• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.149-156
• /
• 2022

In the current COVID-19 pandemic, fake news and misinformation related to COVID-19 have been causing serious confusion in our society. To accurately detect such fake news, social context-based methods have been widely studied in the literature. They detect fake news based on the social context that indicates how a news article is propagated over social media (e.g., Twitter). Most existing COVID-19 related datasets gathered for fake news detection, however, contain only the news content information, but not its social context information. In this case, the social context-based detection methods cannot be applied, which could be a big obstacle in the fake news detection research. To address this issue, in this work, we collect from Twitter the social context information based on CoAID, which is a COVID-19 news content dataset built for fake news detection, thereby building CoAID⁺ that includes both the news content information and its social context information. The CoAID⁺ dataset can be utilized in a variety of methods for social context-based fake news detection, thus would help revitalize the fake news detection research area. Finally, through a comprehensive analysis of the CoAID⁺ dataset in various perspectives, we present some interesting features capable of differentiating real and fake news.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.263-278
• /
• 2022

With the recent advent of IoT technology, automatic pet feeders are being distributed so that owners can feed their companion animals while they are out. However, due to behaviors of pets, the method of measuring weight, which is important in automatic feeding, can be easily damaged and broken when using the scale. The 3D camera method has disadvantages due to its cost, and the 2D camera method has relatively poor accuracy when compared to 3D camera method. Hence, the purpose of this study is to propose a deep learning approach that can accurately estimate weight while simply using a 2D camera. For this, various convolutional neural networks were used, and among them, the ResNet101-based model showed the best performance: an average absolute error of 3.06 grams and an average absolute ratio error of 3.40%, which could be used commercially in terms of technical and financial viability. The result of this study can be useful for the practitioners to predict the weight of a standardized object such as feed only through an easy 2D image.

• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.217-226
• /
• 2022

In the view of the application of high-precision spatial information production, UAV (Umanned Aerial Vehicle)-Photogrammetry has a problem in that it lacks specific procedures and detailed regulations for quantitative quality verification methods or certification of captured images. In addition, test tools for UAV image quality assessment use only the GSD (Ground Sample Distance), not MTF (Modulation Transfer Function), which reflects image resolution and contrast at the same time. This fact makes often the quality of UAV image inferior to that of manned aerial image. We performed MTF and GSD analysis simultaneously using a siemens star to confirm the necessity of MTF analysis in UAV image quality assessment. The analyzing results of UAV images taken with different payload and sensors show that there is a big difference in σ_MTF values, representing image resolution and the degree of contrast, but slightly different in GSD. It concluded that the MTF analysis is a more objective and reliable analysis method than just the GSD analysis method, and high-quality drone images can only be obtained when the operator make images after judging the proper selection the sensor performance, image overlaps, and payload type. However, the results of this study are derived from analyzing only images acquired by limited sensors and imaging conditions. It is therefore expected that more objective and reliable results will be obtained if continuous research is conducted by accumulating various experimental data in related fields in the future.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.1
• /
• pp.53-62
• /
• 2021

After the first to present projected moving pictures to audiences, the film industry has been reshaping along with technological advancements. Through the full-scale introduction of visual effects-oriented post-production and digital technologies in the film-making process, the film industry has not only undergone significant changes in the production, but is also embracing the cutting edge technologies broadly and expanding the scope of industry. Not long after the change to digital cinema, the concept of artificial intelligence, first known at the Dartmouth summer research project in 1956, before the digitalization of film, is expected to bring about a big transformation in the film industry once again. Large volume of clear digital data from digital film-making makes easy to apply recent artificial intelligence technologies represented by machine learning and deep learning. The use of artificial intelligence techniques is prominent around major visual effects studios due to automate many laborious, time-consuming tasks currently performed by artists. This study aims to predict how artificial intelligence technology will change the film industry in the future through analysis of visual effects production cases using artificial intelligence technology as a production tool and to discuss the industrial potential of artificial intelligence as visual effects technology.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.15-29
• /
• 2021

Many countries and companies are pursuing and developing Artificial intelligence as it is the core technology of the 4th industrial revolution. Global IT companies such as Apple, Microsoft, Amazon, Google and Samsung have all released their own AI assistant hardware products, hoping to increase customer loyalty and capture market share. Competition within the industry for AI agent is intense. AI assistant products that command the biggest market shares and customer loyalty have a higher chance of becoming the industry standard. This study analyzed the current status of major overseas and domestic IT companies in the field of artificial intelligence, and suggested future strategic directions for voice UI technology development and user satisfaction. In terms of B2B technology, it is recommended that IT companies use cloud computing to store big data, innovative artificial intelligence technologies and natural language technologies. Offering voice recognition technologies on the cloud enables smaller companies to take advantage of such technologies at considerably less expense. Companies also consider using GPT-3(Generative Pre-trained Transformer 3) an open source artificial intelligence language processing software that can generate very natural human-like interactions and high levels of user satisfaction. There is a need to increase usefulness and usability to enhance user satisfaction. This study has practical and theoretical implications for industry and academia.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.93-98
• /
• 2022

With the development of new digital technologies, research on various learning tools is being actively conducted. These learning tools are also being developed so that they can be applied to various environments by applying the technology of artificial intelligence or using smart functions to which big data technology is applied. These smart learning tools are contributing a lot to increasing educational effectiveness and learning efficiency. Recently, various learning tools have been applied in universities, and solutions for smart learning from smart attendance are introduced to improve student learning efficiency. This study intends to propose a design for a smart learning tool that can increase the efficiency of project progress and increase the scalability of the results when conducting a company's customized project through such a university's smart learning tool. The proposed smart learning tool is expected to have the advantage of being able to easily adapt to the practical business project as the company-customized projects that can improve practical skills are smoothly used as a learning tool. The proposed project-based smart learning tool model is later built as a related LMS and applied to actual project progress to check its utility, and to revise and supplement the proposed smart learning tool model to provide a project-based smart learning function want to strengthen.

• The Journal of the Korea Contents Association
• /
• v.22 no.10
• /
• pp.765-777
• /
• 2022

The purpose of this study is to present a digital transformation-based learning model that can be used in universities based on learning digital transformation in order f to be competitive in a rapidly changing environment. Literature review, case study, and focus group interview were conducted and the implications for the learning model from these are as follows. Universities that stand out in related fields are actively using learning analysis to implement dashboards, develop predictive models, and support adaptive learning based on big data, They also have actively introduced advanced edutech to classes. In addition, problems and difficulties faced by other universities and K University when implementing digital transformation were also confirmed. Based on these findings, a digital transformation-based learning model of K University was developed. This model consists of four dimensions: diagnosis, recommendation, learning, and success. It allows students to proceed with learning by diagnosing and recommending various learning processes necessary for individual success, and systematically managing learning outcomes. Finally, academic and practical implications about the research results were discussed.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.913-924
• /
• 2022

In this paper, we presented a database construction of undersea images for the Habitats of Ecklonia cava and Sargassum and conducted an experiment for semantic segmentation using state-of-the-art (SOTA) models such as High Resolution Network-Object Contextual Representation (HRNet-OCR) and Shifted Windows-L (Swin-L). The result showed that our segmentation models were superior to the existing experiments in terms of the 29% increased mean intersection over union (mIOU). Swin-L model produced better performance for every class. In particular, the information of the Ecklonia cava class that had small data were also appropriately extracted by Swin-L model. Target objects and the backgrounds were well distinguished owing to the Transformer backbone better than the legacy models. A bigger database under construction will ensure more accuracy improvement and can be utilized as deep learning database for undersea images.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.21-33
• /
• 2022

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.