• 대한원격탐사학회지
• /
• 제38권4호
• /
• pp.343-353
• /
• 2022

An attempt to derive the surface temperature from the Korea Multi-purpose Satellite (KOMPSAT)-3A mid-wave infrared (MWIR) data acquired over the southern California on Nov. 14, 2015 has been made using the MODerate resolution atmospheric TRANsmission (MODTRAN) radiative transfer model. Since after the successful launch on March 25, 2015, the KOMPSAT-3A spacecraft and its two payload instruments - the high-resolution multispectral optical sensor and the scanner infrared imaging system (SIIS) - continue to operate properly. SIIS uses the MWIR spectral band of 3.3-5.2 ㎛ for data acquisition. As input data for the realistic simulation of the KOMPSAT-3A SIIS imaging conditions in the MODTRAN model, we used the National Centers for Environmental Prediction (NCEP) atmospheric profiles, the KOMPSAT-3Asensor response function, the solar and line-of-sight geometry, and the University of Wisconsin emissivity database. The land cover type of the study area includes water,sand, and agricultural (vegetated) land located in the southern California. Results of surface temperature showed the reasonable geographical pattern over water, sand, and agricultural land. It is however worthwhile to note that the surface temperature pattern does not resemble the top-of-atmosphere (TOA) radiance counterpart. This is because MWIR TOA radiances consist of both shortwave (0.2-5 ㎛) and longwave (5-50 ㎛) components and the surface temperature depends solely upon the surface emitted radiance of longwave components. We found in our case that the shortwave surface reflection primarily causes the difference of geographical pattern between surface temperature and TOA radiance. Validation of the surface temperature for this study is practically difficult to perform due to the lack of ground truth data. We therefore made simple comparisons with two datasets over Salton Sea: National Aeronautics and Space Administration (NASA) Jet Propulsion Laboratory (JPL) field data and Salton Sea data. The current estimate differs with these datasets by 2.2 K and 1.4 K, respectively, though it seems not possible to quantify factors causing such differences.

• 한국전자통신학회논문지
• /
• 제18권1호
• /
• pp.29-38
• /
• 2023

인간의 생체 신호 데이터가 인간의 상태를 가장 잘 설명할 수 있다 할지라도 실제 운전 중에 운전자의 생체 데이터를 얻어 운전자의 상태를 판단하는 일은 쉽지 않다. 본 논문에서는 이러한 한계를 극복하기 위한 방법 중 하나로 운전자의 주행 정보를 이용한 운전자 스트레스 모니터링 시스템을 제안한다. 운전자의 주행 정보는 OBD-II 스캐너를 통해 취득하고, 실제 운전자의 운전 스트레스 여부는 E4 밴드를 통해 취득한 EDA 데이터를 이용하여 판단한다. 스트레스 감지 모델은 MLP 신경망 모델을 사용하였으며 약 한 달 간의 운행 데이터를 이용하여 학습시켰다. 제안한 시스템을 평가하기 위하여 약 1시간의 운행 데이터를 사용하였고 약 92%의 정확도를 얻을 수 있었다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Imaging Science in Dentistry
• /
• 제53권3호
• /
• pp.199-207
• /
• 2023

Purpose: The objective of this study was to evaluate the accuracy and effectiveness of an artificial intelligence (AI) program in identifying dental conditions using panoramic radiographs(PRs), as well as to assess the appropriateness of its treatment recommendations. Materials and Methods: PRs from 100 patients(representing 4497 teeth) with known clinical examination findings were randomly selected from a university database. Three dentomaxillofacial radiologists and the Diagnocat AI software evaluated these PRs. The evaluations were focused on various dental conditions and treatments, including canal filling, caries, cast post and core, dental calculus, fillings, furcation lesions, implants, lack of interproximal tooth contact, open margins, overhangs, periapical lesions, periodontal bone loss, short fillings, voids in root fillings, overfillings, pontics, root fragments, impacted teeth, artificial crowns, missing teeth, and healthy teeth. Results: The AI demonstrated almost perfect agreement (exceeding 0.81) in most of the assessments when compared to the ground truth. The sensitivity was very high (above 0.8) for the evaluation of healthy teeth, artificial crowns, dental calculus, missing teeth, fillings, lack of interproximal contact, periodontal bone loss, and implants. However, the sensitivity was low for the assessment of caries, periapical lesions, pontic voids in the root canal, and overhangs. Conclusion: Despite the limitations of this study, the synthesized data suggest that AI-based decision support systems can serve as a valuable tool in detecting dental conditions, when used with PR for clinical dental applications.

