• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1149-1161
• /
• 2021

With a trend of the utilization of computer vision for satellite images, cloud detection using deep learning also attracts attention recently. In this study, we conducted a U-Net cloud detection modeling using SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset with the image data augmentation and carried out 10-fold cross-validation for an objective assessment of the model. Asthe result of the blind test for 1800 datasets with 512 by 512 pixels, relatively high performance with the accuracy of 0.821, the precision of 0.847, the recall of 0.821, the F1-score of 0.831, and the IoU (Intersection over Union) of 0.723. Although 14.5% of actual cloud shadows were misclassified as land, and 19.7% of actual clouds were misidentified as land, this can be overcome by increasing the quality and quantity of label datasets. Moreover, a state-of-the-art DeepLab V3+ model and the NAS (Neural Architecture Search) optimization technique can help the cloud detection for CAS500 (Compact Advanced Satellite 500) in South Korea.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.71-80
• /
• 2024

In this study, a proposed ensemble learning technique aims to enhance the semantic segmentation performance of images captured by Unmanned Aerial Vehicles (UAVs). With the increasing use of UAVs in fields such as urban planning, there has been active development of techniques utilizing deep learning segmentation methods for land cover segmentation. The study suggests a method that utilizes prominent segmentation models, namely U-Net, DeepLabV3, and Fully Convolutional Network (FCN), to improve segmentation prediction performance. The proposed approach integrates training loss, validation accuracy, and class score of the three segmentation models to enhance overall prediction performance. The method was applied and evaluated on a land cover segmentation problem involving seven classes: buildings,roads, parking lots, fields, trees, empty spaces, and areas with unspecified labels, using images captured by UAVs. The performance of the ensemble model was evaluated by mean Intersection over Union (mIoU), and the results of comparing the proposed ensemble model with the three existing segmentation methods showed that mIoU performance was improved. Consequently, the study confirms that the proposed technique can enhance the performance of semantic segmentation models.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.5
• /
• pp.1157-1162
• /
• 2013

We proposed AlGaN/GaN high-electron-mobility transistors (HEMTs) using thermal oxidation for NiOx passivation. Auger electron spectroscopy, secondary ion mass spectroscopy, and pulsed I-V were used to study oxidation features. The oxidation process diffused Ni and O into the AlGaN barrier and formed NiOx on the surface. The breakdown voltage of the proposed device was 1520 V while that of the conventional device was 300 V. The gate leakage current of the proposed device was 3.5 ${\mu}A/mm$ and that of the conventional device was 1116.7 ${\mu}A/mm$. The conventional device exhibited similar current in the gate-and-drain-pulsed I-V and its drain-pulsed counterpart. The gate-and-drain-pulsed current of the proposed device was about 56 % of the drain-pulsed current. This indicated that the oxidation process may form deep states having a low emission current, which then suppresses the leakage current. Our results suggest that the proposed process is suitable for achieving high breakdown voltages in the GaN-based devices.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.151-158
• /
• 2022

The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert's processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.438-440
• /
• 2022

산업 현장에서 인력으로 작업할 수 있는 물리적 한계를 극복하기 위해 특수 목적 차량 작업 시 차량의 넘어짐 방지와 차체 보호를 위해 아웃트리거를 착지시키는데 도로 상태에 따라 사용자가 직접 최적화를 수행하는데 어려움이 존재한다. 본 논문에서는 도로 표면 상태를 신속하게 판단하여 아웃트리거 수직 및 수평 전개 착지 시 시간 소모, 안전사고 발생을 낮추기 위해 시멘틱 분할을 이용한 도로 표면 상태를 분석하는 연구를 수행하였다. 13가지로 구분된 도로 표면 상황에 대하여 DeepLabV3+를 통해 실험한 결과 픽셀 성능0.7819, mIoU 0.7085 결과를 도출하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.222-230
• /
• 2016

HEMIRE is a 6,000-meter-class remotely operated vehicle (ROV) that has been developed for observation and sampling of objects of interest on the deep seabed. We first carried out deep-seabed exploration around the slopes of the Hupo Bank and the Ulleung Basin in the East Sea in June 2015. Over two weeks, a total of 10 dives were made from a support ship, the R/V Onnuri, at eight stations with water depth ranging between 194 and 2,080 m. The dive times ranged from 1 to 6 hours, depending on the operating conditions. We obtained the following results: 1) video images of the deep seafloor; 2) red snow crab density data (a major fishery resource) and inventories of deep-sea fauna, including an unrecorded organism; 3) specific topographies such as canyons slopes; 4) an undisturbed sediment core obtained using a push corer; and 5) observations of the seabed surface covered with discarded anthropogenic waste material.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1266-1271
• /
• 2022

Cats have strong wildness so they have a characteristic of hiding diseases well. The disease may have already worsened when the guardian finds out that the cat has a disease. It will be of great help in treating the cat's disease if the owner can recognize the cat's polydipsia, polyuria, and frequent urination more quickly. In this paper, 1) Efficient version of DeepLabCut for pose estimation, 2) YOLO v4 for object detection, 3) LSTM is used for behavior prediction, and 4) BoT-SORT is used for object tracking running on an artificial intelligence device. Using artificial intelligence technology, it predicts the cat's next, polyuria and frequency of urination through the analysis of the cat's behavior pattern from the home CCTV video and the weight sensor of the water bowl. And, through analysis of cat behavior patterns, we propose an application that reports disease prediction and abnormal behavior to the guardian and delivers it to the guardian's mobile and the server system.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.289-303
• /
• 2022

In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.