• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.81-90
• /
• 2021

There are various optimization problems in real world and research continues to solve them. An optimization problem is the problem of finding a combination of parameters that maximizes or minimizes the objective function. Harmony search is a population-based metaheuristic algorithm for solving optimization problems and it is designed to mimic the improvisation of jazz music. Harmony search has been actively applied to optimization problems in various fields such as civil engineering, computer science, energy, medical science, and water quality engineering. Harmony search has a simple working principle and it has the advantage of finding good solutions quickly in constrained optimization problems. Especially there are various application cases showing high accuracy with a low number of iterations by improving the solution through the empirical derivative. In this paper, we explain working principle of Harmony search and classify the leading research in recent 3 years, review them according to category, and suggest future research directions. The research is divided into review by field, algorithmic analysis and theory, and application to real world problems. Application to real world problems is classified according to the purpose of optimization and whether or not they are hybridized with other metaheuristic algorithms.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.423-431
• /
• 2023

The purpose of this study is to analyze the factors affecting the classification of the severity of contrast media side effects based on the patient's body information using artificial intelligence techniques to be used as basic data to reduce the degree of contrast medium side effects. The data used in this study were 606 examiners who had no contrast medium side effects in the past history survey among 1,235 cases of contrast medium side effects among 58,000 CT scans performed at a general hospital in Seoul. The total data is 606, of which 70% was used as a training set and the remaining 30% was used as a test set for validation. Age, BMI(Body Mass Index), GFR(Glomerular Filtration Rate), BUN(Blood Urea Nitrogen), GGT(Gamma Glutamyl Transgerase), AST(Aspartate Amino Transferase,), and ALT(Alanine Amiono Transferase) features were used as independent variables, and contrast media severity was used as a target variable. AUC(Area under curve), CA(Classification Accuracy), F1, Precision, and Recall were identified through AdaBoost, Tree, Neural network, SVM, and Random foest algorithm. AdaBoost and Random Forest show the highest evaluation index in the classification prediction algorithm. The largest factors in the predictions of all models were GFR, BMI, and GGT. It was found that the difference in the amount of contrast media injected according to renal filtration function and obesity, and the presence or absence of metabolic syndrome affected the severity of contrast medium side effects.

• Journal of the Daesoon Academy of Sciences
• /
• v.17
• /
• pp.173-196
• /
• 2004

Miroku belief observed in Japanese folklore and popular religions is originated from the faith in a bodhisattva called Miroku (Maitreya) who, depending on Buddhist account, is supposed to appear in this world to save all mankind. This faith, together with the millenarianism inherent in it, was disseminated into many areas of East and Southeast Asia. It developed in various ways, being associated with the religious tradition of each area where it was accepted. In Japanese folklore and popular religions the aspiration for the "World of Miroku", the ideal world expected to be realized in the future, has been its most notable feature. This paper examines the notion of the "World of Miroku" developed in the cult of Mount Fuji in early modern Japan. In particular this paper focuses on the "World of Miroku" appearing in the teachings of Fuji-ko and Fujido, which were the organizations of lay believers. Through the examination this paper made the following facts clear. (1) The notion of the "World of Miroku" developed by Fuji-ko and Fujido had its bases in Miroku belief of Japanese folklore. (2) However the notion of the "World of Miroku" in the teachings of Fuji-ko and Fujido was quite different from that of the folklore. While the "World of Miroku" appearing in the folklore is characterized by good harvest and abundant gold and silver, Fuji-ko and Fujido leaders thought that all people, including the emperor and the shogun, would earnestly carry out their house business, do their best to promote the happiness of the others, and pray for the salvation of all mankind in the "World of Miroku". (3) The notion about the changes of the world, which was particular to Fuji-ko and Fujido, accounts for such development in the concept of the "World of Miroku". According to the notion the current world was recognized as the second stage, between the original world in the past and the "World of Miroku" in the future, in the history of human beings. This idea helped the leaders of Fuji-ko and Fujido to develop the theories of world renewal, in which the wrong doings of the rulers and poor morality of the people were to be corrected in the "World of Miroku". (4) One of the most important features of the "World of Miroku" was the equality between men and women according to the teachings of Fujido. Both Fuji-ko and Fujido had opposed to the prevailing view of women, in which women were regarded as being sinful and polluted. Fujido further tried to improve the status of women in their families and the society. (5) In accordance with such an innovatory view, Fujido challenged the custom of excluding women from sacred places, Mount Fuji in particular. Through clarifying these facts this paper shows that Miroku belief could function as a basis for developing the ideas concerning the world renewal in early modern Jap

