• Journal of Korean Society of Archives and Records Management
• /
• v.21 no.4
• /
• pp.101-115
• /
• 2021

Access re-review is a valuable and important task, but it is burdensome for archivists. Thus, an access re-review automation was proposed to address this. In this situation, the National Archives of Korea actually utilized the access re-review solution in the performance of the "2020 Access Re-Review Project" and compared and analyzed it with human work. The project was, however, not a research project centered on analysis on access re-review solutions, and it has a limited result in terms of experimental use of commercial programs. Nevertheless, in the current situation where there are only macro and superficial discussions on access re-review of intelligent archives, it would be meaningful to apply the access re-review solution to archivists in real businesses and examine the results. This paper seeks to discuss the practicality that can mitigate the task of access re-review through an analysis of use cases of access re-review solutions.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.1
• /
• pp.18-23
• /
• 2022

Electrohydrodynamic jet (e-jet) printing, a type of direct contactless microfabrication technology, is a versatile fabrication process that enables a wide range of micro/nanopattern arrays by applying a strong electric field between the nozzle and the substrate. In general, the morphology and the thickness of polymers/quantum dot micropatterns show a systematic dependence on the diameter of the nozzle and the ink composition with a fully automated printing machine. The purpose of this report is to provide typical examples of e-jet printed micropatterns of polymers/quantum dots to explain the effect of each process variable on the result of experiments. Here, we demonstrate several operating conditions that allow high-resolution printing of layers of polymers/quantum dots with a precise control over thickness and submicron lateral resolution.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.21-28
• /
• 2022

ASTC is one of the standard texture formats supported in OpenGL ES 3.2 and Vulkan 1.0 (and later versions), and it has been increasingly used on mobile platforms (Android and iOS). ASTC's most important feature is the block size configuration, thereby providing a trade-off between compression quality and rates. With the higher number of textures, however, it is difficult to manually determine the optimal block sizes of each texture. To solve the problem, we present a new approach based on PSNR values to automatically determine the ASTC block size. A brute-force approach, which compresses a texture on all block sizes and compares the PSNR values of the compressed textures, can increase the compression time by up to 14 times. In contrast, our three-step approach minimizes the compression-time overhead. According to our experiments on a texture set including 64 various textures, our method determined the block sizes from 4×4 to 12×12 and reduced the size of compressed files by 68%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.4
• /
• pp.210-219
• /
• 2023

The decline in the rural populace and an aging workforce have led to fatalities due to worsening environments and hazards within vinyl greenhouses. Therefore, it is necessary to automate crop cultivation and disease detection system in greenhouses to prevent labor loss. In this paper, an object detection-based model is used to detect diseased crop in greenhouses. In addition, the system proposed configures the environment of the artificial intelligence model in the cloud to ensure stability. The system captures images taken inside the vinyl greenhouse and stores them in a database, and then downloads the images to the cloud to perform inference based on Yolo-v4 for detection, generating JSON files for the results. Analyze this file and send it to the database for storage. From the experimental results, it was confirmed that disease detection through object detection showed high performance in real environments like vinyl greenhouses. It was also verified that efficient monitoring is possible through the database

• Journal of Advanced Navigation Technology
• /
• v.27 no.4
• /
• pp.473-480
• /
• 2023

This study evaluated a novel method of defining the automatic flight path of unmanned aerial vehicles (UAVs) for search and rescue missions in a VR environment. The developed VR content reserves miniature digital twins of a building in the fire and a steep mountain terrain site. The users drow the UAV's scanning path using hand gestures on the surface of digital twins, and then the UAV make an automatic flight along the defined path. According to human-in-the-loop simulation tests comparing the novel method with a conventional manual flight task with 19 participants, the novel method did not improve the mission performance but participants felt a lower mental workload. The designer may need to consider the automation support on the vulnerable points of the SAR mission environment while maintaining experts' mapping capability.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.206-208
• /
• 2022

