• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.113-128
• /
• 2024

Items of road tunnel PISD (Precise Inspection for Safety and Diagnosis) were reviewed and analyzed using newly enhanced MMS (Mobile Mapping System) technology. Possible items with MMS can be visual inspection, survey and non-destructive test, structural analysis, and maintenance plan. The resolution of 3D point cloud decreased when the vehicle speed of MMS is too fast while the calibration error increased when it is too slow. The speed measurement of 50 km/h is determined to be effective in this study. Although image resolution by MMS has a limit to evaluating the width of crack with high precision, it can be used as data to identify the status of facilities in the tunnel and determine whether they meet disaster prevention management code of tunnel. 3D point cloud with MMS can be applicable for matching of cross-section and also possible for the variation of longitudinal survey, which can intuitively check vehicle clearance throughout the road tunnel. Compared with the measurement of current PISD, number of test and location of survey is randomly sampled, the continuous measurement with MMS for environment condition can be effective and meaningful for precise estimation in various analysis.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.195-200
• /
• 2024

The purpose of this study is to propose optimized cognitive warfare strategies for the Korean Peninsula by analyzing recent war case studies. Through the analysis of the Armenia-Azerbaijan war, the Israel-Palestine conflict, the Ukraine-Russia war, and the Israel-Hamas conflict, it was found that the following aspects are crucial in conducting cognitive warfare: 1) applying methods according to objectives, 2) organizing and structuring appropriately to the objectives and means, and 3) utilizing various means from both civilian and military sectors. Based on these findings, cognitive warfare strategies optimized for the operational environment of the Korean Peninsula were suggested in terms of the three elements of military innovation. From the aspect of methodology, it is recommended to develop cognitive warfare scenarios based on legitimacy and legality, and to integrate roles according to the level of warfare. Regarding organization and structuring, the establishment of a national-level control tower and the construction of an integrated response system involving civilians, government, military, and police based on legislation are proposed. In terms of means, it is suggested to utilize various tools from the civilian, government, military, and police sectors, such as North Korean defectors, psychological warfare broadcasts against North Korea, social media, and cyber operations, for auditory, visual, and message delivery. In future battlefields characterized by hyper-connectivity and hyper-intelligence, the execution of cognitive warfare will become increasingly important. Therefore, it is necessary to continuously develop optimized cognitive warfare strategies for the Korean Peninsula through comprehensive national efforts.

• Communications of Mathematical Education
• /
• v.38 no.3
• /
• pp.443-458
• /
• 2024

This study analyzed the mathematical academic perspective and the actual status of the school field on the introduction of a definite integral as a 'Fundamental Theorem of Calculus' in the 2015 revised mathematics curriculum. Therefore, in order to investigate the mathematical academic perspective and the actual status of the school field, a study was conducted with 12 professors majoring in mathematical analysis and 36 teachers. From a mathematical academic point of view, professors majoring in mathematical analysis said that introducing a definite integral as a 'Fundamental Theorem of Calculus' in the 2015 revised mathematics curriculum was difficult to significantly represent the essence and meaning of the definite integral. In addition, in the actual status of the school field, teachers recognize the need for a relationship between a definite integral and the area of a figure, but when a definite integral is introduced as a 'Fundamental Theorem of Calculus', students find it difficult to recognize the relationship between the definite integral and the area of a figure. As the 2022 revised curriculum, which will be implemented later, introduces definite integrals as a 'Fundamental Theorem of Calculus' this study can consider implications for the introduction and guidance of static integrals. And, this study proposed a follow-up study on an effective teaching and learning method that can relate the definite integral to the area of the figure when introducing the definite integral as the 'Fundamental Theorem of Calculus' and on various visual tools and media.

