• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.537-542
• /
• 2021

This paper improves the possibility of recognizing fast-moving objects through the YOLO (You Only Look Once) deep learning recognition model in an application environment for object recognition in images. The purpose was to study the method of collecting semantic data through processing. In the recognition model, the moving object recognition error was identified as unrecognized because of the difference between the frame rate of the camera and the moving speed of the object and a misrecognition due to the existence of a similar object in an environment adjacent to the object. To minimize the recognition errors by compensating for errors, such as unrecognized and misrecognized objects through the proposed data collection method, and applying vision processing technology for the causes of errors that may occur in images acquired for sports (tennis games) that can represent real similar environments. The effectiveness of effective secondary data collection was improved by research on methods and processing structures. Therefore, by applying the data collection method proposed in this study, ordinary people can collect and manage data to improve their health and athletic performance in the sports and health industry through the simple shooting of a smart-phone camera.

• Journal of the Korean Society of Floral Art and Design
• /
• no.42
• /
• pp.97-116
• /
• 2020

In this paper, the need for lifelong education and distance education is increasing due to the decrease of population and the increase of life expectancy. In addition, the popularization and everydayization of education, which combines daily life and learning, is an educational feature. Individuals can more easily access knowledge, and video plays an important role. Video content is the most basic medium that leads to the popularization and daily life of education. With the development of information and communication technology, popularization of media content production and editing technology, anyone can easily create and share. The video education contents business is expected to increase globally through SNS. Especially, the video contents education industry related to flower design is regarded as a suitable content field in an era where environment is essential. In the modern era, characterized by the "one-person household, one-person media" era, the environment of plants protects people from stress by restoring human emotional efficiency, environmental comfort, and stability. In other words, because humans have a preference for nature, plants play an important role for humanity recovery. Against this backdrop, flower design is expected to be a promising industrial sector with high growth, high value added and high job creation effects. In the era of the fourth revolution of the human race, competitive video contents are expected to influence the growth of the future country. will be.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• Journal of the Korean Wood Science and Technology
• /
• v.32 no.5
• /
• pp.12-19
• /
• 2004

This study was performed to investigate the optimum condition of protease production from submerged culture of oak mushroom (Lentinula edodes, Sanlim No. 5) and its enzymatic features. Among several combinations of media, the combination of wheat bran, corn flour, water and corn oil (WB+CF+W+ CO) yielded 84.8 U/g of maximum protease activity. This combination of ingredients, in spite of not being particularly protein-rich in comparison to the other media, allowed for good growth of the fungus and maximal protease production. Comparison of different growth medium liquids indicated that demineralized water afforded the best growth of the fungus and the highest protease activity. Acetate buffer and acidified water negatively affected The protease production peaked around 72 hr of incubation, and decreased thereafter. The molecular weights of produced protease were about 45,000 by Sephadex G-75 chromatography. The pH optimum for protease activity was 4, while maximal activity incubated at 37℃ for 1 hr was observed between pH 4~6. The optimum temperature of this protease was 55℃, and the enzyme was active over a broad temperature range (30~60℃), indicating that this protease would be suitable for a wide range of applications where. different pH and temperature are necessary, such as digestive aids, food industry, beer and tannery industries.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.6
• /
• pp.87-99
• /
• 2022

The meat consumption per person has continuously increased in recent years. However, the labor force in the domestic livestock industry has decreased due to the declining and ageing population. In order to increase productivity, the government have developed and distributed design standard of livestock houses. Presently, report showed that the adaptation rate of the developed livestock house design standard on the real farm was still low. Thus, this paper aimed to find ways to improve the utilization of the design standard through surveys. The survey was conducted on 650 farms across the country. Analysis of the result showed that in the poultry house, the unawareness of farmers to the design standard was found to be the biggest reason for not using the design standards. On the other hand, in the swine house, the previously built swine houses do not fit with the design standard. From these result, the following recommendations were suggested: 1) promotion and education are needed to enhance usage of design standard; 2) since it is impossible to make a design standard considering all the farm sites, it is important to consider the conditions of various farm site prior to enhancement of the design standard; 3) improvement factors such as reinforcing the ventilation design, reflecting animal welfare, preventing livestock diseases, and enhancing ICT devices can also be promoted.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.395-402
• /
• 2022

