• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.11-14
• /
• 2020

The importance of data in the development of deep learning is very high. Data with high morphological features are usually utilized in the domains where careful lens calibrations are needed by a human to capture those data. Synthesis of high morphological data for that domain can be a great asset to improve the classification accuracy of systems in the field. Unsupervised learning can be employed for this task. Generating photo-realistic objects of interest has been massively studied after Generative Adversarial Network (GAN) was introduced. In this paper, we propose Morpho-GAN, a method that unifies several GAN techniques to generate quality data of high morphology. Our method introduces a new suitable training objective in the discriminator of GAN to synthesize images that follow the distribution of the original dataset. The results demonstrate that the proposed method can generate plausible data as good as other modern baseline models while taking a less complex during training.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.129-136
• /
• 2020

Augmented reality (AR) technology assists construction workers by superimposing additional virtual information onto their real worksite environments. Ideally, this provides them with a better understanding of their tasks and hence boosts task performance. However, the additional information that AR places in users' field of view could limit their ability to understand what is going on in their surroundings and to predict how conditions may change in the near future. AR-assisted systems on construction sites could therefore expose their users to safety risks due to disturbance from the system. Hence, it is important to understand how AR-assisted systems can block users' understanding of their immediate environments, and in turn, how worksite safety in the construction industry could be improved through better design of such systems. This preliminary research conducted a laboratory experiment that simulated rebar inspection tasks and compared the situational awareness of AR users against that of subjects using traditional paper-based inspection methods, as measured by the Situation Awareness Rating Technique. Based on the results, we discuss the safety impact of head-mounted AR-assisted displays on situational awareness during construction tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2718-2731
• /
• 2023

This paper presents a method of using syntax and shallow semantic analysis for Vietnamese question generation (QG). Specifically, our proposed technique concentrates on investigating both the syntactic and shallow semantic structure of each sentence. The main goal of our method is to generate questions from a single sentence. These generated questions are known as factoid questions which require short, fact-based answers. In general, syntax-based analysis is one of the most popular approaches within the QG field, but it requires linguistic expert knowledge as well as a deep understanding of syntax rules in the Vietnamese language. It is thus considered a high-cost and inefficient solution due to the requirement of significant human effort to achieve qualified syntax rules. To deal with this problem, we collected the syntax rules in Vietnamese from a Vietnamese language textbook. Moreover, we also used different natural language processing (NLP) techniques to analyze Vietnamese shallow syntax and semantics for the QG task. These techniques include: sentence segmentation, word segmentation, part of speech, chunking, dependency parsing, and named entity recognition. We used human evaluation to assess the credibility of our model, which means we manually generated questions from the corpus, and then compared them with the generated questions. The empirical evidence demonstrates that our proposed technique has significant performance, in which the generated questions are very similar to those which are created by humans.

• Educational Technology International
• /
• v.25 no.1
• /
• pp.27-65
• /
• 2024

The purpose of this study was to identify differences in learning patterns according to content complexity in video-based learning environments and to derive variables that have an important effect on learning achievement within particular learning contexts. To achieve our aims, we observed and collected data on learners' cognitive processes through perceived affordances, using behavioral logs and eye movements as specific indicators. These two types of reaction data were collected from 67 male and female university students who watched two learning videos classified according to their task complexity through the video learning player. The results showed that when the content complexity level was low, learners tended to navigate using other learners' digital logs, but when it was high, students tended to control the learning process and directly generate their own logs. In addition, using derived prediction models according to the degree of content complexity level, we identified the important variables influencing learning achievement in the low content complexity group as those related to video playback and annotation. In comparison, in the high content complexity group, the important variables were related to active navigation of the learning video. This study tried not only to apply the novel variables in the field of educational technology, but also attempt to provide qualitative observations on the learning process based on a quantitative approach.

• Journal of Information Technology Applications and Management
• /
• v.30 no.1
• /
• pp.81-95
• /
• 2023

As the DT of micro businesses emerges as an important task, the government is also promoting support projects such as policy establishment and micro business education. This study aims to develop a new index (checklist) that can objectively measure the level of digital literacy required for DT in the tertiary industry, which accounts for the largest share of micro business owners. In this study, indicators were derived through review of existing studies and FGI, and the validity and reliability of Likert 5 were measured for decision makers in the tertiary industry. In the field of digital literacy for micro business owners, a total of 22 indicators were developed, largely composed of basic technology environment competency, information utilization competency, information dissemination and production capability, and mind recognition capability. This study has academic significance in that it can contribute to accurately understanding the digital capabilities of micro business owners by developing a digital literacy index for micro business owners, a specific group lacking in research.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.221-227
• /
• 2024

