• Proceedings of the Korean DIstribution Association Conference
• /
• 2003.02a
• /
• pp.123-166
• /
• 2003

Marketing channel is recognized as one of the society systems which have the character of functional organization. These organizations are related to each other for specialized and cooperative work. Channel members in distribution channel are striving to accomplish exchange through reciprocal action. Thus channel members exercise their power to take better position in exchange. There will be struggling between members about satisfaction and conflict during this power exercise. Now a days, buyers use more harsh power as large retail firms are increasing. This phenomenon is occurring in the distribution channel. However, there will be different phenomenon in case of agricultural products. Not like industrial product suppliers, agricultural product suppliers have various supply channels and many agricultural products are seasonal. It has also unstable amount supplies. There should be differentiated marketing in agricultural products. Relatively weaker powered suppliers have to strengthen comparative factors and also have to be technically specialized through assessed experience in order to establish strong product sales chain. Making a brand of agricultural product would be also a good idea to increase the product comparability. Channel members need to be recognized their specialized functions in order to make balanced distribution channel. There have to be conversion of concept of relation between suppliers and buyers from subordinate relationship to cooperative relationship.

• Progress in Medical Physics
• /
• v.10 no.3
• /
• pp.133-140
• /
• 1999

In this paper, as a preliminary study for developing a full 3D electron dose calculation algorithm, We developed 2.5D electron dose calculation algorithm by extending 2D pencil-beam model to consider three dimensional geometry such as air-gap and obliquity appropriately. The dose calculation algorithm was implemented using the IDL5.2(Research Systems Inc., USA), For calculation of the Hogstrom's pencil-beam algorithm, the measured data of the central-axis depth-dose for 12 MeV(Siemens M6740) and the linear stopping power and the linear scattering power of water and air from ICRU report 35 was used. To evaluate the accuracy of the implemented program, we compared the calculated dose distribution with the film measurements in the three situations; the normal incident beam, the 45$^{\circ}$ oblique incident beam, and the beam incident on the pit-shaped phantom. As results, about 120 seconds had been required on the PC (Pentium III 450MHz) to calculate dose distribution of a single beam. It needs some optimizing methods to speed up the dose calculation. For the accuracy of dose calculation, in the case of the normal incident beam of the regular and irregular shaped field, at the rapid dose gradient region of penumbra, the errors were within $\pm$3 mm and the dose profiles were agreed within 5%. However, the discrepancy between the calculation and the measurement were about 10% for the oblique incident beam and the beam incident on the pit-shaped phantom. In conclusions, we expended 2D pencil-beam algorithm to take into account the three dimensional geometry of the patient. And also, as well as the dose calculation of irregular field, the irregular shaped body contour and the air-gap could be considered appropriately in the implemented program. In the near future, the more accurate algorithm will be implemented considering inhomogeneity correction using CT, and at that time, the program can be used as a tool for educational and research purpose. This study was supported by a grant (＃HMP-98-G-1-016) of the HAN(Highly Advanced National) Project, Ministry of Health & Welfare, R.O.K.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.147-157
• /
• 2013

