• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.141-149
• /
• 2007

Associating the shoulder line with head location of the human body is useful in verifying, localizing and tracking persons in an image. Since the head line and the shoulder line, what we call ${\Omega}$-shape, move together in a consistent way within a limited range of deformation, we can build a statistical shape model using Active Shape Model (ASM). However, when the conventional ASM is applied to ${\Omega}$-shape fitting, it is very sensitive to background edges and clutter because it relies only on the local edge or gradient. Even though appearance is a good alternative feature for matching the target object to image, it is difficult to learn the appearance of the ${\Omega}$-shape because of the significant difference between people's skin, hair and clothes, and because appearance does not remain the same throughout the entire video. Therefore, instead of teaming appearance or updating appearance as it changes, we model the discriminative appearance where each pixel is classified into head, torso and background classes, and update the classifier to obtain the appropriate discriminative appearance in the current frame. Accordingly, we make use of two features in fitting ${\Omega}$-shape, edge gradient which is used for localization, and discriminative appearance which contributes to stability of the tracker. The simulation results show that the proposed method is very robust to pose change, occlusion, and illumination change in tracking the head and shoulder line of people. Another advantage is that the proposed method operates in real time.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1749-1758
• /
• 1997

This paper suggests the development of dynamic forecasting model for short-term power demand based on Radial Basis Function Network and Pal's GLVQ algorithm. Radial Basis Function methods are often compared with the backpropagation training, feed-forward network, which is the most widely used neural network paradigm. The Radial Basis Function Network is a single hidden layer feed-forward neural network. Each node of the hidden layer has a parameter vector called center. This center is determined by clustering algorithm. Theatments of classical approached to clustering methods include theories by Hartigan(K-means algorithm), Kohonen(Self Organized Feature Maps %3A SOFM and Learning Vector Quantization %3A LVQ model), Carpenter and Grossberg(ART-2 model). In this model, the first approach organizes the load pattern into two clusters by Pal's GLVQ clustering algorithm. The reason of using GLVQ algorithm in this model is that GLVQ algorithm can classify the patterns better than other algorithms. And the second approach forecasts hourly load patterns by radial basis function network which has been constructed two hidden nodes. These nodes are determined from the cluster centers of the GLVQ in first step. This model was applied to forecast the hourly loads on Mar. $4^{th},\;Jun.\;4^{th},\;Jul.\;4^{th},\;Sep.\;4^{th},\;Nov.\;4^{th},$ 1995, after having trained the data for the days from Mar. $1^{th}\;to\;3^{th},\;from\;Jun.\;1^{th}\;to\;3^{th},\;from\;Jul.\;1^{th}\;to\;3^{th},\;from\;Sep.\;1^{th}\;to\;3^{th},\;and\;from\;Nov.\;1^{th}\;to\;3^{th},$ 1995, respectively. In the experiments, the average absolute errors of one-hour ahead forecasts on utility actual data are shown to be 1.3795%.

• Korean Journal of Organic Agriculture
• /
• v.7 no.2
• /
• pp.89-97
• /
• 1999

Through manifestation of the principles of commodity production spatial sharing of labour can be observed in the agriculture as well as in cattle production. Better adjustment of the production structure to the environment factors brings higher yields and more effective production. In being able to maximize the profit the entrepreneurs opt for producing output that closely matches to their featuring conditions. In contrary to the relatively high "mobility" of crop production animal husbandry and within this cattle production - as known - is strictly chained to forage production. On the basis of our economic research and as a result of multivariable analysis(factor analysis) it can be concluded that two variable groups(factors) are highly dominant in organizing profitable cattle production. First of them is the crop site factor (indicated by gold crown value), the second is the forage production feature(forage and grassland area and the yield of them). During recent years the weight of environmental factors suffered from devaluation. As a result of the central economic administration differentiating effects were suppressed and the chances of equalizing concepts strengthened. The outcome can be observed even today. In the regions, for example, being predominantly suitable for grass and forage cropping the milk and slaughter cattle production decreased. The same is ture for com and pig production regions. Unexploitment of local environmental features can be observed mainly in grassland management. Branches being potential user of grasslands hardly take them into consideration. Main method of rational use of grasslands is pasturing. Presence of pastures and the usage of them through cattle production is highly important not only for profitable production but also for maintaining ecological stability.