In autonomous navigation systems, the need for fast and accurate image processing using deep learning and advanced sensor technologies is paramount. These systems rely heavily on the ability to process and interpret visual data swiftly and precisely to ensure safe and efficient navigation. Despite the critical importance of such capabilities, there has been a noticeable lack of research specifically focused on ship image classification for maritime applications. This gap highlights the necessity for more in-depth studies in this domain. In this paper, we aim to address this gap by presenting a comprehensive comparative study of ship image classification using two distinct neural network models: the Feedforward Neural Network (FNN) and the Convolutional Neural Network (CNN). Our study involves the application of both models to the task of classifying ship images, utilizing a dataset specifically prepared for this purpose. Through our analysis, we found that the Convolutional Neural Network demonstrates significantly more effective performance in accurately classifying ship images compared to the Feedforward Neural Network. The findings from this research are significant as they can contribute to the advancement of core source technologies for maritime autonomous navigation systems. By leveraging the superior image classification capabilities of convolutional neural networks, we can enhance the accuracy and reliability of these systems. This improvement is crucial for the development of more efficient and safer autonomous maritime operations, ultimately contributing to the broader field of autonomous transportation technology.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.9-18
• /
• 2024

Digital therapy has emerged as a novel treatment modality, propelled by advancements in information and communication technology. In the last five years, there has been a substantial surge in research publications addressing digital therapeutics (DTx) interventions, signaling a sustained upward trajectory in this field. The dynamic nature of computer science, marked by continuous innovation and development, underscores the need for agile adaptation to rapid changes. Consequently, computer science education is compelled to offer students insights into the latest trends. This research endeavors to contribute to the evolving landscape by developing textbooks that impart knowledge about DTx, an integration of information technology. The study focuses on the application of these textbooks to elementary and middle school students in South Korea. The instructional materials have been carefully organized to enable students to learn about the principle of Attention Deficit Hyperactivity Disorder (ADHD) DTx at the elementary level and the DTx that can prevent and address the digital drama at the middle school level. Based on the application of the textbook, students who received instruction using the textbook showed statistically significant improvements in all subcategories of creative problem-solving ability, including idea modification, visualization, task focus, analogy, idea generation, and elaboration (p<.01). Additionally, there were statistically significant changes in students' self-efficacy before and after using the textbook, with negative efficacy decreasing, and positive efficacy and social efficacy increasing (p<.001).

• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• Journal of Radiation Protection and Research
• /
• v.33 no.4
• /
• pp.151-160
• /
• 2008

In Korean nuclear power plants (NPPs), two thermoluminescent dosimeters (TLD) were provided to workers who work in an inhomogeneous radiation field; one on the chest and the other on the head. In this way, the effective dose for radiation workers at NPPs was determined by the high deep dose between two radiation dose from these TLDs. This represented a conservative method of evaluating the degree of exposure to radiation. In this study, to prevent the overestimation of the effective dose, field application experiments were implemented using two-dosimeter algorithms developed by several international institutes for the selection of an optimal algorithm. The algorithms used by the Canadian Ontario Power Generation (OPG) and American ANSI HPS N13.41, NCRP (55/50), NCRP (70/30), EPRI (NRC), Lakslumanan, and Kim (Texas A&M University) were extensively analyzed as two-dosimeter algorithms. In particular, three additional TLDs were provided to radiation workers who wore them on the head, chest, and back during maintenance periods, and the measured value were analyzed. The results found no significant differences among the calculated effective doses, apart from Lakshmanan's algorithm. Thus, this paper recommends the NCRP(55/50) algorithm as an optimal two-dosimeter algorithm in consideration of the solid technical background of NCRP and the convenience of radiation works. In addition, it was determined that a two-dosimeter is provided to a single task which is expected to produce a dose rate of more than 1 mSv/hr, a difference of dose rates depending on specific parts of the body of more than 30%, and an exposure dose of more than 2 mSv.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.21-29
• /
• 2016

Cell segmentation is an important but time-consuming and laborious task in biological image analysis. An automated, robust, and fast method is required to overcome such burdensome processes. These needs are, however, challenging due to various cell shapes, intensity, and incomplete boundaries. A precise cell segmentation will allow to making a pathological diagnosis of tissue samples. A vast body of literature exists on cell segmentation in microscopy images [1]. The majority of existing work is based on input images and predefined feature models only - for example, using a deformable model to extract edge boundaries in the image. Only a handful of recent methods employ data-driven approaches, such as supervised learning. In this paper, we propose a novel data-driven cell segmentation algorithm for bright-field microscopy images. The proposed method minimizes an energy formula defined by two dictionaries - one is for input images and the other is for their manual segmentation results - and a common sparse code, which aims to find the pixel-level classification by deploying the learned dictionaries on new images. In contrast to deformable models, we do not need to know a prior knowledge of objects. We also employed convolutional sparse coding and Alternating Direction of Multiplier Method (ADMM) for fast dictionary learning and energy minimization. Unlike an existing method [1], our method trains both dictionaries concurrently, and is implemented using the GPU device for faster performance.