• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권9호
• /
• pp.2170-2190
• /
• 2012

There are nowadays strong demands for intelligent surveillance systems, which can infer or understand more complex behavior. The application of crowd density estimation methods could lead to a better understanding of crowd behavior, improved design of the built environment, and increased pedestrian safety. In this paper, we propose a new crowd density estimation method, which aims at estimating not only a moving crowd, but also a stationary crowd, using images captured from surveillance cameras situated in various public locations. The crowd density of the moving people is measured, based on the moving area during a specified time period. The moving area is defined as the area where the magnitude of the accumulated optical flow exceeds a predefined threshold. In contrast, the stationary crowd density is estimated from the coarseness of textures, under the assumption that each person can be regarded as a textural unit. A multilayer neural network is designed, to classify crowd density levels into 5 classes. Finally, the proposed method is experimented with PETS 2009 and the platform of Gangnam subway station image sequences.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 추계학술대회 논문집
• /
• pp.61-65
• /
• 2008

Urban flooding with surcharges in sewer system was investigated because of unexpected torrential storm events these days, causing significant amounts of human and economic damages. Although there are limitations in forecasting and preventing natural disasters, integrated urban flooding management system using the SWMM engine and Web technology will be an effective tool in securing safety in operating Bi-modal transportation system. In addition, the integrated urban flooding management system can be linked with general and transportation-related disaster management system in the future. In this study, With simulated values by the SWMM, which is a core engine of the Bi-modal disaster management system, flash flooding area estimation module was developed. Thus, the SWMM system codes were modified and new module was developed and integrated with the existing SWMM interface using the Delphi programming language. The flash flooding area estimation module is fully integrated with the SWMM interface, thus the area is estimated on-the-fly inside the system.

• 한국위험물학회지
• /
• 제6권2호
• /
• pp.68-76
• /
• 2018

This study aims to provide a methodological framework to estimate the travel demand of hazardous materials transporting vehicles by link and analyze daily traffic patterns on an expressway to develop safety roadway management strategies. Traffic volume of hazardous material vehicles is counted through the on-site investigation at twenty-five tollgates on the expressway, and their demands by a link are predicted through origin-destination flows estimation. The result shows that the number of the domestic hazardous materials vehicles is approximately 51,207 vehicles per day and it indicates that hazardous materials transport vehicles account for 1.5% of total daily traffic on the internal expressway and 6.2% of total cargo traffic volumes. This study roughly estimated how many hazardous materials vehicles pass through the expressway segment. Thus it is expected to be utilized for establishing a systematic highway management strategy in the future by calculating the traffic volume of the hazardous material vehicles traveling on the interstate expressway.

• 전력전자학회논문지
• /
• 제26권3호
• /
• pp.183-191
• /
• 2021

A battery management system (BMS) provides some functions for ensuring safety and reliability that includes algorithms estimating battery states. Given the changes caused by various operating conditions, the state-of-health (SOH), which represents a figure of merit of the battery's ability to store and deliver energy, becomes challenging to estimate. Machine learning methods can be applied to perform accurate SOH estimation. In this study, we propose a Long-Term Recurrent Convolutional Network (LRCN) that combines the Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) to extract aging characteristics and learn temporal mechanisms. The dataset collected by the battery aging experiments of NASA PCoE is used to train models. The input dataset used part of the charging profile. The accuracy of the proposed model is compared with the CNN and LSTM models using the k-fold cross-validation technique. The proposed model achieves a low RMSE of 2.21%, which shows higher accuracy than others in SOH estimation.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.532-548
• /
• 2021

Nuclear power plants contain several monitoring systems that can identify the in-vessel phenomena of a severe accident (SA). Though a lot of analysis and research is carried out on SA, right from the development of the nuclear industry, not all the possible circumstances are taken into consideration. Therefore, to improve the efficacy of the safety of nuclear power plants, additional analytical studies are needed that can directly monitor severe accident phenomena. This paper presents an interacting multiple model (IMM) based fault detection and diagnosis (FDD) approach for the identification of in-vessel phenomena to provide the accident propagation information using reactor vessel (RV) out-wall temperature distribution during severe accidents in a nuclear power plant. The estimation of wall temperature is treated as a state estimation problem where the time-varying wall temperature is estimated using IMM employing three multiple models for temperature evolution. From the estimated RV out-wall temperature and rate of temperature, the in-vessel phenomena are identified such as core meltdown, corium relocation, reactor vessel damage, reflooding, etc. We tested the proposed method with five different types of SA scenarios and the results show that the proposed method has estimated the outer wall temperature with good accuracy.