• 대한원격탐사학회지
• /
• 제39권4호
• /
• pp.425-440
• /
• 2023

Monitoring water surface has become one of the most prominent areas of research in addressing environmental challenges.Accurate and automated detection of watersurface in remote sensing imagesis crucial for disaster prevention, urban planning, and water resource management, particularly for a country where water plays a vital role in human life. However, achieving precise detection poses challenges. Previous studies have explored different approaches,such as analyzing water indexes, like normalized difference water index (NDWI) derived from satellite imagery's visible or infrared bands and using k-means clustering analysis to identify land cover patterns and segment regions based on similar attributes. Nonetheless, challenges persist, notably distinguishing between waterspectralsignatures and cloud shadow or terrain shadow. In thisstudy, our objective is to enhance the precision of water surface detection by constructing a comprehensive water database (DB) using existing digital and land cover maps. This database serves as an initial assumption for automated water index analysis. We utilized 1:5,000 and 1:25,000 digital maps of Korea to extract water surface, specifically rivers, lakes, and reservoirs. Additionally, the 1:50,000 and 1:5,000 land cover maps of Korea aided in the extraction process. Our research demonstrates the effectiveness of utilizing a water DB product as our first approach for efficient water surface extraction from satellite images, complemented by our second and third approachesinvolving NDWI analysis and k-means analysis. The image segmentation and binary mask methods were employed for image analysis during the water extraction process. To evaluate the accuracy of our approach, we conducted two assessments using reference and ground truth data that we made during this research. Visual interpretation involved comparing our results with the global surface water (GSW) mask 60 m resolution, revealing significant improvements in quality and resolution. Additionally, accuracy assessment measures, including an overall accuracy of 90% and kappa values exceeding 0.8, further support the efficacy of our methodology. In conclusion, thisstudy'sresults demonstrate enhanced extraction quality and resolution. Through comprehensive assessment, our approach proves effective in achieving high accuracy in delineating watersurfaces from satellite images.

• 인터넷정보학회논문지
• /
• 제24권4호
• /
• pp.85-92
• /
• 2023

X-ray, Computed Tomography (CT), Magnetic Resonance Imaging (MRI)과 같은 의료데이터에서 딥러닝을 활용해 질병 유무 판별 태스크와 같은 문제를 해결하려는 시도가 활발하다. 대부분의 데이터 기반 딥러닝 문제들은 높은 정확도 달성과 정답과 비교하는 성능평가의 활용을 위해 지도학습기법을 사용해야 한다. 지도학습에는 다량의 이미지와 레이블 세트가 필요하지만, 학습에 충분한 양의 의료 이미지 데이터를 얻기는 어렵다. 다양한 데이터 증강 기법을 통해 적은 양의 의료이미지와 레이블 세트로 지도학습 기반 모델의 과소적합 문제를 극복할 수 있다. 본 연구는 딥러닝 기반 갈비뼈 골절 세그멘테이션 모델의 성능 향상과 효과적인 좌우 반전, 회전, 스케일링 등의 데이터 증강 기법을 탐색한다. 좌우 반전과 30° 회전, 60° 회전으로 증강한 데이터셋은 모델 성능 향상에 기여하지만, 90° 회전 및 ⨯0.5 스케일링은 모델 성능을 저하한다. 이는 데이터셋 및 태스크에 따라 적절한 데이터 증강 기법의 사용이 필요함을 나타낸다.

• Clinics in Shoulder and Elbow
• /
• 제25권4호
• /
• pp.304-310
• /
• 2022

Background: The Boileau classification distinguishes three surgical neck fracture patterns: types A, B, and C. However, the reproducibility of this classification on plain radiographs is unclear. Therefore, we questioned what the interobserver agreement and accuracy of displaced surgical neck fracture patterns is categorized according to the modified Boileau classification. Does the reliability to recognize these fracture patterns differ between orthopedic residents and attending surgeons? Methods: This interobserver study consisted of a randomly retrieved series of 30 plain radiographs representing clinical practice in a level 1 and a level 2 trauma center. Radiographs were included from patients (≥18 years) who sustained an isolated displaced surgical neck fracture if they were taken ≤1 week after initial injury. A ground truth was established by consensus among three senior orthopedic surgeons. All images were assessed by 17 orthopedic residents and 17 attending orthopedic trauma surgeons. Results: Agreement for the modified Boileau classification was fair (κ=0.37; 95% confidence interval [CI], 0.36-0.38) with an accuracy of 62% (95% CI, 57%-66%). Comparison of interobserver variability between residents and attending surgeons revealed a significant but clinically irrelevant difference in favor of attending surgeons (0.34 vs. 0.39, respectively, Δκ=0.05, 95% CI, 0.02-0.07). Conclusions: The modified Boileau classification yields a low interobserver agreement with an unsatisfactory accuracy in a panel of orthopedic residents and attending surgeons. This supports the hypothesis that surgical neck fractures are challenging to categorize and that this classification should not be used to determine prognosis if only plain radiographs are available.

