• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.5 no.4
• /
• pp.320-334
• /
• 2000

Deep-sea surface sediment were analyzed for their geotechnical properties, and the sediment samples were collected with a multiple-corer from 31 stations along the track line (131$^{\circ}$30'W, 5-12$^{\circ}$N) in the northeast equatorial Paciflc. Most of the sediments from the northern part (8-12$^{\circ}$N) showed typical properties of siliceous sediments, whereas the southern part (5-6$^{\circ}$N) showed calcareous characteristics due to high biogenic carbonate productivity in the surface waters, where its water depth was shallower than the carbonate compensation depth (CCD: 4,400 m). Geotechnical properties changed sharply at the boundary of 7$^{\circ}$N. Calcareous sediments from the southern part had low water contents, low porosity, low shear strength, high bulk density and high specific grain density, whereas siliceous sediments from the northern part attained high water content, high porosity, high shear strength, low bulk density and low specific grain density. Higher sediment activities were observed in the northern sediment samples than the southern sediment samples. The core samples of the northern sediments were divided into a semi-liquid upper layer and a consolidated lower layer with a boundary at 5-8 cm. These sediment samples showed a rapid increasing pattern along the downcore in original shear strength when an opposite trend was observed in the southern samples. The results showed that sediment variabilities in geotechnical properties between the northern and southern parts such as productivities of surface water, grain solubility due to water depth variation, sedimentation rate, erosion and redistribution of sediment, and combined sedimentary processes were distinctly different along the latitude.

• Journal of the Korean Wood Science and Technology
• /
• v.14 no.1
• /
• pp.3-44
• /
• 1986

In order to obtain the basic physical and mechanical properties of steel wire reinforced particleboard, particleboards were formed with large particles through 2.11 mm (12 meshes) and retained on 1.27mm (20 meshes) sieves and small particles through 1.27mm (20 meshes) and retained on 0.42mm (60 meshes) sieves from the plywood mill wastes of meranti (Shorea spp.) in the form of pallmanchips, applying urea-formaldehyde resin as an adhesive on the particle surface in 10 percent on the oven dried weight of particles, and arranging steel wires of 1mm in diameter 5,10,15,20, and 25mm in longitudinal and transverse direction with crossing in the mid of the board depth in single layer boards, 10mm in longitudinal or transverse direction without crossing in two layers and 10mm in longitudinal and transverse directions with and without crossing in three steel wire layers boards. The stepwise 9-minutes-multi-pressing schedule in 5 minutes at 35 kgf/$cm^2$, 2.5 minutes at 25 kgf/$cm^2$. and 1.5 minutes at 15 kgf/$cm^2$ was applied for $300{\times}200{\times}13$mm board at the temperature of 160$^{\circ}C$ in a hot press. Specific gravity, thickness swelling, bending properties of modulus of rupture (MOR), modulus of elasticity(MOE), work to proportional limit, and work to ultimate load, internal bond (IB), and screw holding power(SHP) of the reinforced boards were analyzed on the wire openings and wire layers. The results obtained are summarized as follows; 1) In specific gravity, particleboards with large particles and small particles had higher value with more steel wire placements and more steel layers composition, 2) Particleboards with large particles in accordance with more steel wire liners composition gave very poor thickness swelling. 3) The mechanical properties of particleboards formed with large or small particles were reinforced with more steel wire layers. Therefore, bending strength was improved in modulus of rupture, modulus of elasticity, and work to ultimate load. Especiallv, particleboards with two or three steel wire layers showed the tension lamination effect when the steels in lower steel wire layer were oriented parallel to the board length. 4) The modulus of rupture, modulus of elasticity, and work to ultimate load in bending varied with opening area, distance of lengthwise wires multipled by distance of transverse wires. Particleboards formed with large particles resulted in higher value in modulus of rupture with 1.5-3 $cm^2$ opening area, 1-2cm distance between transverse wires, and 1.5-2.5cm distance between lengthwise wires. Particle boards formed with small particles showed higher value with 0.5-1.5$cm^2$ or 3.75-6.25 $cm^2$ opening area, 0.5 or 2.5cm distance between transverse wires. 5) In modulus of elasticity, particleboards formed with large particles with one steel wire layer suggested higher value with 5-3$cm^2$ opening area, 1-2.5cm distance between transverse wires and also 1-2.5 cm distance between lengthwise wires. Particleboards formed with small particles showed higher value with 0.75-1.25$cm^2$ or 3-6.25$cm^2$ opening area and 0.5 or 2.5cm distance between transverse wires. 6) Particleboards formed with large particles gaved higher value in work to ultimate load with 1-3$cm^2$ opening area. Particleboards formed with small particles showed increasing tendancy with decreasing opening area. 7) In internal bond and screw holding power, particleboards formed with large particles had increasing value in two and three steel wire layers compositions, but particleboards formed with small particles showed no difference. Particleboards formed with large particles containing one steel wire layer showed no difference in internal bond and screw holding power, and particleboards formed with small panicles containing one steel wire layer resulted in increasing value in internal bond and decreasing value in screw holding power in accordance with increase in opening area.