• Structural Monitoring and Maintenance
• /
• 제9권4호
• /
• pp.305-321
• /
• 2022

Bridge structural health monitoring with the aim of continuously assessing structural safety and reliability represents a topic of major importance for worldwide infrastructure managers. In the last two decades, due to their potential economic and operational advantages, drive-by approaches experienced growing consideration from researcher and engineers. This work addresses two technical topics regarding indirect frequency estimation methods: bridge and vehicle dynamics overlapping, and bridge expansion joints impact. The experimental campaign was conducted on a mixed multi-span bridge located in Lombardy using a Ford Galaxy instrumented with a mesh of wireless accelerometers. The onboard time series were acquired for a number of 10 passages over the bridge,performed at a travelling speed of 30 km/h, with no limitations imposed to traffic. Exploiting an ad-hoc sensors positioning, pitch vehicle motion was compensated, allowing to estimate the first two bridge bending frequencies from PSD functions; moreover, the herein adopted approach proved to be insensitive to joints disturbance. Conclusively, a sensitivity study has been conducted to trace the relationship between estimation accuracy and number of trips considered in the analysis. Promising results were found, pointing out a clear positive correlation especially for the first bending frequency.

• 한국자동차공학회논문집
• /
• 제19권1호
• /
• pp.51-57
• /
• 2011

Information of the lateral velocity and the sideslip angle in a vehicle is very useful in many active vehicle safety applications such as yaw stability control and rollover prevention. Because cost-effective sensors to measure the lateral velocity and the sideslip angle are not available, reliable algorithms to estimation them are necessary. In this paper, a sliding mode observer is designed to estimate the lateral velocity. The side slip angle is estimated using the recursive least square with the disturbance observer and the pseudo integral. The estimated parameters from the combined estimation method are updated recursively to minimize the discrepancy between the model and the physical plant, and any possible effects caused by disturbances. The performance of the proposed monitoring system is evaluated through simulations and experiments.

• Nuclear Engineering and Technology
• /
• 제49권7호
• /
• pp.1457-1462
• /
• 2017

Unsteady thermal processes in storage containers with spent nuclear fuel were modeled. The daily fluctuations of outer ambient temperatures were taken into account. The modeling approach, which is based on the solving of conjugate and inverse heat transfer problems, was verified by comparison of measured and calculated temperatures in outer channels. The time delays in the reaching of maximal temperatures for each spent fuel assembly were calculated. Results of numerical investigations show that daily fluctuation of outer temperatures does not have a large influence on the maximal temperatures of stored spent fuel, so that fluctuation can be neglected and only daily average temperature should be considered for safety estimation using the "best estimation" approach.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집E
• /
• pp.361-366
• /
• 2001

The present study describes a practical estimation procedure about the pantograph under several severe aerodynamic load conditions. As the operating speed of the Korean Train Express(KTX) reaches 350km/h, structural safety at various conditions should be examined at the design stage. In the present study, a compact and reliable procedure is developed to get aerodynamic loads on each part of the pantograph regarding the typhoon condition, the train/tunnel interaction, the train/train interaction and the side wind condition. In the estimation procedure, 3-dimensional steady and unsteady CFD simulation around the high speed train facilitates assigning the external local flow condition around the pantograph. The procedure is verified using the results of the low speed wind tunnel test at JARI and applied to 7 flow conditions and 4 operation configurations.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2007년도 정기총회 및 학술발표대회
• /
• pp.49-52
• /
• 2007

Terrestrial Laser Scanning(TLS) was developed at the mid-to-late 1990s. This technique enables to perform reconnaissance surveying of regions or structures hard to access. Besides, TLS has been extended its application gradually such as preservation of historical remains, underground surveys, slopes, glaciers monitoring and so on. However, though the technique has a lot of advantages, an application for structural health and safety monitoring is a beginning stage and it need much research. Therefore in this study, as a groundwork, the estimation model on stress of structures using TLS and Finite Element Method(FEM) applied by the Digital Elevation Model(DEM) technique of geoinformatics is proposed. For the verification of this model, experiments were performed with a continuous steel beam subjected to point loads and outputs were compared with those of electrical strain sensors.