• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2024년도 제69차 동계학술대회논문집 32권1호
• /
• pp.45-46
• /
• 2024

본 논문에서는 Self-Attention 기반 딥러닝 기법인 Dense Prediction Transformer(DPT) 모델을 MVTec Anomaly Detection(MVTec AD) 데이터셋에 적용하여 실제 산업 제품 이미지 내 이상 부분을 분할하는 연구를 진행하였다. DPT 모델의 적용을 통해 기존 Convolutional Neural Network(CNN) 기반 이상 탐지기법의 한계점인 지역적 Feature 추출 및 고정된 수용영역으로 인한 문제를 개선하였으며, 실제 산업 제품 데이터에서의 이상 분할 시 기존 주력 기법인 U-Net의 구조를 적용한 최고 성능의 모델보다 1.14%만큼의 성능 향상을 보임에 따라 Self-Attention 기반 딥러닝 기법의 적용이 산업 제품 이상 분할에 효과적임을 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1024-1026
• /
• 2003

The purpose of establishing GPS networks of continuously operating reference stations (CORS) is aimed to assist land surveying or crustal deformation in the early stage. However, with a fast evolving and improving path the GPS technique has been extended to accurately measure atmospheric precip itable water vapor as a core objective of many projects developed in many countries and regions such as the SuomiNet (U.S., UNAVCO), COST716 (European, COST), GEONET (Japan, GSI), ...etc. In this paper, we present the current progress of the being-set-up GPS network in Taiwan whose atmospheric profile observations mainly count on the traditional radiosonde soundings as typically seen in any other part of the world. The GPS data collected from the Taiwan dense GPS network primarily supported by Central Weather Bureau are processed using the Bernese software version 4.2. Precipitable water vapor is then derived with the auxiliary surface meteorological measurements. Time series of precipitable water are examined and analyzed. A focus on the extreme weather cases is shown as an example.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.139-146
• /
• 2022

Wireless access technologies are emerging to enable high data rates for mobile users and novel applications that encompass both human and machine-type interactions. An essential approach to meet the rising demands on network capacity and offer high coverage for wireless users on upcoming fifth generation (5G) networks is heterogeneous networks (HetNets), which are generated by combining the installation of macro cells with a large number of densely distributed small cells Deployment in 5G architecture has several issues because to the rising complexity of network topology in 5G HetNets with many distinct base station types. Aside from the numerous benefits that dense small cell deployment delivers, it also introduces key mobility management issues such as frequent handover (HO), failures, delays and pingpong HO. This article investigates 5G HetNet mobility management in terms of radio resource control. This article also discusses the key challenges for 5G mobility management.

• 인터넷정보학회논문지
• /
• 제20권4호
• /
• pp.91-102
• /
• 2019

자율주행 시스템에서, 카메라에 포착된 영상을 통하여 보행자를 분류하는 기능은 보행자 안전을 위하여 매우 중요하다. 기존에는 HOG(Histogram of Oriented Gradients)나 SIFT(Scale-Invariant Feature Transform) 등으로 보행자의 특징을 추출한 후 SVM(Support Vector Machine)으로 분류하는 기술을 사용했었으나, 보행자 특징을 위와 같이 수동(handcrafted)으로 추출하는 것은 많은 한계점을 가지고 있다. 따라서 본 논문에서는 CNN(Convolutional Neural Network)의 깊은 특징(deep features)과 전이학습(transfer learning)을 사용하여 보행자를 안정적이고 효과적으로 분류하는 방법을 제시한다. 본 논문은 2가지 대표적인 전이학습 기법인 고정특징추출(fixed feature extractor) 기법과 미세조정(fine-tuning) 기법을 모두 사용하여 실험하였고, 특히 미세조정 기법에서는 3가지 다른 크기로 레이어를 전이구간과 비전이구간으로 구분한 후, 비전이구간에 속한 레이어들에 대해서만 가중치를 조정하는 설정(M-Fine: Modified Fine-tuning)을 새롭게 추가하였다. 5가지 CNN모델(VGGNet, DenseNet, Inception V3, Xception, MobileNet)과 INRIA Person데이터 세트로 실험한 결과, HOG나 SIFT 같은 수동적인 특징보다 CNN의 깊은 특징이 더 좋은 성능을 보여주었고, Xception의 정확도(임계치 = 0.5)가 99.61%로 가장 높았다. Xception과 유사한 성능을 내면서도 80% 적은 파라메터를 학습한 MobileNet이 효율성 측면에서는 가장 뛰어났다. 그리고 3가지 전이학습 기법중 미세조정 기법의 성능이 가장 우수하였고, M-Fine 기법의 성능은 미세조정 기법과 대등하거나 조금 낮았지만 고정특징추출 기법보다는 높았다.

