• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.312-320
• /
• 2023

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

• Corrosion Science and Technology
• /
• v.18 no.6
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.3
• /
• pp.9-15
• /
• 2020

This study analyzed high school informatics textbooks that were developed based on the 2015 Revised National Curriculum. Content analysis was adopted to analyze the organization system of the textbooks. Learning objectives were also analyzed according to Anderson's taxonomy of educational objectives. Through content analysis, it was revealed that the textbooks were composed of activities, differentiated learning, and small group learning to promote core competencies. The analysis of learning objectives of the textbooks showed that 'understanding' (41%), 'developing' (20%), and 'applying' (18%) were the three highest criteria in terms of cognitive processes; in terms of type of knowledge, conceptual knowledge accounts for the highest(45%), followed by procedural (32%), and factual (12%). Further methods to improve the textbook quality is proposed based on the results from this analysis.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.20 no.2
• /
• pp.471-476
• /
• 2006

Chongmyung-tang(CMT, 聰明湯), oriental herbal medicine which consists of Polygaglae Radix(遠志), Acori Graminei Rhizoma(石菖蒲) and Hoelen(白茯神) has effect on amnesia, dementia. In order to evaluate effect of CMT on memory and learning in mice, CMT extract was used for studies. This paper describes the effects of CMT extract on memory and learning processes by using the passive and active avoidance performance tests, novel object recognition task and water maze task. The CMT extract ameliorated the memory retrieval deficit induced by ethanol in the passive avoidance responses but did not affect ambulatory activity of normal mice. These results suggest that CMT has an ameliorating effect on memory retrieval impairment. CMT extract decreased spontaneous motor activity(SMA) in the latter sessions of memory registration in active avoidance responses. These results suggest that CMT has partly transquilizing or antianxiety effects. In novel object recognition task to measure visual recognition memory, CMT-administered mice enhanced in long term memory for 1-3 days. In water maze task to measure spatial learning, which requires the activation of NMDA receptors in the hippocampus, spatial learning in CMT-administered mice was faster than in wild-type mice. These results suggest that CMT enhances memory and activates NMDA receptors.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.797-802
• /
• 2016

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.257-263
• /
• 2019

This paper is a study on mathematical aspects that can be basic for understanding and applying the contents of machine learning. If you are familiar with mathematics in the field of computer science, you can create algorithms that can diversify researches and implement them faster, so you can implement many real-life ideas. There is no curriculum standard for mathematics in the field of machine learning, and there are many absolutely lacking mathematical contents that are taught in the curriculum presented at existing universities. Machine learning now includes speech recognition systems, search engines, automatic driving systems, process automation, object recognition, and more. Many applications that you want to implement combine a large amount of data with many variables into the components that the programmer generates. In this course, the mathematical areas required for computer engineer (CS) practitioners and computer engineering educators have become diverse and complex. It is important to analyze the mathematical content required by engineers and educators and the mathematics required in the field. This paper attempts to present an effective range design for the essential processes from the basic education content to the deepening education content for the development of many researches.

• Journal of Veterinary Clinics
• /
• v.40 no.4
• /
• pp.243-259
• /
• 2023

Machine learning and deep learning (ML/DL) algorithms have been successfully applied in medical practice. However, their application in veterinary medicine is relatively limited, possibly due to a lack in the quantity and quality of relevant research. Because the potential demands for ML/DL applications in veterinary clinics are significant, it is important to note the current gaps in the literature and explore the possible directions for advancement in this field. Thus, a scoping review was conducted as a situation analysis. We developed a search strategy following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed and Embase databases were used in the initial search. The identified items were screened based on predefined inclusion and exclusion criteria. Information regarding model development, quality of validation, and model performance was extracted from the included studies. The current review found 55 studies that passed the criteria. In terms of target animals, the number of studies on industrial animals was similar to that on companion animals. Quantitative scarcity of prediction studies (n = 11, including duplications) was revealed in both industrial and non-industrial animal studies compared to diagnostic studies (n = 45, including duplications). Qualitative limitations were also identified, especially regarding validation methodologies. Considering these gaps in the literature, future studies examining the prediction and validation processes, which employ a prospective and multi-center approach, are highly recommended. Veterinary practitioners should acknowledge the current limitations in this field and adopt a receptive and critical attitude towards these new technologies to avoid their abuse.

