• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Korean Journal of Optics and Photonics
• /
• v.16 no.3
• /
• pp.182-190
• /
• 2005

The fiber Raman amplifier(FRA) is a distinctly advantageous technology. Due to its wider, flexible gain bandwidth, and intrinsically lower noise characteristics, FRA has become an indispensable technology of today. Various FRA modeling methods, with different levels of convergence speed and accuracy, have been proposed in order to gain valuable insights for the FRA dynamics and optimum design before real implementation. Still, all these approaches share the common platform of coupled ordinary differential equations(ODE) for the Raman equation set that must be solved along the long length of fiber propagation axis. The ODE platform has classically set the bar for achievable convergence speed, resulting exhaustive calculation efforts. In this work, we propose an alternative, highly efficient framework for FRA analysis. In treating the Raman gain as the perturbation factor in an adiabatic process, we achieved implementation of the algorithm by deriving a recursive relation for the integrals of power inside fiber with the effective length and by constructing a matrix formalism for the solution of the given FRA problem. Finally, by adiabatically turning on the Raman process in the fiber as increasing the order of iterations, the FRA solution can be obtained along the iteration axis for the whole length of fiber rather than along the fiber propagation axis, enabling faster convergence speed, at the equivalent accuracy achievable with the methods based on coupled ODEs. Performance comparison in all co-, counter-, bi-directionally pumped multi-channel FRA shows more than 102 times faster with the convergence speed of the Average power method at the same level of accuracy(relative deviation < 0.03dB).

• Journal of Korea Water Resources Association
• /
• v.46 no.12
• /
• pp.1193-1207
• /
• 2013

Increase of impervious area caused by overdevelopment has led to increase of runoff and then the problem of flooding and NPS were brought up. In addition, as decrease of base flow made groundwater level to decline, a stream that dries up is issued. low impact development (LID) method which is possible to mimic hydrological water cycle, minimize the effect of development, and improve water cycle structure is proposed as an alternative. As introduction of LID in domestic increases, the study on small watershed is in process mainly. Also, analysis of property of hydrological runoff and load on midsize watershed, like sewage treatment district, is required, the study on it is still insufficient. So, area applying LID practices from watershed of Dongrae stream is pinpointed and made the ratio and then expand it to watershed of Oncheon stream. Among low impact development practices, Green Roof, Porous Pavement, and Bio- retention are selected for the application considering domestic situations and simulated with SWMM-LID model of each watershed and improvement of water cycle and reduction of non-point pollution loads was analysed. Improvement of water cycle and reduction of non-point pollution loads were analyzed including the property of rainfall and soil over long term simulation. The model was executed according to scenario based on combination of LID as changing conductivity in accordance with soil type of the watershed. Also, this study evaluated area of LID application that meets the efficiency of conventional management as a criteria for area of LID practices applying to sewer treatment district by comparing the efficiency of LID application with that of conventional method.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.1-17
• /
• 2023

With the recent rapid development of ICT(Information and Communication Technology) and the popularization of digital devices, the size of the online market continues to grow. As a result, we live in a flood of information. Thus, customers are facing information overload problems that require a lot of time and money to select products. Therefore, a personalized recommender system has become an essential methodology to address such issues. Collaborative Filtering(CF) is the most widely used recommender system. Traditional recommender systems mainly utilize quantitative data such as rating values, resulting in poor recommendation accuracy. Quantitative data cannot fully reflect the user's preference. To solve such a problem, studies that reflect qualitative data, such as review contents, are being actively conducted these days. To quantify user review contents, text mining was used in this study. The general CF consists of the following three steps: user-item matrix generation, Top-N neighborhood group search, and Top-K recommendation list generation. In this study, we propose a recommendation algorithm that applies an extended similarity measure, which utilize quantified review contents in addition to user rating values. After calculating review similarity by applying TF-IDF, Word2Vec, and Doc2Vec techniques to review content, extended similarity is created by combining user rating similarity and quantified review contents. To verify this, we used user ratings and review data from the e-commerce site Amazon's "Health and Personal Care". The proposed recommendation model using extended similarity measure showed superior performance to the traditional recommendation model using only user rating value-based similarity measure. In addition, among the various text mining techniques, the similarity obtained using the TF-IDF technique showed the best performance when used in the neighbor group search and recommendation list generation step.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.263-286
• /
• 2022

