• 한국ITS학회:학술대회논문집
• /
• v.2006 no.10
• /
• pp.25-30
• /
• 2006

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.25-39
• /
• 2018

The purpose of this study is to develop an efficient incident detection algorithm by applying machine learning, which is being widely used in the transport sector. As a first step, network of the target site was constructed with micro-simulation model. Secondly, data has been collected under various incident scenarios produced with combination of variables that are expected to affect the incident situation. And, detection results from both McMaster algorithm, a well known incident detection algorithm, and the Naive Bayes algorithm, developed in this study, were compared. As a result of comparison, Naive Bayes algorithm showed less negative effect and better detect rate (DR) than the McMaster algorithm. However, as DR increases, so did false alarm rate (FAR). Also, while McMaster algorithm detected in four cycles, Naive Bayes algorithm determine the situation with just one cycle, which increases DR but also seems to have increased FAR. Consequently it has been identified that the Naive Bayes algorithm has a great potential in traffic incident detection.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.229-239
• /
• 2008

Most algorithms for detecting incidents have been developed under the premise that congestion must happen whenever an incident occurs. For that reason, the performance of these algorithms could not be guaranteed in cases where congestion did not happen due to traffic operations with low flows despite the occurrence of an incident. The objective of this paper is to develop an automatic incident detection algorithm using a new diagram that can reliably detect the incident under various conditions of traffic operations including a low volume state. Compared with the McMaster Algorithm, the proposed algorithm in this paper was evaluated with three different cases in which the incidents occur in traffic operations with a low volume state, a relatively high volume state, and a recurrent congestion state. It is shown that the new algorithm has a capability to identify the flow characteristics of incidents for all the three cases and is much better than McMaster algorithm in terms of detection rate and false alarm rate.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.121-124
• /
• 2015

본 논문은 Multiscale Gradients (MSG)를 기반으로 한 Color Filter Array Interpolation을 배경으로 Kodak Dataset보다 실제 디지털 카메라로 촬영한 이미지에 가까운 McMaster Dataset에서 개선된 성능을 내는 알고리듬을 제안한다. MSG는 녹색 채널 보간, 녹색 채널 갱신, 빨간색, 파란색 채널 보간의 과정을 거친다. 이때 높은 스펙트럼 상관관계, 낮은 색채도, 낮은 색 경사도를 가진 Kodak Dataset과 달리 자연 이미지에서는 녹색 채널 갱신 과정의 추정방법을 사용하면 화질 및 Color Peak Signal to Noise Ratio (CPSNR)이 저하되는 것을 확인하였다. 이러한 실험결과를 바탕으로 개선된 필터와 색상 보간 과정을 통해 기존의 알고리듬에 비해 향상된 성능을 보여주는 알고리듬을 제안한다.

• Nuclear Engineering and Technology
• /
• v.53 no.10
• /
• pp.3275-3285
• /
• 2021

A Nuclear Power Plant (NPP) is a complex dynamic system-of-systems with highly nonlinear behaviors. In order to control the plant operation under both normal and abnormal conditions, the different systems in NPPs (e.g., the reactor core components, primary and secondary coolant systems) are usually monitored continuously, resulting in very large amounts of data. This situation makes it possible to integrate relevant qualitative and quantitative knowledge with artificial intelligence techniques to provide faster and more accurate behavior predictions, leading to more rapid decisions, based on actual NPP operation data. Data-driven models (DDM) rely on artificial intelligence to learn autonomously based on patterns in data, and they represent alternatives to physics-based models that typically require significant computational resources and might not fully represent the actual operation conditions of an NPP. In this study, a feed-forward backpropagation artificial neural network (ANN) model was trained to simulate the interaction between the reactor core and the primary and secondary coolant systems in a pressurized water reactor. The transients used for model training included perturbations in reactivity, steam valve coefficient, reactor core inlet temperature, and steam generator inlet temperature. Uncertainties of the plant physical parameters and operating conditions were also incorporated in these transients. Eight training functions were adopted during the training stage to develop the most efficient network. The developed ANN model predictions were subsequently tested successfully considering different new transients. Overall, through prompt prediction of NPP behavior under different transients, the study aims at demonstrating the potential of artificial intelligence to empower rapid emergency response planning and risk mitigation strategies.

