• Journal of Dental Rehabilitation and Applied Science
• /
• v.38 no.4
• /
• pp.196-203
• /
• 2022

Purpose: This study aimed to evaluate the accuracy and clinical usability of an identification model using deep learning for 79 dental implant types. Materials and Methods: A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. The collected implant images were 79 types from 18 manufacturers. EfficientNet and Meta Pseudo Labels algorithms were used. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels. For Meta Pseudo Labels, two models were applied according to the widen factor. Top 1 accuracy was measured for EfficientNet and top 1 and top 5 accuracy for Meta Pseudo Labels were measured. Results: EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Conclusion: All four deep learning algorithms used for implant identification in this study showed close to 90% accuracy. In order to increase the clinical applicability of deep learning for implant identification, it will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification.

• Health Policy and Management
• /
• v.9 no.3
• /
• pp.70-94
• /
• 1999

This paper was performed for a cost-effectiveness analysis of pharmacologic treatment of hypercholesterolemia. Agents modeled were cholestyramine, gemfibrozil. bezafibrate, lovastatin, pravastatin, simvastatin. Pharmacologic effectiveness was estimated by regression from reported clinical trials. Pharmacologic effects were expressed as the percent change of blood cholesterol level. Cost estimates included patients' travel expenses and time loss as well as resource consumption in the health care sector. Bezafibrate was the most efficient agent for reducing total cholesterol levels, having an cost over 1 year of ￦31.400 per percent reduction in total cholesterol. Simvastatin (10mg/d) was also efficient(￦33,100 per percent reduction). Chole styramine(8g/d) was least efficient at ￦90,200. For low-density lipoprotein cholesterol. simvastatin(10mg/d) was most efficient, at ￦23,200 per percent reduction, followed by lovastatin(20mg/d) at ￦28,000. Gemfibrozil was least efficient at ￦77,800 per percent reduction. For high-density lipoprotein cholesterol. bezafibrate(400mg/d) was most efficient at ￦39,300 per percent increase of high-density lipoprotein cholesterol. Cholestyramine was least efficient at ￦514,700. Analyses combining low-density lipoprotein cholesterol and high-density cholesterol effects suggest that bezafibrate(600mg/d) and simvastatin (10mg/d) were most efficient for reducing cardiovascular risk. The cost-effectiveness analysis results show that both simvastatin and bezafibrate could be efficient treatment. Simvastatin provide more effective treatment at higher cost, whereas bezafibrate is more cost-effective, as it may be less effective, at lower cost. Therefore, clinicians should choose reasonable treatment according to the patient's needs This pharmacoeconimc analysis will provide a guideline for efficient pharmacologic treatment and also be reference data for pricing new drugs.

• Journal of the Korean Mathematical Society
• /
• v.44 no.4
• /
• pp.971-985
• /
• 2007

A sequential optimality condition characterizing the efficient solution without any constraint qualification for an abstract convex vector optimization problem is given in sequential forms using subdifferentials and ${\epsilon}$-subdifferentials. Another sequential condition involving only the subdifferentials, but at nearby points to the efficient solution for constraints, is also derived. Moreover, we present a proposition with a sufficient condition for an efficient solution to be properly efficient, which are a generalization of the well-known Isermann result for a linear vector optimization problem. An example is given to illustrate the significance of our main results. Also, we give an example showing that the proper efficiency may not imply certain closeness assumption.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.11 no.3
• /
• pp.49-56
• /
• 2011

This paper deals with a methodology for searching optimal route of hazard material (hazmat) vehicles. When we make a decision of hazmat optimal paths, there is a conflict between the public aspect which wants to minimize risk and the private aspect which has a goal of minimizing travel time. This paper presents Efficient Vector Labeling algorithm as a methodology for searching optimal path of hazmat transportation, which is intrinsically one of the multi-criteria decision making problems. The output of the presented algorithm is a set of Pareto optimal paths considering both risk and travel time at a time. Also, the proposed algorithm is able to identify non-dominated paths which are significantly different from each other in terms of links used. The proposed Efficient Vector Labeling algorithm are applied to test bed network and compared with the existing k-shortest path algorithm. Analysis of result shows that the proposed algorithm is more efficient and advantageous in searching reasonable alternative routes than the existing one.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.26-37
• /
• 2022

In this paper, images are automatically acquired to control the initial disease of strawberries among facility cultivation crops, and disease analysis is performed using the EfficientNet model to inform farmers of disease status, and disease diagnosis service is proposed by experts. It is possible to obtain an image of the strawberry growth stage and quickly receive expert feedback after transmitting the disease diagnosis analysis results to farmers applications using the learned EfficientNet model. As a data set, farmers who are actually operating facility cultivation were recruited and images were acquired using the system, and the problem of lack of data was solved by using the draft image taken with a cell phone. Experimental results show that the accuracy of EfficientNet B0 to B7 is similar, so we adopt B0 with the fastest inference speed. For performance improvement, Fine-tuning was performed using a pre-trained model with ImageNet, and rapid performance improvement was confirmed from 100 Epoch. The proposed service is expected to increase production by quickly detecting initial diseases.

• Journal of the Korean Ceramic Society
• /
• v.51 no.2
• /
• pp.103-106
• /
• 2014

Nacre is an organic-inorganic composite material; it is composed of $CaCO_3$ platelet and protein. The microstructure of nacre is a matrix that is similar to bricks and mortar. Technology inspired by nature is called biomimetic technology. In this study, to make high thermal conducting ceramic composite materials using biomimetic technology, a porous green body was prepared with BN platelets. PMMA was infiltrated into the porous green body to make a composite. The microstructure of the composite was observed with FESEM, and the thermal properties were measured. The thermal conductivity of the prepared organic-inorganic composite was 4.19 $W/m{\cdot}K$.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.169-172
• /
• 2008

This paper is a report of designing for high efficient LED lights driver. The main purpose of driver designing is meet the requirement the high efficient energy regulation for light of Korea. To meet the regulation the high efficient, the circuit adapted wide range resonant power supply and current regulate circuit to adjust LED current. This product archived excellent performance as well as reliable operation.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.16 no.2
• /
• pp.1-12
• /
• 1991

The purpose of this paper are to find the relations between efficient faces and the regions of weights on the objective functions in Multi-objective Linear Programming. First, we define the region of weights corresponding to an efficient face, and find the changing pattern within the region of weights. Second, we find the eqution of the dimensional relation between the efficient face and the region of weight corrsponding to it.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1375-1378
• /
• 1987

In this paper, an efficient data compression algorithm for binary image is proposed. This algorithm makes use of the fact that boundaries contain all the information about such images. The compression efficiency is then further increased by efficient coding of Boundary Information Matrix. The comparison of performance with modified Huffman coding was made by a computer simulation with some images. The results of simulation showed that the proposed algorithm was more efficient than modified Huffman code.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.10a
• /
• pp.199-204
• /
• 2000

In this study, an optimum design algorithm using efficient reanalysis is proposed for seismic design of RC Piers. The proposed algorithm for optimization of RC Piers is based on efficient reanalysis technique. Considering structural behavior of RC Piers, several other approximation techniques, such as artificial constraint deletion is introduced to increase the efficiency of optimization. The efficiency and robustness of the proposed algorithm increase the proposed reanalysis technique is demonstrated by comparing it with a conventional optimization algorithm. A few of design examples are optimized to show the applicability of the proposed algorithm.