• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.22-29
• /
• 2022

In this paper, for the purpose of designing an real-time unmanned monitoring system, the YOLOv5s (small) object detection model was applied on the NVIDIA TX2^TM AI (Artificial Intelligence) edge computing platform in order to design the fundamental function of an unmanned monitoring system that can detect objects in real time. YOLOv5s was applied to the our real-time unmanned monitoring system based on the performance evaluation of object detection algorithms (for example, R-CNN, SSD, RetinaNet, and YOLOv5). In addition, the performance of the four YOLOv5 models (small, medium, large, and xlarge) was compared and evaluated. Furthermore, based on these results, the YOLOv5s model suitable for the design purpose of this paper was ported to the NVIDIA TX2^TM AI edge computing system and it was confirmed that it operates normally. The real-time unmanned monitoring system designed as a result of the research can be applied to various application fields such as an security or monitoring system. Future research is to apply NMS (Non-Maximum Suppression) modification, model reconstruction, and parallel processing programming techniques using CUDA (Compute Unified Device Architecture) for the improvement of object detection speed and performance.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.5
• /
• pp.474-482
• /
• 2020

To ensure the safe operation of offshore plants, a system is needed for evaluating the equipment performance and for monitoring the results. Currently, owing to the operating environments of of shore plants situated far from the land, measurement data must be periodically stored in storage devices and carried on the land for evaluating the equipment performance. Consequently, it is difficult to prevent equipment failure because the performance evaluation cycle is long. Furthermore, until the next performance evaluation is conducted, it is difficult to determine the equipment's degree of performance degradation. Hence, it is necessary to install an onboard equipment performance monitoring system within the offshore plant. In this study, to evaluate and visualize the results of equipment performance within an offshore plant, a database was designed as the initial step towards the development of an equipment performance monitoring system. The tag data of major equipment were selected and analyzed. Furthermore, in order to store and manage the data measured in real time within the offshore plant, a database was developed for the onboard equipment performance monitoring system.

• Journal of Korean Society of Disaster and Security
• /
• v.6 no.2
• /
• pp.31-39
• /
• 2013

Seoul city has been carried out the actual conditional investigation about street monitoring from January to June of 2013. As the result of this investigation, it has been performed aleady the Seoul city's BSI goal of 2013. The 9,722 cases were reported through the street monitoring activities. Despite of increasing drastically for 1,151 cases's record of 2012, Street monitoring activity appeared wide variations in the region, ages, vocation and gender. Also it depended on 14 outstanding persons of merely 2.2%. They reported 6,546 cases that run to 67.3%. On the basis of Herbert W. Heinrich's law of 1:29:300, the dead of 28, seriously and the slightly injured of 816 and the latent injured of 8,442 were decreased. It respected and protected the 9,287 Seoul citizen's life. This study reseted a definite goal of monitoring and estimated a performance possibility as well as suggested a monitoring expert system, monitor increase, grade evaluation incentive, general evaluation method throughout priority analysis of Gangdong-gu case.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.717-724
• /
• 2011

In order to commercialize the track systems including the turnouts developed in Korea, the guideline of technical and systematic performance evaluation considering local environment was established on Aug. 2010. It consists of a technical compatibility, laboratory test and in-service test. Technical compatibility and laboratory test of the domestically-developed swing-nose crossing turnout on slab track(F18.5) were evaluated according to the guideline. And then in-service test was performed for the turnout installed at the 2nd phase site of Kyung-Bu HSR. In-service test is comprised of monitoring, and field and on-board test during KTX operation, where monitoring is to check the maintainability, and field and on-board test is to confirm structural and running safety. This paper is intended to explain the requirements for the in-serve test and analyze the results of monitoring and the data measured at field and on-board. Based on the in-service test, it is proven that performance of the domestically-developed swing-nose crossing turnout on slab track(F18.5) well satisfies the requirements of the guideline.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.2
• /
• pp.959-968
• /
• 2017

Electrical safety monitoring System (ESMS) is a critical component in modern power systems, which is characterized by large-scale access points, massive users and versatile requirements. For convenience of the information integration and analysis, the software development, maintenance, and application in the system, the cloud platform based ESMS is established and assessed in this paper. Firstly the framework of the system is proposed, and then the assessment scheme with a set of evaluation indices are presented, by which the appropriate cloud product can be chosen to meet the requirements of a specific application. Moreover, to calculate the weights of the evaluation indices under uncertainty, an improved interval AHP method is adopted to take into consideration of the fuzziness of expert scoring, the qualitative consistency test, and the two normalizations in the process of eigenvectors. Case studies have been made to verify the feasibility of the assessment approach for ESMS.

