• IMMUNE NETWORK
• /
• v.11 no.6
• /
• pp.368-375
• /
• 2011

Background: Recent clinical observation reported that there was a significant correlation between change in circulating vascular endothelial growth factor (VEGF) levels and the occurrence of severe acute graft-versus-host disease (GVHD) following allogeneic hematopoietic stem cell transplantation (allo-HSCT), but the action mechanisms of VEGF in GVHD have not been demonstrated. Methods: This study investigated whether or not blockade of VEGF has an effect on acute GVHD in a lethally irradiated murine allo-HSCT model of $B6\;(H-2^b)\;{\rightarrow}B6D2F1\;(H-2^{b/d})$. Syngeneic or allogeneic recipient mice were injected subcutaneously with anti-VEGF peptides, dRK6 ($50{\mu}g/dose$) or control diluent every other day for 2 weeks (total 7 doses). Results: Administration of the dRK6 peptide after allo-HSCT significantly reduced survival with greaterclinical GVHD scores and body weight loss. Allogeneic recipients injected with the dRK6 peptide exhibited significantly increased circulating levels of VEGF and expansion of donor $CD3^+$ T cells on day +7 compared to control treated animals. The donor $CD4^+$ and $CD8^+$ T-cell subsets have differential expansion caused by the dRK6 injection. The circulating VEGF levels were reduced on day +14 regardless of blockade of VEGF. Conclusion: Together these findings demonstrate that the allo-reactive responses after allo-HSCT are exaggerated by the blockade of VEGF. VEGF seems to be consumed during the progression of acute GVHD in this murine allo-HSCT model.

• Journal of Information Technology Services
• /
• v.23 no.3
• /
• pp.103-118
• /
• 2024

Due to the advancement of virtual reality technology, virtual idols are widely used in industrial and cultural content industries. However, it is difficult to utilize virtual idols' social perceptions because they are not properly understood. Therefore, this paper collected and analyzed YouTube comments to identify differences about social perception through comparative analysis between virtual idols and general idols. The dataset was constructed by crawling comments from music videos with more than 10 million views of virtual idols and more than 10,000 comments. Keyword frequency and TF-IDF values were derived from the collected dataset, and the connection centrality CONCOR cluster was analyzed with a semantic network using the UCINET program. As a result of the analysis, it was found that virtual idols frequently used keywords such as "person," "quality," "character," "reality," "animation," while reactions and perceptions were derived from general idols. Based on the results of this analysis, it was found that while general idols are mainly evaluated with their appearance and cultural factors, social perceptions of virtual idols' values are mixed with evaluations of cultural factors such as "song," "voice," and "choreography," focusing on technical factors such as "people," "quality," "character," and "animation." However, keywords such as "song," "voice," "choreography," and "music" are included in the top 30 like regular idols and appear in the same cluster, suggesting that virtual idols are gradually shifting away from minority tastes to mainstream culture. This study aims to provide academic and practical implications for the future expansion of the industry and cultural content industry of virtual idols by grasping the social perception of virtual idols.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.1-6
• /
• 2021

Most of the match-3 puzzle games supports automatic play using the MCTS algorithm. However, implementing reinforcement learning agents is not an easy job because it requires both the knowledge of machine learning and the way of complex interactions within the development environment. This study proposes a method in which we can easily design reinforcement learning agents and implement game play agents by applying PPO(Proximal Policy Optimization) algorithms. And we could identify the performance was increased about 44% than the conventional method. The tools we used are the Unity 3D game engine and Unity ML SDK. The experimental result shows that agents became to learn game rules and make better strategic decisions as experiments go on. On average, the puzzle gameplay agents implemented in this study played puzzle games better than normal people. It is expected that the designed agent could be used to speed up the game level design process.

• Land and Housing Review
• /
• v.13 no.2
• /
• pp.81-90
• /
• 2022

This study is based on social needs for green healing spaces assumed to enhance mental health in a city. This study proposes development directions through the analysis of modern social recognition factors for neighborhood gardens. As a research method, web information data was collected using Textom among big data tools. Text Mining was conducted to extract elements and analyze their relationship through keyword analysis, network analysis, and cluster analysis. As a result, first, the healing space and the healing environment were creating an eco-friendly healthy environment in a space close to the neighborhood within the city. Second, neighborhood gardens included projects and activities that involved government, local administration, and citizens by linking facilities as well as living culture and urban environments. These gardens have been reinforced through green welfare and service programs. In conclusion, friendly gardens in the neighborhood for the purpose of public interest, which are beneficial to mental health, are green infrastructures as a healing environment that can produce positive effects.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.557-561
• /
• 2021

A meatadata has become an essential element in order to recommend video content to users. However, it is passively generated by video content providers. In the paper, a method for automatically generating metadata was studied in the existing manual metadata input method. In addition to the method of extracting emotion tags in the previous study, a study was conducted on a method for automatically generating metadata for genre and country of production through movie audio. The genre was extracted from the audio spectrogram using the ResNet34 artificial neural network model, a transfer learning model, and the language of the speaker in the movie was detected through speech recognition. Through this, it was possible to confirm the possibility of automatically generating metadata through artificial intelligence.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.278-281
• /
• 2018

