• Journal of Korean Society for Quality Management
• /
• v.48 no.4
• /
• pp.581-596
• /
• 2020

Purpose: purpose of this study was to propose the web application platform which can be to detect and discriminate various diseases and pest of tomato plant based on the large amount of disease image data observed in the facility or the open field. Methods: The deep learning algorithms uesed at the web applivation platform are consisted as the combining form of Faster R-CNN with the pre-trained convolution neural network (CNN) models such as SSD_mobilenet v1, Inception v2, Resnet50 and Resnet101 models. To evaluate the superiority of the newly proposed web application platform, we collected 850 images of four diseases such as Bacterial cankers, Late blight, Leaf miners, and Powdery mildew that occur the most frequent in tomato plants. Of these, 750 were used to learn the algorithm, and the remaining 100 images were used to evaluate the algorithm. Results: From the experiments, the deep learning algorithm combining Faster R-CNN with SSD_mobilnet v1, Inception v2, Resnet50, and Restnet101 showed detection accuracy of 31.0%, 87.7%, 84.4%, and 90.8% respectively. Finally, we constructed a web application platform that can detect and discriminate various tomato deseases using best deep learning algorithm. If farmers uploaded image captured by their digital cameras such as smart phone camera or DSLR (Digital Single Lens Reflex) camera, then they can receive an information for detection, identification and disease control about captured tomato disease through the proposed web application platform. Conclusion: Incheon Port needs to act actively paying.

• Steel and Composite Structures
• /
• v.38 no.1
• /
• pp.87-102
• /
• 2021

To investigate the failure form, bending stiffness, and residual bearing capacity of monolithic composite beams with laminated slab throughout the fire process, fire tests of four monolithic composite beams with laminated slab were performed under constant load and temperature increase. Different factors such as post-pouring layer thickness, lap length of the prefabricated bottom slab, and stud spacing were considered in the fire test. The test results demonstrate that, under the same fire time and external load, the post-pouring layer thickness and stud spacing are important parameters that affect the fire resistance of monolithic composite beams with laminated slab. Similarly, the post-pouring layer thickness and stud spacing are the predominant factors affecting the bending stiffness of monolithic composite beams with laminated slab after fire exposure. The failure forms of monolithic composite beams with laminated slab after the fire are approximately the same as those at room temperature. In both cases, the beams underwent bending failure. However, after exposure to the high-temperature fire, cracks appeared earlier in the monolithic composite beams with laminated slab, and both the residual bearing capacity and bending stiffness were reduced by varying degrees. In this test, the bending bearing capacity and ductility of monolithic composite beams with laminated slab after fire exposure were reduced by 23.3% and 55.4%, respectively, compared with those tested at room temperature. Calculation methods for the residual bearing capacity and bending stiffness of monolithic composite beams with laminated slab in and after the fire are proposed, which demonstrated good accuracy.

• Korean Journal of Veterinary Research
• /
• v.61 no.2
• /
• pp.19.1-19.7
• /
• 2021

Feline panleukopenia virus (FPV) causes leukopenia and severe hemorrhagic diarrhea, killing 50% of naturally infected cats. Although intact FPV can serve as an antigen in the hemagglutination inhibition (HI) test, an accidental laboratory-mediated infection is concern. A non-infectious diagnostic reagent is required for the HI test. Here, we expressed the viral protein 2 (VP2) gene of the FPV strain currently prevalent in South Korea in a baculovirus expression system; VP2 protein was identified by an indirect immunofluorescence assay, electron microscopy (EM), Western blotting (WB), and a hemagglutination assay (HA). EM showed that the recombinant VP2 protein self-assembled to form virus-like particles. WB revealed that the recombinant VP2 was 65 kDa in size. The HA activity of the recombinant VP2 protein was very high at 1:2¹⁵. A total of 143 cat serum samples were tested using FPV (HI-FPV test) and the recombinant VP2 protein (HI-VP2 test) as HI antigens. The sensitivity, specificity, and accuracy of the HI-VP2 test were 99.3%, 88.9%, and 99.3%, respectively, compared to the HI-FPV test. The HI-VP2 and HI-FPV results correlated significantly (r = 0.978). Thus, recombinant VP2 can substitute for intact FPV as the serological diagnostic reagent of the HI test for FPV.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.4
• /
• pp.353-358
• /
• 2022

