• Journal of the Korean Institute of Gas
• /
• v.8 no.2 s.23
• /
• pp.15-27
• /
• 2004

The purpose of this paper is to improve the performance of Polymer electrolyte fuel cell(PEMFC) by studying the channel dimension of bipolar plates using commercial CFD program 'Fluent'. Simulations are done ranging from 0.5 to 3.0mm for different size in order to find the channel size which shoves the highst hydrogen consumption. The results showed that the smaller channel width, land width, channel depth, the higher hydrogen consumption in anode. When channel width is increased, the pressure drop in channel is decreased because total channel length Is decreased, and when land width is increased, the net hydrogen consumption is decreased because hydrogen is diffused under the land width. It is also found that the influence of hydrogen consumption is larger at different channel width than it at different land width. The change of hydrogen consumption with different channel depth isn't as large as it with different channel width, but channel depth has to be small as can as it does because it has influence on the volume of bipolar plates. however the hydrogen utilization among the channel sizes more than 1.0mm which can be machined in reality is the most at channel width 1.0, land width 1.0, channel depth 0.5mm and considered as optimum channel size. The fuel cell combined with 2cm${\times}$2cm diagonal or serpentine type flow field and MEA(Membrane Electrode Assembly) is tested using 100W PEMFC test station to confirm that the channel size studied in simulation. The results showed that diagonal and serpentine flow field have similarly high OCV and current density of diagonal (low field is higher($2-40mA/m^2$) than that of serpentine flow field under 0.6 voltage, but the current density of serpentine type has higher performance($5-10mA/m^2$) than that of diagonal flow field under 0.7-0.8 voltage.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.

• Journal of Navigation and Port Research
• /
• v.38 no.4
• /
• pp.373-378
• /
• 2014

In order to prepare for recapitalization of differential GNSS (DGNSS) reference station and integrity monitor (RSIM) due to GNSS diversification, this paper focuses on differential correction algorithm using GPS/Galileo pesudorange. The technical standards on operation and broadcast of DGNSS RSIM are described as operation of differential GPS (DGPS) RSIM for conversion of DGNSS RSIM. Usually, in order to get the differential corrections of GNSS pesudorange, the system must know the real positions of satellites and user. Therefore, for calculating the position of Galileo satellites correctly, using the equation for calculating the SV position in Galileo ICD (Interface Control Document), it estimates the SV position based on Ephemeris data obtained from user receiver, and calculates the clock offset of satellite and user receiver, system time offset between GPS and Galileo, then determines the pseudorange corrections of GPS/Galileo. Based on a platform for performance verification connected with GPS/Galileo integrated signal simulator, it compared the PRC (pseudorange correction) errors of GPS and Galileo, analyzed the position errors of DGPS, DGalileo, and DGPS/DGalileo respectively. The proposed method was evaluated according to PRC errors and position accuracy at the simulation platform. When using the DGPS/DGalileo corrections, this paper could confirm that the results met the performance requirements of the RTCM.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.97-117
• /
• 2021

Predicting term deposit subscriptions is one of representative financial marketing in banks, and banks can build a prediction model using various customer information. In order to improve the classification accuracy for term deposit subscriptions, many studies have been conducted based on machine learning techniques. However, even if these models can achieve satisfactory performance, utilizing them is not an easy task in the industry when their decision-making process is not adequately explained. To address this issue, this paper proposes an explainable scheme for term deposit subscription forecasting. For this, we first construct several classification models using decision tree-based ensemble learning methods, which yield excellent performance in tabular data, such as random forest, gradient boosting machine (GBM), extreme gradient boosting (XGB), and light gradient boosting machine (LightGBM). We then analyze their classification performance in depth through 10-fold cross-validation. After that, we provide the rationale for interpreting the influence of customer information and the decision-making process by applying Shapley additive explanation (SHAP), an explainable artificial intelligence technique, to the best classification model. To verify the practicality and validity of our scheme, experiments were conducted with the bank marketing dataset provided by Kaggle; we applied the SHAP to the GBM and LightGBM models, respectively, according to different dataset configurations and then performed their analysis and visualization for explainable term deposit subscriptions.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.8
• /
• pp.132-139
• /
• 2015

Visual SLAM(Simultaneous Localization And Mapping) has been used widely to estimate a mobile robot's location. Visual SLAM estimates relative motions with static visual features over image sequence. Because visual SLAM methods assume generally static features in the environment, we cannot obtain precise results in dynamic situation including many moving objects: cars and human beings. This paper presents a stereo vision based SLAM method in dynamic environment. First, we extract disparity map with stereo vision and compute optical flow. We then compute disparity change that is the estimated flow field between stereo views. After examining the disparity change value, we detect ROIs(Region Of Interest) in disparity space to determine dynamic scene objects. In indoor environment, many structural planes like walls may be determined as false dynamic elements. To solve this problem, we segment the scene into planar structure. More specifically, disparity values by the stereo vision are projected to X-Z plane and we employ Hough transform to determine planes. In final step, we remove ROIs nearby the walls and discriminate static scene elements in indoor environment. The experimental results show that the proposed method can obtain stable performance in dynamic environment.