• Nuclear Engineering and Technology
• /
• 제54권6호
• /
• pp.2297-2310
• /
• 2022

A condensation heat transfer model is essential to accurately predict the performance of the passive containment cooling system (PCCS) during an accident in an advanced light water reactor. However, most of existing models tend to predict condensation heat transfer very well for a specific range of thermal-hydraulic conditions. In this study, a new correlation for condensation heat transfer coefficient (HTC) is presented using machine learning technique. To secure sufficient training data, a large number of pseudo data were produced by using ten existing condensation models. Then, a neural network model was developed, consisting of a fully connected layer and a convolutional neural network (CNN) algorithm, DenseNet. Based on the hold-out cross-validation, the neural network was trained and validated against the pseudo data. Thereafter, it was evaluated using the experimental data, which were not used for training. The machine learning model predicted better results than the existing models. It was also confirmed through a parametric study that the machine learning model presents continuous and physical HTCs for various thermal-hydraulic conditions. By reflecting the effects of individual variables obtained from the parametric analysis, a new correlation was proposed. It yielded better results for almost all experimental conditions than the ten existing models.

• 대한방사선기술학회지:방사선기술과학
• /
• 제43권5호
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• Journal of Astronomy and Space Sciences
• /
• 제36권1호
• /
• pp.35-43
• /
• 2019

The Optical Wide-field patroL-Network (OWL-Net) is a global optical network for Space Situational Awareness in Korea. The primary operational goal of the OWL-Net is to track Low Earth Orbit (LEO) satellites operated by Korea and to monitor the Geostationary Earth Orbit (GEO) region near the Korean peninsula. To obtain dense measurements on LEO tracking, the chopper system was adopted in the OWL-Net's back-end system. Dozens of angle-only measurements can be obtained for a single shot with the observation mode for LEO tracking. In previous work, the reduction process of the LEO tracking data was presented, along with the mechanical specification of the back-end system of the OWL-Net. In this research, we describe an integrity assessment method of time-position matching and verification of results from real observations of LEO satellites. The change rate of the angle of each streak in the shot was checked to assess the results of the matching process. The time error due to the chopper rotation motion was corrected after re-matching of time and position. The corrected measurements were compared with the simulated observation data, which were taken from the Consolidated Prediction File from the International Laser Ranging Service. The comparison results are presented in the In-track and Cross-track frame.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.272-273
• /
• 2019

VVC(Versatile Video Coding)는 YUV 입력 영상에 대하여 Luma 성분과 Chroma 성분에 대하여 각각 다른 최적의 방법으로 블록분할 후 해당 블록에 대해서 화면 내 예측 또는 화면 간 예측을 수행하고, 예측영상과 원본영상의 차이를 변환, 양자화하여 압축한다. 이 과정에서 복원영상에는 블록화 노이즈, 링잉 노이즈, 블러링 노이즈 발생한다. 본 논문에서는 인코더에서 원본영상과 복원영상의 잔차신호에 대한 MAE(Mean Absolute Error)를 추가정보로 전송하여 이 추가정보와 복원영상을 이용하여 Deep Learning 기반의 신경망 네트워크로 영상의 품질을 높이는 방법을 제안한다. 복원영상의 노이즈를 감소시키기 위하여 영상을 $32{\times}32$블록의 임의로 분할하고, DenseNet기반의 UNet 구조로 네트워크를 구성하였다.

• 한국ITS학회 논문지
• /
• 제20권6호
• /
• pp.313-330
• /
• 2021

카메라와 라이다가 탑재된 자율주행 시스템에서 깊이완성기술을 통해 조밀한 깊이추정을 할 수 있다. 특히, 자기지도학습을 이용하면 깊이정답이 없는 주행데이터로도 깊이완성 네트워크의 학습이 가능하다. 실제 자율주행환경에서 이러한 깊이완성의 출력은 다른 알고리즘들의 입력으로 사용되므로 매우 빠른 지연속도를 요구한다. 그래서 본 논문에서는 종래의 연구들처럼 네트워크를 고도화하여 정확도를 높이기보단 추론속도를 극대화한 형태의 깊이완성 네트워크를 사용한다. GPU 연산에 최적화된 RegNet 인코더를 사용하고 네트워크의 병렬성을 고려한 U-Net 형태의 네트워크를 설계한다. 대신, 본 논문에서는 자기지도학습 과정에서 정확도를 높일 수 있는 몇 가지 기법들을 제시한다. 제시하는 기법들은 신뢰할 수 없는 라이다 입력에 대한 강인함을 높이고 사전에 추출한 시맨틱 정보를 바탕으로 에지와 하늘 영역에 대한 깊이 추정 품질을 향상시킨다. 실험을 통해 우리의 모델은 매우 경량임에도 (2.42ms at 1280x480) 노이즈에 강하며 최신 연구들과 대등한 정확도를 보임을 확인한다.