• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.819-834
• /
• 2022

Artificial Intelligence (AI) techniques have been effectively used for image classification, object detection, and image segmentation. Along with the recent advancement of computing power, deep learning models can build deeper and thicker networks and achieve better performance by creating more appropriate feature maps based on effective activation functions and optimizer algorithms. This review paper examined technical and academic trends of Convolutional Neural Network (CNN) and Transformer models that are emerging techniques in remote sensing and suggested their utilization strategies and development directions. A timely supply of satellite images and real-time processing for deep learning to cope with disaster monitoring will be required for future work. In addition, a big data platform dedicated to satellite images should be developed and integrated with drone and Closed-circuit Television (CCTV) images.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.11
• /
• pp.305-314
• /
• 2017

The purpose of this study is examining the status of Education Welfare Priority Support Project and providing constructive strategies for future direction. In order to collect data, we have used on-line survey, in-depth interview personnels in charge of 17 school districts and open forum with municipal board members of education along with related literature review. As results, since 2003, the effectiveness of the Education Welfare Priority Support Project has been proved and the areas have been expanded. Furthermore, institutional stability has been confirmed along with the supports of enforcement ordinance of the Elementary and Secondary Education Acts and Ministry of Education Ordinances. However, since the management authority of the project has transferred to 17 provincial offices of education, it shows the tendency of that the overall programs were not fully activated and gradually stagnated. According to these issues, we proposed various implemental policy suggestions though the revision of Article 28 of elementary and secondary education-related law.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.546-549
• /
• 2022

The installation rate of AMI (advanced metering infrastructure) capable of automatic electricity measurement is less than 43% nationwide and 10.5% in rural areas, which is very poor. Therefore, for the smart grid, automatic information recording of the watt-hour meter is required. For this purpose, it is necessary to develop a system capable of remote meter reading and use control by improving the existing watt-hour meter. In this paper, in order to enable the AMI function of the existing electricity meter, the remote meter reading and control technology of the existing electricity meter for AMI, the core of the smart grid, was developed using IoT and AI. The main research content was to recognize numbers using Tensorflow and Open-cv to convert it into a power meter sensing device for SG. We confirmed and checked the performance using the protyope system.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.111-121
• /
• 2015

Until now, the operation of community welfare centers for people with disabilities has brought a positive or a generous awareness. Nevertheless, in order to obtain a wide range of welfare outcomes efficiently, the imperative step in rehabilitation researches is to determine whether reasonable and scientific services are being provided to people with disabilities in rehabilitation centers. The purpose of this study was to analyze efficiency and productivity of 176 community welfare centers for people with disabilities. As a result, average technical efficiency for community welfare centers for people with disabilities was 0.4488; pure technical efficiency and scale efficiency was 0.6040 and 0.7080, respectively. The major conclusions of this study were as follows. First, applying the technical efficiency analysis, DMU2, DMU3, DMU8, DMU9, DMU11, DMU13, DMU14 were shown above average. It seems to have a regard for political elements in accordance with the regional social and economic differences. Second, as a result of scale efficiency analysis, the inefficient community welfare centers for people with disabilities such as DMU1, DMU5, DMU12, DMU16 are required to improve the number of employees, revenue, facility area. Finally, this study is expected to be an effectiveness analysis and performance evaluation for the rehabilitation services.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1643-1652
• /
• 2022

Deposited Marine Debris(DMD) can negatively affect marine ecosystems, fishery resources, and maritime safety and is mainly detected by sonar sensors, lifting frames, and divers. Considering the limitation of cost and time, recent efforts are being made by integrating underwater images and artificial intelligence (AI). We conducted a comparative study of You Only Look Once Version 5 (YOLOv5) and You Only Look Once Version 7 (YOLOv7) models to detect DMD from underwater images for more accurate and efficient management of DMD. For the detection of the DMD objects such as glass, metal, fish traps, tires, wood, and plastic, the two models showed a performance of over 0.85 in terms of Mean Average Precision (mAP@0.5). A more objective evaluation and an improvement of the models are expected with the construction of an extensive image database.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.913-924
• /
• 2022

In this paper, we presented a database construction of undersea images for the Habitats of Ecklonia cava and Sargassum and conducted an experiment for semantic segmentation using state-of-the-art (SOTA) models such as High Resolution Network-Object Contextual Representation (HRNet-OCR) and Shifted Windows-L (Swin-L). The result showed that our segmentation models were superior to the existing experiments in terms of the 29% increased mean intersection over union (mIOU). Swin-L model produced better performance for every class. In particular, the information of the Ecklonia cava class that had small data were also appropriately extracted by Swin-L model. Target objects and the backgrounds were well distinguished owing to the Transformer backbone better than the legacy models. A bigger database under construction will ensure more accuracy improvement and can be utilized as deep learning database for undersea images.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.190-197
• /
• 2013