• Journal of The Korean Association For Science Education
• /
• v.34 no.5
• /
• pp.511-521
• /
• 2014

In this study, we conducted an exploratory investigation of the imaginative writing processes of middle school students. Twelve 8th graders were asked to imagine and write about the daily life of atoms, assuming that they became specific atoms for themselves. The think-aloud method was used to investigate students' writing processes. We recorded students' writing processes, and also collected the data through interviews to clarify ambiguities in their writing processes. The analyses of the results revealed that their imaginative writing processes could be classified into the three types by the two aspects of writing process components (retrieving information and generating ideas). That is, the integration of retrieving information and generating ideas, the predominant retrieving information, and the predominant generating ideas. The students who were classified into the type of the integration of retrieving information and generating ideas came up with a story and properly introduced science concepts into it. These suggested that this type of students expressed their own understanding more effectively, and that this type was most appropriate for imaginative writing in learning science. The results also showed that the imaginative writing processes were greatly influenced by whether the planning step was adequately considered or not. On the bases of the results, we suggest the teaching strategies for effective imaginative writing in learning science.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.3
• /
• pp.26-33
• /
• 1997

Problem-Based Learning(PBL) is at the forefront of educational reform. The acceptance of PBL as an educational approach with wide application represents a major change in thinking about educational processes and their relationships to the wider community. In 1969, PBL as a method was introduced at the Medical School of McMaster University in Hamilton, Canada. The most important advantages in PBL are acquiring knowledge that can be retrieved and applied, learning to learn(self-directed learning) and learning to analyze and solve Problems. PBL is widely used within the sector where it had its origin, namely health profession education. A generally accepted starting point in the development of a problem-based curriculum is the set of professional competencies of future graduates, which describe the typical problems professionals have to deal with. Formulating learning objectives highly depends on the format and content of the presented problems. Contrary to that, in a classic course in higher education, it is customary that teachers express objectives in a compulsory subject matter. Curricula which advocate problem-based learning generally use case studies in the form of paper cases, simulations and real patients with the intention of stimulating classroom discussion of clinical and basic science concepts within a problem-solving framework. One goal of using paper cases is to stimulate the learning of basic science within a clinical situation. Through self-directed study the students solve problems and explore the psycho-social dimensions within the cases. The general outcome based on the program evaluation research of PBL is that PBL students respond positively about the learning experience. In summary, PBL is a curriculum design and a teaching/learning strategy which simultaneously develops higher order thinking and disciplinary knowledge bases and skills by placing students in the active role of practitioners(or problem solvers) confronted with a situation(ill-structured problem) which reflects the real world.

• Journal of the Korean School Mathematics Society
• /
• v.22 no.4
• /
• pp.395-413
• /
• 2019

The purpose of this study was to find out how Blended e-Learning affected the teaching and learning of engineering mathematics for engineering students. It has researched the application condition of Blended e-Learning and the students' attitude in the offline classes of students. The subject were 42 students of Junior in the Department of Mechanic Engineering in M-University participated in the study. The lecturer taught the class for the students by fact-to-face teaching at the offline. It was recorded all processes during the class, and the video was loaded at the Learning Management System(LMS). The students studied online by themselves. This study investigated the attitude of students at the offline and the Utilization of Online Data by learners through the mixed class for one semester. The results were as follows. First, Blended e-Learning applied engineering mathematics affected positively for the self-regulated and individualized learning to the students. Second, Blended e-Learning has shown a positive impact on the teaching and learning of engineering mathematics. Finally, it also had a positive effect on the class satisfaction level of students.