• Applied Microscopy
• /
• 제51권
• /
• pp.4.1-4.12
• /
• 2021

Fluorescence in situ hybridization (FISH) is a technique to visualize specific DNA/RNA sequences within the cell nuclei and provide the presence, location and structural integrity of genes on chromosomes. A confocal Whole Slide Imaging (WSI) scanner technology has superior depth resolution compared to wide-field fluorescence imaging. Confocal WSI has the ability to perform serial optical sections with specimen imaging, which is critical for 3D tissue reconstruction for volumetric spatial analysis. The standard clinical manual scoring for FISH is labor-intensive, time-consuming and subjective. Application of multi-gene FISH analysis alongside 3D imaging, significantly increase the level of complexity required for an accurate 3D analysis. Therefore, the purpose of this study is to establish automated 3D FISH scoring for z-stack images from confocal WSI scanner. The algorithm and the application we developed, SHIMARIS PAFQ, successfully employs 3D calculations for clear individual cell nuclei segmentation, gene signals detection and distribution of break-apart probes signal patterns, including standard break-apart, and variant patterns due to truncation, and deletion, etc. The analysis was accurate and precise when compared with ground truth clinical manual counting and scoring reported in ten lymphoma and solid tumors cases. The algorithm and the application we developed, SHIMARIS PAFQ, is objective and more efficient than the conventional procedure. It enables the automated counting of more nuclei, precisely detecting additional abnormal signal variations in nuclei patterns and analyzes gigabyte multi-layer stacking imaging data of tissue samples from patients. Currently, we are developing a deep learning algorithm for automated tumor area detection to be integrated with SHIMARIS PAFQ.

• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3268-3276
• /
• 2023

The practice of identifying the potential zones for mineral exploration in a speedy and low-cost method includes the use of satellite imagery analysis as a part of remote sensing techniques. It is challenging to explore the iron mineralization of a region through conventional methods which are a time-consuming process. The current study utilizes the Hyperion satellite imagery for mapping the iron mineralization and associated geological features in the Irikkur region, Kannur, Kerala. Along with the remote sensing results, the field study and laboratory-based analysis were conducted to retrieve the ground truth point and geochemical proportion to verify the iron ore mineralization. The MC simulation showed for shielding properties indicate an increase in the linear attenuation coefficient with raising the Fe₂O₃+SiO₂ concentrations in the investigated rocks where it is varied at 0.662 MeV in the range 0.190 cm^-1 - 0.222 cm^-1 with rising the Fe₂O₃+SiO₂ content from 57.86 wt% to 71.15 wt%. The analysis also revealed that when the γ-ray energy increased from 0.221 MeV to 2.506 MeV, sample 1 had the largest linear attenuation coefficient, ranging from 9.33 cm1 to 0.12 cm^-1. Charnockite rocks were found to have exceptional shielding qualities, making them an excellent natural choice for radiation shielding applications.

• 한국컴퓨터그래픽스학회논문지
• /
• 제29권1호
• /
• pp.1-11
• /
• 2023

딥러닝 기반의 이미지 세그멘테이션은 차선 인식을 위해 널리 사용되는 접근 방식 중 하나로, 차선의 키포인트를 추출하기 위한 후처리 과정이 필요하다. 일반적으로 키포인트는 사용자가 지정한 임계값을 기준으로 추출한다. 하지만 최적의 임계값을 찾는 과정은 큰 노력을 요구하며, 데이터 세트(또는 이미지)마다 최적의 값이 다를 수 있다. 본 연구는 사용자의 직접 임계값 지정 대신, 대상의 이미지에 맞추어 적절한 임계값을 자동으로 설정하는 키포인트 추출 알고리즘을 제안한다. 본 논문의 키포인트 추출 알고리즘은 차선 영역과 배경의 명확한 구분을 위해 줄 단위 정규화를 사용한다. 그리고 커널 밀도 추정을 사용하여, 각 줄에서 각 차선의 키포인트를 추출한다. 제안하는 알고리즘은 TuSimple과 CULane 데이터 세트에 적용되었으며, 고정된 임계값 사용 대비 정확도 및 거리오차 측면에서 1.80%p와 17.27% 향상된 결과를 얻는 것을 확인하였다.