Bulky iron-core potential transformers (PT) are installed in a tank of gas insulated switchgears (GIS) for a system voltage measurement in power substations. In this paper, we studied an electronic voltage transformer (EVT) embedded in a spacer for miniaturization, eco-friendliness, and performance improvement of GIS. The prototype EVT consists of a capacitive probe (CP) that can be embedded in a spacer and a voltage Follower with a high input and a low output impedance. The CP was fabricated in the form of a Flexible-PCB to acquire the insulation performance and to withstand vibration and shock during operation. Voltage ratio of the prototype EVT is about 42,270, and the frequency bandwidth of -3 dB ranges from 0.33 Hz to 3.9 MHz. The voltage ratio error evaluated at about 6%, 12% and 18% of the rated voltage of 170 kV was 0.32%, and the phase error was 12.9 minutes. These results were within the accuracy for the class 0.5 specified in IEC 60044-7 and satisfy even in ranges from 80% to 120% of the rated voltage. If the prototype EVT replaces the conventional iron-core potential transformer, it is expected that the height of the GIS could be reduced by 11% and the amount of SF₆ will be reduced by at least 10%.

• Clinics in Shoulder and Elbow
• /
• v.25 no.3
• /
• pp.182-187
• /
• 2022

Background: This study was designed to evaluate and compare the diagnostic value of magnetic resonance imaging (MRI) and indirect magnetic resonance arthrography (I-MRA) imaging with those of arthroscopy and each other. Methods: This descriptive-analytical study was conducted in 2020. All patients who tested positive for labrum lesions during that year were included in the study. The patients underwent conservative treatment for 6 weeks. In the event of no response to conservative treatment, MRI and I-MRA imaging were conducted, and the patients underwent arthroscopy to determine their ultimate diagnosis and treatment plan. Imaging results were assessed at a 1-week interval by an experienced musculoskeletal radiologist. Image interpretation results and arthroscopy were recorded in the data collection form. Results: Overall, 35 patients comprised the study. Based on the kappa coefficient, the results indicate that the results of both imaging methods are in agreement with the arthroscopic findings, but the I-MRA consensus rate is higher than that of MRI (0.612±0.157 and 0.749±0.101 vs. 0.449±0.160 and 0.603±0.113). The sensitivity, specificity, negative predictive value, positive predictive value, and accuracy of MRI in detecting labrum tears were 77.77%, 75.00%, 91.30%, 50.00%, and 77.14%, respectively, and those of I-MRA were 88.88%, 75.00%, 92.30%, 66.66%, and 85.71%. Conclusions: Here, I-MRA showed higher diagnostic value than MRI for labral tears. Therefore, it is recommended that I-MRA be used instead of MRI if there is an indication for potential labrum lesions.

• Geomechanics and Engineering
• /
• v.29 no.2
• /
• pp.113-131
• /
• 2022

A rockburst is a common disaster in deep-tunnel excavation engineering, especially for high-geostress areas. An anomalously low friction effect is one of the most important inducements of rockbursts. To elucidate the correlation between an anomalously low friction effect and a rockburst, we establish a two-dimensional prediction model that considers the discontinuous structure of a rock mass. The degree of freedom of the rotation angle is introduced, thus the motion equations of the blocks under the influence of a transient disturbing force are acquired according to the interactions of the blocks. Based on the two-dimensional discontinuous block model of deep rock mass, a rockburst prediction model is established, and the initiation process of ultra-low friction rockburst is analyzed. In addition, the intensity of a rockburst, including the location, depth, area, and velocity of ejection fragments, can be determined quantitatively using the proposed prediction model. Then, through a specific example, the effects of geomechanical parameters such as the different principal stress ratios, the material properties, a dip of principal stress on the occurrence form and range of rockburst are analyzed. The results indicate that under dynamic disturbance, stress variation on the structural surface in a deep rock mass may directly give rise to a rockburst. The formation of rockburst is characterized by three stages: the appearance of cracks that result from the tension or compression failure of the deformation block, the transformation of strain energy of rock blocks to kinetic energy, and the ejection of some of the free blocks from the surrounding rock mass. Finally, the two-dimensional rockburst prediction model is applied to the construction drainage tunnel project of Jinping II hydropower station. Through the comparison with the field measured rockburst data and UDEC simulation results, it shows that the model in this paper is in good agreement with the actual working conditions, which verifies the accuracy of the model in this paper.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.593-615
• /
• 2022

