• Smart Structures and Systems
• /
• 제12권3_4호
• /
• pp.345-361
• /
• 2013

Locating and assessing the severity of damage in large or complex structures is one of the most challenging problems in the field of civil engineering. Considering that the wavelet packet transform (WPT) has the ability to clearly reflect the damage characteristics of structural response signals and the artificial neural network (ANN) is capable of learning in an unsupervised manner and of forming new classes when the structural exhibits change, this paper investigates a multi-stage structural damage diagnosis method by using the WPT and ANN based on "energy-damage" theory, in which, the wavelet packet component energies are first extracted to be damage sensitive feature and then adopted as input into an improved back propagation (BP) neural network model for damage diagnosis in a step by step mode. To validate the efficacy of the presented approach of the damage diagnosis, the benchmark structure of the American Society of Civil Engineers (ASCE) is employed in the case study. The results of damage diagnosis indicate that the method herein is computationally efficient and is able to detect the existence of different damage patterns in the simulated experiment where minor, moderate and severe damages corresponds to involving in the loss of stiffness on braces or the removal bracing in various combinations.

• 한국정보통신학회논문지
• /
• 제6권6호
• /
• pp.819-826
• /
• 2002

셀룰러 뉴럴 네트워크는 국부적 연결특성을 가지고 있어 실시간 이미지처리에 적합한 뉴럴 네크워크이다. 또한 국부적 연결특징은 VLSI구현에 적합하다. 그의 응용분야는 패턴인식과 숫자인식 및 영상처리에 응용되고 있다. 본 논문에서, CNN은 전처리 단계로서 숫자의 특징점 추출에 이용된다. CNN을 이용한 그림자검출은 4내지 6방향으로 검출하여 숫자의 특징점을 방향별로 추출한다. 분류단계에서 이러한 형상자료는 다층BP뉴럴 네트워크의 입력벡터에 적합하도록 압축되어 입력된다. 실험결과 CNN을 통한 숫자인식은 굴림체의 경우96%이상의 인식율을 보여 만족할 만한 결과를 얻었다.

• 한국정보통신학회논문지
• /
• 제23권8호
• /
• pp.975-980
• /
• 2019

본 논문에서는 차세대 이동통신 시스템의 핵심 요소 기술 중의 하나로 각광 받고 있는 다중 사용자 다중 안테나 네트워크에서 사용자 선택을 위한 심화 학습 기반 스케쥴링 기법을 제안한다. 제안된 신경망을 학습시키기 위하여 기존의 최적 방식을 통해서 90,000 데이터 샘플을 확보하였으며, 추가적인 10,000 데이터 샘플을 이용하여 최종 학습된 신경망의 과최적화 여부를 확인하였다. 제안된 신경망 기반의 스케쥴링 알고리즘은 초기 학습 시에는 상당한 복잡도와 학습 시간이 필요하지만, 일단 학습이 완료된 이후에는 추가적인 복잡도가 유발되지 않는 장점이 있다. 반면에, 기존의 최적 방식은 매 스케쥴링마다 동일한 복잡도의 계산이 지속적으로 요구된다. 다양한 컴퓨터 시뮬레이션 결과에 따르면, 제안된 심화 학습 기반의 스케쥴링 기법은 10dB 보다 낮은 SNR에서는 기존 최적 알고리즘의 약 88~96%에 이르는 평균 전송 속도의 합을 얻을 수 있으며, 10dB 이상의 SNR에서는 최적의 평균 전송 속도의 합을 얻을 수 있다.

• 환경영향평가
• /
• 제18권5호
• /
• pp.271-280
• /
• 2009

The objective of this study is to develop a reliable flow forecasting model based on neural network algorithm in order to provide flow rate at stream sections without flow measurement in Nakdong river. Stream flow rate measured at 8-days interval by Nakdong river environment research center, daily upper dam discharge and precipitation data connecting upstream stage gauge were used in this development. Back propagation neural network and multi-layer with hidden layer that exists between input and output layer are used in model learning and constructing, respectively. Model calibration and verification is conducted based on observed data from 3 station in Nakdong river.

