• Smart Structures and Systems
• /
• 제6권3호
• /
• pp.263-275
• /
• 2010

In the last decade, wireless sensor networks have emerged as a promising technology that could accelerate progress in the field of structural monitoring. The main advantages of wireless sensor networks compared to conventional monitoring technologies are fast deployment, small interference with the surroundings, self-organization, flexibility and scalability. These features could enable mass application of monitoring systems, even on smaller structures. However, since wireless sensor network nodes are battery powered and data communication is the most energy consuming task, transferring all the acquired raw data through the network would dramatically limit system lifetime. Hence, data reduction has to be achieved at the node level in order to meet the system lifetime requirements of real life applications. The objective of this paper is to discuss some general aspects of data processing and management in monitoring systems based on wireless sensor networks, to present a prototype monitoring system for civil engineering structures, and to illustrate long-term field test results.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• 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.

• Nuclear Engineering and Technology
• /
• 제47권5호
• /
• pp.624-632
• /
• 2015

A self-diagnostic monitoring system is a system that has the ability to measure various physical quantities such as temperature, pressure, or acceleration from sensors scattered over a mechanical system such as a power plant, in order to monitor its various states, and to make a decision about its health status. We have developed a self-diagnostic monitoring system for an air-operated valve system to be used in a nuclear power plant. In this study, we have tried to improve the self-diagnostic monitoring system to increase its reliability. We have implemented three different machine learning algorithms, i.e., logistic regression, an artificial neural network, and a support vector machine. After each algorithm performs the decision process independently, the decision-making module collects these individual decisions and makes a final decision using a majority vote scheme. With this, we performed some simulations and presented some of its results. The contribution of this study is that, by employing more robust and stable algorithms, each of the algorithms performs the recognition task more accurately. Moreover, by integrating these results and employing the majority vote scheme, we can make a definite decision, which makes the self-diagnostic monitoring system more reliable.

• Journal of Information Processing Systems
• /
• 제17권5호
• /
• pp.905-917
• /
• 2021

In recent years, edge computing technology consists of several Internet of Things (IoT) devices with embedded sensors that have improved significantly for monitoring, detection, and management in an environment where big data is commercialized. The main focus of edge computing is data optimization or task offloading due to data and task-intensive application development. However, existing offloading approaches do not consider correlations and associations between data and tasks involving edge computing. The extent of collaborative offloading segmented without considering the interaction between data and task can lead to data loss and delays when moving from edge to edge. This article proposes a range segmentation of dynamic offloading (RSDO) algorithm that isolates the offload range and collaborative edge node around the edge node function to address the offloading issue.The RSDO algorithm groups highly correlated data and tasks according to the cause of the overload and dynamically distributes offloading ranges according to the state of cooperating nodes. The segmentation improves the overall performance of edge nodes, balances edge computing, and solves data loss and average latency.

• 감성과학
• /
• 제4권2호
• /
• pp.63-68
• /
• 2001

조명 색온도에 따른 작업자의 피로도를 평가하기 위하여 세 종류의 조명 색온도(2700 K, 4000 K, 6500 K)를 실험변수로 하여 모니터상에서 오류수정 작업이 수행되었다. 색온도의 변화에 따른 인체의 영향을 평가하기 위하여 먼저 주관평가와 작업수행도의 상관관계를 분석하였다. 시각피로·정신피로와 집중도에 관한 주관평가를 실시한 결과, 2700 K에서 시각피로 및 정신피로가 가장 적고 집중도가 높으며 작업수행도가 가장 좋았다. 6500 K에서 정신피로를 가장 많이 느끼고 집중도가 제일 낮았으나, 시각피로를 가장 많이 느낀 4000 K에서의 작업수행도가 가장 낮았다. 결과적으로 세 가지 색온도 조건 중 2700 K가 모니터상의 오류수정 작업에 가장 적합하다고 할 수 있다.