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2013.11a
• /
• pp.23-24
• /
• 2013

Micrometeorological fluxes measured over a tall forest in a complex terrain are difficult to interpret. $CO_2$ storage often makes significant contributions to net ecosystem exchange of $CO_2$ (NEE) in early morning and during nighttime due to calm and stable conditions. We measured the above-canopy $CO_2$ flux along with its concentration profiles at eight levels within and above the canopy to evaluate $CO_2$ storage term. Our question is whether or not the $CO_2$ storage term can be estimated accurately from a single level measurement of $CO_2$ concentration in a complex terrain. Our objectives are (1) to document vertical profiles of $CO_2$ concentration and (2) to compare the diurnal and seasonal variations of $CO_2$ storages estimated from single and multi-level $CO_2$ concentration data. Seasonally averaged Diurnal variations of $CO_2$ concentration ranged from 398 to 455 ppm near the forest floor at 0.1 m whereas they ranged from 364 to 395 ppm at 40 m in the atmosphere. The diurnal variation of vertical profiles of $CO_2$ concentration shows very interesting features with season. At all eight levels, diurnal variation of $CO_2$ concentration showed little change in winter. In spring, the diurnal variations of $CO_2$ concentration at 8 levels showed three distinct groups of layers with height: the first layer: 0.1m (near surface), second layer: 1.0 m and 4.0m (below canopy) and the third layer: 7.4m to 40.7 m (near canopy and above). In summer, these three groups of layers were further separated with larger variations whereas such distinction became smaller in fall. The diurnal variation of $CO_2$ concentration in the first three layers near surface always showed higher concentration with larger variability. Typically, $CO_2$ concentration showed peaks in early morning and in the evening. After the evening peak, $CO_2$ concentration gradually increased except for those near the surface (i.e., 0.1, 1.0 and 4.0 m) where the concentrations actually decreased. We suspect that this could be attributed to the drainage flow of $CO_2$ along the hill slope from the headwater to downstream, which is not taken into account for net ecosystem $CO_2$ exchange. In comparison to the results of other studies, the distinct and different vertical structures of $CO_2$ concentrations observed at our site may be due to complex terrain and weak turbulent mixing under calm conditions at the site. The annual mean of diurnal variation of $CO_2$ storage flux from single level ranged from -0.6 to $0.9{\mu}mol\;m^{-2}s^{-1}$ and from multi-level from -1.2 to $1.0{\mu}\;{\mu}mol\;m^{-2}s^{-1}$. When compared against the results from the multi-level concentrations, the storage flux estimated from a single-level concentration was generally adequate except for specific hours near sunrise and sunset. Further details and their implication will be discussed in the presentation.