• Korean Journal of Health Education and Promotion
• /
• v.18 no.2
• /
• pp.45-63
• /
• 2001

The objective of this study is to give basic materials for selection and improvement of contents of safety education, which is substantially helpful to elementary students, by analysis of contents of safety education in some subjects and assessment of the needs of elementary students for safety education. For this purpose, this study was analyzed the contents of safety education in five subjects for elementary school and conducted the survey of 883 students in some elementary schools in Seoul from April 7 to 22, 2000. The results were as follows; 1. As a result of analysis of the proportion of contents regarding safety-related education in some subjects, Physical Education occupied the highest proportion (14.09％), and that was followed by Practical Subject (9.55％) and Moral Education (9.34％). However, the proportions in Social Study and Natural Science were very low, 1.85％ and 1.31％ each. In total lines of these five subjects, the numbers of line regarding safety education was contained by 5.78％. 2. Analyzing the proportion of domains of safety education in five textbooks, the Meaning of Safety and Basic Principles occupied the highest portion (29.5％), and that was followed by the Home Safety (24.0％), the Safety in School (17.1％), and the Play and Leisure Safety (14.0％). The Coping with Accidents and First Aid, the Safety from Fire and Explosion, and the Traffic Safety occupied relatively low portion, 6.9％, 5.7％, and 2.8％ each. 3. As a result of analysis of the proportion of the safety education domain in each subject, the Meaning of Safety and Basic Principles occupied the highest portion (23.6％) in Moral Education, the Home Safety (12.7％) in Practical Subject, and the Play and Leisure Safety (10.9％) in Physical Education. 4. Most of the participants in this survey experienced the Home Accidents (71.1％). And also, they experienced the Play and Leisure Accidents (57.9％), the Accidents in School (49.7％), the Traffic Accidents (45.3％), and the Fire and Explosion Accidents (24.7％) in order. 5. In the average proportion of the needs of participants for safety education in each domain, the Coping with Accidents and First Aid has the highest point (4.05). And, that was followed by the Home safety (3.79), the Safety from Fire and Explosion (3.73), the Meaning of Safety and Basic Principles (3.65), the Play and Leisure Safety (3.50), the Safety in School (3.37), and the Traffic Safety (3.35). The average proportion of the needs for safety education of total domains was 3.66. 6. In the needs for safety education regarding the feature of participants, it showed higher scores in female students than male ones (p〈0.001), in lower grader than higher grader (p〈0.05), and in the students born to wealth than those born poor (p〈0.05). Also, the children who recognize the necessity of safety education showed higher scores of the needs for safety education (p〈0.001). And it also showed the same results of high score to the children whose parents did the safety education (p〈0.00l) and to the children and their parents who have the higher degree of practicing safety (p〈0.001), and these differences were statistically significant. 7. In the extent of preference for methods of safety education, it showed high score to the Field Learning, followed by the Audio- Visual Education, the Discussion, and the Instruction of teacher. In the extent of preference for subjects regarding the contents of safety education by each domain, it showed high score to the subject of Safety for 4 domains - the Meaning of Safety and Basic Principles, the Traffic Safety, the Safety from Fire and Explosion, and the Coping with Accidents and First Aid. And also, they preferred Moral Education for 2 domains - the Home safety and the Safety in School, and Physical Education for a domain of the Play and Leisure Safety. 8. While 27 of 36 detail items was contained the contents of safety education, the proportion of needs of participants for safety education showed more than average 3.00 score in 34 of 36 detail items. However, none of 9 detail items was included in five textbooks. Also, 2 detail items - the Coping with Disasters and the Safety from Poisoning - were included together 2 parts; One part had the higher ranked 7 items acquired by analysis of the needs, and the other had the higher ranked 7 items acquired by analysis of the contents. But, except those 2 items, none of items were matched with each part.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.6
• /
• pp.418-427
• /
• 2003

