• Structural Engineering and Mechanics
• /
• v.83 no.1
• /
• pp.1-17
• /
• 2022

The static design approach in the current code implies that the inherent torsional moment represents the state of zero inertial torsional moments at the center of mass (CM). However, both experimental and analytical results prove the existence of a large amount of the inertial torsional moment at the CM. Also, the definition of eccentricity by engineers, which is referred to as the resistance eccentricity, is defined as the distance between the center of mass and the center of resistance, which is conceptually different from the static eccentricity in the current codes, defined as the arm length about the center of rotation. The difference in the definitions of eccentricity should be made clear to avoid confusion about the torsion design. This study proposed prediction equations as a function of resistance eccentricity based on a resistance eccentricity model with advantages of (1) the recognition of the existence of torsional moment at the CM, (2) the avoidance of the confusion by using resistance eccentricity instead of the design eccentricity, and (3) a clear relationship of applied inertial forces at the CM and resisting forces. These predictions are compared with the seismic responses obtained from time-history analyses of a five-story building structure under moderate and severe earthquakes. Then, the trend of the resistance eccentricity corresponding to the maximum edge drift is investigated for elastic and inelastic responses. The comparison given in this study shows that these prediction equations can serve as a useful reference for the prediction in both the elastic and the inelastic ranges.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.6
• /
• pp.591-601
• /
• 2021

Recently, infrared object detection(IOD) has been extensively studied due to the rapid growth of deep neural networks(DNN). Adversarial attacks using imperceptible perturbation can dramatically deteriorate the performance of DNN. However, most adversarial attack works are focused on visible image recognition(VIR), and there are few methods for IOD. We propose deep learning-based adversarial attacks for IOD by expanding several state-of-the-art adversarial attacks for VIR. We effectively validate our claim through comprehensive experiments on two challenging IOD datasets, including FLIR and MSOD.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.91-98
• /
• 2023

Human-object interaction(HOI) detection requires both object detection and interaction recognition, and requires a large amount of data to learn a detection model. Current opened dataset is insufficient in scale for training model enough. In this paper, we propose an easy and effective data augmentation method called Simple Quattro Augmentation(SQA) and Random Quattro Augmentation(RQA) for human-object interaction detection. We show that our proposed method can be easily integrated into State-of-the-Art HOI detection models with HICO-DET dataset.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.208-215
• /
• 2023

Deep learning techniques provide powerful solutions to several pattern-recognition problems, including Raman spectral classification. However, these networks require large amounts of labeled data to perform well. Labeled data, which are typically obtained in a laboratory, can potentially be alleviated by data augmentation. This study investigated various data augmentation techniques and applied multiple deep learning methods to Raman spectral classification. Raman spectra yield fingerprint-like information about chemical compositions, but are prone to noise when the particles of the material are small. Five augmentation models were investigated to build robust deep learning classifiers: weighted sums of spectral signals, imitated chemical backgrounds, extended multiplicative signal augmentation, and generated Gaussian and Poisson-distributed noise. We compared the performance of nine state-of-the-art convolutional neural networks with all the augmentation techniques. The LeNet5 models with background noise augmentation yielded the highest accuracy when tested on real-world Raman spectral classification at 88.33% accuracy. A class activation map of the model was generated to provide a qualitative observation of the results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.113-117
• /
• 2020

Images were taken under various weather such as rain, haze, snow often show low visibility, which can dramatically decrease accuracy of some tasks in computer vision: object detection, segmentation. Besides, previous work to enhance image usually downsample the image to receive consistency features but have not yet good upsample algorithm to recover original size. So, in this research, we jointly implement removal streak in heavy rain image and super resolution using a deep network. We put forth a 2-stage network: a multi-model network followed by a refinement network. The first stage using rain formula in the single image and two operation layers (addition, multiplication) removes rain streak and noise to get clean image in low resolution. The second stage uses refinement network to recover damaged background information as well as upsample, and receive high resolution image. Our method improves visual quality image, gains accuracy in human action recognition task in datasets. Extensive experiments show that our network outperforms the state of the art (SoTA) methods.

