• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2992-2994
• /
• 2000

In cope with insufficient agricultural labor and requirement of high quality product Hydroponics is a really good method. It makes the high density agriculture possible and all the growing environments controllable. So its research is so much progressing to maximize the quantity and quality of farm products. Furthermore, the big progress, in the research of a future agriculture. is systematically conducted for the automatic controlled system. In this paper, a practical automatic control cultivation system is implemented. To automatically control and optimize the very nonlinear and time-varying growth of farm products, a hybrid strategy(FECA: Fuzzy Expertized Control Algorithm) is proposed which serially combines a fuzzy expert system with the fuzzy logic control. The fuzzy expert system (FMES: Fuzzy Model-based Expert System) is intended to overcome the non-linearity of the growth of farm products. The part of fuzzy controller is incorporated to solve the time-variance of the growth of farm products. Finally. the efficiency and the effectiveness of the implemented agricultural automation system is presented through the cultivation results.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1329-1331
• /
• 2003

Improvement of the classification accuracy is one of the major concerns in the field of remote sensing application research in recent years. Previous research shows that the accuracy of the conventional classification methods based only on the original spectral information were usually unsatisfied and need to be refined by manual edit. This present paper describes a method of combining the image processing, ancillary data (such as digital elevation model) and expert knowledge (especially the knowledge of local professionals) to improve the efficiency and accuracy of the satellite image classification in hilly land. Firstly, the Landsat TM data were geo-referenced. Secondly, the individual bands of the image were intensitynormalized and the normalized difference vegetation index (NDVI) image was also generated. Thirdly, a set of sample pixels (collected from field survey) were utilized to discover their corresponding DN (digital number) ranges in the NDVI image, and to explore the relationships between land use type and its corresponding spectral features . Then, using the knowledge discovered from previous steps as well as knowledge from local professionals, with the support of GIS technology and the ancillary data, a set of conditional statements were applied to perform the TM imagery classification. The results showed that the integration of image processing and spatial analysis functions in GIS improved the overall classification result if compared with the conventional methods.

• Journal of radiological science and technology
• /
• v.43 no.6
• /
• pp.461-467
• /
• 2020

In the field of nuclear medicine, errors are sometimes generated because the assessment of the uniformity of gamma cameras relies on the naked eye of the evaluator. To minimize these errors, we created an artificial intelligence model based on CNN algorithm and wanted to assess its usefulness. We produced 20,000 normal images and partial cold region images using Python, and conducted artificial intelligence training with Resnet18 models. The training results showed that accuracy, specificity and sensitivity were 95.01%, 92.30%, and 97.73%, respectively. According to the results of the evaluation of the confusion matrix of artificial intelligence and expert groups, artificial intelligence was accuracy, specificity and sensitivity of 94.00%, 91.50%, and 96.80%, respectively, and expert groups was accuracy, specificity and sensitivity of 69.00%, 64.00%, and 74.00%, respectively. The results showed that artificial intelligence was better than expert groups. In addition, by checking together with the radiological technologist and AI, errors that may occur during the quality control process can be reduced, providing a better examination environment for patients, providing convenience to radiologists, and improving work efficiency.

• International Journal of Korean Welding Society
• /
• v.1 no.1
• /
• pp.17-22
• /
• 2001

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

• Journal of Korean Elementary Science Education
• /
• v.36 no.1
• /
• pp.1-15
• /
• 2017

The purpose of this study is to analyze the problems of land and sea breeze model experiment that has presented in $5^{th}$ grade curriculum in chapter "Weather and our lives" and makes better model simulation so that learners can have better and more effective way to study it. To survey the opinions from dedicated teachers about land and sea breeze model experiment, we produced the survey through interview with science exclusive teacher from M elementary school. An elementary science education expert, 3 men of science EdD modified and complemented survey and started Delphi survey to 12 science teachers who have career teaching more than 3 years. The problems found in this survey were 'one heat bulb, short heating time, small temperature difference of water and sand, lack of class time, empty space between sand and water, back of transparent boxes, little amount of scent and the location of the it' etc. But the most of all, it is hard to see the successful result of the experiment. Based on these kinds of investigations, and lots of trial and error, redesigned the new model experiment that has the most similarity to the real one and high probability of success. According to this, it was able to see the smoke forms horizontal movement along the sand and the smoke goes in one circulation cycle. through this experiment, we made a conclusion that although those scientific experiments in textbook were developed through lots of considerations of expert, to consider the aspect of consumer, it needs to reach the educational agreement about simulation experiment so that It can lead to successful experiment and high quality education.