This study acquires NBA statistical information for a total of 32 years from 1990 to 2022 using web crawling, observes variables of interest through exploratory data analysis, and generates related derived variables. Unused variables were removed through a purification process on the input data, and correlation analysis, t-test, and ANOVA were performed on the remaining variables. For the variable of interest, the difference in the mean between the groups that advanced to the playoffs and did not advance to the playoffs was tested, and then to compensate for this, the average difference between the three groups (higher/middle/lower) based on ranking was reconfirmed. Of the input data, only this year's season data was used as a test set, and 5-fold cross-validation was performed by dividing the training set and the validation set for model training. The overfitting problem was solved by comparing the cross-validation result and the final analysis result using the test set to confirm that there was no difference in the performance matrix. Because the quality level of the raw data is high and the statistical assumptions are satisfied, most of the models showed good results despite the small data set. This study not only predicts NBA game results or classifies whether or not to advance to the playoffs using machine learning, but also examines whether the variables of interest are included in the major variables with high importance by understanding the importance of input attribute. Through the visualization of SHAP value, it was possible to overcome the limitation that could not be interpreted only with the result of feature importance, and to compensate for the lack of consistency in the importance calculation in the process of entering/removing variables. It was found that a number of variables related to three points and errors classified as subjects of interest in this study were included in the major variables affecting advancing to the playoffs in the NBA. Although this study is similar in that it includes topics such as match results, playoffs, and championship predictions, which have been dealt with in the existing sports data analysis field, and comparatively analyzed several machine learning models for analysis, there is a difference in that the interest features are set in advance and statistically verified, so that it is compared with the machine learning analysis result. Also, it was differentiated from existing studies by presenting explanatory visualization results using SHAP, one of the XAI models.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.29 no.3
• /
• pp.153-161
• /
• 2023

The worldwide effects of COVID-19 have led to a surge in online shopping and contactless services. The consumption pattern has caused the issues such as the environmental pollution together with the increase of plastic waste. Reducing the reliance on the petroleum based plastic use for the package and replacing it with environmentally friendly material are the simple ways in order to solve those problems. Paper is an eco-friendly product with high recyclability as the food packaging materials but has still poor barrier properties. A barrier coating on surface of the paper can be achieved with the proper packaging materials featuring water, gas and grease barrier. Polyethylene (PE) or polypropylene (PP) coatings which are generally laminated or coated to paper are widely used in food packaging applications to protect products from moisture and provide water or grease resistance. However, recycling of packaging containing PE or PP matrix is limited and costly because those films are difficult to degrade in the environment. This study investigated the recyclability of modified acrylic emulsion coating papers compared to PE and PP polymer matrixes as well as their mechanical and gas barrier properties. The results showed that PE or modified acrylic emulsion coated papers had better mechanical properties compared to the uncoated paper as a control. PE or PP coating papers showed strong oil resistance property, achieving a kit rating of 12. Those papers also had a significantly higher percentage of screen reject during the recycling process than modified acrylic coated paper which had a screen rejection rate of 6.25%. In addition an uncoated paper had similar value of a screen rejection rate. It may suggest that modified acrylic emulsion coating paper can be more easily recycled than PE or PP coating papers. The overall results of the study found that modified acrylic emulsion coating paper would be a viable alternative to suggest a possible solution to an environmental problem as well as enhancing the weak mechanical and poor gas barrier properties of the paper against moisture.

• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.47-55
• /
• 2015

Recently, the environment of a hospital information system is a trend to combine various SMART technologies. Accordingly, various smart devices, such as a smart phone, Tablet PC is utilized in the medical information system. Also, these environments consist of various applications executing on heterogeneous sensors, devices, systems and networks. In these hospital information system environment, applying a security service by traditional access control method cause a problems. Most of the existing security system uses the access control list structure. It is only permitted access defined by an access control matrix such as client name, service object method name. The major problem with the static approach cannot quickly adapt to changed situations. Hence, we needs to new security mechanisms which provides more flexible and can be easily adapted to various environments with very different security requirements. In addition, for addressing the changing of service medical treatment of the patient, the researching is needed. In this paper, we suggest a dynamic approach to medical information systems in smart mobile environments. We focus on how to access medical information systems according to dynamic access control methods based on the existence of the hospital's information system environments. The physical environments consist of a mobile x-ray imaging devices, dedicated mobile/general smart devices, PACS, EMR server and authorization server. The software environment was developed based on the .Net Framework for synchronization and monitoring services based on mobile X-ray imaging equipment Windows7 OS. And dedicated a smart device application, we implemented a dynamic access services through JSP and Java SDK is based on the Android OS. PACS and mobile X-ray image devices in hospital, medical information between the dedicated smart devices are based on the DICOM medical image standard information. In addition, EMR information is based on H7. In order to providing dynamic access control service, we classify the context of the patients according to conditions of bio-information such as oxygen saturation, heart rate, BP and body temperature etc. It shows event trace diagrams which divided into two parts like general situation, emergency situation. And, we designed the dynamic approach of the medical care information by authentication method. The authentication Information are contained ID/PWD, the roles, position and working hours, emergency certification codes for emergency patients. General situations of dynamic access control method may have access to medical information by the value of the authentication information. In the case of an emergency, was to have access to medical information by an emergency code, without the authentication information. And, we constructed the medical information integration database scheme that is consist medical information, patient, medical staff and medical image information according to medical information standards.y Finally, we show the usefulness of the dynamic access application service based on the smart devices for execution results of the proposed system according to patient contexts such as general and emergency situation. Especially, the proposed systems are providing effective medical information services with smart devices in emergency situation by dynamic access control methods. As results, we expect the proposed systems to be useful for u-hospital information systems and services.