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.134-139
• /
• 2023

Rehabilitators perform outpatient treatment and daily rehabilitation exercises to recover physical function with the aim of quickly returning to society after surgical treatment. Unlike performing exercises in a hospital with the help of a professional therapist, there are many difficulties in performing rehabilitation exercises by the patient on a daily basis. In this paper, we propose a CNN-LSTM-based upper limb rehabilitation real-time monitoring system so that patients can perform rehabilitation efficiently and with correct posture on a daily basis. The proposed system measures biological signals through shoulder-mounted hardware equipped with EMG and IMU, performs preprocessing and normalization for learning, and uses them as a learning dataset. The implemented model consists of three polling layers of three synthetic stacks for feature detection and two LSTM layers for classification, and we were able to confirm a learning result of 97.44% on the validation data. After that, we conducted a comparative evaluation with the Teachable machine, and as a result of the comparative evaluation, we confirmed that the model was implemented at 93.6% and the Teachable machine at 94.4%, and both models showed similar classification performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.37 no.6
• /
• pp.57-65
• /
• 2010

Physical activity of the people has decreased due to a sedentary lifestyle according to developing the economy throughout the world. It is thought to increase the risk of chronic diseases, including obesity, diabetes, etc. People are interested in walking, which is an easy activity to engage in as an antidote to chronic diseases. The aim of this study is to increase the diminishing physical activity of modem society by inducing walking as part of everyday life through building a walking-based activity-friendly city where people can live merrily, safely and pleasantly. For this purpose, this study conducted a satisfaction survey to dwellers of Jinhae on the physical pedestrian environments which affect determining walking participation and intentions of people, and also provided a valid model to evaluate the effects of the physical environmental factors on walking satisfaction using factor analysis and multiple linear regression analysis. The results are summarized as follows. The 18 variables of the physical pedestrian environments were selected based on pre-literature reviews. The results of the satisfaction surveys showed that the satisfaction of crossing aids in segments was highest, while the building feature was the lowest. Factor analysis was run through a two-step process. The first analysis was conducted to examine the adequacy of this factor analysis on the selected 18 variables. As a result, two variables were removed and the remaining 16 variables were extracted to the four factors by second analysis. Each factor was named function of path, effect of traffic, amenity and safety based on the each factor's commonality. Each factor score of the extracted four factors was set as the independent variable, while the overall walking satisfaction was set as the dependent variable. Then, the multiple linear regression analysis was conducted and showed that all four factors had a positive influence on the overall satisfaction of walking, especially the 'function of path' and 'amenity' factors, followed by 'effect of traffic' and 'safety'. The results of this research will be used as foundational data for creating a walking-based activity-friendly city.

• Journal of Korean Society of Transportation
• /
• v.20 no.3
• /
• pp.149-158
• /
• 2002

For the purpose of preciously describing real time traffic pattern in urban road network, dynamic network loading(DNL) models able to simulate traffic behavior are required. A number of different methods are available, including macroscopic, microscopic dynamic network models, as well as analytical model. Equivalency minimization problem and Variation inequality problem are the analytical models, which include explicit mathematical travel cost function for describing traffic behaviors on the network. While microscopic simulation models move vehicles according to behavioral car-following and cell-transmission. However, DNL models embedding such travel time function have some limitations ; analytical model has lacking of describing traffic characteristics such as relations between flow and speed, between speed and density Microscopic simulation models are the most detailed and realistic, but they are difficult to calibrate and may not be the most practical tools for large-scale networks. To cope with such problems, this paper develops a new DNL model appropriate for dynamic traffic assignment(DTA), The model is combined with vertical queue model representing vehicles as vertical queues at the end of links. In order to compare and to assess the model, we use a contrived example network. From the numerical results, we found that the DNL model presented in the paper were able to describe traffic characteristics with reasonable amount of computing time. The model also showed good relationship between travel time and traffic flow and expressed the feature of backward turn at near capacity.

