• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.31-43
• /
• 2022

Recently, metaverse is rapidly expanding its area as a platform that can be applied to various fields. In particular, the function that allows many users to interact in a three-dimensional space allows VR/AR-based educational content to be used as a more advanced concept. Due to the nature of engineering education, it is often based on three-dimensional objects. In the case of a three-dimensional object, it is difficult to explain through two-dimensional videos or documents, and it becomes more difficult to express when the process of changing the object is included. The three-dimensional space of the metaverse can improve this difficulty based on real-time rendering. Another characteristic of engineering education is that there are many invisible elements. Although it is involved in the movement of objects due to electromagnetic fields, magnetic fields, and forces, it is the main reason for increasing learning difficulty because it is invisible. These problems can also help learning because they can be visually represented in the metaverse space. In this paper, the results of the establishment of the metaverse platform for engineering education and the real-time lecture contents produced based on it are described, and the applied results and lecture evaluation are discussed. Lectures using a total of 9 metaverse contents were conducted, and 90% of the positive lecture evaluation results were obtained.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.67-77
• /
• 2022

The sense of touch by natural wind is one of the most common feels that every person experiences in daily life. However, it has been rarely studied how natural wind can be reproduced in a VR environment and whether the multisensory contents equipped with artificial winds do improve human emotion or not. To address these issues, we first propose a wind reproduction VR system guided by video and wind capture data and also study the effect of the system on positive affect. We collected wind direction and speed data together with a 360-degree video on a yacht. These pieces of data were used to produce a multisensory VR environment by our wind reproduction VR system. 19 college students participated in the experiments, where the Korean version of Positive and Negative Affect Schedule (K-PANAS) was introduced to measure their emotions. Through the K-PANAS, we found that 'inspired' and 'active' emotions increase significantly after experiencing the yacht VR contents with artificial wind. Our experimental results also show that another emotion, 'interested', is most notably affected depending on the presence of the wind. The presented system can be effectively used in various VR applications such as interactive media and experiential contents.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.79-89
• /
• 2022

With the popularity and the advanced graphics hardware technology of mobile devices, various mobile applications that help children with physical activities have been studied. This paper presents SandUp, a mobile application that guides the play of building sand castles using artificial intelligence and augmented reality(AR) technology. In the process of building the sandcastle, children can interactively explore the target virtual sandcastle through the smartphone display using AR technology. In addition, to help children complete the sandcastle, SandUp informs the sand shape and task required step by step and provides visual and auditory feedback while recognizing progress in real-time using the phone's camera and deep learning classification. We prototyped our SandUp app using Flutter and TensorFlow Lite. To evaluate the usability and effectiveness of the proposed SandUp, we conducted a questionnaire survey on 50 adults and a user study on 20 children aged 4~7 years. The survey results showed that SandUp effectively helps build the sandcastle with proper interactive guidance. Based on the results from the user study on children and feedback from their parents, we also derived usability issues that can be further improved and suggested future research directions.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.1-22
• /
• 2023

Existing studies on mixed ratings that combine ESG ratings and credit ratings have been rare. Through meta-frontier analysis, this study examines the relationship between the prime and non-prime groups in ESG ratings, credit ratings, and mixed ratings that consider ESG ratings and credit ratings at the same time. Efficiency was compared. Meta-frontier analysis was used to compare the efficiency of 143 listed manufacturing companies in Korea between the prime and non-prime groups based on the ESG ratings assigned to them by KCGS and the credit ratings assigned by Korea's three major credit rating agencies. As a result of this study, first, the meta-efficiency of the prime mixed-grade group was statistically more efficient than the non-prime mixed-grade group under the variable return scale (VRS) assumption. Second, the prime ESG rating group had a relatively higher proportion of scale inefficiency than the non-prime ESG rating group. Third, in terms of economies of scale, the prime credit rating group had a higher proportion of diminishing returns to scale (DRS) than the non-prime credit rating group. This study will help companies interested in sustainability management to do ESG management.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.69-77
• /
• 2023

This study proposes a rigid-body tracking based virtual avatar application method to increase the social presence and provide various experiences of virtual reality(VR) users in an immersive virtual environment. The proposed method estimates the motion of a virtual avatar through inverse kinematics based on real-time rigid-body tracking based on motion capture using markers. Through this, it aims to design a highly immersive virtual environment with simple object manipulation in the real world. Science experiment educational contents are produced to experiment and analyze applications related to immersive virtual environments through virtual avatars. In addition, audiovisual education, full-body tracking, and the proposed rigid-body tracking method were compared and analyzed through survey. In the proposed virtual environment, participants wore VR HMDs and conducted a survey to confirm immersion and educational effects from virtual avatars performing experimental educational actions from estimated motions. As a result, through the method of utilizing virtual avatars based on rigid-body tracking, it was possible to induce higher immersion and educational effects than traditional audiovisual education. In addition, it was confirmed that a sufficiently positive experience can be provided without much work for full-body tracking.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.137-147
• /
• 2023

This paper presents a motion-capture-based projection VR system to explore the effectiveness of gamification in improving environmental awareness. We examine the key components of positive and negative VR game content and analyze the impact of individual and cooperative play methods on promoting sustainable behaviors. Our findings are as follows. Firstly, we discovered that the use of positive content in individual play mode was effective in improving awareness of the importance of recycling. Secondly, we confirmed that the use of positive content in cooperative play mode and the use of negative content in individual play mode were each effective in enhancing awareness of the seriousness of environmental pollution. Thirdly, we found that experiencing positive content first, followed by negative content, in individual play mode was effective in increasing interest in the environment. Based on these findings, we determined that adjusting the order of use of positive and negative content is more effective than simply using positive or negative content alone for improving environmental awareness. Moreover, considering the importance of recycling, the seriousness of environmental pollution, and the level of interest in the environment, we confirmed that individual play mode is effective and cooperative play mode can be more effective depending on the measure.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.85-92
• /
• 2023

Recently, interest in artificial intelligence has increased due to the development of artificial intelligence fields such as ChatGPT and self-driving cars. However, there are still many unknown elements in training process of artificial intelligence, so that optimizing the model requires more time and effort than it needs. Therefore, there is a need for a tool or methodology that can analyze the weight changes during the training process of artificial intelligence and help out understatnding those changes. In this research, I propose a visualization system which helps people to understand the accumulated weight changes. The system calculates the weights for each training period to accumulates weight changes and stores accumulated weight changes to plot them in 3D space. This research will allow us to explore different aspect of artificial intelligence learning process, such as understanding how the model get trained and providing us an indicator on which hyperparameters should be changed for better performance. These attempts are expected to explore better in artificial intelligence learning process that is still considered as unknown and contribute to the development and application of artificial intelligence models.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.33-43
• /
• 2023

Not only emotions affect physical sensations, but they also have an impact on physical movements. The responses to emotions vary depending on the type of emotional stimuli. However, research on the effects of emotional stimuli on the activation of bodily movements has not been rigorously examined, and these effects have not been investigated in Autonomous Emotion Recognition (AER) systems. In this study, we aimed to compare the emotional responses of 20 participants to three types of emotional stimuli (words, pictures, and videos) and investigate their activation or deactivation for the AER system. Our dependent measures included emotional responses, computer-based self-reporting methods, and bodily movements recorded using motion capture devices. The results suggested that video stimuli elicited higher levels of emotional movement, and emotional movement patterns were similar across different types of emotional stimuli for happiness, sadness, anger, and neutrality. Additionally, the findings indicated that bodily changes observed during video stimuli had the highest classification accuracy. These findings have implications for future research on the bodily changes elicited by emotional stimuli.