• 한국지능시스템학회논문지
• /
• 제11권2호
• /
• pp.178-183
• /
• 2001

Welding is essential for the manufacture of a range of engineering components which may vary from very large structures such as ships and bridges to very complex structures such as aircraft engines, or miniature components for microelectronic applications. Especially, a domestic situation of the welding automation is still depend on the arc sensing system in comparison to the vision sensing system. Specially, the gap-detecting of workpiece using conventional arc sensor is proposed in this study. As a same principle, a welding current varies with the size of a welding gap. This study introduce to the fuzzy membership filter to cancel a high frequency noise of welding current, and ART2 which has the competitive learning network classifies the signal patterns the filtered welding signal. A welding current possesses a specific pattern according to the existence or the size of a welding gap. These specific patterns result in different classification in comparison with an occasion for no welding gap. The patterns in each case of 1mm, 2mm, 3mm and no welding gap are identified by the artificial neural network.

• 한국멀티미디어학회논문지
• /
• 제11권9호
• /
• pp.1286-1295
• /
• 2008

기존의 2D 애니메이션에 나타나는 캐릭터 색은 아트 디렉터의 주관적 색감에 의해 지정되고 있는데 장면의 분위기가 달라지면 동일 캐릭터일지라도 지정되는 색이 다르게 된다. 본 논문에서는 2D 애니메이션 각 장면마다의 캐릭터 색을 자동 생성할 뿐 아니라 아트 디렉터의 주관적 색감을 재현하기 위해 비선형시스템인 신경회로망을 이용하여 캐릭터 색을 자동적으로 변환하는 모델을 제안하였다. 구체적으로, 기존의 2D 애니메이션 장면에 있는 캐릭터 색을 활용하여 캐릭터의 기본색이 각 장면마다 달라지는 것을 신경회로망으로 학습시켜 어떠한 캐릭터 일지라도 기본색 만 주어진다면 그 장면 분위기에 잘 어울리는 색을 자동으로 변환하는 것이 가능하도록 하였다. 그리고 애니메이션 색채전문가들의 평가를 통해 다양한 장면에서 자동 변환된 캐릭터 색에 대한 자연스러움의 정도를 검증함으로써 본 연구에서 제안한 장면에 따른 캐릭터 색의 자동변환 시스템의 타당성을 입증하였다.

• 센서학회지
• /
• 제30권5호
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.527-531
• /
• 1998

This study introduce to the fuzzy membership filter to cancel a high frequency noise of welding current. And ART2 which has the competitive learning network classifiers the signal patterns for the filtered welding signal. A welding current possesses a specific pattern according to the existence or the size of a welding gap. These specific patterns result in different classification in comparison with an occasion for no welding gap. The patterns In each case of 1mm, 2mm, 3mm, and no welding gap are identified by the artificial neural network. These procedure is an off-line execution. In on-line execution, the identification model of neural network for the classified pattern is located on ahead of the welding plant. And when the welding current patterns pass through the neural network in the direction of feedforward. it is possible to recognize the existence or the size of a welding gap.

• 대한산업공학회지
• /
• 제24권2호
• /
• pp.223-240
• /
• 1998

The purpose of this paper is to develop the pattern recognition system with a 'Robust' concept to be applicable to flexible manufacture automation in practice. The 'Robust' concept has four meanings as follows. First, pattern recognition is performed invariantly in case the object to be recognized is translated, scaled, and rotated. Second, it must have strong resistance against noise. Third, the completely learned system is adjusted flexibly regardless of new objects being added. Finally, it has to recognize objects fast. To develop the proposed system, contouring, spectral analysis and Fuzzy ART neural network are used in this study. Contouring and spectral analysis are used in preprocessing stage, and Fuzzy ART is used in object classification stage. Fuzzy ART is an unsupervised neural network for solving the stability-plasticity dilemma.