The early Web technology was to show text information through a browser. However, as web technology advances, it is possible to show large amounts of multimedia data through browsers. Web technologies are being applied in a variety of fields such as sensor network, hardware control, and data collection and analysis for big data and AI services. As a result, the standard has been prepared for the Internet of Things, which typically controls a sensor via HTTP communication and provides information to users, by installing a web browser on the interface of the Internet of Things. In addition, the recent development of web-assembly enabled 3D objects, virtual/enhancing real-world content that could not be run in web browsers through a native language of C-class. Factors that evaluate the performance of existing Web applications include performance, network resources, and security. However, since there are many areas in which web applications are applied, it is time to revisit and review these factors. In this thesis, we will conduct an analysis of the factors that assess the performance of a web application. We intend to establish an indicator of the development of web-based applications by reviewing the analysis of each element, its main points, and its needs to be supplemented.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.49-57
• /
• 2022

The government is making great efforts to prevent crimes such as missing children by using public CCTVs. However, there is a shortage of operating manpower, weakening of concentration due to long-term concentration, and difficulty in tracking. In addition, applying real-time object search, re-identification, and tracking through a deep learning algorithm showed a phenomenon of increased parameters and insufficient memory for speed reduction due to complex network analysis. In this paper, we designed the network to improve speed and save memory through the application of Yolo v4, which can recognize real-time objects, and the application of Batch and TensorRT technology. In this thesis, based on the research on these advanced algorithms, OSNet re-ranking and K-reciprocal nearest neighbor for re-identification, Jaccard distance dissimilarity measurement algorithm for correlation, etc. are developed and used in the solution of CCTV national safety identification and tracking system. As a result, we propose a solution that can track objects by recognizing and re-identification objects in real-time within situation of a Korean public multi-CCTV environment through a set of algorithm combinations.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.79-99
• /
• 2015

The prediction of bankruptcy has been extensively studied in the accounting and finance field. It can have an important impact on lending decisions and the profitability of financial institutions in terms of risk management. Many researchers have focused on constructing a more robust bankruptcy prediction model. Early studies primarily used statistical techniques such as multiple discriminant analysis (MDA) and logit analysis for bankruptcy prediction. However, many studies have demonstrated that artificial intelligence (AI) approaches, such as artificial neural networks (ANN), decision trees, case-based reasoning (CBR), and support vector machine (SVM), have been outperforming statistical techniques since 1990s for business classification problems because statistical methods have some rigid assumptions in their application. In previous studies on corporate bankruptcy, many researchers have focused on developing a bankruptcy prediction model using financial ratios. However, there are few studies that suggest the specific types of bankruptcy. Previous bankruptcy prediction models have generally been interested in predicting whether or not firms will become bankrupt. Most of the studies on bankruptcy types have focused on reviewing the previous literature or performing a case study. Thus, this study develops a model using data mining techniques for predicting the specific types of bankruptcy as well as the occurrence of bankruptcy in Korean small- and medium-sized construction firms in terms of profitability, stability, and activity index. Thus, firms will be able to prevent it from occurring in advance. We propose a hybrid approach using two artificial neural networks (ANNs) for the prediction of bankruptcy types. The first is a back-propagation neural network (BPN) model using supervised learning for bankruptcy prediction and the second is a self-organizing map (SOM) model using unsupervised learning to classify bankruptcy data into several types. Based on the constructed model, we predict the bankruptcy of companies by applying the BPN model to a validation set that was not utilized in the development of the model. This allows for identifying the specific types of bankruptcy by using bankruptcy data predicted by the BPN model. We calculated the average of selected input variables through statistical test for each cluster to interpret characteristics of the derived clusters in the SOM model. Each cluster represents bankruptcy type classified through data of bankruptcy firms, and input variables indicate financial ratios in interpreting the meaning of each cluster. The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy. In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.85-92
• /
• 2021

Ambient Air Vaporizer (AAV) is an essential facility in the process of generating natural gas that uses air in the atmosphere as a medium for heat exchange to vaporize liquid natural gas into gas-state gas. AAV is more economical and eco-friendly in that it uses less energy compared to the previously used Submerged vaporizer (SMV) and Open-rack vaporizer (ORV). However, AAV is not often applied to actual processes because it is heavily affected by external environments such as atmospheric temperature and humidity. With insufficient operational experience and facility operations that rely on the intuition of the operator, the actual operation of AAV is very inefficient. To address these challenges, this paper proposes an artificial intelligence-based model that can intelligent AAV operations based on operational big data. The proposed artificial intelligence model is used deep neural networks, and the superiority of the artificial intelligence model is verified through multiple regression analysis and comparison. In this paper, the proposed model simulates based on data collected from real-world processes and compared to existing data, showing a 48.8% decrease in power usage compared to previous data. The techniques proposed in this paper can be used to improve the energy efficiency of the current natural gas generation process, and can be applied to other processes in the future.