• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.81-86
• /
• 2023

Recently, there has been an increased demand for light-emitting diode (LED) due to the growing emphasis on environmental protection. However, the use of GaN-based sapphire in LED manufacturing leads to the generation of defects, such as dislocations caused by lattice mismatch, which ultimately reduces the luminous efficiency of LEDs. Moreover, most inspections for LED semiconductors focus on evaluating the luminous efficiency after packaging. To address these challenges, this paper aims to detect defects at the wafer stage, which could potentially improve the manufacturing process and reduce costs. To achieve this, image processing and deep learning-based defect detection techniques for Sapphire Epi-Wafer used in Green LED manufacturing were developed and compared. Through performance evaluation of each algorithm, it was found that the deep learning approach outperformed the image processing approach in terms of detection accuracy and efficiency.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.183-193
• /
• 2024

Recurrent Neural Network technology that learns past patterns and predicts future patterns using technology for recognizing and classifying objects is being applied to various industries, economies, and languages. And research for practical use is making a lot of progress. However, research on the application of Recurrent Neural Networks for evaluating and predicting the safety of mechanical structures is insufficient. Accurate detection of external load applied to the outside is required to evaluate the safety of mechanical structures. Learning of Recurrent Neural Networks for this requires a large amount of load data. This study applied the Gated Recurrent Unit technique to examine the possibility of load learning and investigated the possibility of applying a stacked Auto Encoder as a way to secure load data. In addition, the usefulness of learning mechanical loads was analyzed with the Gated Recurrent Unit technique, and the basic setting of related functions and parameters was proposed to secure accuracy in the recognition and prediction of loads.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.2
• /
• pp.203-210
• /
• 1996

A linear neural unit with a modified anti-Hebbian learning rule has been shown to be able to optimally fit curves, surfaces, and hypersurfaces by adaptively extracting the minor component of the input data set. In this paper, we study how to use the robust version of this neural fitting method for linear regression analysis. Furthermore, we compare this method with other methods when data set is contaminated by outliers.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.102.1-102
• /
• 2002

In this paper, we propose Self-organizing neurofuzzy networks(SONFN) and discuss their comprehensive design methodology. The proposed SONFN is generated from the mutually combined structure of both neurofuzzy networks (NFN) and polynomial neural networks(PNN) for model identification of complex and nonlinear systems. NFN contributes to the formation of the premise part of the SONFN. The consequence part of the SONFN is designed using PNN. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. We discuss two kinds of SONFN architectures and propose a comprehensive learning algorithm. It is shown that this network...

• Journal of Korean Academy of Nursing
• /
• v.30 no.4
• /
• pp.1055-1065
• /
• 2000

The purpose of this study was to develop, through the integration of instructional theory, a Courseware and to investigate the effectiveness of a web-based computer assisted instruction(WBI) program for preventing drug abuse, a serious problem for youth problem. During the first stage of this study done "Drug Abuse Prevention" Courseware was developed based on, Gagn & Brigg's instructional design theory, Keller's ARCS theory and the CAI model of Hannafin & Peck. For the second stage, the courseware was used to provide education for students adolescents in drug abuse prevention. This study used an quasi-experimental, one-group pretest-posttest design with a convenience sample of 36 male high school students who were at one high school located in Seoul. Data were collected using self-reported questionnaires which included a learning achievement tool, the Keller's IMMS (Instructional Material Motivation Survey), on attitudes to drug use, and on responses to the WBI instruction. Prior to the experiment, the "drug abuse prevention" learning method and the procedures of the study were explained to the students, and then the learning achievement of the subjects was measured as a pretest. The students were then given 2 weeks WBI utilizing the courseware. A post-test which included the pre-test learning achievement questionnaire and a survey of learning motivation and attitudes toward drug were given two weeks after the education was completed. The data analysis was done using SPSS/PC. Paired t-test was used to analyze the differences between the pre-test and post-test scores for learning achievement. The results of the analysis are as follows: There were significant differences in learning achievement between the pre-test and post-test(t=-18.62, p=0.000). The hypothesis, that learning achievement will be higher, after the class has used the courseware, than before was supported. The scores for learning motivation and attitudes toward drugs were also higher than the results of existing studies. In conclusion, this study suggests that WBI is an effective learning method in the prevention of drug abuse for adolescents as it can be used for self-learning and repeated learning as assisted instruction. Recommendation would be given that further research needs to be develped in the courseware by cognitive learning style and by multimedia courseware and virtual reality system.

