• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2008년도 하계학술발표대회 논문집
• /
• pp.282-287
• /
• 2008

Identification of steady-state is the first step in developing a fault detection and diagnosis (FDD) system. In a complete FDD system, the steady-state detector will be included as a module in a self-learning algorithm which enables the working system's reference model to "tune" itself to its particular installation. In this study, a steady-state detector of a residential air conditioner based on moving windows was designed. Seven representing measurements were selected as key features for steady-state detection. The optimized moving window size and the feature thresholds was suggested through startup transient test and no-fault steady-state test. Performance of the steady-state detector was verified during indoor load change test. From the research, the general methodology to design a moving window steady-state detector was provided for vapor compression applications.

• Perspectives in Nursing Science
• /
• 제8권2호
• /
• pp.86-96
• /
• 2011

Purpose: This study examined the effects of simulation-based education on knowledge about and self-confidence in maternity nursing care in senior students. Methods: One group, pre-post design, was utilized with 28 students. The simulation-based maternity nursing education that consisted of two sessions each 2 hours long for intrapartum and postpartum care was provided to 4 small groups. An expert panel of 3 maternity clinical instructors developed the module with a high-fidelity maternal simulator. Core items of knowledge about and self-confidence in maternity nursing care were measured with 13 items before and after the sessions. Results: The knowledge score did not increase significantly (z=-1.95, p=.05); however, self-confidence in maternity nursing care showed a significant change in the posttest (z=-2.82, p<.001). The subjective evaluation of the students indicated that the simulation-based education was helpful in preparing for clinical practicum as far as interaction with clients, psychological readiness to practice, and learning efficiencies. Conclusion: The simulation-based nursing education was useful in improving self-confidence in clinical performance for childbirth and postpartum care in nursing students. Along with the application of diverse scenarios in simulations, modules with standard patients and role-plays are also recommended for maternity nursing practicum to empower the competency of the students.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권11호
• /
• pp.585-592
• /
• 2016

글이나 대화를 일정한 주제의 단위로 나누는 것을 주제 분리라고 한다. 지금까지 주제 분리는 주로 완결된 하나의 문서에서 최적화된 분리를 찾는 방향으로 진행되어 왔다. 하지만 몇몇 응용은 글이나 대화가 진행 중에 주제 분리를 할 필요가 있다. 본 논문에서는 합성곱 신경망을 이용한 교사 학습 모델을 통해 문장의 진행 중에 주제 분리를 수행하는 모델에 대해 제안한다. 그리고 제안한 모델의 성능 검증을 위해 On-line 상황을 가정한 실험과 기존의 C99모델을 결합한 실험을 수행하였다. 실험결과 각각 17.8과 11.95의 Pk 점수를 얻었고, 이를 통해 본 논문의 모델을 통한 On-line 상황에서의 주제 분리 활용의 가능성을 확인하였다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2008년 영문 학술대회
• /
• pp.72-79
• /
• 2008

The weak point of the artificial neural network(ANN) is that it is easy to fall in local minima when it learns too much nonlinear data. Accordingly, the classification ratio must be low. To overcome this weakness, the hybrid method has been proposed. That is, the ANN learns data selectively after detecting the defect position by the support vector machine(SVM). First, the SVM has been used for determination of the defect position and then the magnitude of the defect has been measured by the ANN. In off-design condition, the operation region of the engine is wide and the nonlinearity of learning data increases. The module system, dividing the whole operating region into reasonably small-size sections, has been suggested to solve this problem. In this study, the proposed algorithm has diagnosed the defects of triple components as well as single and dual components of the gas turbine engine in off-design condition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• 방송공학회논문지
• /
• 제23권6호
• /
• pp.760-767
• /
• 2018

첨단 운전자 지원 시스템(ADAS)은 차량 기술 분야에서 활발한 연구가 이루어지고 있는 기술이다. ADAS 기술은 직접적으로 차량을 제어하는 기술과 간접적으로 운전자에게 편의를 제공하는 기술로 나뉜다. 본 논문에서는 야간 도로 영상을 보정하여 운전자에게 시각적 편의를 제공하는 시스템을 제안한다. 제안하는 시스템은 전방 블랙박스 카메라로부터 촬영된 도로 영상을 입력받는다. 입력된 영상은 가로 축을 따라 세 부분으로 분할된 뒤 일괄적으로 이미지 변환 모듈을 통해 각각 낮 영상으로 변환된다. 변환된 영상은 다시 결합된 뒤 운전자에게 제공되어 시각적 편의를 제공한다. 본 논문의 실험 결과를 통해 제안한 시스템이 기존의 밝기 변환 알고리즘과 비교하여 우수한 성능을 보임을 입증한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 추계학술대회
• /
• pp.227-230
• /
• 2009

본 논문에서는 유비쿼터스 네트워크에서 요구되는 다양한 장치의 통합 연동의 방안을 제안한다. 다양한 장치의 연동은 최근에 사용되어지는 고성능의 멀티미디어장치 뿐만 아니라 기존의 가정에서 사용되고 있는 저성능의 단순 가전기기까지 모든 종류의 장치 연결에 제약이 없어야 한다. 이에 본문에서는 기존의 저성능 가전기기를 대상으로 표준 미들웨어를 활용하여 네트워크 프로토콜의 연동을 통해 효율적인 장치의 연결과 제어 관리의 제공을 목적으로 한다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.412-434
• /
• 2023

This study discusses the high-order diffusion method in the wavelet domain. It aims to improve the edge protection capability of the high-order diffusion method using wavelet coefficients that can reflect image information. During the first step of the proposed diffusion method, the wavelet packet decomposition is a more refined decomposition method that can extract the texture and structure information of the image at different resolution levels. The high-frequency wavelet coefficients are then used to construct the edge detection function. Subsequently, because accurate wavelet coefficients can more accurately reflect the edges and details of the image information, by introducing the idea of state weight, a scheme for recovering wavelet coefficients is proposed. Finally, the edge detection function is constructed by the module of the wavelet coefficients to guide high-order diffusion, the denoised image is obtained. The experimental results showed that the method presented in this study improves the denoising ability of the high-order diffusion model, and the edge protection index (SSIM) outperforms the main methods, including the block matching and 3D collaborative filtering (BM3D) and the deep learning-based image processing methods. For images with rich textural details, the present method improves the clarity of the obtained images and the completeness of the edges, demonstrating its advantages in denoising and edge protection.

• 방송공학회논문지
• /
• 제28권2호
• /
• pp.230-237
• /
• 2023

자율주행은 4차 산업의 핵심 기술로 차, 드론, 자동차, 로봇 등 다양한 곳에 응용 가능하다. 그 중 위치 추정 기술은 GPS, 센서, 지도 등을 활용하여, 객체나 사용자의 위치를 파악하는 기술로 자율주행을 구현하기 위한 핵심적인 기술 중 하나이다. GPS나 LIDAR 등의 센서를 이용하여 위치 추정이 가능하지만, 이는 매우 고가이고 무거운 장비를 탑재해야 하며 지하 혹은 터널 등 전파 방해가 있는 곳의 경우 정밀한 위치 추정이 어렵다는 단점이 있다. 본 논문에서는 이를 보완하기 위해 저가의 비전 카메라로 획득한 컬러 영상을 입력으로 하여 관심 영역 추출 네트워크와 영상 분할 지도를 이용한 영상 검색 기술을 제안한다.