• 융합신호처리학회논문지
• /
• 제22권1호
• /
• pp.1-6
• /
• 2021

최근에 IT 기술의 발전과 비용을 절감하는 방식으로 무인감시설비가 도입되어 운영되고 있다. 무인감시설비는 효율적이고 경제적인 측면으로 장점이 있지만, 무인감시설비의 고장, 오작동이 발생하면서 감시 공백과 침입자로 인한 시설 파손 및 정보 유출 등 피해가 발생 되는 단점이 있다. 그리고 무인감시설비의 점검 차원에서 담당자의 상시 방문이 필요하고 이에 따른 관리 비용이 발생하고 있다. 본 논문에서는 무인감시설비의 상태를 실시간 점검하여 오작동과 같은 문제를 감시설비의 상태 확인 및 자동복구하고 담당자에게 실시간으로 상황을 문자메시지로 통보하는 시스템을 설계하였다. 설계할 시스템은 영상, 음향, 조명 등의 무인감시설비의 주요 장비의 작동 상태에 관한 정보를 수신하고 판단하는 통합형 네트워크 비디오 서버(NVR)와 무인감시설비의 상태를 감지하고 전원 복구하는 제어장치와 SMS 서버를 이용한 실시간 문자메시지로 구성되어 있다.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.416-421
• /
• 2022

본 연구에서는 영상감시 장치에 액정 기반 편광 제어 기술을 결합하여 피사체에서 반사된 빛의 부분 선형 편광을 제거할 수 있는 편광 영상감치 장치 시스템을 제안한다. 빛의 편광 방향을 전기 광학적으로 변조하는 TN(Twisted Nematic) 액정을 사용하면 카메라 렌즈 앞에서 편광 필터를 기계적으로 회전할 필요가 없다. 이러한 기술을 사용하여 얻은 여러 편광 이미지는 컴퓨터 소프트웨어에 의해 이미지화된다. 또한 액정 패널은 사각형 형태로 생산되어 왔으나 대부분의 카메라 렌즈는 일반적으로 원형이고 렌즈 주변에 조명이나 기타 구동 장치가 설치되어 있어 원형 액정 패널을 적용하여 공간을 최적화하였다. 이 기술의 개발을 통해 전기적으로 전환 가능하고 공간에 최적화된 액정 편광 패널이 개발되었다.

• 한국의학물리학회지:의학물리
• /
• 제32권4호
• /
• pp.92-98
• /
• 2021

Purpose: This study automatically discriminates homogeneous and structure edge regions on computed tomography (CT) images, and it evaluates the noise level and edge preservation ratio (EPR) according to the different types of iterative reconstruction (IR). Methods: The dataset consisted of CT scans of 10 patients reconstructed with filtered back projection (FBP), statistical IR (iDose⁴), and iterative model-based reconstruction (IMR). Using the 10th and 85th percentiles of the structure coherence feature, homogeneous and structure edge regions were localized. The noise level was estimated using the averages of the standard deviations for five regions of interests (ROIs), and the EPR was calculated as the ratio of standard deviations between homogeneous and structural edge regions on subtraction CT between the FBP and IR. Results: The noise levels were 20.86±1.77 Hounsfield unit (HU), 13.50±1.14 HU, and 7.70±0.46 HU for FBP, iDose⁴, and IMR, respectively, which indicates that iDose⁴ and IMR could achieve noise reductions of approximately 35.17% and 62.97%, respectively. The EPR had values of 1.14±0.48 and 1.22±0.51 for iDose⁴ and IMR, respectively. Conclusions: The iDose⁴ and IMR algorithms can effectively reduce noise levels while maintaining the anatomical structure. This study suggested automated evaluation measurements of noise levels and EPRs, which are important aspects in CT image quality with patients' cases of FBP, iDose⁴, and IMR. We expect that the inclusion of other important image quality indices with a greater number of patients' cases will enable the establishment of integrated platforms for monitoring both CT image quality and radiation dose.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.183-188
• /
• 2022

Recently, more and more researches aimed at the development of automated and autonomous ships are appearing in the scientific environment. One of the main reason is the need to solve the problems of safe navigation and reducing accidents due to human factor, as well as the ever-increasing problem associated with the lack of qualified maritime personnel. Development of technologies based on application of artificial intelligence also plays important role, after all for realization of autonomous navigation concept and enhancement of ship automatic maneuvering processes, advancement of maneuvering functions and elaboration of specific algorithms on prevention of close quarter situations and dangerous approach of ships will be required. The purpose of this work is the review of preconditions of occurrence of the autonomous ship navigation conception, overview of introduction stages and prospects for ship remote control based on unmanned technologies, analysis of technical and intellectual decisions of autonomous surface ships, main research tendencies. The research revealed that the technology of autonomous ship navigation requires further development and improvement, especially in terms of the data transmission protocols upgrading, sensors of navigation information and automatic control systems modernization, which allows to perform monitoring of equipment with the aim of improving the functions of control over the autonomous surface ship operation.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• 한국지반신소재학회논문집
• /
• 제22권3호
• /
• pp.27-35
• /
• 2023

굴착 공사 중 가시설의 안정성을 확보하는 것은 매우 중요하다. 설계 시 지반의 안정성을 수치해석을 통해 분석하고 있지만, 시공시에는 여건이 달라지기 때문에 계측으로 벽체 안정성을 분석하는 일은 필수불가결한 일이다. 공사현장에서의 계측비용은 매우 낮은 단가로 책정되어있으며 이를 통해 흙막이 벽체의 사고위험성은 예측되고 있다. 따라서 본 연구에서는 흙막이 벽체의 자동 혹은 무선 시스템 계측의 중요성을 가상의 사고사례 분석을 통해 공사기간 및 사고비용을 산정하고 이를 계측비용과 비교하여 무선 및 자동계측 업무의 중요성을 주장하였다. 굴착공사 중 중대형 파괴 시 사고처리 금액에 대하여 계측비용은 5% 미만으로 계측비용을 증가시켜 사고를 미연에 방지하는 것이 경제적일 수 있다.