With the advent of the digital environment that can be accessed anytime, anywhere with the introduction of high-speed network, the free distribution and use of digital content were made possible. Ironically this environment is raising a variety of copyright infringement, and product images used in the online shopping mall are pirated frequently. There are many controversial issues whether shopping mall images are creative works or not. According to Supreme Court's decision in 2001, to ad pictures taken with ham products is simply a clone of the appearance of objects to deliver nothing but the decision was not only creative expression. But for the photographer's losses recognized in the advertising photo shoot takes the typical cost was estimated damages. According to Seoul District Court precedents in 2003, if there are the photographer's personality and creativity in the selection of the subject, the composition of the set, the direction and amount of light control, set the angle of the camera, shutter speed, shutter chance, other shooting methods for capturing, developing and printing process, the works should be protected by copyright law by the Court's sentence. In order to receive copyright protection of the shopping mall images by the law, it is simply not to convey the status of the product, the photographer's personality and creativity can be recognized that it requires effort. Accordingly, the cost of making the mall image increases, and the necessity for copyright protection becomes higher. The product images of the online shopping mall have a very unique configuration unlike the general pictures such as portraits and landscape photos and, therefore, the general image watermarking technique can not satisfy the requirements of the image watermarking. Because background of product images commonly used in shopping malls is white or black, or gray scale (gradient) color, it is difficult to utilize the space to embed a watermark and the area is very sensitive even a slight change. In this paper, the characteristics of images used in shopping malls are analyzed and a watermarking technology which is suitable to the shopping mall images is proposed. The proposed image watermarking technology divide a product image into smaller blocks, and the corresponding blocks are transformed by DCT (Discrete Cosine Transform), and then the watermark information was inserted into images using quantization of DCT coefficients. Because uniform treatment of the DCT coefficients for quantization cause visual blocking artifacts, the proposed algorithm used weighted mask which quantizes finely the coefficients located block boundaries and coarsely the coefficients located center area of the block. This mask improves subjective visual quality as well as the objective quality of the images. In addition, in order to improve the safety of the algorithm, the blocks which is embedded the watermark are randomly selected and the turbo code is used to reduce the BER when extracting the watermark. The PSNR(Peak Signal to Noise Ratio) of the shopping mall image watermarked by the proposed algorithm is 40.7~48.5[dB] and BER(Bit Error Rate) after JPEG with QF = 70 is 0. This means the watermarked image is high quality and the algorithm is robust to JPEG compression that is used generally at the online shopping malls. Also, for 40% change in size and 40 degrees of rotation, the BER is 0. In general, the shopping malls are used compressed images with QF which is higher than 90. Because the pirated image is used to replicate from original image, the proposed algorithm can identify the copyright infringement in the most cases. As shown the experimental results, the proposed algorithm is suitable to the shopping mall images with simple background. However, the future study should be carried out to enhance the robustness of the proposed algorithm because the robustness loss is occurred after mask process.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.149-169
• /
• 2020

"The Urban Renewal New Deal project", one of the government's major national projects, is about developing underdeveloped areas by investing 50 trillion won in 100 locations on the first year and 500 over the next four years. This project is drawing keen attention from the media and local governments. However, the project model which fails to reflect the original characteristics of the area as it divides project area into five categories: "Our Neighborhood Restoration, Housing Maintenance Support Type, General Neighborhood Type, Central Urban Type, and Economic Base Type," According to keywords for successful urban regeneration in Korea, "resident participation," "regional specialization," "ministerial cooperation" and "public-private cooperation", when local governments propose urban regeneration projects to the government, they can see that it is most important to accurately understand the characteristics of the city and push ahead with the projects in a way that suits the characteristics of the city with the help of local residents and private companies. In addition, considering the gentrification problem, which is one of the side effects of urban regeneration projects, it is important to select and implement urban regeneration types suitable for the characteristics of the area. In order to supplement the limitations of the 'Urban Regeneration New Deal Project' methodology, this study aims to propose a system that recommends urban regeneration types suitable for urban regeneration sites by utilizing various machine learning algorithms, referring to the urban regeneration types of the '2025 Seoul Metropolitan Government Urban Regeneration Strategy Plan' promoted based on regional characteristics. There are four types of urban regeneration in Seoul: "Low-use Low-Level Development, Abandonment, Deteriorated Housing, and Specialization of Historical and Cultural Resources" (Shon and Park, 2017). In order to identify regional characteristics, approximately 100,000 text data were collected for 22 regions where the project was carried out for a total of four types of urban regeneration. Using the collected data, we drew key keywords for each region according to the type of urban regeneration and conducted topic modeling to explore whether there were differences between types. As a result, it was confirmed that a number of topics related to real estate and economy appeared in old residential areas, and in the case of declining and underdeveloped areas, topics reflecting the characteristics of areas where industrial activities were active in the past appeared. In the case of the historical and cultural resource area, since it is an area that contains traces of the past, many keywords related to the government appeared. Therefore, it was possible to confirm political topics and cultural topics resulting from various events. Finally, in the case of low-use and under-developed areas, many topics on real estate and accessibility are emerging, so accessibility is good. It mainly had the characteristics of a region where development is planned or is likely to be developed. Furthermore, a model was implemented that proposes urban regeneration types tailored to regional characteristics for regions other than Seoul. Machine learning technology was used to implement the model, and training data and test data were randomly extracted at an 8:2 ratio and used. In order to compare the performance between various models, the input variables are set in two ways: Count Vector and TF-IDF Vector, and as Classifier, there are 5 types of SVM (Support Vector Machine), Decision Tree, Random Forest, Logistic Regression, and Gradient Boosting. By applying it, performance comparison for a total of 10 models was conducted. The model with the highest performance was the Gradient Boosting method using TF-IDF Vector input data, and the accuracy was 97%. Therefore, the recommendation system proposed in this study is expected to recommend urban regeneration types based on the regional characteristics of new business sites in the process of carrying out urban regeneration projects."

