• Nuclear Engineering and Technology
• /
• 제51권4호
• /
• pp.1169-1175
• /
• 2019

The minimum detectable activity (MDA) value was derived according to the flow rate of the sample and degree of amplification of the device by sending the sample directly from the collection site to the detection part through a pump. This method can lead to reduction in time and cost compared to the existing measurement method that uses a pre-treatment process. In this study, experiments were conducted on $^3H$ and $^{90}Sr$, which are the major pure beta-emitting radionuclides, by setting the sample flow rate and the amplification gain as factors. The MDA values were derived according to the flow rates, considering that the flow rate can affect the MDA values. There were no change in the MDA under different flow rates of 0, 600, 800, and 1000 mL/min. Therefore, it was confirmed that the flow rate may not be considered when collecting samples for monitoring in actual field. As the degree of amplification of the amplifier increased, the time required to reach the target MDA decreased. When the amplification was quadrupled, the detection efficiency increased by approximately 23.4 times, and the time to reach the MDA decreased to approximately 1/550 times. This method offers the advantage of real-time on-site monitoring.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 C
• /
• pp.1891-1893
• /
• 2000

In this paper, we studied the diagnostic technique to analyze the deterioration of cast resin transformer using partial discharge detection for on-site application.

• 국제초고층학회논문집
• /
• 제9권4호
• /
• pp.335-342
• /
• 2020

This article comes up with a new method which is based on the visual characteristic of the objects and machine learning technology to achieve semi-automated recognition of the personnel, machine & materials of the construction sites. Balancing the real-time performance and accuracy, using Faster RCNN (Faster Region-based Convolutional Neural Networks) with transfer learning method appears to be a rational choice. After fine-tuning an ImageNet pre-trained Faster RCNN and testing with it, the result shows that the precision ratio (mAP) has so far reached 67.62%, while the recall ratio (AR) has reached 56.23%. In other word, this recognizing method has achieved rational performance. Further inference with the video of the construction of Huoshenshan Hospital also indicates preliminary success.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.455-462
• /
• 2020

Noise which is unwanted sound is a serious pollutant that can affect human health, as well as the working and living environment if exposed to humans. However, current noise management on the construction project is generally conducted after the noise exceeds the regulation standard, which increases the conflicts with inhabitants near the construction site and threats to the safety and productivity of construction workers. To overcome the limitations of the current noise management methods, the activities of construction equipment which is the main source of construction noise need to be managed throughout the construction period in real-time. Therefore, this paper proposed a framework for automatically detecting noise sources in construction sites in real-time based on convolutional neural networks (CNNs) according to the following four steps: (i) Step 1: Definition of the noise sources; (ii) Step 2: Data preparation; (iii) Step 3: Noise source classification using the audio CNN; and (iv) Step 4: Noise source detection using the visual CNN. The short-time Fourier transform (STFT) and temporal image processing are used to contain temporal features of the audio and visual data. In addition, the AlexNet and You Only Look Once v3 (YOLOv3) algorithms have been adopted to classify and detect the noise sources in real-time. As a result, the proposed framework is expected to immediately find construction activities as current noise sources on the video of the construction site. The proposed framework could be helpful for environmental construction managers to efficiently identify and control the noise by automatically detecting the noise sources among many activities carried out by various types of construction equipment. Thereby, not only conflicts between inhabitants and construction companies caused by construction noise can be prevented, but also the noise-related health risks and productivity degradation for construction workers and inhabitants near the construction site can be minimized.

• 대한원격탐사학회지
• /
• 제32권5호
• /
• pp.403-412
• /
• 2016

Compact Reconnaissance Imaging Spectrometer for Mars(CRISM)은 489개의 밴드를 가지는 화성정찰궤도선의 초분광 카메라로써 이를 이용한 화성 지표의 광물 분포에 대한 많은 연구가 진행되어 왔다. 본 연구에서는 USGS의 스펙트럼 라이브러리를 기반으로 화성 Gusev Crater의 Spirit(Mars Exploration Rover A) 로버 착륙지에 대한 CRISM 영상에 Matched Filter와 Adaptive Cosine Estimator(ACE) 표적 탐지 알고리즘을 적용하여 광물 분포를 확인하고자 하였다. 연구 결과 감람석, 휘석, 자철석 등의 광물들이 Gusev 크레이터의 Columbia Hills에서 탐지되어 Spirit 로버의 지상 탐사 결과와 일치하고 있음을 확인하였다. 본 연구는 그간 CRISM의 광물 분포 연구가 일부 몇 개 밴드의 반사도만을 통해 계산된 광물 지수에 의존하던 것에서 관측 파장 대역 전체를 활용하는 초분광 표적 탐지 알고리즘을 이용한 새로운 적용방법을 제시한 것에 의의가 있다고 할 수 있다.