• Clinical and Experimental Pediatrics
• /
• v.51 no.3
• /
• pp.323-328
• /
• 2008

Purpose : Asthma is defined as chronic inflammation of the lower small airways, and bronchial hyperreactivity (BHR) is a pathophysiologic feature of asthma. It has been proposed that although there is no direct variable capable of assessing the small airways, a forced expiratory flow of between 25 and 75 percent ($FEF_{25-75}$) might be considered a more sensitive early marker of small airway obstruction than the forced expiratory volume in 1 second ($FEV_1$). Thus, we proposed that the presence and degree of positive responses to bronchial methacholine testing were related to the difference (DFF) and ratio (RFF) between $FEV_1$ and $FEF_{25-75}$ in asthmatic children. Methods : The subjects were 583 symptomatic children, including 324 children with BHR and 259 controls. Pulmonary function tests, methacholine challenge tests, and skin prick tests were performed, and the total eosinophil count, total serum IgE, and serum eosinophil cationic protein level were measured in all subjects. From a concentration-response curve, the methacholine concentration required to produce a decrease of 20% from post-saline $FEV_1$ was calculated ($PC_{20}$). Results : The median DFF and RFF values decreased in controls compared to subjects with bronchial hyperresponsiveness, and this trend was found in groups ranked by its severity. $PC_{20}$ had a negative correlation with DFF and RFF. Cutoff values of 0.5 for DFF and 1.042 for RFF were identified, and sensitivity and specificity were calculated. Conclusion : This study revealed that DFF and RFF might be predictive of bronchial hyperresponsiveness in the context of normal $FEV_1$ in children.

• Cartoon and Animation Studies
• /
• s.39
• /
• pp.261-295
• /
• 2015

Cyber singer appeared in the late 1990s has disappeared briefly appeared. although a few attempts in the 2000s, it did not show significant successes. cyber singer was born thanks to the technical development of the IT industry and the emergence of an idol training system in the music industry. It was developed by Vocaloid 'Seeyou' starting from 'Adam'. cyber singer that differenatiated typical digital characters in a cartoon or game may be subject to idolize to the music as a medium. They also feature forming a plurality of fandom. therefore, such attempts and repeated failures, this could be considered a fashion, but it flew content creation and ongoing attempts to take advantage of the new media, such as Vocaloid can see that there are expectations for a true Cyber-born singer. Early-Cyber singer is made only resemble human appearance, but 'Sciart' and 'Seeyou' has been evolving to becoming more like the human capabilities. in this paper, stylized cyber singer had disappeared in the past in the process of developing the technology to evolve into own artificial life does not end in failure cases, gradually led to a change in public perceptions of the image look looking machine was an attempt in that sense. With the direction of the evolution of the mechanical function to obtain a human, fun and human exchanges and mutual feelings. And it is equipped with an artificial life form that evolved with it only in appearance and function. in order to support this logic, I refer to the study of the coevolution of man and machine at every Bruce Mazlish. And, I have analyzed the evolution of cyber singer Bruce research from the perspective of the development process since the late 1990s, the planning of the eight singers who have appeared and design of the cyber character and important voices to be evaluated as a singer (vocal). The machine has been evolving coevolution with humans. cyber singer ambivalent development targets are recognized, but strive to become the new artificial creatures of horror idea of human desire and death continues. therefore, the new Cyber-organisms are likely to be the same style as 'Seeyou'. because, cartoon forms and whirring voice may not be in the form of a signifier is the real human desires, but this is because the contemporary public's desire to be desired and the technical development of this type can be created at the point where the cross-signifier.