• Korean Journal of Poultry Science
• /
• v.50 no.4
• /
• pp.303-310
• /
• 2023

The current study was conducted to compare the effect of crossbred on the body weight and laying performance of Korean native chicken from hatch to week 40. A total of 873 one-day-old chicks were divided into twelve crossbreds (i.e., CFCK, CFYC, CFYD, CKCF, CKYC, CKYD, YCYD, YCCF, YCCK, YDCF, YDCK, and YDYC) and commercial layer (Hy-Line Brown) were obtained as a counterpart in the study. All the birds are raised in battery cages (76 × 61 × 46 cm³) and then raised until 14 weeks and subsequently moved to layer battery cages (60 × 25 × 45 cm³) and raised until 16 weeks. The body weight and viability were measured biweekly from hatching to week 16. The week of 16, body weight range was about 1,010.24 to 1,411.77 g. The body weight of specific crossbreeds (i.e., CKCF, YCYD, and YDYC) was found to be comparable to that of Hy-Line Brown). The viability hatch to week 14 range was about 55 to 100% and however week 14 to 16 range was 80 to 100%. The crossbred (i.e., CKCF) recorded superior (P<0.05) viability throughout the whole experiment period, even compared with Hy-Line Brown (100% vs 96%). Our results are indicating that crossbreds Korean native chicken including CKCF, and YDYC has the potential to enhance key features of laying hens during the growing phase like optimal body weight and higher viability.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.193-215
• /
• 2016

In recent years, the proliferation of diverse social networking services has led users to use many mediums simultaneously depending on their individual purpose and taste. Besides, while collecting information about particular themes, they usually employ various mediums such as social networking services, Internet news, and blogs. However, in terms of management, each document circulated through diverse mediums is placed in different categories on the basis of each source's policy and standards, hindering any attempt to conduct research on a specific category across different kinds of sources. For example, documents containing content on "Application for a foreign travel" can be classified into "Information Technology," "Travel," or "Life and Culture" according to the peculiar standard of each source. Likewise, with different viewpoints of definition and levels of specification for each source, similar categories can be named and structured differently in accordance with each source. To overcome these limitations, this study proposes a plan for conducting category mapping between different sources with various mediums while maintaining the existing category system of the medium as it is. Specifically, by re-classifying individual documents from the viewpoint of diverse sources and storing the result of such a classification as extra attributes, this study proposes a logical layer by which users can search for a specific document from multiple heterogeneous sources with different category names as if they belong to the same source. Besides, by collecting 6,000 articles of news from two Internet news portals, experiments were conducted to compare accuracy among sources, supervised learning and semi-supervised learning, and homogeneous and heterogeneous learning data. It is particularly interesting that in some categories, classifying accuracy of semi-supervised learning using heterogeneous learning data proved to be higher than that of supervised learning and semi-supervised learning, which used homogeneous learning data. This study has the following significances. First, it proposes a logical plan for establishing a system to integrate and manage all the heterogeneous mediums in different classifying systems while maintaining the existing physical classifying system as it is. This study's results particularly exhibit very different classifying accuracies in accordance with the heterogeneity of learning data; this is expected to spur further studies for enhancing the performance of the proposed methodology through the analysis of characteristics by category. In addition, with an increasing demand for search, collection, and analysis of documents from diverse mediums, the scope of the Internet search is not restricted to one medium. However, since each medium has a different categorical structure and name, it is actually very difficult to search for a specific category insofar as encompassing heterogeneous mediums. The proposed methodology is also significant for presenting a plan that enquires into all the documents regarding the standards of the relevant sites' categorical classification when the users select the desired site, while maintaining the existing site's characteristics and structure as it is. This study's proposed methodology needs to be further complemented in the following aspects. First, though only an indirect comparison and evaluation was made on the performance of this proposed methodology, future studies would need to conduct more direct tests on its accuracy. That is, after re-classifying documents of the object source on the basis of the categorical system of the existing source, the extent to which the classification was accurate needs to be verified through evaluation by actual users. In addition, the accuracy in classification needs to be increased by making the methodology more sophisticated. Furthermore, an understanding is required that the characteristics of some categories that showed a rather higher classifying accuracy of heterogeneous semi-supervised learning than that of supervised learning might assist in obtaining heterogeneous documents from diverse mediums and seeking plans that enhance the accuracy of document classification through its usage.