• Tuberculosis and Respiratory Diseases
• /
• v.86 no.2
• /
• pp.94-101
• /
• 2023

A recent understanding of the dynamic continuous spectrum of Mycobacterium tuberculosis infection has led to the recognition of incipient tuberculosis, which refers to the latent infection state that has begun to progress to active tuberculosis. The importance of early detection of these individuals with a high-risk of progression to active tuberculosis is emphasized to efficiently implement targeted tuberculosis preventive therapy. However, the tuberculin skin test or interferon-γ release assay, which is currently used for the diagnosis of latent tuberculosis infection, does not aid in the prediction of the risk of progression to active tuberculosis. Thus, a novel test is urgently needed. Recently, simultaneous and systematic analysis of differentially expressed genes using a high-throughput platform has enabled the discovery of key genes that may serve potential biomarkers for the diagnosis or prognosis of diseases. This host transcriptional investigation has been extended to the field of tuberculosis, providing promising results. The present review focuses on recent progress and challenges in the field of blood transcriptional signatures to predict progression to active tuberculosis.

• Korea Trade Review
• /
• v.45 no.3
• /
• pp.147-166
• /
• 2020

As the volume of trade between Korea and Vietnam increases, the number and amount of commercial disputes between Korean and Vietnamese companies are increasing. In the case of Vietnam, due to differences in the arbitration system and norms due to the socialist state system, foreign companies lack confidence in the settlement of disputes through commercial arbitration in Vietnam. At this point, it is necessary to not only discuss commercial disputes and settlements, but also to closely review and understand Vietnam's commercial dispute settlement system. Therefore, this study examines the current status and characteristics of Vietnam's commercial disputes and analyzes the actual problems of Vietnam Commercial Arbitration System that arise through the arbitral award of the Vietnam International Arbitration Center (VIAC), Vietnam's representative arbitration agency, and precedents on the recognition and enforcement of foreign arbitration awards in Vietnamese courts. In the end, this study seeks to revitalize the Vietnam Commercial Arbitration so that each disputed party may quickly deal with the commercial disputes, and seeks a more smooth solution through commercial arbitration in future trade claims between Korean and Vietnamese companies.

• Journal of Contemporary Eastern Asia
• /
• v.22 no.2
• /
• pp.18-38
• /
• 2023

This paper examines the Chinese government's response to four epidemic crises, including COVID-19, and analyzes the similarities and differences in these responses. It argues that while the Chinese government learned from previous epidemics and improved its handling of subsequent outbreaks, a significant variation occurred during the COVID-19 pandemic, which had a detrimental impact globally. Existing scholarly research on China's epidemic responses has often been limited in scope, focusing on individual crises and neglecting the central-local government relationship in crisis decision-making. By adopting a comprehensive approach, this paper delves into the nuanced dynamics of China's responses to these epidemics. It highlights the variations in responses, attributing them to the Chinese government's fear of undermined legitimacy and its consideration of its international image. The government's recognition of the importance of public perception and trust, both domestically and globally, has shaped its crisis management strategies. Through a detailed analysis of these factors, this paper contributes to a deeper understanding of the variations observed in China's epidemic responses. It emphasizes the significance of the central-local government relationship and the government's international image in determining its actions during epidemics. Recognizing these factors can provide policymakers and researchers with insights to shape future epidemic response strategies and foster effective global health governance.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.385-392
• /
• 2023

The smart tourism service provides tourists with personal travel planner services and context-awareness-based tour guide services. In this paper, we propose the personal travel planner service that creates my travel itinerary using the smart tourism app and the travel planner system. The smart tourism app provides recommended travel products and POI tourist information used to create my travel itinerary. The smart tourism app also provides the smart tourism chatbot service that allows users to select POI tourist information easily and conveniently. The travel planner system consists of the smart tourism information system and the smart tourism chatbot system. The smart tourism information system provides users with travel planner services, recommended travel products, and POI tourism information through the smart tourism app. The smart tourism chatbot system consists of named entity recognition (NER), dialogue state tracking (DST), and Neo4J servers, and provides chatbot services as a smart tourism app. Users can create their own travel itinerary, modify the travel itinerary while traveling, and then register it as a recommended travel product to users, including acquaintances.