• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.405-408
• /
• 2016

Games like Go, Chess, Janggi have helped to brain development of the people. These games are developed by computer program. And many algorithms have been developed to allow myself to play. The person winning chess program was developed in the 1990s. But game of go is too large number of cases. So it was considered impossible to win professional go player. However, with the use of MCTS(Monte Carlo Tree Search) and CNN(Convolutional Neural Network), the performance of the go algorithm is greatly improved. In this paper, using CNN and MCTS were proceeding development of go algorithm. Using the manual of go learning CNN look for the best position, MCTS calculates the win probability in the game to proceed with simulation. In addition, extract pattern information of go using existing manual of go, plans to improve speed and performance by using it. This method is showed a better performance than general go algorithm. Also if it is receiving sufficient computing power, it seems to be even more improved performance.

• Journal of the Korea Society for Simulation
• /
• v.28 no.1
• /
• pp.23-39
• /
• 2019

The use of drone-bots is demanded in times regarding the reduction of military force, the spread of the life-oriented thought, and the use of innovative technology in the defense through the fourth industrial revolution. Especially, the drone's surveillance and reconnaissance are expected to play a big role in the future battlefield. However, there are not many cases in which the concept of operation is studied scientifically. In this study, We propose search algorithms for reconnaissance drone through simulation analysis. In the simulation, the drone and target move linearly in continuous space, and the target is moving adopting the Random-walk concept to reflect the uncertainty of the battlefield. The research investigates the effectiveness of existing search methods such as Parallel and Spiral Search. We analyze the probabilistic analysis for detector radius and the speed on the detection probability. In particular, the new detection algorithms those can be used when an enemy moves toward a specific goal, PS (Probability Search) and HS (Hamiltonian Search), are introduced. The results of this study will have applicability on planning the path for the reconnaissance operations using drone-bots.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1384-1389
• /
• 2020

Although the fintech industry is developing rapidly around the world, the domestic development situation is rather slow compared to the speed. Therefore, the future development direction can be set by analyzing the current status of the fintech industry in order to suggest the direction of development in the domestic fintech industry. The main services provided by companies belonging to the domestic fintech industry are in the areas of remittance settlement, financial investment, asset management, crowdfunding, P2P finance, overseas remittance, fintech SI, insurtech, virtual currency, security, and authentication. It is divided into. This study identifies the main technologies used in the service and grasps the current domestic status. In addition, it analyzes the distribution of workers by each service. This study is expected to play an important role in the development of the financial industry through technical analysis of fintech companies.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.81-86
• /
• 2020

This study aimed to speculate on Youtube for national certification education in makeup in the Untact period derived from the pandemic phenomenon such as the COVID 19. For the purpose, this study surveyed perception on Youtube on national certification education, characteristics of the programs, selection standards, continuance and recommendation intention and supplementations. The results are: The perception on Youtube was very positive(75.5%); Among characteristics, the mean value of informativeness was 3.54, that of play speed control as an advantage was 4.07 and that of feedback limit as a disadvantage was 3.64. In respect to selection standards, 44.5% of the subjects selected a program based on professionalism; 82.0% had continuance intention and 82.6% had recommendation intention. As for the needs of supplementation, the mean value of sanitation education was 4.20, that of updated regulations was 4.13 and that of feedback was 4.0. Therefore, it is suggested that if an interactive education system is supplemented in exact information and feedback, Youtube makeup certification programs will be further facilitated as useful education materials for makeup development.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1464-1475
• /
• 2020

Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.

• Journal of East Asia Management
• /
• v.3 no.1
• /
• pp.11-23
• /
• 2022

Under the circumstances of China's slower economic growth, the first document ofthe central committee of the CPC continue to focus on "three agricultures" problems, agriculture play a basic role on China's economic. Since 2007, the first document directly stresses the important role of agricultural and fisheries every year. Central Government Working Report of 2015 also stresses that under the new normal of economy, it is important to improve quality and efficiency of agriculture. Agricultural focus going forward will be on improving capacity of competitiveness, innovation and sustainable development.The fishery as an important part of agriculture plays a vital role in the protection of national food security, the prosperity of the rural economy and the optimization of national food structure. However, the situation faced on accelerating the speed of Chinese fisheries is still grim. As an important fishery breeding city in my country, Weihai has achieved remarkable results in the development of fisheries. Based on the input-output indicators of Weihai City from 2010 to 2020, this article uses the DEA model method to conduct a comprehensive analysis of the factors affecting the fishery production efficiency in Weihai City. This paper calculates the two stages of comprehensive efficiency, pure technical efficiency and scale efficiency, and comprehensive compares the two stages. The research results show that: From 2010 to 2020, the average comprehensive technical efficiency of Weihai fishery was 0.928, the average scale efficiency was 0.963, and the average pure technical efficiency was 0.963. The comprehensive technical efficiency of Weihai fishery production showed an upward and downward trend, the pure technical efficiency showed a downward and then upward trend, and the pure technical efficiency showed a fluctuating trend.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.299-307
• /
• 2022