• The Korean Journal of Archival Studies
• /
• no.45
• /
• pp.219-253
• /
• 2015

The Records Management System in Japan has been developed to a comprehensive and unitary records management system based on the records life-cycle principle from the enactment of 'the Public Records and Archives Management Act' in 2009 and its implementation in April, 2011. The scope of objects has also been extended to documents of independent administrative institutions and specific confidential documents on diplomacy and defense. In addition, a series of Electronic Documents Management Systems have been built for the transfer of electronic records to the National Archives of Japan, which is called the Electronic Records Archives of Japan, in connection with the records and archives management systems covering creation, management, transfer, preservation, and use of electronic records. This paper deals with the core contents and characteristics of the records management system of Japan, focusing on the operational structure of the records and archives management law and electronic documents management. Firstly, The Cabinet Office and professional groups in records and archives management started to work on reformation of the records management system from 2003 and resulted in enactment of the Public Records and Archives Management Act in 2009. In that sense, the Public Records and Archives Management Act can be evaluated as a result of constant activities of the records management community in Japan for realization of accountabilities of government agencies to the general public. Secondly, the Public Records Management Act of Japan has a coherent multi-layer structure from the law, enforcement ordinances, guidelines, and to institutional documents management regulations in the operational system. This is a systematic structure for providing practical business units of each administrative agency with detailed standards on the basis of guidelines and making them to prepare their own specific application standards related to their unique businesses. Unlike the past, the National Archives of Japan became to be able to identify specific historial documents which should be transferred to the archives by selecting important historical records as early as possible after creating and receiving them in each institution through the retention schedule. Thirdly, Japan started to operate a system in regard to electronic records transfer and preservation in 2011. In order to prepare for it, each administrative agency has used EDMS in creation and management of electronic records. A Guideline for the Standard Format and Media released by the Cabinet Office in 2010 is also for the transfer of electronic records to the Electronic Records Archives of Japan. In future, it is necessary to conduct further studies on activities of the records and archives management community in Japan, relating to long-term preservation and use of electronic records.

• 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 Korean Society of Forest Science
• /
• v.66 no.1
• /
• pp.16-36
• /
• 1984