• Korean Journal of Heritage: History & Science
• /
• v.43 no.3
• /
• pp.26-47
• /
• 2010

When the term conservation is used with regard to excavated features, it means not only conservation but also restoration. Restoring the features here does not imply restoring their original form but restoring their form at the moment of excavation. That means, the conservation of excavated features includes the concept of both reparation and restoration. The way of conserving excavated features can be largely categorized into on-site conservation and transfer conservation. On-site conservation means to conserve excavated features as they were at the excavation site. It can be further categorized into soil-covered on-site conservation, in which excavated features are covered with soil to prevent them from being damaged, and exposed on-site conservation in which the features were conserved as they were exposed. Transfer conservation is operated on the premise that excavated features are transferred to another place. It can be further categorized into original form transfer, transcribing transfer, reproduction transfer, and dismantlement transfer. Original form transfer refers to the method of moving the original forms of excavated features to another place. Transcribing transfer refers to moving some of the surfaces of excavated features to another place. Reproduction transfer refers to restoring the forms of excavated features in another place after copying the forms of excavated features at the excavation site. Dismantlement transfer refers to the method of restoring excavated features in a place other than the excavation site in the reverse order of dismantlement after dismantling the features at the excavation site. The most fundamental issue regarding conserving excavated features is the conservation of their original forms. However, the conservation of excavated features tends to be decided depending on a variety of conditions such as society, economy, culture, and local situations. In order to conserve excavated features more effectively, more detailed and specialized conservation methods should be created. Furthermore, continuing research is needed to find the most effective way of conserving them through exchange with other neighboring academic fields and scientific technology.

• Journal of Rhinology
• /
• v.25 no.2
• /
• pp.86-90
• /
• 2018

Background and Objectives: Although polyvinyl acetate ($Merocel^{(R)}$) has been widely used as a packing material after septoplasty, removable nasal packing can increase patient discomfort, local pain, and pressure. Furthermore, the removal of nasal packing has been described as the most uncomfortable and distressing feature associated with septoplasty. The purpose of this study was to investigate the efficacy of polyvinyl acetate with carboxymethyl cellulose sheet ($Rhinocel^{(R)}$) nasal packing on patient subjective symptoms, degree of bleeding, hemostasis, and wound healing following septoplasty. Subjects and Method: Forty patients with nasal septum deviation requiring septoplasty were included. Following surgery, one nasal cavity was packed with $Rhinocel^{(R)}$ and the other one with $Merocel^{(R)}$. Patient subjective symptoms while the packing was in situ, hemostatic properties, pain on removal, degree of bleeding on removal, duration of hemostasis after removal, postoperative wound healing, and the cost of the pack were evaluated. Results: Although the two types of packing materials were equally effective in controlling postoperative bleeding after septoplasty, $Rhinocel^{(R)}$ was significantly more comfortable while in situ and less painful on removal than $Merocel^{(R)}$, which was associated with significantly more bleeding on removal and so more time was needed to control hemorrhage. There was no significant difference in postoperative wound healing or pack cost. Conclusion: The use of $Rhinocel^{(R)}$ after septoplasty has less discomfort, greater patient satisfaction, and less bleeding on removal with no adverse reactions compared to $Merocel^{(R)}$ packing. Therefore, $Rhinocel^{(R)}$ may be a useful packing material after septoplasty.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.307-332
• /
• 2022

One of the most intensively conducted research areas in business application study is a bankruptcy prediction model, a representative classification problem related to loan lending, investment decision making, and profitability to financial institutions. Many research demonstrated outstanding performance for bankruptcy prediction models using artificial intelligence techniques. However, since most machine learning algorithms are "black-box," AI has been identified as a prominent research topic for providing users with an explanation. Although there are many different approaches for explanations, this study focuses on explaining a bankruptcy prediction model using a counterfactual example. Users can obtain desired output from the model by using a counterfactual-based explanation, which provides an alternative case. This study introduces a counterfactual generation technique based on a genetic algorithm (GA) that leverages both domain knowledge (i.e., causal feasibility) and feature importance from a black-box model along with other critical counterfactual variables, including proximity, distribution, and sparsity. The proposed method was evaluated quantitatively and qualitatively to measure the quality and the validity.

