade of aircraft parts.

• Journal of Technologic Dentistry
• /
• v.17 no.1
• /
• pp.41-57
• /
• 1995

This study was conducted to collect and analyze previous information in order to manage efficience, improve experience effect and promote employment rate. The questionnaire interview with 27 chief of dental Laboratory refered clinical experience in technology department about clinical experience in 14 Jumior colleges were also investigated. The results were summarried as follows : The portion of age of 35-39 among chief of dental Laboratory was 40.7% which was the highest, that of male was 96.3%, that of junior college graduate was 97.5%, that of 10years experience was 92.6% and that of ceramic technician was 85.2%, 63.0% dental laboratory for clinical experience was a bore space of 30pyong. Aspect of dental laboratory management, manufacturing all part of prosthetic restoration was 29.6%, othodontic appliance and ceramic restoration was 7.4%, 3.8%, each. The percentage of 40.7 was having connection with 30-3a dental clinics and referring case per day was 10-19 cases(40.7%), manufacturing time of referred prosthetic restoration was 3-4 days(77.8%), places preparing seminar room for education was 29.6%, above a place of 40pyong was 11.1% 30-34 pyong and 35-39 pyong was 7.4% each. During training of 2 years education course student, 18.5% was rack of thorough occupational career. While 44.4% will want the more salary among 3years education course student, 74.1% will expect the more dental techmicians would engaged in their field, 51.9% will hope improve of their theory and practice, 29.6% be expected better skill and 14.8% be expected better theory. Attitude of clinical experience places was distributed by 59.3% of offering only experience chance, 25.9% of wasting time and 29.0% of annoying. The big emphasis of climical experience was thorough occupational career(44.4%). The clinical experience places of our college were selected after direct visiting, so their condition of management was not that bad but most of dental laboratory were poor in management state and working environment. Therefore it is difficult to choose appropriate places and dental Laboratory are also limited manpower and time as suppliers. So that it recommended to induce flexible management of experience period by interval and rotation of experience places among college and to applicate intern-system for employment ant industry-college cooperation aspect.

• Solar Energy
• /
• v.13 no.2_3
• /
• pp.65-78
• /
• 1993

An overdose of fossil fuel for greenhouse heating causes not only the high cost and low quality of agricultural products, but also the environmental pollution of farm village. To solve these problems it is desirable to maximize the solar energy utilization for the heating of greenhouse in winter season. In this study phase change materials were selected to store solar energy concentratively for heating the greenhouse and their characteristics of thermal energy storage were analyzed. The results were summarized as follows. The organic $C_{28}H_{58}$, and the inorganic $CH_3COONa{\cdot}3H_2O\;and\;Na_2SO_4{\cdot}10H_2O$ were selected as low temperature latent heat storage materials. The equation of critical radius was derived to define the generating mechanism of the maximum latent heat of phase change materials. The melting point of $C_{28}H_{58}$ was $62^{\circ}C$, and the latent heat was $50.0{\sim}52.0kcal/kg$. The specific heat of liquid and solid phase was $0.54{\sim}0.69kcal/kg^{\circ}C$ and $0.57{\sim}0.75kcal/kg^{\circ}C$ respectively. The melting point of $CH_3COONa{\cdot}3H_2O$ was $61{\sim}62^{\circ}C$, the latent heat was $64.9{\sim}65.8$ kcal/kg and the specific heat of liquid and solid phase was respectively $0.83kcal/kg^{\circ}C$ and $0.51{\sim}0.52kcal/kg^{\circ}C$. The melting point of $Na_2SO_4{\cdot}10H_2O$ was $30{\sim}30.9^{\circ}C$, the latent heat was 53.0 kcal/kg and the specific heat of liquid and solid phase was respectively $0.78{\sim}0.89kcal/kg^{\circ}C$ and $0.50{\sim}0.7kcal/kg^{\circ}C$ When the urea of 21.85% was added to control the melting point of $Na_2SO_4{\cdot}10H_2O$ and the phase change cycles were repeated from 0 to 600, the melting point was $16.7{\sim}16.0^{\circ}C$ and the latent heat was $36.0{\sim}28.0kcal/kg^{\circ}C$.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.34 no.5
• /
• pp.536-544
• /
• 2001