Objects: $^{99m}-lactosylated$ human serum albumin (LSA) is a newly synthesized radiopharmaceutical that binds to asialoglycoprotein receptors, which are specifically presented on the hepatocyte membrane. Hepatic uptake and blood clearance of LSA were evaluated in rat with acute hepatic injury induced by dimethylnitrosamine (DMN) and results were compared with corresponding findings of liver enzyme profile and these of histologic changes. Materials and Methods: DMN (27 mg/kg) was injected intraperitoneally in Sprague-Dawley rat to induce acute hepatic injury. At 3(DMN-3), 8(DMN-8), and 21 (DMN-21) days after injection of DMN, LSA injected intravenously, and dynamic images of the liver and heart were recorded for 30 minutes. Time-activity curves of the heart and liver were generated from regions of interest drawn over liver and heart area. Degree of hepatic uptake and blood clearance of LSA were evaluated with visual interpretation and semiquantitative analysis using parameters (receptor index : LHL3 and index of blood clearance : HH3), analysis of time-activity curve was also performed with curve fitting using Prism program. Results: Visual assessment of LSA images revealed decreased hepatic uptake in DMN treated rat, compared to control group. In semiquantitative analysis, LHL3 was significantly lower in DMN treated rat group than control rat group (DMN-3: 0.842, DMN-8: 0.898, DMN-21: 0.91, Control: 0.96, p<0.05), whereas HH3 was significantly higher than control rat group (DMN-3: 0.731,.DMN-8: 0.654, DMN-21: 0.604, Control: 0.473, p<0.05). AST and ALT were significantly higher in DMN-3 group than those of control group. Centrilobular necrosis and infiltration of inflammatory cells were most prominent in DMN-3 group, and were decreased over time. Conclusion: The degree of hepatic uptake of LSA was inversely correlated with liver transaminase and degree of histologic liver injury in rat with acute hepatic injury.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.89-105
• /
• 2014

After emergence of Internet, social media with highly interactive Web 2.0 applications has provided very user friendly means for consumers and companies to communicate with each other. Users have routinely published contents involving their opinions and interests in social media such as blogs, forums, chatting rooms, and discussion boards, and the contents are released real-time in the Internet. For that reason, many researchers and marketers regard social media contents as the source of information for business analytics to develop business insights, and many studies have reported results on mining business intelligence from Social media content. In particular, opinion mining and sentiment analysis, as a technique to extract, classify, understand, and assess the opinions implicit in text contents, are frequently applied into social media content analysis because it emphasizes determining sentiment polarity and extracting authors' opinions. A number of frameworks, methods, techniques and tools have been presented by these researchers. However, we have found some weaknesses from their methods which are often technically complicated and are not sufficiently user-friendly for helping business decisions and planning. In this study, we attempted to formulate a more comprehensive and practical approach to conduct opinion mining with visual deliverables. First, we described the entire cycle of practical opinion mining using Social media content from the initial data gathering stage to the final presentation session. Our proposed approach to opinion mining consists of four phases: collecting, qualifying, analyzing, and visualizing. In the first phase, analysts have to choose target social media. Each target media requires different ways for analysts to gain access. There are open-API, searching tools, DB2DB interface, purchasing contents, and so son. Second phase is pre-processing to generate useful materials for meaningful analysis. If we do not remove garbage data, results of social media analysis will not provide meaningful and useful business insights. To clean social media data, natural language processing techniques should be applied. The next step is the opinion mining phase where the cleansed social media content set is to be analyzed. The qualified data set includes not only user-generated contents but also content identification information such as creation date, author name, user id, content id, hit counts, review or reply, favorite, etc. Depending on the purpose of the analysis, researchers or data analysts can select a suitable mining tool. Topic extraction and buzz analysis are usually related to market trends analysis, while sentiment analysis is utilized to conduct reputation analysis. There are also various applications, such as stock prediction, product recommendation, sales forecasting, and so on. The last phase is visualization and presentation of analysis results. The major focus and purpose of this phase are to explain results of analysis and help users to comprehend its meaning. Therefore, to the extent possible, deliverables from this phase should be made simple, clear and easy to understand, rather than complex and flashy. To illustrate our approach, we conducted a case study on a leading Korean instant noodle company. We targeted the leading company, NS Food, with 66.5% of market share; the firm has kept No. 1 position in the Korean "Ramen" business for several decades. We collected a total of 11,869 pieces of contents including blogs, forum contents and news articles. After collecting social media content data, we generated instant noodle business specific language resources for data manipulation and analysis using natural language processing. In addition, we tried to classify contents in more detail categories such as marketing features, environment, reputation, etc. In those phase, we used free ware software programs such as TM, KoNLP, ggplot2 and plyr packages in R project. As the result, we presented several useful visualization outputs like domain specific lexicons, volume and sentiment graphs, topic word cloud, heat maps, valence tree map, and other visualized images to provide vivid, full-colored examples using open library software packages of the R project. Business actors can quickly detect areas by a swift glance that are weak, strong, positive, negative, quiet or loud. Heat map is able to explain movement of sentiment or volume in categories and time matrix which shows density of color on time periods. Valence tree map, one of the most comprehensive and holistic visualization models, should be very helpful for analysts and decision makers to quickly understand the "big picture" business situation with a hierarchical structure since tree-map can present buzz volume and sentiment with a visualized result in a certain period. This case study offers real-world business insights from market sensing which would demonstrate to practical-minded business users how they can use these types of results for timely decision making in response to on-going changes in the market. We believe our approach can provide practical and reliable guide to opinion mining with visualized results that are immediately useful, not just in food industry but in other industries as well.

