• 대한기계학회논문집A
• /
• 제26권12호
• /
• pp.2475-2482
• /
• 2002

The measurement of residual stresses by the hole-drilling method has been commonly used to evaluate residual stresses in structural members. In this method, eccentricity can usually occur between the hole center and rosette gage center. In this study, the error due to the hole eccentricity is compensated using the neural network. The neural network has trained training examples of normalized eccentricity, eccentric direction and direction of maximum stress at eccentric case using backpropagation learning process. The trained neural network could compensated the error of measured residual stress in experiments with hole eccentricity. The proposed neural network is very useful for compensation of the error due to hole eccentricity in hole-drilling method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.102-105
• /
• 2019

In the classical single-image super-resolution (SISR) reconstruction method using convolutional neural networks, the extracted features are not fully utilized, and the training time is too long. Aiming at the above problems, we proposed an improved SISR method based on a residual network. Our proposed method uses a feature fusion technology based on improved residual blocks. The advantage of this method is the ability to fully and effectively utilize the features extracted from the shallow layers. In addition, we can see that the feature fusion can adaptively preserve the information from current and previous residual blocks and stabilize the training for deeper network. And we use the global residual learning to make network training easier. The experimental results show that the proposed method gets better performance than classic reconstruction methods.

• Nuclear Engineering and Technology
• /
• 제49권4호
• /
• pp.817-824
• /
• 2017

Residual stress is a critical element in determining the integrity of parts and the lifetime of welded structures. It is necessary to estimate the residual stress of a welding zone because residual stress is a major reason for the generation of primary water stress corrosion cracking in nuclear power plants. That is, it is necessary to estimate the distribution of the residual stress in welding of dissimilar metals under manifold welding conditions. In this study, a cascaded support vector regression (CSVR) model was presented to estimate the residual stress of a welding zone. The CSVR model was serially and consecutively structured in terms of SVR modules. Using numerical data obtained from finite element analysis by a subtractive clustering method, learning data that explained the characteristic behavior of the residual stress of a welding zone were selected to optimize the proposed model. The results suggest that the CSVR model yielded a better estimation performance when compared with a classic SVR model.

• 디지털콘텐츠학회 논문지
• /
• 제12권4호
• /
• pp.467-474
• /
• 2011

청각장애인을 위한 청능 및 언어 훈련은 비장애인과 소통능력을 배양하는 기본적인 훈련이지만 동시에 부모나 지도교사의 경제적부담, 육체적 피로를 수반한다. 이를 해결하기 위해 웹기반의 청능 및 언어 훈련 콘텐츠가 계속해서 개발되어 왔다. 그러나 장애인의 청각상태 및 학습능력의 차이가 존재함에도 불구하고 이런 개인 차이를 고려하지 않은 채 개발되고 있다. 따라서 장애자의 상태와 잔존청력, 학습능력 및 훈련성취도를 정확히 평가하고 분석하여 장애자에게 적절한 훈련진도를 계획하는 것이 중요하다. 본 논문에서 청각장애자를 위해 개인평가에 따라 다양하게 청능 언어 훈련을 기획하고 관리해주는 청능 및 언어 훈련 서비스 모델을 제안한다. 또한 이 모델을 기반으로 하는 기능성 게임콘텐츠를 기획하는 설계방법을 제시한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권6호
• /
• pp.1818-1832
• /
• 2022

Violence in the Internet era poses a new challenge to the current counter-riot work, and according to research and analysis, most of the violent incidents occurring are related to the dissemination of violence images. The use of the popular deep learning neural network to automatically analyze the massive amount of images on the Internet has become one of the important tools in the current counter-violence work. This paper focuses on the use of transfer learning techniques and the introduction of an attention mechanism to the residual network (ResNet) model for the classification and identification of violence images. Firstly, the feature elements of the violence images are identified and a targeted dataset is constructed; secondly, due to the small number of positive samples of violence images, pre-training and attention mechanisms are introduced to suggest improvements to the traditional residual network; finally, the improved model is trained and tested on the constructed dedicated dataset. The research results show that the improved network model can quickly and accurately identify violence images with an average accuracy rate of 92.20%, thus effectively reducing the cost of manual identification and providing decision support for combating rebel organization activities.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제9권2호
• /
• pp.37-44
• /
• 2020

본 논문에서는 딥 러닝 기반의 전-자동 심장 분할 알고리즘을 제안한다. 본 논문에서 제안하는 딥 러닝 모델은 기존 U-Net에 residual recurrent convolutional block과 residual multi-dilated convolutional block을 삽입하여 성능을 개선한 모델이다. 모델의 성능은 테스트 데이터 세트를 전-자동 분할한 결과와 영상의학 전문가의 수동 분할 결과를 비교하여 분석하였다. CT 영상에서 평균 96.88%의 DSC, 95.60%의 precision과 97.00%의 recall 결과를 얻었다. 분할된 영상은 3차원 볼륨 렌더링 기법을 적용하여 시각화한 후 관찰하여 분석할 수 있었다. 실험 결과를 통해 제안된 알고리즘이 다양한 심장 하부 구조를 분할하기에 효과적인 것을 알 수 있었다. 본 논문에서 제안하는 알고리즘이 전문의 또는 방사선사의 임상적 보조역할을 수행할 수 있을 것으로 기대한다.

• Nuclear Engineering and Technology
• /
• 제53권11호
• /
• pp.3465-3473
• /
• 2021

For a long time, research into integrated deterministic-probabilistic safety assessment has been continuously conducted to point out and overcome the limitations of classical ET (event tree)/FT (fault tree) based PSA (probabilistic safety assessment). The current paper also attempts to assert the reason why a technical transformation from classical PSA is necessary with a re-interpretation of the categories of risk. In this study, residual risk was classified into interpolating- and extrapolating-censored categories, which represent risks that are difficult to identify through an interpolation or extrapolation of representative scenarios due to potential nonlinearity between hardware and human behaviors intertwined in time and space. The authors hypothesize that such risk can be dealt with only if the classical ETs/FTs are freely relocated, entailing large-scale computation associated with physical models. The functional elements that are favorable to find residual risk were inferred from previous studies. The authors then introduce their under-development enabling techniques, namely DICE (Dynamic Integrated Consequence Evaluation) and DeBATE (Deep learning-Based Accident Trend Estimation). This work can be considered as a preliminary initiative to find the bridging points between deterministic and probabilistic assessments on the pillars of big data technology.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집A
• /
• pp.412-418
• /
• 2001

The measurement of residual stresses by the hole-drilling method has been commonly used to evaluate residual stresses in structural members. In this method, eccentricity can usually occur between the hole center and rosette gage center. In this study, the error due to the hole eccentricity is corrected using the neural network. The neural network has trained training examples of normalized eccentricity, eccentric direction and direction of maximum stress at eccentric case using backpropagation learning process. The trained neural network could corrected the error of measured residual stress in experiments with hole eccentricity. The proposed neural network is very useful for correction of the error due to hole eccentricity in hole-drilling method.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.203-211
• /
• 2021

Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.1-7
• /
• 2018

The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.