• Asia Marketing Journal
• /
• v.13 no.4
• /
• pp.253-264
• /
• 2012

A growing number of Korean companies are trying to expand their business area into global market due to saturation in the Korean domestic market. Home shopping industry arriving on mature stage is faced with less growth recently. CJ O Shopping which is a top ranked home shopping company in Korea, has been showing meaningful performances by earlier moving to global market with thorough preparations. CJ O Shopping's global marketing strategy focused on asian countries including China, India, Vietnam, and Japan is going successfully, which enables top ranked on-line retailing company in asia as well as in Korea. CJ O Shopping effectively penetrated into overseas market with both core competence based on Korean home shopping model and rigorous preliminary study on target market. Especially shoppertainment (Shopping+Entertainment) that is unique feature of globally competitive Korean home shopping created huge differentiations in target market. Also choosing the influential local partner, sharing the business goals, and building the joint venture could make stable operations, thereby easily earning of well-established awareness from target consumers. A step ahead entry of competitors and intensive localization of CJ O Shopping's core competence for arriving safe in target market were additional key factors for global marketing success. We can extract above key factors for success as implications of case study on CJ O Shopping's global marketing, and expect those factors to be spread into lots of Korean companies and utilized as successful strategies for global marketing.

• Journal of the Korean Magnetics Society
• /
• v.3 no.1
• /
• pp.48-55
• /
• 1993

We report the photoemission (PES) studies for the Co/Pd multilayter. The Co 3d PES spectrum of Co/Pd exhibits two interesting features, one near the Fermi energy, $E_{F}$, and another at ~2.5 eV below $E_{F}$. The Co 3d peak near $E_{F}$ of Co/Pd is much narrower than that of the bulk Co, consistent with the enhanced Co magnetic moment in Co/Pd compared to that in the bulk Co. The Co 3d feature at ~-2.5 eV resembles the Pd valence band structures, which suggests a substantial hybridization between the Co and Pd sublayers. The Co 3d PES spectrum of Co/Pd is compared with the existing band structures, obtained using the local spin density functional calculations. A reasonable agreement is found concerning the bandwidth of the occupied part of the Co 3d band, whereas a narrow Co 3d peak near $E_{F}$ seems not to be described by the band structure calculations.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.4
• /
• pp.332-337
• /
• 2023

Korea is not only surrounded by the sea on three sides, but also has national and local rivers extending 26,843 km, so it has a geographical feature in which abundant sea and inland water surface coexist. As the number of ships operating in the inland waters is continuously increasing due to the improvement of national income, the risk of ship accidents and human casualties in the inland waters is also increasing. In this study, a macroscopic plan for the safety management of inland water ships was presented through investigation of inland water related laws and operation status analysis. As an improvement plan, as a hardware infrastructure it is proposed to secure sufficient inland water fire-boats to secure the golden time for early response to accidents and lifesaving, and to operate an institution specializing in the prevention of inland water ships accidents. And as a software infrastructure, establish departure control standards for inland water ships and the safety diagnosis system currently applied only to sea going ships, the introduction of a system tailored to the characteristics of inland water ships. The proposed inland water safety management policy is expected to contribute to the preparation of prompt and systematic countermeasures in the event of an inland water ship accident, and it is hoped that it will serve as an opportunity to continue to pay attention to safety-related research on inland water ships, which was briefly activated after the sinking of M/V Sewol.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.