• 비파괴검사학회지
• /
• 제24권1호
• /
• pp.45-51
• /
• 2004

발전소 보일러튜브는 장시간 동안 고온고압하의 기혹한 조건으로 운전됨에 따라 크리프, 열피로와 같은 각종 열화에 의해 누설손상이 발생하고 있다. 이러한 누설손상을 실시간 감시하고 진단하기 위하여 음향방출기술을 이용한 현장적용 연구를 수행하였다. 또한 고장예측 진단기술, 튜브의 수명관리 및 설비 감시에 활용할 수 있도록 음향방출 진단시스템을 개발하여 현장에 설치하고, 보일러 운전상태에 따른 신호측정 및 평가, 누설위치 판별 등에 대해 고찰하였다. 누설감지는 저주파 및 고주파대역의 누설로 구분하여 음향방출신호를 각각 측정 및 평가하였다. 현장적용 연구결과로부터 실시간으로 보일러튜브 상태감시와 누설위치 추적이 가능하였으며, 향후 본 기술을 이용하면 발전설비 안전운전과 발전소 정지에 따른 경제적 손실 예방에 크게 기여할 것으로 기대된다.

• Structural Engineering and Mechanics
• /
• 제54권2호
• /
• pp.221-237
• /
• 2015

An integrated method is proposed for structural nonlinear damage detection based on time series analysis and the higher statistical moments of structural responses in this study. It combines the time series analysis, the higher statistical moments of AR model residual errors and the fuzzy c-means (FCM) clustering techniques. A few comprehensive damage indexes are developed in the arithmetic and geometric mean of the higher statistical moments, and are classified by using the FCM clustering method to achieve nonlinear damage detection. A series of the measured response data, downloaded from the web site of the Los Alamos National Laboratory (LANL) USA, from a three-storey building structure considering the environmental variety as well as different nonlinear damage cases, are analyzed and used to assess the performance of the new nonlinear damage detection method. The effectiveness and robustness of the new proposed method are finally analyzed and concluded.

• Journal of Microbiology and Biotechnology
• /
• 제26권8호
• /
• pp.1457-1463
• /
• 2016

Vibrio anguillarum, a devastating pathogen causing vibriosis among marine fish, is prevailing in worldwide fishery industries and accounts for grievous economic losses. Therefore, a rapid on-site detection and diagnostic technique for this pathogen is in urgent need. In this study, two mouse monoclonal antibodies (MAbs) against V. anguillarum, 6B3-C5 and 8G3-B5, were generated by using hybridoma technology and their isotypes were characterized. MAb 6B3-C5 was chosen as the detector antibody and conjugated with quantum dots. Based on MAb 6B3-C5 labeled with quantum dots, a modified dot blot assay was developed for the on-site determination of V. anguillarum. It was found that the method had no cross-reactivity with other than V. anguillarum bacteria. The detection limit (LOD) for V. anguillarum was 1 × 10³ CFU/ml in cultured bacterial suspension samples, which was a 100-fold higher sensitivity than the reported colloidal gold immunochromatographic test strip. When V. anguillarum was mixed with turbot tissue homogenates, the LOD was 1 × 10³ CFU/ml, suggesting that tissue homogenates did not influence the detection capabilities. Preenrichment with the tissue homogenates for 12 h could raise the LOD up to 1 × 10² CFU/ml, confirming the reliability of the method.

• Journal of Veterinary Science
• /
• 제21권5호
• /
• pp.79.1-79.12
• /
• 2020

Background: Recently, the pork industry of Thailand faced an epidemic of highly virulent strains of porcine reproductive and respiratory syndrome virus (PRRSV), which spread throughout Southeast Asia, including the Lao People's Democratic Republic and Cambodia. Hence, the rapid and on-site screening of infected pigs on a farm is essential. Objectives: To develop the new aptamer as a biosensor for detection PRRSV which are rapid and on-site screening of infected pig. Methods: New aptamers against PRSSV were identified using the combined techniques of capillary electrophoresis, colorimetric assay by gold nanoparticles, and quartz crystal microbalance (QCM). Results: Thirty-six candidate aptamers of the PRRSV were identified from the systematic evolution of ligands by exponential enrichment (SELEX) by capillary electrophoresis. Only 8 out of 36 aptamers could bind to the PRSSV, as shown in a colorimetric assay. Of the 8 aptamers tested, only the 1F aptamer could bind specifically to the PRSSV when presented with the classical swine fever virus and a pseudo rabies virus. The QCM was used to confirm the specificity and sensitivity of the 1F aptamer with a detection limit of 1.87 × 10¹⁰ particles. Conclusions: SELEX screening of the aptamer equipped with capillary electrophoresis potentially revealed promising candidates for detecting the PRRSV. The 1F aptamer exhibited the highest specificity and selectivity against the PRRSV. These findings suggest that 1F is a promising aptamer for further developing a novel PRRSV rapid detection kit.