• Journal of the Korean Wood Science and Technology
• /
• 제51권4호
• /
• pp.295-308
• /
• 2023

This study applied a real-time IoT (Internet of Things) environmental monitoring system to wooden cultural heritages (WCHs) located in suburbs and forests in Korea. It automated the graphs of seasonal Temperature (T) and relative humidity (RH) changes inside the heritage structures and seasonal Performance Index (PI) values. While utilizing line graphs of the existing T and RH change trends and a bar graph expressing the PI values, this study examined the current status of the conservation environment inside the WCHs throughout the year and its diagnosis. Consequently, at higher latitudes, the organic cultural heritage repeatedly experienced large T fluctuations, and the risk of physical and chemical degradation of the materials was greater. However, the RH showed significant seasonal differences, even within the same latitude, indicating that the impact of latitude was not significant. Therefore, the staff in charge must manage RH by considering the surrounding environmental conditions and adjusting the internal environment of the structures. The PI values for the year-round T and RH inside the heritages were confirmed to only be a maximum of approximately 60% of the environmental suitability for conservation throughout the year, depending on the season. The relationship between the germination and growth potential period of xerophilic fungi and the monthly internal temperature and humidity in five heritages located at different latitudes was analyzed. As a result, we could thus determine that four particular months of the year (June-September) represent the periods with the highest risk of damage from xerophilic fungi in the country, regardless of latitude.

• 한국지형학회지
• /
• 제28권1호
• /
• pp.51-66
• /
• 2021

This study shows that coastal sand dunes are negatively affected by coastal forests. In South Korea, planting pine trees on the dunes has been carried out to stabilize the dune landscapes and protect residential areas from coastal disasters since the 20th century. However, this strategy could reduce the resilience of dunes. In this study, we selected three monitoring sites with automated weather stations to compare the geomorphological and environmental characteristics between tree-covered and grass-covered dunes at Sohwang-ri, Boryeong-si, Chungnam Province for three years. In addition, we monitored the rates of erosion and deposition using eight pins along the dune crests. We found that the forest affected both wind velocity and direction, resulting in decreased blown sand supply to the dunes in front of the forest. The velocity of the strong winds faster than 5 m/s diminished to 10%-30% of the control sites, and the direction of northwesterly wind were skewed to the north by about 6°. Sand deposition occurred at about 15-20 m away from the pine forest and the amount was only 1/10 of the deposition within the grass-covered dunes. This study suggests that planting trees in coastal dunes is an undesirable strategy with negative impacts on the landscape management.

• 대한의생명과학회지
• /
• 제29권4호
• /
• pp.363-370
• /
• 2023

Human respiratory viral infections such as COVID-19 are highly contagious, so continuous management of airborne viruses is essential. In particular, indoor air monitoring is necessary because the risk of infection increases in poorly ventilated indoors. However, the current method of detecting airborne viruses requires a lot of time from sample collection to confirmation of results. In this study, we proposed a system that can monitor airborne viruses in real time to solve the deficiency of the present method. Air samples were collected in liquid form through a bio sampler, in which case the virus is present in low concentrations. To detect viruses from low-concentration samples, viral RNA was concentrated and extracted using silica-magnetic beads. RNA binds to silica under certain conditions, and by repeating this binding reaction, bulk samples collected from the air can be concentrated. After concentration and extraction, viral RNA is specifically detected through real-time qPCR (quantitative polymerase chain reaction). In addition, based on liquid handling technology, we have developed an automatic machine that automatically performs the entire testing process and can be easily used even by non-experts. To evaluate the system, we performed air sample collection and automated testing using bacteriophage MS2 as a model virus. As a result, the air-collected samples concentrated by 45 times then initial volume, and the detection sensitivity of PCR also confirmed a corresponding improvement.

• 한국전자통신학회논문지
• /
• 제19권4호
• /
• pp.763-770
• /
• 2024

현재 해수를 이용하는 육상 양식장에서는 실시간 수질 모니터링 및 시설 자동화 시스템, 용존산소 자동 공급장치 등 다양한 장비를 도입하여 사용하고 있다. 또한 양식장의 다양한 장비에서 수집되는 데이터는 수질 환경, 시설 운영, 작업장 영상정보 등 정형, 비정형 형태의 빅데이터를 생산한다. 양식장 운영 환경에서 생산되는 빅데이터는 운영 및 생산 효율 개선을 목표로 다양한 방법을 개발하고 적용을 시도하고 있다. 본 연구에서는 육상 양식장에서 생산되는 빅데이터를 효과적으로 분석하고 시각화하기 위한 시스템을 개발하는 것을 목표로, 양식장 빅데이터 분석 시스템에서 활용이 가능한 데이터 시각화 프로세스를 제시하고 빅데이터 시각화 도구를 개발하고 결과를 비교한다. 그리고 시계열 특성을 가지는 빅데이터의 비교 및 탐색이 직관적인 시각화 모델을 제시한다.