• Journal of the Korean School Mathematics Society
• /
• v.1 no.1
• /
• pp.97-109
• /
• 1998

The activities of teaching and learning are to try to reach the lesson object most closely in many ways. Considering that the lesson objects are to get the principle or law of a concept, to acquire the mathematical function, to master it through repeated exercises and to solve mathematical problems, we need many ways to reach such objects. Among the many ways, we can first think of one: the students will learn with curiosity and according to their own ability or advancing level in learning when teachers study and prepare necessary contents enough in advance by using computers, showing the right program to learners' needs. For example, defining definite integral by measuration by parts will help understand measuration by parts well and know the meaning of definite integral correctly, In teaching and learning by the use of this program, the educational effects are expected as follows. 1. It is thought that this program will stimulate the desire for and interest in learning because it used animation and acoustic effect. And voluntary and positive thinking activity will be shown. 2. It is expected that the conviction of formulas will be got and the concept of definite integral will be remembered firmly by showing how to measure the width of circle with the use of measuration by parts in various other ways instead of the ways used at present. 3. It is expected that students will feel the pleasure of mathematics in life when they recognize mathematical facts scattered really in our life rather than mathematical difficulties. 4. It is expected that the repeated review of programs already designed will remove the fear of incomplete parts and help review again. 5. It is certain that positive attitude in life will be formed as teacher-centered class is changed into learner-centered class and unwilling study is changed into self-oriented study. However, I think this program is insufficient for humanbeing-centered education given directly in contact with students on the ground of the variety in mathematical education and applications in many ways. And mechanically inhuman computers leave some solutions to be desired

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.3
• /
• pp.117-127
• /
• 1995

In this paper, we suggest a motion analysis method using ART-I1 competitive learning neural network and fuzzy reasoning by matching the same objects through the consecutive image sequence. we use the size and mean intensity of the region obtained from image segmentation for the region matching by the region and use a ART-I1 competitive learning neural network wh~ch has a learning ability to reflect the topology of the input patterns in order to select characteristic points to describe the shape of a region. Motion vectors for each regions are obtained by matching selected characteristic points. However, the two dimensional image, the projection of the the three dimensional real world, produces fuzziness in motion analysis due to its incompleteness by nature and the error from image segmentation used for extracting information about objects. Therefore, the belief degrees for each regions are calculated using fuzzy reasoning to l-nanipulate uncertainty in motion estimation.

• Journal of Elementary Mathematics Education in Korea
• /
• v.11 no.1
• /
• pp.81-98
• /
• 2007

In order to help students learn geometric concepts in mathematics in an easy and interesting way, the present study restructured the textbook so that it utilizes GSP based on van Hiele's theory. In addition, we purposed to examine how effective the restructured textbook is in enhancing students' van Hiele level and to lay a base for the active use of GSP in learning figures in elementary school. In conclusion, the results of this study is expected to solve problems in the structure of the current textbook such as the violation of continuity in van Hiele's theory and inconsistency between the level of textbook contents and students' level through the restructuring of the textbook using GSP and provide helps for effective figure learning. In addition, this research is expected to be an opportunity for the active use of GSP in teaching figures in elementary school.

• International Journal of Computer Science & Network Security
• /
• v.24 no.3
• /
• pp.59-70
• /
• 2024

Background: The COVID-19 pandemic (the form of coronaviruses) developed at the end of 2019 and spread rapidly to almost every corner of the world. It has infected around 25,334,339 of the world population by the end of September 1, 2020 [1] . It has been spreading ever since, and the peak specific to every country has been rising and falling and does not seem to be over yet. Currently, the conventional RT-PCR testing is required to detect COVID-19, but the alternative method for data archiving purposes is certainly another choice for public departments to make. Researchers are trying to use medical images such as X-ray and Computed Tomography (CT) to easily diagnose the virus with the aid of Artificial Intelligence (AI)-based software. Method: This review paper provides an investigation of a newly emerging machine-learning method used to detect COVID-19 from X-ray images instead of using other methods of tests performed by medical experts. The facilities of computer vision enable us to develop an automated model that has clinical abilities of early detection of the disease. We have explored the researchers' focus on the modalities, images of datasets for use by the machine learning methods, and output metrics used to test the research in this field. Finally, the paper concludes by referring to the key problems posed by identifying COVID-19 using machine learning and future work studies. Result: This review's findings can be useful for public and private sectors to utilize the X-ray images and deployment of resources before the pandemic can reach its peaks, enabling the healthcare system with cushion time to bear the impact of the unfavorable circumstances of the pandemic is sure to cause

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1911-1916
• /
• 2005

In this study, the basic motor control system had been investigated. The Discrete-Time Feedback Error Learning (DTFEL) method is used to control this system. This method is anologous to the original continuous-time version Feedback Error Learning(FEL) control which is proposed as a control model of cerebellum in the field of computational neuroscience. The DTFEL controller consists of two main parts, a feedforward controller part and a feedback controller part. Each part will deals with different control problems. The feedback controller deals with robustness and stability, while the feedforward controller deals with response speed. The feedforward controller, used to solve the tracking control problem, is adaptable. To make such the tracking perfect, the adaptive law is designed so that the feedforward controller becomes an inverse system of the controlled plant. The novelty of FEL method lies in its use of feedback error as a teaching signal for learning the inverse model. The PD control theory is selected to be applied in the feedback part to guarantee the stability and solve the robust stabilization problems. The simulation of each individual part and the integrated one are taken to clarify the study.