• 인지과학
• /
• 제26권1호
• /
• pp.53-67
• /
• 2015

메타인지적 모니터링은 자신의 인지 활동을 점검하고 평가하는 고차원적 인지과정이며, 인지과정에 대한 정확한 이해는 효율적인 통제를 가능하게 만든다. 신경학적으로 모니터링과 관련된 뇌 영역은 전 전두피질(PFC)로 이 영역은 발달 상 가장 늦게 완성되는 것으로 알려져 왔으며, 이는 모니터링 능력이 청소년 후기에도 발달 중에 있음을 시사한다. 본 연구에서는 메타인지적 정확성을 평가하는 방법 중 하나인 학습에 대한 판단(JOL)을 측정함으로써 대학생과 고등학생에서 나타나는 발달상의 차이를 알아보고자 하였다. 인천 소재의 하늘고등학교 학생 58명과 수원 소재 아주대학교 학생 60명이 실험에 참가하였으며, 참가자들은 스페인어와 한국어 쌍으로 제시된 단어를 학습한 후 향후 기억 수행에 대한 판단을 하였다(JOL). 실제 점수와 예상점수(JOL)의 차를 중심으로 모니터링 정확성을 평가한 결과, 두 집단 모두 자신의 점수를 실제 점수보다 더 높다고 생각하는 과잉확신(overconfidence)을 보였다. 또한, 실제 정답과 예상 점수가 떨어진 정도(absolute bias)를 측정한 결과 대학생 집단에 비해 고등학생 집단에서 모니터링의 정확성이 유의미하게 낮은 것으로 나타났다. 문항의 난이도에 따라 모니터링 점수를 비교해 본 결과 쉬운 문항에 비해 어려운 문항에서 더 과잉 확신하며 모니터링의 정확도가 떨어짐을 알 수 있었다. 이러한 경향은 고등학생 집단에서 더 두드러지게 나타났으며, 특히 어려운 과제를 할 때 고등학생 집단이 대학생 집단에 비해 자신의 현재 상태를 정확하게 판단하지 못하고 있음을 알 수 있다. 정확한 모니터링을 통한 학습판단은 적절한 학습전략을 선택하는데 매우 중요한 요소이므로 고등학생 집단의 모니터링 향상을 위한 방안의 모색이 필요하다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.985-988
• /
• 2006

Oil spills cause huge material damage. Oil and oil products spills may occur at any stage of the offshore oil production and transportation cycle. Therefore taking into account the current trends of oil production, the task of creating a system for shelf and tank fleet monitoring becomes very crucial today. This document describes the technology being implemented to improve oil spill monitoring and surveillance, to ensure SAR data fast acquisition and processing and to develop geographic information systems in support of spill response decision making. The results of technology implementation are also presented below.

• 대한안전경영과학회지
• /
• 제12권2호
• /
• pp.65-73
• /
• 2010

In an automated industry PLC plays a central role to control the manufacturing system. Therefore, fault free operation of PLC controlled manufacturing system is essential in order to maximize a firm's productivity. On the contrary, distributed nature of manufacturing system and growing complexity of the PLC programs presented a challenging task of designing a rapid fault finding system for an uninterrupted process operation. Hence, designing an intelligent monitoring, and diagnosis system is needed for smooth functioning of the operation process. In this paper, we propose a method to continuously acquire a stream of PLC signal data from the normal operational PLC-based manufacturing system and to generate diagnosis model from the observed PLC signal data. Consequently, the generated diagnosis model is used for distinguish the possible abnormalities of manufacturing system. To verify the proposed method, we provided a suitable case study of an assembly line.

• 한국컴퓨터정보학회논문지
• /
• 제22권11호
• /
• pp.1-7
• /
• 2017

In this paper, we introduce three monitoring filtering techniques which reduce the overheads of dynamic data race detection. It is well known that detecting data races dynamically in multi-threaded programs is quite hard and troublesome task, because the dynamic detection techniques need to monitor all execution of a multi-threaded program and to analyse every conflicting memory and thread operations in the program. Thus, the main drawback of the dynamic analysis for detecting data races is the heavy additional time and space overheads for running the program. For the practicality, we also empirically compare the efficiency of three monitoring filtering techniques. The results using OpenMP benchmarks show that the filtering techniques are practical for dynamic data race detection, since they reduce the average runtime overhead to under 10% of that of the pure detection.