• The Journal of Korean Association of Computer Education
• /
• v.21 no.4
• /
• pp.39-52
• /
• 2018

There has been a lot of interest in flipped learning, but lacked practical research to support the faculty developing flipped learning courses in higher education institutions. The purpose of this study is to develop a consulting model for developing a flipped learning course that can be practically used by institutions such as center for teaching and learning that support faculty teaching to improve the quality of instruction. A 'Coaching based on flip learning course development consulting model' was derived through literature review and expert feedback. The 8-step model is as follows: 1) survey of class development, 2) course orientation, 3) flipped learning, 4) expert class analysis, 5) flipped learning coaching, 6) flipped learning operation, 7) instructor reflection, and 8) feedback and revision. Based on the results of this study, it is possible to provide professional and practical guide systematically, and also help to improve quality of lesson.

• Journal of the Korea Society for Simulation
• /
• v.22 no.1
• /
• pp.87-95
• /
• 2013

In the research and development processes of new product, the design objects are frequently redesigned on the basis of experimental results. Most of the conventional CAD systems are based on the computer simulation to reduce the number of redesign. However, these types of CAD systems do not have the functions to infer the cause of trouble in experiments of mock-up and the redesign counterplan of new product. This paper proposes a methodology to establish the DESYR ver. 1(Design Expert SYstem for Research and development) system, which possesses the engineering model of design object in the model database, and refines the model on the basis of experimental results of the prototype. The blackboard inference model has been applied to infer the redesign counterplan. And the validity of DESYR ver. 1 system has been verified by developing the new type of magnetic bearing.

• Imaging Science in Dentistry
• /
• v.51 no.3
• /
• pp.299-306
• /
• 2021

Purpose: This study aimed to propose a fully automatic landmark identification model based on a deep learning algorithm using real clinical data and to verify its accuracy considering inter-examiner variability. Materials and Methods: In total, 950 lateral cephalometric images from Yonsei Dental Hospital were used. Two calibrated examiners manually identified the 13 most important landmarks to set as references. The proposed deep learning model has a 2-step structure-a region of interest machine and a detection machine-each consisting of 8 convolution layers, 5 pooling layers, and 2 fully connected layers. The distance errors of detection between 2 examiners were used as a clinically acceptable range for performance evaluation. Results: The 13 landmarks were automatically detected using the proposed model. Inter-examiner agreement for all landmarks indicated excellent reliability based on the 95% confidence interval. The average clinically acceptable range for all 13 landmarks was 1.24 mm. The mean radial error between the reference values assigned by 1 expert and the proposed model was 1.84 mm, exhibiting a successful detection rate of 36.1%. The A-point, the incisal tip of the maxillary and mandibular incisors, and ANS showed lower mean radial error than the calibrated expert variability. Conclusion: This experiment demonstrated that the proposed deep learning model can perform fully automatic identification of cephalometric landmarks and achieve better results than examiners for some landmarks. It is meaningful to consider between-examiner variability for clinical applicability when evaluating the performance of deep learning methods in cephalometric landmark identification.

• Journal of Korean Academy of Nursing
• /
• v.49 no.4
• /
• pp.398-410
• /
• 2019

Purpose: This study used a system dynamics methodology to identify correlation and nonlinear feedback structures among factors affecting adolescent cyberbullying victims (CV) in Korea and to construct and verify a simulation model. Methods: Factors affecting CV were identified by reviewing a theoretical background in existing literature and referencing various statistical data. Related variables were identified through content validity verification by an expert group, after which a causal loop diagram (CLD) was constructed based on the variables. A stock-flow diagram (SFD) using Vensim Professional 7.3 was used to establish a CV model. Results: Based on the literature review and expert verification, 22 variables associated with CV were identified and the CLD was prepared. Next, a model was developed by converting the CLD to an SFD. The simulation results showed that the variables such as negative emotions, stress levels, high levels of conflict in schools, parental monitoring, and time spent using new media had the strongest effects on CV. The model's validity was verified using equation check, sensitivity analysis for timestep and simulation with 4 CV adolescent. Conclusion: The system dynamics model constructed in this study can be used to develop intervention strategies in schools that are focused on counseling that can prevent cyberbullying and assist in the victims' recovery by formulating a feedback structure and capturing the dynamic changes observed in CV. To prevent cyberbullying, it is necessary to develop more effective strategies such as prevention education, counseling and treatment that considers factors pertaining to the individual, family, school, and media.

• Applied Chemistry for Engineering
• /
• v.7 no.2
• /
• pp.371-378
• /
• 1996

A prototype of expert system which can support the operation for the municipal waste water treatment plant located at Kyoung-Ki Do, Kwang-ju Kun was developed and tested. This system provides (i) tracking the cause of the problem, (ii) analysis, and (iii) solution Knowledge-base consists of about 100 production-rules for the biological wastewater process, such as bio-reactor and final clarifier. Rules were obtained from the analysis of the problems such as sludge bulking. The system provides stable process control and management and effectively helps inexperienced operators with advanced and standard technologies. Future works will focus to develop a statistical process control model and associate with expert system. The control model can process the operation data statistically; analyze the relationship between affecting factors and control variables; and provide optimum operation parameters.