• Computers and Concrete
• /
• v.22 no.1
• /
• pp.1-10
• /
• 2018

In this study an implicit algorithm for modeling of propagation of macrocracks in 3D concrete structures suffering from alkali-silica reaction has been developed and implemented. The formulation of the problem prior to the onset of localized deformation is based on a chemo-elasticity approach. The localized deformation mode, involving the formation of macrocracks, is described using a simplified form of the strong discontinuity approach (SDA) that employs a volume averaging technique enhanced by a numerical procedure for tracing the propagation path in 3D space. The latter incorporates a non-local smoothening algorithm. The formulation is illustrated by a number of numerical examples that examine the crack propagation pattern in both plain and reinforced concrete under different loading scenarios.

• Journal of Korean Society of Transportation
• /
• v.24 no.3 s.89
• /
• pp.39-50
• /
• 2006

This study aims to introduce a basic principle to improve the incident detection algorithm using traffic flow diagrams that can classify traffic states with a high reliability on the basis of the analysis of traffic flow characteristics under the recurrent or incident congestions. It is tried to newly classify the traffic states with the speed-flow and speed-occupancy diagrams. This is because McMaster algorithm has a tendancy on not identifying the traffic states exactly using the flow-occupancy diagram. In this study it shows that the classification of traffic states is applicable to use speed-occupancy relationship Therefore, it is necessary to determine some parameters to correctly classify the areas representing the traffic states and it may be possible to develop a new algorithm to detect the incident with a high reliability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.110-116
• /
• 2017

This paper presents an effective demosaicking algorithm for color filter array (CFA) images acquired from single-sensor devices based on directional interpolation and nonlocal properties of the image. We interpolate the G channel considering diagonal directions as well as horizontal and vertical directions, using a small number of pixels to reflect local properties of the image. Then, we overcome image degradations, such as zipper effects near edges and false colors, by applying nonlocal means (NLM) filtering to the interpolated pixels. R and B channels are reproduced by using directional interpolation with information of the reconstructed G channel and NLM filtering. Experimental results for various McMaster images with high saturation and color changes show that the proposed algorithm accomplishes high PSNR compared with conventional methods. Moreover, the proposed method demonstrates better subjective quality compared with existing methods in terms of reduction of quality degradation, like false colors, and preservation of the image structures, such as edges and textures.

• Journal of Power Electronics
• /
• v.19 no.5
• /
• pp.1182-1192
• /
• 2019

In order to improve the conversion efficiency and mitigate the EMI problem of conventional hard-switching inverters, a new soft-switching DC-AC inverter with a compact structure and a low modulation complexity is proposed in this paper. In the proposed structure, resonant inductors are connected in series for the arm branches, and resonant capacitors are connected in parallel for the neutral point branches. With the help of resonant components, the proposed structure achieves zero-current switching on the arm branches and zero-voltage switching on the neutral point branches. When compared with state-of-art soft-switching topologies, the proposed topology does not need auxiliary switches. Moreover, the commutation algorithm to realize soft-switching can be easily implemented. In this paper, the principle of the resonant operation of the proposed soft-switching converter is presented and its performance is verified through simulation studies. The feasibility of the proposed inverter is evaluated experimentally with a 2.4-kW prototype.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.69-72
• /
• 2018

본 논문은 Multiscale Gradients (MSG)를 기반으로 한 Color Filter Array Interpolation을 토대로 개선된 필터와 보간 과정의 알고리듬을 제안한다. MSG는 초록색 채널 보간, 초록색 채널 갱신, 빨간색 및 파란색 채널 보간 과정으로 이루어진다. 이때, 더욱 정교한 보간을 위해 필터의 크기를 증가시키고, 보간 과정에 이용되는 주변 픽셀의 개수를 늘렸다. 이러한 실험을 통해 높은 스펙트럼 상관관계, 낮은 채도, 낮은 색 경사도를 가진 Kodak dataset과 자연 영상과 유사한 특성을 갖는 McMaster dataset 모두의 경우에서 Color Peak Signal to Noise Ratio (CPSNR)이 향상되는 것을 확인하였다.