Harmony Search (HS) is a relatively recently developed meta-heuristic optimization algorithm, and various studies have been conducted on it. HS is based on the musician's improvisational performance, and the objective variables play the role of the instrument. However, each instrument is given only a sound range, and there is no concept of a scale that can be said to be the basis of music. In this study, the performance of the algorithm is improved by introducing a scale to the existing HS and quantizing the bandwidth. The introduced scale was applied to HM initialization instead of the existing method that was randomly initialized in the sound band. The quantization step can be set arbitrarily, and through this, a relatively large bandwidth is used at the beginning of the algorithm to improve the exploration of the algorithm, and a small bandwidth is used to improve the exploitation in the second half. Through the introduction of scale and bandwidth quantization, it was possible to reduce the algorithm performance deviation due to the initial value and improve the algorithm convergence speed and success rate compared to the existing HS. The results of this study were confirmed by comparing examples of optimization values for various functions with the conventional method. Specific comparative values were described in the simulation.

• Journal of Integrative Natural Science
• /
• v.15 no.3
• /
• pp.131-136
• /
• 2022

Cell migration is essential for diverse cellular processes including wound healing, immune response, development, and cancer metastasis. Pi3-kinase (PI3K) is a key regulator for actin cytoskeleton and phosphorylates phosphatidylinositol (4,5)-diphosphate (PIP2) to phosphatidylinositol (3,4,5)-trisphosphate (PIP3). High levels of PIP3 by PI3Ks are associated with increased levels of F-actin and pseudopod extension at the leading edge of migrating cells such as neutrophils and Dictyostelium. LY294002 is a well-known PI3K specific inhibitor. Here, we investigated the effect of LY294002 on cell migration. First, we evaluated the appropriate concentration of dimethyl sulfoxide (DMSO) for using as a solvent for LY294002. DMSO is a highly polar organic reagent and one of the most common solvent for organic and inorganic chemicals. Cell morphology and cell migration were unaffected at the concentrations less than 0.1 % DMSO. Therefore, stock solution of LY294002 was prepared so that the final concentration of DMSO was 0.1 % or less when treated. When cells were treated with LY294002, cell migration was increased in a concentration-dependent manner. The maximum speed was detected in the presence of 30 µM LY294002. These results suggest that PI3Ks play a inhibitory role in regulating cell migration in our experimental conditions.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.159-167
• /
• 2009

The vehicles play a significant role in modern people's life as economy grows. The development of car navigation system(CNS) provides various convenience because it shows the driver where they are and how to get to the destination from the point of source. However, the existing map-based CNS does not consider any environments such as traffic congestion. Given the same starting point and destination, the system always provides the same route and the required time. This paper proposes a path planning method with traffic prediction by applying historical driving information to the Fuzzy theory and Bayesian update. Fuzzy theory classifies the historical driving information into groups of leaving time and speed rate, and the traffic condition of each time zone is calculated by Bayesian update. An ellipse area including starting and destination points is restricted in order to reduce the calculation time. The accuracy and practicality of the proposed scheme are verified by several experiments and comparisons with real navigation.

• Korean Journal of Exercise Nutrition
• /
• v.13 no.2
• /
• pp.161-167
• /
• 2009

The purpose of this study was to investigate whether two different exercises, acute exhaustive exercise and long-term endurance exercise training could affect to the expression of Mn-SOD, HSP70, and PPAR-γ protein in myocardium. The Wistar-Kyoto rats(n=24, 4 weeks) were used and randomly divided into 3 groups; endurance exercise training group (EET, n=8), acute exhaustive exercise group (AEE, n=8) or control group (CON, n=8). EET performed treadmill exercise for 12 weeks (5 days/week, 30~60 min/day). AEE exercised treadmill running (speed increased gradually to 14-26 m/min, 60 min ±10min) until exhausted when EET finished the program. Then, all the rats were sacrificed 48 hours rest at least after the last session of their own exercise program. Hearts were isolated and then the expression of Mn-SOD, HSP70, and PPAR-γ were analyzed by western blotting. One-way repeated ANOVA was used and p value under 0.05 was considered as statistical significance. The results were followed as; the expression of Mn-SOD of AEE was decreased compared with CON. However, the expression of Mn-SOD of EET was increased compared with CON. There was significant difference between AEE and EET in the expression of Mn-SOD. The expressions of HSP70 and PPAR-γ in the both AEE and EET were significantly increased compared with CON. In conclusion, acute exhaustive exercise might induce oxidative stress wheres endurance exercise training could ameliorate the oxidative conditions by increase of Mn-SOD, HSP70, and PPAR-γ. Therefore, we suggested that endurance exercise training could enhance the complementary antioxidant system and improve to prevent apoptosis. Further, a long-term moderat aerobic exercise program might play a important role in mitochondrial biogenesis in the heart.