As the big data industry has recently developed significantly, interest in privacy violations caused by personal information leakage has increased. There have been attempts to automate this through named entity recognition in natural language processing. In this paper, named entity recognition data is constructed semi-automatically by identifying sentences with de-identification information from de-identification information in Korean Wikipedia. This can reduce the cost of learning about information that is not subject to de-identification compared to using general named entity recognition data. In addition, it has the advantage of minimizing additional systems based on rules and statistics to classify de-identification information in the output. The named entity recognition data proposed in this paper is classified into twelve categories. There are included de-identification information, such as medical records and family relationships. In the experiment using the generated dataset, KoELECTRA showed performance of 0.87796 and RoBERTa of 0.88.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.302-313
• /
• 2023

This paper aims to develop a framework that can fully automate the quality management of training data used in large-scale Artificial Intelligence (AI) models built by the Ministry of Science and ICT (MSIT) in the 'AI Hub Data Dam' project, which has invested more than 1 trillion won since 2017. Autonomous driving technology using AI has achieved excellent performance through many studies, but it requires a large amount of high-quality data to train the model. Moreover, it is still difficult for humans to directly inspect the processed data and prove it is valid, and a model trained with erroneous data can cause fatal problems in real life. This paper presents a dataset reconstruction framework that removes abnormal data from the constructed dataset and introduces strategies to improve the performance of AI models by reconstructing them into a reliable dataset to increase the efficiency of model training. The framework's validity was verified through an experiment on the autonomous driving dataset published through the AI Hub of the National Information Society Agency (NIA). As a result, it was confirmed that it could be rebuilt as a reliable dataset from which abnormal data has been removed.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.129-136
• /
• 2022

The most important part of the smart livestock building system is to maintain a breeding environment so that livestock can grow to high quality despite changes in the internal and external atmospheric environment. Especially, it is very important to maintain the temperature and humidity in the livestock building because various diseases occur during the summer and winter. To manage the environment suitable for livestock, a smartfarm system for livestock building is applied, but it is very expensive. In this study, we propose a hardware design and control method for low cost system based on HMI and fuzzy control. To evaluate the performance of the proposed system, we did a simulation experiment in the atmospheric conditions of summer and winter. As a result, it showed the performance of minimizing the temperature and humidity stress of livestock. And when applied to the livestock building, the proposed system showed stable control performance even in the change of the external atmospheric environment. Therefore, as with these results, if proposed system in this study is applied to the smart farm system, it will be effective in managing the environment of livestock building.

• Korean Chemical Engineering Research
• /
• v.61 no.2
• /
• pp.247-257
• /
• 2023

Precise counting of cell number stands in important position within clinical and research laboratories. Conventional methods such as hemocytometer, migration/invasion assay, or automated cell counters have limited in analytical time, cost, and accuracy., which needs an alternative way with time-efficient in-situ approach to broaden the application avenue. Here, we present simple coding-based cell counting method using image analysis tool, freely available image software (ImageJ). Firstly, we encapsulated RFP-expressing bacteria in a droplet using microfluidic device and automatically performed fluorescence image-based analysis for the quantification of cell numbers. Also, time-lapse images were captured for tracking the change of cell numbers in a droplet containing different concentrations of antibiotics. This study confirms that our approach is approximately 15 times faster and provides more accurate number of cells in a droplet than the external analysis program method. We envision that it can be used to the development of high-throughput image-based cell counting analysis.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.2
• /
• pp.329-335
• /
• 2023

Avocado, a superfood selected by Time magazine and one of the late ripening fruits, is one of the foods with a big difference between local prices and domestic distribution prices. If this sorting process of avocados is automated, it will be possible to lower prices by reducing labor costs in various fields. In this paper, we aim to create an optimal classification model by creating an avocado dataset through crawling and using a number of deep learning-based transfer learning models. Experiments were conducted by directly substituting a deep learning-based transfer learning model from a dataset separated from the produced dataset and fine-tuning the hyperparameters of the model. When an avocado image is input, the model classifies the ripeness of the avocado with an accuracy of over 99%, and proposes a dataset and algorithm that can reduce manpower and increase accuracy in avocado production and distribution households.