• 산업공학
• /
• 제11권2호
• /
• pp.119-124
• /
• 1998

This paper proposes a new part family classification system (IPFACS: Image Processing and Fuzzy ART based Clustering System), which incorporates image processing techniques and a modified fuzzy ART neural network algorithm. IPFACS can classify parts based on geometrical shape and manufacturing attributes, simultaneously. With a proper reduction and normalization of an image data through the image processing methods and adding method in the modified Fuzzy ART, different types of geometrical shape data and manufacturing attribute data can be simultaneously classified in the same system. IPFACS has been tested for an example set of hypothetical parts. The results show that IPFACS provides a good feasible approach to form families based on both geometrical shape and manufacturing attributes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.138-140
• /
• 2005

A fuzzy ARTMAP neural network and a fuzzy ART neural network are proposed to identify $H_2S$, $NH_3$ and their mixtures and to estimate their concentrations, respectively. Features are extracted from a micro gas sensor array operated in a thermal modulation plan. After dimensions of the features are reduced by a preprocessing scheme, the features are fed into the proposed fuzzy neural networks. By computer simulations, the proposed methods are shown to be fast in learning and accurate in concentration estimating. The results are compared with other methods and discussed.

• 대한기계학회논문집
• /
• 제18권8호
• /
• pp.1939-1951
• /
• 1994

This study introduces a new tool breakage detecting technology comprised of an unsupervised neural network combined with adaptive time series autoregressive(AR) model where parameters are estimated recursively at each sampling instant using a parameter adaptation algorithm based on an RLS(Recursive Least Square). Experiment indicates that AR parameters are good features for tool breakage, therefore it can be detected by tracking the evolution of the AR parameters during milling process. an ART 2(Adaptive Resonance Theory 2) neural network is used for clustering of tool states using these parameters and the network is capable of self organizing without supervised learning. This system operates successfully under the wide range of cutting conditions without a priori knowledge of the process, with fast monitoring time.

• 한국통신학회논문지
• /
• 제30권2C호
• /
• pp.31-40
• /
• 2005

오류 역전파 알고리즘의 문제점과 ART 신경회로망의 문제점을 개선하기 위해 Jacobs가 제안한 delta-bar-delta 방법과 신경회로망을 결합한 자가 생성 지도 학습 알고리듬을 제안한다. 입력층과 은닉층에서는 ART-1과 ART-2 알고리듬을 이용하고, winner-take-all 방식은 완전 연결 구조이나 연결된 가중치만을 조정하도록 채택하였다. 실험을 위해 학생증, 주민등록증, 컨테이너의 영상으로 추출한 패턴을 신경회로망의 은닉층 노드에 대해 실험하였고, 실험결과 제안된 자기 생성 지도 학습알고리듬이 지역최소화, 학습 속도, 정체 현상이 기존의 방법보다 성능이 개선된 것을 확인하였다.

• Advances in Computational Design
• /
• 제8권1호
• /
• pp.37-59
• /
• 2023

Squat reinforced concrete (SRC) shear walls are a critical part of the structure for both office/residential buildings and nuclear structures due to their significant role in withstanding seismic loads. Despite this, empirical formulae in current design standards and published studies demonstrate a considerable disparity in predicting SRC wall shear strength. The goal of this research is to develop and evaluate hybrid and ensemble artificial neural network (ANN) models. State-of-the-art population-based algorithms are used in this research for hybrid intelligence algorithms. Six models are developed, including Honey Badger Algorithm (HBA) with ANN (HBA-ANN), Hunger Games Search with ANN (HGS-ANN), fitness-distance balance coyote optimization algorithm (FDB-COA) with ANN (FDB-COA-ANN), Averaging Ensemble (AE) neural network, Snapshot Ensemble (SE) neural network, and Stacked Generalization (SG) ensemble neural network. A total of 434 test results of SRC walls is utilized to train and assess the models. The results reveal that the SG model not only minimizes prediction variance but also produces predictions (with R²= 0.99) that are superior to other models.