• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• 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)
• /
• v.14 no.11
• /
• 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.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• 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
• /
• v.22 no.4
• /
• 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.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• Nuclear Engineering and Technology
• /
• v.54 no.6
• /
• 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.

• Journal of radiological science and technology
• /
• v.43 no.5
• /
• 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
• /
• v.36 no.1
• /
• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.