• 산업공학
• /
• 제16권spc호
• /
• pp.28-32
• /
• 2003

In this paper, the fuzzy group method data handling-type(GMDH) neural networks and their application to the forecasting of mobile communication system are described. At present, GMDH family of modeling algorithms discovers the structure of empirical models and it gives only the way to get the most accurate identification and demand forecasts in case of noised and short input sampling. In distinction to neural networks, the results are explicit mathematical models, obtained in a relative short time. In this paper, an adaptive learning network is proposed as a kind of neuro-fuzzy GMDH. The proposed method can be reinterpreted as a multi-stage fuzzy decision rule which is called as the neuro-fuzzy GMDH. The GMDH-type neural networks have several advantages compared with conventional multi-layered GMDH models. Therefore, many types of nonlinear systems can be automatically modeled by using the neuro-fuzzy GMDH. The computer program is developed and successful applications are shown in the field of estimating problem of mobile communication with the number of factors considered.

• ETRI Journal
• /
• 제46권2호
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 1989년도 한글날기념 학술대회 발표논문집
• /
• pp.267-271
• /
• 1989

최근 Scofield는 coulomb energy network에 적용할 수 있는 learning algorithm(supervised learning algorithm)을 제안하였다. 이 learning algorithm은 multi-layer network에도 쉽게 적용이 가능하고 한 layer 에서 발생한 error가 다른 layer에 영향을 주지 않아서 system을 modular하게 구성할 수가 있으며 각 layer를 독립적으로 learning 시킬 수 있는 특징이 있다. 본 논문에서는 coulomb energy network를 이용하여 한글인식을 위한 neural network를 구현하여 인식실험을 한 결과와 구현한 network 에서 인식율을 높이기 위한 방안 (2 stage learning) 을 제시한다.

• 한국위성정보통신학회논문지
• /
• 제9권4호
• /
• pp.26-31
• /
• 2014

본 논문은 컬러 영상에서 색상과 움직임 정보를 이용하여 후보영역을 특정하고 연기의 특성들을 추출하여 신경망을 사용한 검출의 성능을 분석하여 제시한다. 기존 연기 검출 알고리즘에서는 연기의 움직임, 색상을 분석하여 후보영역으로 특정하고 그 영역 안에서 연기의 여러 특성을 분석 하는 방법을 이용한다. 하지만 대부분 처음 발생하는 연기의 색상조건을 고려하지 않았기 때문에 조기 검출에는 적절하지 못하다. 본 논문은 연기의 색상과 움직임의 특성을 분석하여 그에 알맞은 방법을 적용하여 후보영역을 폭넓게 결정하고 그 영역 내에서 연기의 확산과 투명성을 인공신경망에 적용시킴으로써 나오는 성능을 분석하였다. 모의실험 결과는 91.31%의 검출율과, 2.62%의 오검출율 성능을 확인할 수 있었다.

• 소성∙가공
• /
• 제27권3호
• /
• pp.154-159
• /
• 2018

In the rectangular bar multi-stage drawing process, the cross-section dimensional accuracy of the rectangular bar varies depending on the aspect ratio and process conditions. It is very important to predict the dimensional error of the cross-section occurring in the multi-stage drawing process according to the aspect ratio of the rectangular bar and the half die angle of each pass. In this study, a process map for improving the dimensional accuracy according to the aspect ratio was derived in the drawing process of a rectangular bar. FE-simulation of the multi-stage shape drawing process was carried out with four types of rectangular bar. The results of the FE-simulation were trained to the nonlinear relationship between the shape parameters using an Artificial Neural Network (ANN), and the process maps were derived from them. The optimum half die angles were determined from the process maps on the dimensional accuracy. The validity of the suggested process map for aspect ratios 1.25~2:1 were verified through FE-simulation and experimentation.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.151-160
• /
• 2023

Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.