• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.845-848
• /
• 2017

In this paper, we implemented a system to detect dangerous situations by recognizing the dangerous elements for infants by reading 2D images of children's houses, parks, playgrounds, and living rooms where infants are present through Faster R-CNN. We have implemented a detection model based on data that can be easily obtained from real life. Currently, machine learning is commercialized based on speech recognition and behavior data. However, this model can be applied to various service fields Respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.343-347
• /
• 2002

In this paper, we can easily update teaming information by using database built in web server system in implementation of a web courseware that a learner can effectively team the 'Digital Circuits' subject. Also, we offered multimedia elements such as graphics, animations, and voices etc. for increasing understanding and interaction of teaming and designed and implemented a simulation-type web courseware of practice-oriented. In result, it can encourage a learner with a motive of learning and increase effects of teaming. Also, a learner can learn various contents because we can add teaming contents to database according to needs. Furthermore, it can improve understanding for teaming by offering feedback on the result. In future, we need to design and implement circuits with more complex and many functions by adding circuit with function that can store.

• Journal of The Korean Association of Information Education
• /
• v.10 no.3
• /
• pp.327-340
• /
• 2006

EduGame is suitable to create interesting and self-directed education environment. This paper develops edugame applicable to learning of History centered on Goguryeo history in elementary school. It is named to 'Bukbeol'. The main theme is that we must let elementary students to have a correct understanding about Goguryeo history. It is time to consider that China distorts Goguryeo history. To implement this game we have to consider the interesting elements in contexts and technology in order to overcome the formal combination of education and amusement. Bukbeol is developed with RPG making 2003(RPGツワ一ル2003) made by Enterbrain company in Japan. And this edugame is applied to students to investigate the degree of satisfaction. Results show the possibility for the study of history and necessity of graphic interface.

• Nuclear Engineering and Technology
• /
• v.53 no.11
• /
• pp.3465-3473
• /
• 2021

For a long time, research into integrated deterministic-probabilistic safety assessment has been continuously conducted to point out and overcome the limitations of classical ET (event tree)/FT (fault tree) based PSA (probabilistic safety assessment). The current paper also attempts to assert the reason why a technical transformation from classical PSA is necessary with a re-interpretation of the categories of risk. In this study, residual risk was classified into interpolating- and extrapolating-censored categories, which represent risks that are difficult to identify through an interpolation or extrapolation of representative scenarios due to potential nonlinearity between hardware and human behaviors intertwined in time and space. The authors hypothesize that such risk can be dealt with only if the classical ETs/FTs are freely relocated, entailing large-scale computation associated with physical models. The functional elements that are favorable to find residual risk were inferred from previous studies. The authors then introduce their under-development enabling techniques, namely DICE (Dynamic Integrated Consequence Evaluation) and DeBATE (Deep learning-Based Accident Trend Estimation). This work can be considered as a preliminary initiative to find the bridging points between deterministic and probabilistic assessments on the pillars of big data technology.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.43-54
• /
• 2019

Currently, a majority of artificial intelligence is used to secure big data; however, it is concentrated in a few of major companies. Therefore, automatic data augmentation and efficient learning algorithms for small-scale data will become key elements in future artificial intelligence competitiveness. In addition, it is necessary to develop a technique to learn meanings, correlations, and time-related associations of complex modal knowledge similar to that in humans and expand and transfer semantic prediction/knowledge inference about unknown data. To this end, a neural memory model, which imitates how knowledge in the human brain is processed, needs to be developed to enable knowledge expansion through modality cooperative learning. Moreover, declarative and procedural knowledge in the memory model must also be self-developed through human interaction. In this paper, we reviewed this essential methodology and briefly described achievements that have been made so far.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2012-2027
• /
• 2019