• Journal of the HCI Society of Korea
• /
• v.7 no.2
• /
• pp.25-34
• /
• 2012

A veterinary student learns and experiences veterinary processes though experiments and practices using real animals. However, animal protection laws regulate animal experiments and restrict number of the experiments on laboratory animals, veterinary students would have less chances of the experiments and the practices for their veterinary training with real animals. This paper proposes a simulator for veterinary education based on augmented reality (AR). We selected an intravenous injection procedure for the simulation because the injection procedure is the most frequently used procedure during veterinary training and the most difficult stage for beginning veterinary students. The proposed AR simulator provides with a tangible prop, of which shape looks like a leg of a real dog. It also has a injection simulator, which receives user's input and sends force feedbacks to indicate results of the injection simulation. We developed a WorkBench type AR system with an LED display and cameras for visual information processing. Finally, we evaluated its performance through experiments and user studies to check its acceptance level and usability of the proposed system. We compared the proposed system with a traditional video based education and an AR based system using a head mounded display (HMD). The results that the proposed system showed better performances over these systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.6
• /
• pp.33-43
• /
• 2003

In this paper, we proposed a real-time watermarking algorithm to be combined and to work with a DWT(Discrete Wavelet Transform)-based image compressor. To reduce the amount of computation in selecting the watermarking positions, the proposed algorithm uses a pre-established look-up table for critical values, which was established statistically by computing the correlation according to the energy values of the corresponding wavelet coefficients. That is, watermark is embedded into the coefficients whose values are greater than the critical value in the look-up table which is searched on the basis of the energy values of the corresponding level-1 subband coefficients. Therefore, the proposed algorithm can operate in a real-time because the watermarking process operates in parallel with the compression procession without affecting the operation of the image compression. Also it improved the property of losing the watermark and the efficiency of image compression by watermark inserting, which results from the quantization and Huffman-Coding during the image compression. Visual recognizable patterns such as binary image were used as a watermark The experimental results showed that the proposed algorithm satisfied the properties of robustness and imperceptibility that are the major conditions of watermarking.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.2
• /
• pp.34-44
• /
• 2024

Recently, due to abnormal climate caused by climate change, natural disasters such as floods, landslides, and soil outflows are rapidly increasing. In Korea, more than 63% of the land is vulnerable to slope disasters due to the geographical characteristics of mountainous areas, and in particular, Quarry mines soil and rocks, so there is a high risk of landslides not only inside the workplace but also outside.Accordingly, this study built a DEM using UAV and aviation LiDAR for monitoring the quarry, conducted a time series change analysis, and proposed an optimal DEM construction method for monitoring the soil collection site. For DEM construction, UAV and LiDAR-based Point Cloud were built, and the ground was extracted using three algorithms: Aggressive Classification (AC), Conservative Classification (CC), and Standard Classification (SC). UAV and LiDAR-based DEM constructed according to the algorithm evaluated accuracy through comparison with digital map-based DEM.

• Journal of KIISE:Software and Applications
• /
• v.37 no.8
• /
• pp.611-619
• /
• 2010

This paper presents an efficient modeling system of virtual pottery in which the user can deform a body of virtual clay with a haptic tool for E-learning. We propose a Circular Sector Element Method (CSEM) which represents the virtual pottery with a set of circular sector elements based on the cylindrical symmetry of pottery. Efficient algorithms for collision detection and response, interactions between adjacent elements, and GPU-based visual-haptic synchronization are designed and implemented for the CSEM. Empirical evaluation showed that the modeling system is computationally efficient with finer details and provides convincing model deformation and force feedback. The developed system, if combined with educational contents, is expected to be used as an effective E-learning platform for elementary school students.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.78-80
• /
• 2015

광적응(Luminance Adaptation; LA) 효과는 영상의 배경 밝기에 따른 왜곡에 대한 시각 인지 민감도가 달라지는 특성을 의미한다. 기존 영상 화질 측정(Image Quality Assessment; IQA) 방법들은 베버의 법칙(Weber' s law) 모델을 이용하여 LA 효과를 IQA 방법에 반영해왔다. 그러나, 이러한 IQA 방법들에 있어서 베버의 법칙 기반 LA 효과 모델은 다음 두 가지 이유로 부정확하게 동작한다: (i) 전통적인 베버의 법칙 모델은 실제 광도(luminance)에 대한 인지 민감도 응답값을 정확히 반영할 수 없다는 것이 밝혀졌다, (ii) 대부분 IQA 방법들은 픽셀 강도 영역에서 계산되지만, 베버의 법칙과 같은 LA 효과 모델들은 광도 영역에서 개발되었다. 따라서 광도와 픽셀 강도간 비선형 관계로 인해 IQA 방법에 반영된 베버의 법칙 기반 LA 효과 모델들은 부정확하게 동작한다. 이 문제를 해결하기 위해, 본 논문에서 처음으로 픽셀 강도 영역에서의 LA 모델을 이론적으로 유도한다. 본 논문에서 제안하는 픽셀 강도 영역에서의 LA 효과 모델은 감마 교정 함수(Gamma correction function)와 광도 영역에서의 LA 효과 모델인 제곱-법칙(power-law) 모델을 기반으로 하는 테일러 급수 확장 근사화를 통해 유도된다. 제안하는 픽셀 강도 영역 LA 효과 모델의 효과를 검증하기 위해, 제안하는 LA 효과 모델을 PSNR 에 도입하여 광범위한 실험을 수행한다. 실험 결과, 제안하는 LA 효과 모델 기반 PSNR 은 PSNR 및 베버의 법칙 기반 PSNR 대비 괄목할 만한 주관적 화질 예측 성능 향상을 보였다.