• The Journal of Korean Academy of Prosthodontics
• /
• v.44 no.4
• /
• pp.421-431
• /
• 2006

Statement of problem : Accurate impression is essential to success of implant prostheses. But there have been few studies about the accuracy of fixture-level impression technique in internal connection implant system. Purpose: This study evaluated the accuracy of splinted fixture-level impression technique using clinical methods and the effect of internal hex on fit of superstructure in internal connection implant system (Astra Tech). Material and method : Two metal master frameworks made from two abutments (Cast-to Abutment ST) each for parallel and divergent conditions and a corresponding. passively fitting, dental stone master cast with four future replicas (Fixture Replica ST) were fabricated. Ten dental stone casts were made with vinyl polysiloxane impressions from the master cast by acrylic resin splinted fixture-level impression technique. To evaluate the accuracy of impression technique, the fit of master frameworks for test models was evaluated using screw resistance test (SRT) and one-screw test. The results of SRT were recorded as SRT values from grade 1 to grade 5 by 1/4 turn. And to evaluate the effect of hex on fit of superstructure, the same tests were performed after removing hexes of master frameworks. Results: 1. There was only one case (2.5%) showing SRT value of test model below ade 2 in total before and after removing hexes of master frameworks. And, by removing hexes. SRT values decreased in only one test model (5%) and did not change in 17 test models (85%). 2. SRT values of the 1$^{st}$ screws were grade 2 in 80% of cases before, and grade 1 in 80% of cases after removing hexes. And, by removing hexes, SRT values decreased in 72.5% of cases. 3. SRT values of the 2$^{nd}$ screws were grade 3 in 85% of cases before, and grade 3 in 95% of cases after removing hexes. And, by removing hexes, SRT values did not change in 85% of cases. 4. There were only 2 cases regarded as acceptable fit by one-screw test, and SRT values of 2$^{nd}$ screws of both cases were grade 2. Conclusion. Within the limitations of this study, future-level impression of internal connection implant system is considered to obtain inaccurate working cast, even using acrylic resin splinted impression technique. And, it is considered to be unable improve the fit to remove the hexes of implant restoration.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.147-156
• /
• 2011

Though a dozen of different software life cycle models are suggested, there is no universal model which can satisfy all the characteristics of software. Organizations mix and match different life cycle models to develop a model more tailored for their systems and capabilities. We suggest overlapped-concurrent development life cycle model that is more suitable in various software development environment. Firstly, we divided the development process into abstract and implementation stage. Abstract stage is from software concept phase to detailed design starting time, and implementation stage is from detailed design phase to system testing phase. Next, the abstract stage introduced the overlapped phase concept that begins the next phase when the step is completed 20% by applying pareto's law. In the implementation stage, we introduced the concurrent development which the several phases are performed some time as when one use-case (UC) is completed the next development phase is started immediately. The proposed model has an advantage that it can reduce the inefficiency of development resource greatly. This model can increase the customer satisfaction with a great product at a low cost and on a short schedule. Also, this model can contribute to increase the software development success rate.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.57-66
• /
• 2021

Deep neural networks (DNNs) provide excellent performance for image, speech, and pattern recognition. However, DNNs sometimes misrecognize certain adversarial examples. An adversarial example is a sample that adds optimized noise to the original data, which makes the DNN erroneously misclassified, although there is nothing wrong with the human eye. Therefore studies on defense against adversarial example attacks are required. In this paper, we have experimentally analyzed the success rate of detection for adversarial examples by adjusting various parameters. The performance of the ensemble defense method was analyzed using fast gradient sign method, DeepFool method, Carlini & Wanger method, which are adversarial example attack methods. Moreover, we used MNIST as experimental data and Tensorflow as a machine learning library. As an experimental method, we carried out performance analysis based on three adversarial example attack methods, threshold, number of models, and random noise. As a result, when there were 7 models and a threshold of 1, the detection rate for adversarial example is 98.3%, and the accuracy of 99.2% of the original sample is maintained.