Purpose: The purpose of this study was to explore and examine the factors influencing customer satisfaction and subscription intention in order to propose useful implication regarding subscription economy model. Methods: This study adopts the extended Unified Theory of Acceptance and Use of Technology model (UTAUT2) as the theoretical framework. On the basis of literature review, this study suggested 9 related hypothesis. To examine the hypothesis proposed, the study designed surveys with 32 questions and 456 answers were collected for the analysis. The study adopted a structural equation model and path analysis, using AMOS and SPSS programs. Results: The results of this study are as follow: All hypothesis except performance expectancy and effort expectancy have significant influence on customer satisfaction. Performance expectancy and effort expectancy have no significant influence on customer satisfaction and facilitate condition is significant but negatively associated with customer satisfaction. Conclusion: Result of this study is expected to suggest data regarding subscription economy and customer satisfaction for business with subscription model. In detail the result implies that highly sophisticated curation system would create more customer satisfaction and subscription intention rather than how a subscription-based platform is easily used. Moreover, curation system of subsription-based music platform should function with high accuracy on recommendation in a creative visual form in order to gain comparative advantage while most platforms have built own curation service.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.163-170
• /
• 2022

This paper introduces a method of extracting facial features due to unrefined inputs in real life and improving the problem of not guaranteeing the ideal performance and speed of the object recognition model through a storage algorithm through weight summation. Many facial recognition processes ensure accuracy in ideal situations, but the problem of not being able to cope with numerous biases that can occur in real life is drawing attention, which may soon lead to serious problems in the face recognition process closely related to security. This paper presents a method of quickly and accurately recognizing faces in real time by comparing feature points extracted as input with a small number of feature points that are not overfit to multiple biases, using that various variables such as picture composition eventually take an average form.

• Journal of Practical Engineering Education
• /
• v.14 no.2
• /
• pp.351-359
• /
• 2022

In this paper, this app is an online learning tool web application that helps learners learn efficiently. It discusses how learners can improve their learning efficiency in these three aspects: retrieval practice, systematization, metacognition. Through this web service, learners can proceed with learning with a flash card-based retrieval practice. In this case, a method of managing a flash card in a form similar to a directory-file system using a composite pattern is described. Learners can systematically organize their knowledge by converting flash cards into a mind map. The color of the mind map varies according to the learner's learning progress, and learners can easily recognize what they know and what they do not know through color. In this case, it is proposed to build a deep learning model to improve the accuracy of an algorithm for determining and predicting learning progress.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.248-248
• /
• 2023

In recent years, the number of landslides in Korea has been increasing due to extreme weather events such as localized heavy rainfall and typhoons. Landslides often occur with debris flows, land subsidence, and earthquakes. They cause significant damage to life and property. 64% of Korea's land area is made up of mountains, the government wanted to predict landslides to reduce damage. In response, the Korea Forest Service has established a 'Landslide Information System' to predict the likelihood of landslides. This system selects a total of 13 landslide factors based on past landslide events. Using the LR technique (Logistic Regression) to predict the possibility of a landslide occurrence and the accuracy is known to be 0.75. However, most of the data used for learning in the current system is on landslides that occurred from 2005 to 2011, and it does not reflect recent typhoons or heavy rain. Therefore, in this study, we will apply a total of six machine learning techniques (KNN, LR, SVM, XGB, RF, GNB) to predict the occurrence of landslides based on the data of Inje, Gangwon-do, which was recently produced by the National Institute of Forest. To predict the occurrence of landslides, it is necessary to process converting landslide events and factors data into a suitable form for machine learning techniques through ArcGIS and Python. In addition, there is a large difference in the number of data between areas where landslides occurred or not. Therefore, the prediction was performed after correcting the unbalanced data using Tomek Links and Near Miss techniques. Moreover, to control unbalanced data, a model that reflects soil properties will use to remove absolute safe areas.