In case of violation of the Personal Information Protection Act, administrative dispositions will be taken according to the legal standards, and the results will be announced. However, the current method has limitations in its effectiveness as repeated administrative dispositions are increasing despite the announcement by the disclosure system of the Personal Information Protection Act. In this paper, we deploy the introduction of the 'public announcement commandment' against violators by analyzing the administrative disposition results according to the violation of the Personal Information Protection Act. It is able to strengthen the existing disclosure system for self-disclose violations by providing easy recognition to the people about the fact of violation itself against the Personal Information Protection Act. Furthermore, we analyze major industries through the industry groups and violations of laws that were subject to publication, and data published on the results of administrative dispositions for violation of the Personal Information Protection Act. Finally, we propose the legal basis for the 'public announcement commandment' which allows the violator to publish by oneself for the announcement of the fact that the corrective action has been taken.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.135-145
• /
• 2022

This paper presented a method to build a predictable smart ammunition logistics system using the 4th industrial technology for ammunition logistics, which is the core functions in the field of defense and logistics. We have analyzed the current level of ammunition logistics with various perspectives such as domestic and overseas logistics policies, technology trends, ammunition logistics characteristics, the smart logistics certification measures by Ministry of Land, Infrastructure and Transport. As a result it is considered that the current ammunition logistics needs needs improvement. To improve this, we presented a direction based on the implications derived after analyzing various ongoing programs such as wired/wireless-based automation, smart ammunition depots, and logistics innovation of the army, navy, and air force that can be applied to the ammunition logistics. In order to implement a data-based smart ammunition logistics management system that can achieve innovation and efficiency of total life cycle while meeting changes in the battlefield environment, we presented 4 objectives such as "automation and modernization of field work", "3D-based storage management & improvement of issuing at war," and "data management for prediction-oriented ammunition management". it is expected that there will be benefits such as improvement of operational continuity, guarantee of ammunition reliability, budget reduction, improvement of inefficiencies such as delay, waiting, and double work, and reduction of accidents.

• KNOM Review
• /
• v.23 no.2
• /
• pp.18-28
• /
• 2020

With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.3
• /
• pp.6-20
• /
• 2022

The restoration of cultural heritage materials is an important research theme. This study improved the existing cultural heritage restoration method and attempted to establish a restoration system for cultural heritage data based on historical documents and visual materials. Recognizing the limitations of existing studies, this paper attempted to restore cultural heritage data through interdisciplinary research. In addition, 3D restoration was carried out after restoration in 2D form based on literature documents rather than existing visual sources. The object of restoration that was selected was "Jeol," which represents the power of the king of Koguryo. Koguryo's Jeol is a type of flag. Jeol appears in the mural in Anak Tomb No. 3. Rather than using only photographic materials of murals, the restoration was carried out through cross-validation of literature data and materials on archaeological art history. This is important in that the restoration carried out in this study is an accurate restoration with a historical understanding based on the literature of the relevant cultural heritage. In this study, a restoration process based on historical records was established. A 3D restoration process was performed by adding and applying visual materials after the object was first shaped based on the literature data. Restoration based on literature and visual materials was carried out based on interdisciplinary research. Therefore, this study aims to build a digital restoration system for cultural heritages and to contribute to spreading the 3D digital restoration research of cultural heritages that can be applied to various platforms.

• Journal of fish pathology
• /
• v.35 no.1
• /
• pp.57-63
• /
• 2022

Vibrio parahaemolyticus and V. vulnificus are known to be infected to human via fisheries products. Therefore, food safety of fisheries products is important for public health and fish industry. This paper was conducted to know how well these human isolates can survive in olive flounder (Paralichthys olivaceus). The growth of V. parahaemolyticus and V. vulnificus showed about 50~60% reduced rates at 25℃ than at 37℃ and did not show any differences according to NaCl concentration of media except the increasing in the growth of V. vulnificus in medium containing 3% NaCl. Artificial infection of 1×10⁶ CFU/fish was carried out to confirm the sensitivity of olive flounder against V. parahaemolyticus and V. vulnificus. After 1 week from injection, no fish was dead. To evaluate nonspecific defense of olive flounder against V. parahaemolyticus and V. vulnificus, the antibacterial potency of serum and epidermal mucus were tested. The number of the vibrios exposed to serum obtained from olive flounder significantly decreased after 3 hours, and epidermal mucus showed decrease of the bacteria over than 90% until 12 hours from exposure. Phagocytosis of head kidney leucocytes of healthy olive flounder against V. parahaemolyticus and V. vulnificus showed in over 70% of leucocytes at the 2 hours. Therefore, cultured olive flounder only as vehicle for human pathogen in environmental water is well developed its antibacterial potency against human pathogens, so the viability of V. parahaemolyticus and V. vulnificus in cultured olive flounder was considered very low.