It is very important in forestry to study the shear strength of weathered granitic soil, because the soil covers 66% of our country, and because the majority of land slides have been occured in the soil. In general, the causes of land slide can be classified both the external and internal factors. The external factors are known as vegetations, geography and climate, but internal factors are known as engineering properties originated from parent rocks and weathering. Soil engineering properties are controlled by the skeleton structure, texture, consistency, cohesion, permeability, water content, mineral components, porosity and density etc. of soils. And the effects of these internal factors on sliding down summarize as resistance, shear strength, against silding of soil mass. Shear strength basically depends upon effective stress, kinds of soils, density (void ratio), water content, the structure and arrangement of soil particles, among the properties. But these elements of shear strength work not all alone, but together. The purpose of this thesis is to clarify the characteristics of shear strength and the related elements, such as water content ($w_o$), void ratio($e_o$), dry density (${\gamma}_d$) and specific gravity ($G_s$), and the interrelationship among related elements in order to decide the dominant element chiefly influencing on shear strength in natural/undisturbed state of weathered granitic soil, in addition to the characteristics of soil hardness of weathered granitic soil and root distribution of Pinus rigida Mill and Pinus rigida ${\times}$ taeda planted in erosion-controlled lands. For the characteristics of shear strength of weathered granitic soil and the related elements of shear strength, three sites were selected from Kwangju district. The outlines of sampling sites in the district were: average specific gravity, 2.63 ~ 2.79; average natural water content, 24.3 ~ 28.3%; average dry density, $1.31{\sim}1.43g/cm^3$, average void ratio, 0.93 ~ 1.001 ; cohesion, $ 0.2{\sim}0.75kg/cm^2$ ; angle of internal friction, $29^{\circ}{\sim}45^{\circ}$ ; soil texture, SL. The shear strength of the soil in different sites was measured by a direct shear apparatus (type B; shear box size, $62.5{\times}20mm$; ${\sigma}$, $1.434kg/cm^2$; speed, 1/100mm/min.). For the related element analyses, water content was moderated through a series of drainage experiments with 4 levels of drainage period, specific gravity was measured by KS F 308, analysis of particle size distribution, by KS F 2302 and soil samples were dried at $110{\pm}5^{\circ}C$ for more than 12 hours in dry oven. Soil hardness represents physical properties, such as particle size distribution, porosity, bulk density and water content of soil, and test of the hardness by soil hardness tester is the simplest approach and totally indicative method to grasp the mechanical properties of soil. It is important to understand the mechanical properties of soil as well as the chemical in order to realize the fundamental phenomena in the growth and the distribution of tree roots. The writer intended to study the correlation between the soil hardness and the distribution of tree roots of Pinus rigida Mill. planted in 1966 and Pinus rigida ${\times}$ taeda in 199 to 1960 in the denuded forest lands with and after several erosion control works. The soil texture of the sites investigated was SL originated from weathered granitic soil. The former is situated at Py$\ddot{o}$ngchangri, Ky$\ddot{o}$m-my$\ddot{o}$n, Kogs$\ddot{o}$ng-gun, Ch$\ddot{o}$llanam-do (3.63 ha; slope, $17^{\circ}{\sim}41^{\circ}$ soil depth, thin or medium; humidity, dry or optimum; height, 5.66/3.73 ~ 7.63 m; D.B.H., 9.7/8.00 ~ 12.00 cm) and the Latter at changun-long Kwangju-shi (3.50 ha; slope, $12^{\circ}{\sim}23^{\circ}$; soil depth, thin; humidity, dry; height, 10.47/7.3 ~ 12.79 m; D.B.H., 16.94/14.3 ~ 19.4 cm).The sampling areas were 24quadrats ($10m{\times}10m$) in the former area and 12 in the latter expanding from summit to foot. Each sampling trees for hardness test and investigation of root distribution were selected by purposive selection and soil profiles of these trees were made at the downward distance of 50 cm from the trees, at each quadrat. Soil layers of the profile were separated by the distance of 10 cm from the surface (layer I, II, ... ...). Soil hardness was measured with Yamanaka soil hardness tester and indicated as indicated soil hardness at the different soil layers. The distribution of tree root number per unit area in different soil depth was investigated, and the relationship between the soil hardness and the number of tree roots was discussed. The results obtained from the experiments are summarized as follows. 1. Analyses of simple relationship between shear strength and elements of shear strength, water content ($w_o$), void ratio ($e_o$), dry density (${\gamma}_d$) and specific gravity ($G_s$). 1) Negative correlation coefficients were recognized between shear strength and water content. and shear strength and void ratio. 2) Positive correlation coefficients were recognized between shear strength and dry density. 3) The correlation coefficients between shear strength and specific gravity were not significant. 2. Analyses of partial and multiple correlation coefficients between shear strength and the related elements: 1) From the analyses of the partial correlation coefficients among water content ($x_1$), void ratio ($x_2$), and dry density ($x_3$), the direct effect of the water content on shear strength was the highest, and effect on shear strength was in order of void ratio and dry density. Similar trend was recognized from the results of multiple correlation coefficient analyses. 2) Multiple linear regression equations derived from two independent variables, water content ($x_1$ and dry density ($x_2$) were found to be ineffective in estimating shear strength ($\hat{Y}$). However, the simple linear regression equations with an independent variable, water content (x) were highly efficient to estimate shear strength ($\hat{Y}$) with relatively high fitness. 3. A relationship between soil hardness and the distribution of root number: 1) The soil hardness increased proportionally to the soil depth. Negative correlation coefficients were recognized between indicated soil hardness and the number of tree roots in both plantations. 2) The majority of tree roots of Pinus rigida Mill and Pinus rigida ${\times}$ taeda planted in erosion-controlled lands distributed at 20 cm deep from the surface. 3) Simple linear regression equations were derived from indicated hardness (x) and the number of tree roots (Y) to estimate root numbers in both plantations.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Journal of Life Science
• /
• v.20 no.4
• /
• pp.467-473
• /
• 2010

Gangliosides are a major component of the plasma membrane of mammalian cells, which are directly involved in a variety of immunological events, including cell-to cell or cell-to-protein interactions. In this study, we investigated whether gangliosides, sialic acid-containing glycosphingolipids, are related to rejection during the xenotransplantation of NIH-miniature pig livers and hearts to humans. Both high performance thin-layer chromatography and immunohistochemistry analyses revealed that the expression of gangliosides in the liver tissue of NIH-miniature pigs was higher than that in the heart. Gangliosides GD3, GD1a, GD1b, GT1b and GQ1b were observed in both the liver and heart, whereas GQ1b was detected only in the liver, indicating that the ganglioside expression profiles are tissue specific. Moreover, other ganglio-series gangliosides, including GM3, were not detected in the livers and hearts of NIH-miniature pigs. Taken together, these results suggest that gangliosides may play important roles in immune responses in clinical xenotransplants of pig livers and hearts.