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Korean Journal of Ecology and Environment
• /
• v.45 no.4
• /
• pp.378-391
• /
• 2012

The objective of this study was to determine temporal patterns and longitudinal gradients of water chemistry at eight artificial reservoirs and ten streams within the Han-River watershed along the main axis of the headwaters to the downstreams during 2009~2010. Also, we evaluated chemical relations and their variations among major trophic variables such as total nitrogen (TN), total phosphorus (TP), and chlorophyll-a (CHL-a) and determined intense summer monsoon and annual precipitation effects on algal growth using empirical regression model. Stream water quality of TN, TP, and other parameters degradated toward the downstreams, and especially was largely impacted by point-sources of wastewater disposal plants near Jungrang Stream. In contrast, summer river runoff and rainwater improved the stream water quality of TP, TN, and ionic contents, measured as conductivity (EC) in the downstream reach. Empirical linear regression models of log-transformed CHL-a against log-transformed TN, TP, and TN : TP mass ratios in five reservoirs indicated that the variation of TP accounted 33.8% ($R^2$=0.338, p<0.001, slope=0.710) in the variation of CHL and the variation of TN accounted only 21.4% ($R^2$=0.214, p<0.001) in the CHL-a. Overall, our study suggests that, primary productions, estimated as CHL-a, were more determined by ambient phosphorus loading rather than nitrogen in the lentic systems of artificial reservoirs, and the stream water quality as lotic ecosystems were more influenced by a point-source locations of tributary streams and intense seasonal rainfall rather than a presence of artificial dam reservoirs along the main axis of the watershed.

• Horticultural Science & Technology
• /
• v.32 no.3
• /
• pp.318-329
• /
• 2014

In order to gain insight into the physiological responses of plants to high temperature stress, the effects of temperature on Chinese cabbage (Brassica campestris subsp. napus var. pekinensis cv. Detong) were investigated through analyses of photosynthesis and chlorophyll fluorescence under 3 different temperatures in the temperature gradient tunnel. Growth (leaf length and number of leaves) during the rosette stage was greater at ambient $+4^{\circ}C$ and ambient $+7^{\circ}C$ temperatures than at ambient temperature. Photosynthetic $CO_2$ fixation rates of Chinese cabbage grown under the different temperatures did not differ significantly. However, dark respiration rate was significantly higher in the cabbage that developed under ambient temperature relative to elevated temperature. Furthermore, elevated growth temperature increased transpiration rate and stomatal conductance resulting in an overall decrease of water use efficiency. The chlorophyll a fluorescence transient was also considerably affected by high temperature stress; the fluorescence yield $F_J$, $F_I$, and $F_P$ decreased considerably at ambient $+4^{\circ}C$ and ambient $+7^{\circ}C$ temperatures, with induction of $F_K$ and decrease of $F_V/F_O$. The values of RC/CS, ABS/CS, TRo/CS, and ETo/CS decreased considerably, while DIo/CS increased with increased growth temperature. The symptoms of soft-rot disease were observed in the inner part of the cabbage heads after 7, 9, and/or 10 weeks of cultivation at ambient $+4^{\circ}C$ and ambient $+7^{\circ}C$ temperatures, but not in the cabbage heads growing at ambient temperature. These results show that Chinese cabbage could be negatively affected by high temperature under a future climate change scenario. Therefore, to maintain the high productivity and quality of Chinese cabbage, it may be necessary to develop new high temperature tolerant cultivars or to markedly improve cropping systems. In addition, it would be possible to use the non-invasive fluorescence parameters $F_O$, $F_V/F_M$, and $F_V/F_O$, as well as $F_K$, $M_O$, $S_M$, RC/CS, ETo/CS, $PI_{abs}$, and $SFI_{abs}$ (which were selected in this study), to quantitatively determine the physiological status of plants in response to high temperature stresses.