Since domestic and foreign platform companies and mobile carriers adopt and use different kinds of smart platforms, developers should develop or convert contents according to each smart platform to provide a single smart content for customers. It takes long time and a lot of money to convert the conventional smart contents in order to serve other smart platforms. For the reason, more attention has been paid on Smart Cross Platform or Hybrid Platform, the core technologies of OSMU(One Source Multi Use) in which, once a program is coded, it can be executed in any platforms regardless of development languages. As a result, PhoneGap and HTML5 based Sencha Touch have been introduced. In this paper, we developed the smart virtual machine, which is built in smart cross platform based smart devices, unlike Android, iOS, Windows Phone devices being dependent of platforms, and helps to download and execute applications, being independent of platforms. the smart virtual machine supports C/C++, and Java language, being differentiated from JVM by sun microsystems that supports only Java language and .NET framework by microsoft that supports only C, C++ and C#. Therefore, it provides contents developers with the environment where they can get a wide range of options in choosing a language and develop smart contents.

• Journal of radiological science and technology
• /
• v.26 no.1
• /
• pp.39-44
• /
• 2003

The aim of this study is to evaluate a efficient w/v% barium suspension and w/v% sodium carboxy methyl cellulose (SCMC) for small bowel examination. Between november 2001 and june 2002, 370 patients were examined small bowel examination with oral administration of barium suspension mixed with SCMC. we classified into six groups including A(fine type 40% $BaSO_4$ mixed 0.5% SCMC and 600 ml 0.5% SCMC administration), B(fine type 30% $BaSO_4$ mixed 0.5% SCMC), C(fine type 20% $BaSO_4$ mixed 0.5% SCMC), D(fine type 25% $BaSO_4$ mixed 0.5% SCMC), E(D mixed coarse type 25% $BaSO_4$ mixed 0.5% SCMC), F(D mixed coarse type 25% $BaSO_4$ mixed 0.75% SCMC). We measured transparency rate of contrast media transit time, administration dose, viscosity and particle size. The transparency rate was higher then 80 kV and 90 kV in 100 kV in the same 20 mAs condition. Transit time was the fastest in A group(mean trans time 56 minutes) and the slowest in E group(mean 100 minutes), Administration dose was the smallest in A group(mean dose 541 ml and the most in E group(mean 1,100 ml), viscosity was the lowest in E(125.1 mpa/s) and the highest in A(375.5 mpa/s), and particle size was $1.0\;{\mu}m$ in A, B, C, and D group, $0.6\;{\mu}m,\;1.0\;{\mu}m,\;10.0\;{\mu}m$ in E, F group. In conclusion, we propose that the efficient condition for small examination is high voltage technique, high density $BaSO_4$, and 0.625% w/v SCMC.

• Journal of radiological science and technology
• /
• v.27 no.3
• /
• pp.51-58
• /
• 2004

The gel, which is stained on probe after ultrasonography, is a good circumstances for proliferation of microbe. This study is to investigate into the actual state of sanitary management, recognition degree and infection level of ultrasonographic probes. We had performed a question with telephone to 42 hospitals in Seoul area from December in 2003. We also cultured to obtained a sample from three ultrasonographic units to investigate infection level of the probes. Sanitary management of the probes was performed in 21 hospitals with alcohol cotton. Sanitary management was performed daily in 14 hospitals. Most hospitals used cotton towel for clearing of gel stained on probes. Preventive management against infection was performed in 32 hospitals with vinyl cover, surgical glove, or alcohol sterilization etc. In the recognition degree on infection, the response that using method of ultrasonographic probes is insanitary were in 78.6%(33 hospitals), and 54.8%(23 hospitals) responded that bacteria can be infected through the probes. In the results of germiculture, bacteria and fungi were detected too number of to count, but escherichia coli was not detected. In conclusion, The gel stained on probe after ultrasonography must be cleared completely, and it is necessary that change of recognition on sanitary management.

• Journal of radiological science and technology
• /
• v.27 no.3
• /
• pp.25-29
• /
• 2004

Among the digital radiography systems, the computed radiography Image Plate Detector System is most frequently being used for the general radiography and also this system commonly diffracts the x-ray images since it is the system that is influenced by the light diffusion from the fluorescent substances. In this study, by using the X-ray Generator, a comparative analysis has been made between 2 different models of computer radiography image plate investigate each model's resolution and sharpness through the modulation transfer function(MTF) measurement. For the analysis, two image plates for general radiography one Fuji ST-VN model(more than 3years old) and one Fuji ST-VL model(less than 2years old) that are currently being used in "Hospital A" were sampled for the MTF measurement here. As the experimental method for this study, the resolution chart method has been carried out by using X-ray generator. Also all the experimental data were printed out by laser printer and measured by microdensitometer. As the results of the experiment carried out in this study, some differences have been found between the two different IP models and Fuji ST-VL has shown its excellence in both of the resolution and the sharpness fields.