• Polymer(Korea)
• /
• v.27 no.3
• /
• pp.189-194
• /
• 2003

Interfacial evaluation, damage sensing and cure monitoring of single carbon fiber/thermo setting composite with different curing processes were investigated using electro-micromechanical test. After curing, the residual stress was monitored by measurement of electrical resistance and then compared to various curing processes. In thermal curing case, matrix tensile strength, modulus and interfacial shear strength were higher than those of ultraviolet curing case. The shrinkage measured during thermal curing occurred significantly by matrix shrinkage and residual stress due to the difference in thermal expansion coefficient. The apparent modulus measured in the thermal curing indicated that mechanical and interfacial properties were highly improved. The reaching time to the same stress of thermal curing was faster than that of UV curing case.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.673-676
• /
• 2017

Accompanying the Internet of Things (IoT) is a demand of advanced applications and services utilizing the potential of the IoT environment. Monitoring the environment for a provision of context-aware services to the human beings is one of the new trends in our future life. The IoTivity Cloud is one of the most notable open-source platform bringing an opportunity to collect, analyze, and interpret a huge amount of data available in the IoT environment. Based on the IoTivity Cloud, we aim to develop a novel platform for comprehensive monitoring of a future network, which facilitates on-demand data collection to enable the network behavior prediction and the quality of user experience maintenance. In consideration of performance evaluation of the monitoring platform, this paper presents results of a preliminary test on the data acquisition/supply process in the IoTivity Cloud.

• Nuclear Engineering and Technology
• /
• v.52 no.8
• /
• pp.1661-1668
• /
• 2020

A physical protection system (PPS) is used for the protection of critical facilities. This paper proposes a structure analytic hierarchy approach (SAHA) for the hierarchical evaluation of the PPS effectiveness in critical infrastructure. SAHA is based on the traditional analysis methods "estimate of adversary sequence interruption, EASI". A community algorithm is used in the building of the SAHA model. SAHA is applied to cluster the associated protection elements for the topological design of complicated PPS with graphical vertexes equivalent to protection elements.

• Smart Structures and Systems
• /
• v.15 no.3
• /
• pp.555-576
• /
• 2015

The large number of long-span bridges constructed in China motivates the applications of structural health monitoring (SHM) technology. Many bridges have been equipped with sophisticated SHM systems in the mainland of China and in Hong Kong of China. Recently, SHM technology has been extended to field test systems. In this view, SHM can serve as a tool to develop the methods of life-cycle performance design, evaluation, maintenance and management of bridges; to develop new structural analysis methods through validation and feedback from SHM results; and to understand the behavior of bridges under natural and man-made disasters, rapidly assess the damage and loss of structures over large regions after disasters, e.g., earthquake, typhoon, flood, etc. It is hoped that combining analytical methods, numerical simulation, small-scale tests and accelerated durability tests with SHM could become the main engine driving the development of bridge engineering. This paper demonstrates the above viewpoint.

• Smart Structures and Systems
• /
• v.11 no.4
• /
• pp.365-386
• /
• 2013

Monitoring systems currently applied to concrete bridges include strain gauges, inclinometers, accelerometers and displacement transducers. In general, vertical displacements are one of the parameters that more often need to be assessed because their information reflects the overall response of the bridge span. However, the implementation of systems to continuously and directly observe vertical displacements is known to be difficult. On the other hand, strain gauges and inclinometers are easier to install, but their measurements provide no more than indirect information regarding the bridge deflection. In this context, taking advantage of the information collected through strain gauges and inclinometers, and the processing capabilities of current computers, a procedure to evaluate bridge girder deflections based on polynomial functions is presented. The procedure has been implemented in an existing software system - MENSUSMONITOR -, improving the flexibility in the data handling and enabling faster data processing by means of real time visualization capabilities. Benefiting from these features, a comprehensive analysis aiming at assessing the suitability of polynomial functions as an approximate solution for deflection curves, is presented. The effect of boundary conditions and the influence of the order of the polynomial functions on the accuracy of results are discussed. Some recommendations for further instrumentation plans are provided based on the results of the present analysis. This work is supported throughout by monitoring data collected from a laboratory beam model and two full-scale bridges.