• Korean Journal of Ecology and Environment
• /
• v.41 no.2
• /
• pp.206-215
• /
• 2008

Temporal and spatial distributions of salinity, temperature, dissolved oxygen (DO), and turbidity were investigated at seven sites in the upper regions of brackish Lake Sihwa with a limited water exchange, from March to October 2005. During the study period, salinity and temperature varied $0.1{\sim}29.9\;psu$ and $4.7{\sim}28.1^{\circ}C$, respectively, depending on seasons and sites sampled. A distinct halocline profile showing the maximum density gradient (difference over $20\;psu\;m^{-1}$ between surface and bottom layers) was observed during the rainy season, due to the decrease of salinity in surface layers by freshwater inflow. This result implies that rainfall event is the important factor forming the halocline. On the other hand, the depth and location of haloeline varied with the amount of seawater through the sluice gates and the operation systems (inflow or outflow). High DO (over 300% saturation) was observed at surface layer above the halocline in April when red tide occurred, whereas low DO (below 20% saturation) was at the bottom layer below the halocline in the rainy season. Turbidity ranged $1.5{\sim}80.3\;NTU$ showing the maximum turbidity at the layers above or upper the halocline. As a result, the distributions of DO and turbidity in the upper regions of brackish Lake Sihwa were largely affected by the variation of salinity. Also, when the halocline was formed, the water quality between upper and lower water layers may be expected completely different. This study suggests that the physicochemical characteristics of water in the brackish regions are closely associated with the causes of eutrophication such as red tide and DO deficit.

• Korean Journal of Soil Science and Fertilizer
• /
• v.34 no.1
• /
• pp.1-7
• /
• 2001

Total upland area for cultivating the vegetable crops in the Alpine soils of Northeastern South Korea has been extending its limit to meet the increasing demand of vegetable food in recent decades. About 70% of these alpine soils are located in over 7% of the slope and most of vegetable crops have been cultivated intensively without practicing the best management systems. Thus, soil erosion and continuous cropping system have degenerated the soil fertility and shown detrimental effects on water quality. We initiated an intensive and extensive investigation to characterize the fertility problems encountered in these uplands. Objectives of this paper were to characterize the fertility status in the Alpine soils cultivated with vegetable crops for many years and to provide the recommendations for adequate soil management measures including fertilization and erosion control. Soils in general have good drainage with textural classes of loam or sandy loam. Their topographical characteristics tended to lead them to shallow plow layers, and the steepness of the terrain created erosion hazard. Of the soils examined, about 11% of uplands over 30% gradient was found in need of an urgent reforestation. A high content of gravel and firm hardness of soil attributed to inhibit the utilization of farm machinery and plant-root development. The average soil pH 5.6 was slightly low relative to pH 5.70 of the national average. Organic matter content was high compared with 2.0% of national average, but decreased with the prolonged cultivation periods. Available $P_2O_5$ concentration was unusually high due to the consequence of over dose application with chemical and organic fertilizers. Exchangeable cations as Ca, Mg, and K were appeared to be decreased in these regions with prolonging the cultivation periods. There were no significant differences in cation exchange capacity (CEC) and electrical conductivity (EC) among locations. Heavy metal contents were mostly lower than the threshold of danger level designated by Soil Environment Conservation Law of South Korea. Results indicated that a proper countermeasure and the best management practice should be immediately implemented to conserve the top soil and fertility in the Alpine regions.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.