Three harmful algal bloom species with similar morphology, Cochlodinium polykrikoides, Gyodinium impudicum and Gymodinium catenatum have damaged to aquatic animals or human health by either making massive blooms or intoxication of shellfishes in a food chain. Eco-physiological and hydrodynamic studies on the harmful algae offer useful informations in the understanding their bloom mechanism by giving promising data for the prediction and modelling of harmful algal blooms event. Thus, we studied the abundance of these species in the coastal area of South Sea of Korea and their effects of temperature, salinity, irradiance and nutrient on the growth for the isolates. The timing for initial appearance of the three species around the coastal area of Namhaedo, Narodo and Wando was between Bate July and late August in 1999 when water temperature ranged from $22.8^{\circ}C\;to\;26.5^{\circ}C$ Vegetative cells of C. polykrikoides and G. impudicum were abundant until late September when water temperature had been dropped to less than $23^{\circ}C$. By contrast, vegetative cell of G. catenatum disappeared before early September, showing shorter period of abundance than the other two species in the South Sea. Both G. impudicum and G. catenatum revealed comparatively low density with a maximal cell density of 3,460 cells/L and 440 cells/L, respectively without making any bloom, while C. polykrikoides made massive blooms with a maximal cell density more than $40\times10^6$cells/L, The three species showed a better growth at the relatively higher water temperature ranging from 22 to $28^{\circ}C$ with their maximal growth rate at $25^{\circ}C$ in culture, which almost corresponded with the water temperature during the outbreak of C. polykrikoides in the coastal area of South Sea. Also, they all showed a relatively higher growth at the salinity from 30 to $35\%$. Specially, G. impudicum showed the euryhalic characteristics among the species, On the other hand, growth rate of G. catenatum decreased sharply with the increase of water temperature at the experimental ranges more than $35\%$. The higher of light intensities showed the better growth rates for the three species, Moreover, C. polykrikoides and G. impudirum continued their exponential growth even at 7,500 lux, the highest level of light intensity in the experiment, Therefore, It is assumed that C. polykrikoides has a physiological capability to adapt and utilize higher irradiance resulting in the higher growth rate without any photo inhibition response at the sea surface where there is usually strong irradiance during its blooming season. Although C. poiykikoides and G. impudicum continued their linear growth with the increase of nitrate ($NO_3^-$) and ammonium ($NH_4^-$) concentrations at less than the $40{\mu}M$, they didn't show any significant differences in growth rates with the increase of nitrate and ammonium concentrations at more than $40{\mu}M$, signifying that the nitrogen critical point for the growth of the two species stands between 13.5 and $40{\mu}M$. Also, even though both of the two species continued their linear growth with the increase of phosphate ($PO_4^{2-}$) concentrations at less than the $4.05{\mu}M$, there were no any significant differences in growth rates with the increase of phosphate concentrations at more than $4.05{\mu}M$, signifying that the phosphate critical point for the growth of the two species stands between 1.35 and $4.05{\mu}M$. On the other hand, C. polykrikoides has made blooms at the oligotrophic environment near Narodo and Namhaedo where the concentration of DIN and DIP are less than 1.2 and $0.3{\mu}M$, respectively. We attributed this phenomenon to its own ecological characteristics of diel vertical migration through which C. polykrikoides could uptake enough nutrients from the deep sea water near bottom during the night time irrespective of the lower nutrient pools in the surface water.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• Clinical and Experimental Pediatrics
• /
• v.45 no.3
• /
• pp.346-353
• /
• 2002

Purpose : Penicillin- and multidrug-resistant S. pneumoniae poses a serious threat to clinicians because the rate of resistance of S. pneumoniae to penicillin in Korea has surged up to the world's highest level. This study was performed to assess the carriage rate, serogroups and antimicrobial susceptibility of S. pneumoniae isolated from oropharynx in children. Methods : From March to July 1998, 209 children under 5 years of age were recruited from five day care centers. The carriage rate for pneumococci was obtained. Antimicrobial susceptibilities were determined with the E-test and agar dilution methods. Serogrouping was performed on 48 of the pneumococcal isolates by the Quellung reaction. Results : The carriage rate of S. pneumoniae was 30.1%. Antimicrobial susceptibility profiles were available for 59 of the isolates. Sixty-six percent of isolates were not susceptible to penicillin, and multidrug-resistance was observed in 76.3% of the isolates. A high proportion of the penicillin-resistant strains showed associated resistance to trimethoprim-sulfamethoxazole, tetracycline, erythromycin, and oxacillin. The most prevalent oropharyngeal serogroups were 19, 6, 3, 23, and 29. Resistance of the pneumococcal isolates to penicillin was different according to the serogroups. All of the strains of serogroup 19, 23, and 29 was resistant to penicillin but 87.5% of serogroup 3 strains were susceptible to penicillin. Conclusion : The resistance rate of S. pneumoniae isolated from oropharynx in children was very high to penicillin and other antimicrobial agents. For the reduction of the drug-resistant rate of S. pneumoniae, clinicians should be required to be more judicious in their use of antimicrobial agents.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• 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.