• Anxiety and mood
• /
• v.15 no.1
• /
• pp.53-60
• /
• 2019

Objective : GRIT is a non-cognitive trait which is defined as perseverance and passion for long-term goals. It predicts success, performance and thedifference from other traits. The purpose of this study was to examine the reliability and validity of the Korean version of the GRIT scale. Methods : A total of 92 patients were enrolled in the study. All patients received psychiatric assessment including Clinical Useful Depression Outcome Scale (CUDOS), Clinical Useful Anxiety Outcome Scale (CUXOS), Patient Health Questionnaire (PHQ-15), Connor-Davidson Resilience Scale (CDRS), Brief Resilience Scale (BRS), and GRIT as well as demographic assessment. Cronbach's alpha coefficient of total GRIT score and the split-half reliability of each item was calculated to assess test reliability. Exploratory and confirmatory factor analyses were performed to select the best fitting model and assess construct validity. Finally, a correlation analysis was performed to check convergent and discriminant validity. Results : Cronbach's alpha coefficient for GRIT was found to be 0.85 and all Cronbach's alpha were more than 0.8 even in cases where all items were deleted. We found 3 appropriate factor models in exploratory factor analysis, compared them with 3 models and chose the 2-factor model as the most suitable based on the best fit test. Finally, correlation of the GRIT with CUDOS, CUXOS, PHQ-15, CDRS and BRS were statistically significant (all p<0.01), with relatively low correlation coefficient. Conclusion : This study indicates that the Korean version of GRIT is a reliable and valid instrument for investigating individual power of passion and perseverance.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.1-6
• /
• 2019

Neural networks have been used to predict the direction of stock index movement from past data. The conventional research that predicts the upward or downward movement of the stock index predicts a rise or fall even with small changes in the index. It is highly likely that losses will occur when trading ETFs by use of the prediction. In this paper, a neural network model that predicts the movement direction of the daily KOrea composite Stock Price Index (KOSPI) to reduce ETF trading losses and earn more than a certain amount per trading is presented. The proposed model has outputs that represent rising (change rate in index ${\geq}{\alpha}$), falling (change rate ${\leq}-{\alpha}$) and neutral ($-{\alpha}$ change rate < ${\alpha}$). If the forecast is rising, buy the Leveraged Exchange Traded Fund (ETF); if it is falling, buy the inverse ETF. The hit ratio (HR) of PNN1 implemented in this paper is 0.720 and 0.616 in the learning and the evaluation respectively. ETF trading yields a yield of 8.386 to 16.324 %. The proposed models show the better ETF trading success rate and yield than the neural network models predicting KOSPI.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.543-552
• /
• 2022

When frost occurs, crops are directly damaged. When crops come into contact with low temperatures, tissues freeze, which hardens and destroys the cell membranes or chloroplasts, or dry cells to death. In July 2020, a sudden sub-zero weather and frost hit the Minas Gerais state of Brazil, the world's largest coffee producer, damaging about 30% of local coffee trees. As a result, coffee prices have risen significantly due to the damage, and farmers with severe damage can produce coffee only after three years for crops to recover, which is expected to cause long-term damage. In this paper, we tried to predict frost using frost generation data and weather observation data provided by the Korea Meteorological Administration to prevent severe frost. A model was constructed by reflecting weather factors such as wind speed, temperature, humidity, precipitation, and cloudiness. Using XGB(eXtreme Gradient Boosting), SVM(Support Vector Machine), Random Forest, and MLP(Multi Layer perceptron) models, various hyper parameters were applied as training data to select the best model for each model. Finally, the results were evaluated as accuracy(acc) and CSI(Critical Success Index) in test data. XGB was the best model compared to other models with 90.4% ac and 64.4% CSI, followed by SVM with 89.7% ac and 61.2% CSI. Random Forest and MLP showed similar performance with about 89% ac and about 60% CSI.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.339-346
• /
• 2022

Recently, the resource depletion and climate change problem caused by the massive usage of fossil fuels for electric power generation has become a critical issue worldwide. According to this issue, interest in renewable energy resources that can replace fossil fuels is increasing. Especially, photovoltaic power has gaining much attention because there is no risk of resource exhaustion compared to other energy resources and there are low restrictions on installation of photovoltaic system. In order to use the power generated by the photovoltaic system efficiently, a more accurate photovoltaic power forecasting model is required. So far, even though many machine learning and deep learning-based photovoltaic power forecasting models have been proposed, they showed limited success in terms of interpretability. Deep learning-based forecasting models have the disadvantage of being difficult to explain how the forecasting results are derived. To solve this problem, many studies are being conducted on explainable artificial intelligence technique. The reliability of the model can be secured if it is possible to interpret how the model derives the results. Also, the model can be improved to increase the forecasting accuracy based on the analysis results. Therefore, in this paper, we propose an explainable photovoltaic power forecasting scheme based on BiLSTM (Bidirectional Long Short-Term Memory) and SHAP (SHapley Additive exPlanations).