Nutritional disorders are one of the most common diseases of crops and they often result in significant loss of agricultural output. Moreover, the imbalance of nutrition element not only affects plant phenotype but also threaten to the health of consumers when the concentrations above the certain threshold. A number of disease identification systems have been proposed in recent years. Either the time consuming or accuracy is difficult to meet current production management requirements. Moreover, most of the systems are hard to be extended, only detect a few kinds of common diseases with great difference. In view of the limitation of current approaches, this paper studies the effects of different trace elements on crops and establishes identification system. Specifically, we analysis and acquire eleven types of tomato nutritional disorders images. After that, we explore training and prediction effects and significances of super resolution of identification model. Then, we use pre-trained enhanced deep super-resolution network (EDSR) model to pre-processing dataset. Finally, we design and implement of diagnosis system based on deep learning. And the final results show that the average accuracy is 81.11% and the predicted time less than 0.01 second. Compared to existing methods, our solution achieves a high accuracy with much less consuming time. At the same time, the diagnosis system has good performance in expansibility and portability.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.137-143
• /
• 2019

As the performance of computers increases, the use of deep learning, which has faced technical limitations in the past, is becoming more diverse. In many fields, deep learning has contributed to the creation of added value and used on the bases of more data as the application become more divers. The process for obtaining a better performance model will require a longer time than before, and therefore it will be necessary to find an optimal model that shows the best performance more quickly. In the artificial neural network modeling a tuning process that changes various elements of the neural network model is used to improve the model performance. Except Gride Search and Manual Search, which are widely used as tuning methods, most methodologies have been developed focusing on heuristic algorithms. The heuristic algorithm can get the results in a short time, but the results are likely to be the local optimal solution. Obtaining a global optimal solution eliminates the possibility of a local optimal solution. Although the Brute Force Method is commonly used to find the global optimal solution, it is not applicable because of an infinite number of hyper parameter combinations. In this paper, we use a statistical technique to reduce the number of possible cases, so that we can find the global optimal solution.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.93-100
• /
• 2020

This study aims to design and develop effective digital contents to improve the ability for artificial intelligence literacy. First, we defined AI literacy and analyzed the competencies required for artificial intelligence literacy. After selecting the educational elements for AI ability, we composed 10 educational programs. To confirm the appropriateness of designed contents, we verified through content validity test by 10 experts. The CVI value was over 0.75, which was highly valid. The developed content was installed on the online system and applied to 55 AI beginners for 4 weeks. The learners showed a positive result of at least 3.85 in the items of content difficulty, understanding, effectiveness, and learning challenge. As a result of this analysis, we can see that the developed content is positive for helping many people understand AI and improving AI literacy.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.341-347
• /
• 2020

In this paper, we propose to discover the certification items and to study the content system for SW education instructors, including SW education based on basic teaching-learning capabilities and Computational Thinking(CT). To this end, SW education instructor qualification were divided into three classes using methods such as prior case studies, Delphi surveys, and expert meetings, and the certification evaluation areas were divided into large areas of 'Teaching and Learning Method' and 'Software Education' reflecting primary and secondary curriculum. Sub-areas and content elements for each series were set and verified through expert Delphi survey. Such research is expected to contribute to the spread and dissemination of SW education by being used meaningfully when establishing a system that fosters SW education instructors and maintains and manages the quality of instructors.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.167-174
• /
• 2022

In metaheuristic algorithms such as Genetic Algorithm (GA), initial population has a significant impact as it affects the time such algorithm takes to obtain an optimal solution to the given problem. In addition, it may influence the quality of the solution obtained. In the machine learning field, feature selection is an important process to attaining a good performance model; Genetic algorithm has been utilized for this purpose by scientists. However, the characteristics of Genetic algorithm, namely random initial population generation from a vector of feature elements, may influence solution and execution time. In this paper, the use of a statistical algorithm has been introduced (Chi2) for feature relevant checks where p-values of conditional independence were considered. Features with low p-values were discarded and subject relevant subset of features to Genetic Algorithm. This is to gain a level of certainty of the fitness of features randomly selected. An ensembled-based learning model for Hepatitis has been developed for Hepatitis C stage classification. 1385 samples were used using Egyptian-dataset obtained from UCI repository. The comparative evaluation confirms decreased in execution time and an increase in model performance accuracy from 56% to 63%.