• The Korean Journal of Nuclear Medicine
• /
• v.39 no.6
• /
• pp.456-463
• /
• 2005

Purpose: we often find variable degrees of FDG uptake and patterns in stomach, which can make difficult to distinguish physiologic uptake from pathologic uptake on FDG PET. The purpose of this study was to find out the significant findings of stomach on FDG PET. Materials and Methods: Thirty-eight patients who underwent both FDG PET and endoscopy within one week from Jun. 2003, to Aug. 2004 were included in this study. We reviewed 38 patients (18 for medical check up, 15 for work up of other malignancies, and 5 for the evaluation of stomach lesion). Their mean age was 56 years old (range:$32{\sim}79$), men and women were 28 and 10, respectively. Two nuclear physicians evaluated five parameters on FDG PET findings of stomach with a consensus: 1) visual grades 2) maximum SUV (max.SUV) 3) focal 4) diffuse and S) asymmetric patterns. We correlated the lesions of FDG PET findings of stomach with those of endoscopy. We considered more than equivocal findings on FDG PET as positive. Results: The six of 38 patients were proven as malignant lesions by endoscopic biopsy and others were inflammatory lesions (ulcer in 3, chronic atrophic gastritis in 12, uncommon forms of gastritis in 5), non-inflammatory lesions (n=3), and normal stomach (n=9). By the visual analysis, malignant lesions had higher FDG uptake than the others. The max.SUV of malignant lesions was $7.95{\pm}4.83$ which was significantly higher than the other benign lesions ($2.9{\pm}0.69$ in ulcer, $3.08{\pm}1.2$ in chronic atrophic gastritis, $3.2{\pm}1.49$ in uncommon forms of gastritis (p=0.044)). In the appearance of stomach on FDG PET, malignant lesions were shown focal (5 of 6) and benign inflammatory lesions were shown diffuse (9 of 20) and asymmetric (14 of 20). Benign lesions and normal stomach were shown variable degrees of uptake and patterns. Some cases of benign inflammatory lesions such as ulcer and gastritis were shown focal and mimicked cancerous lesion (4 of 15). Conclusion: Gastric malignant lesions had higher FDG uptake and focal pattern. However, benign inflammatory lesions had moderate degrees of uptake and diffuse and asymmetric patterns rather than focal. It is difficult to differentiate between benign lesions including normal.

• Cartoon and Animation Studies
• /
• s.44
• /
• pp.1-31
• /
• 2016

In this thesis, the movie with mise-en-scene established was compared with the peculiarity of the play that is the etymological source of the term to identify the peculiarity of mise-en-scene which was substituted into animation to find the peculiarity of mise-en-scene in animation. To emphasize the direct connection between the frame's visual peculiarity and the director's opinions, the mise-en-scene of director centered animation created under a restricted environment was reviewed. Mise-en-scene which started from movie critics theory does not simply mean the arrangement of images in a frame. Mise-en-scene emphasizes the exposure of the work's motive by the visual components. The animation's assuming the middle point of environmental share possessed by play and movie when schematizing the genre peculiarity of animation, play and movie was a noteworthy result. It can be said that the cause is that the animation's peculiarity yield different results depending on the making methods; we verified that this is a key factor in the analysis of animation's mise-en-scene. I emphasized that the peculiarity of animation mise-en-scene is in its making method and material and suggested identifying the work's making methods and analyzing the work's aesthetic results derived in this way. The russian animation which was perceived as peripheral arts was relatively free from the burden of censorship while receiving support from the Soviet as a media for propaganda. The russian animation's mise-en-scene which found the material for its works in the country's folklore was metaphorical, focused on new expression forms and achieved experimental elements. Russian animation pursues a unique aesthetic world through space expression based on the forms of opera or ballet and heavy motions formed static inbetweens.