• Journal of Korea Water Resources Association
• /
• v.56 no.8
• /
• pp.471-484
• /
• 2023

Deep learning models based on generative adversarial neural networks are specialized in generating new information based on learned information. The deep generative models (DGMR) model developed by Google DeepMind is an generative adversarial neural network model that generates predictive radar images by learning complex patterns and relationships in large-scale radar image data. In this study, the DGMR model was trained using radar rainfall observation data from the Ministry of Environment, and rainfall prediction was performed using an generative adversarial neural network for a heavy rainfall case in August 2021, and the accuracy was compared with existing prediction techniques. The DGMR generally resembled the observed rainfall in terms of rainfall distribution in the first 60 minutes, but tended to predict a continuous development of rainfall in cases where strong rainfall occurred over the entire area. Statistical evaluation also showed that the DGMR method is an effective rainfall prediction method compared to other methods, with a critical success index of 0.57 to 0.79 and a mean absolute error of 0.57 to 1.36 mm in 1 hour advance prediction. However, the lack of diversity in the generated results sometimes reduces the prediction accuracy, so it is necessary to improve the diversity and to supplement it with rainfall data predicted by a physics-based numerical forecast model to improve the accuracy of the forecast for more than 2 hours in advance.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• The Journal of Korean Academy of Prosthodontics
• /
• v.45 no.4
• /
• pp.506-521
• /
• 2007

Statement of problem: The cumulative success rate of wide implant is still controversial. Some previous reports have shown high success rate, and some other reports shown high failure rate. Purpose: The aim of this study was to analyze, and compare the biomechanics in wide implant system embeded in different width of crestal bone under different occlusal forces by finite element approach. Material and methods: Three-dimensional finite element models were created based on tracing of CT image of second premolar section of mandible with one implant embedded. One standard model (6mm-crestal bone width, 4.0mm implant diameter central position) was created. Varied crestal dimension(4, 6, 8 mm), different diameter of implants(3.3, 4.0, 5.5, 6.0mm), and buccal position implant models were generated. A 100-N vertical(L1) and 30 degree oblique load from lingual(L2) and buccal(L3) direction were applied to the occlusal surface of the crown. The analysis was performed for each load by means of the ANSYS V.9.0 program. Conclusion: 1. In all cases, maximum equivalent stress that applied $30^{\circ}$ oblique load around the alveolar bone crest was larger than that of the vertical load. Especially the equivalent stress that loaded obliquely in buccal side was larger. 2. In study of implant fixture diameter, stress around alveolar bone was decreased with the increase of implant diameter. In the vertical load, as the diameter of implant increased the equivalent stress decreased, but equivalent stress increased in case of the wide implant that have a little cortical bone in the buccal side. In the lateral oblique loading condition, the diameter of implant increased the equivalent stress decreased, but in the buccal oblique load, there was not significant difference between the 5.5mm and 6.0mm as the wide diameter implant. 3. In study of alveolar bone width, equivalent stress was decreased with the increase of alveolar bone width. In the vertical and oblique loading condition, the width of alveolar bone increased 6.0mm the equivalent stress decreased. But in the oblique loading condition, there was not a difference equivalent stress at more than 6.0mm of alveolar bone width. 4. In study of insertion position of implant fixture, even though the insertion position of implant fixture move there was not a difference equivalent stress, but in the case of little cortical bone in the buccal side, value of the equivalent stress was most unfavorable. 5. In all cases, it showed high stress around the top of fixture that contact cortical bone, but there was not a portion on the bottom of fixture that concentrate highly stress and play the role of stress dispersion. These results demonstrated that obtaining the more contact from the bucco-lingual cortical bone by installing wide diameter implant plays an important role in biomechanics.