• 한국경영과학회지
• /
• 제27권1호
• /
• pp.33-51
• /
• 2002

A fully connected Artificial Neural Network (ANN) contains many connections. Compared to the pruned ANN with fewer connections, the fully connected ANN takes longer time to produce solutions end may not provide appropriate solutions to new unseen date. Therefore, by reducing the sloe of ANN, we can overcome the overfitting problem and increase the computing speed. In this research, we reduced the size of ANN by destroying the connections. In other words, we investigated the performance change of the reduced ANN by systematically destroying the connections. Then we found the acceptable level of connection-destruction on which the resulting ANN Performs as well as the original fully connected ANN. In the previous researches on the sloe reduction of ANN, the reduced ANN had to be retrained every time some connections were eliminated. Therefore, It tool lolly time to obtain the reduced ANN. In this research, however, we provide the acceptable level of connection-destruction according to the size of the fully connected ANN. Therefore, by applying the acceptable level of connection-destruction to the fully connected ANN without any retraining, the reduced ANN can be obtained efficiently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.166-179
• /
• 2021

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

• 한국컴퓨터그래픽스학회논문지
• /
• 제27권5호
• /
• pp.73-79
• /
• 2021

최근 컴퓨터 애니메이션 분야에서는 기존의 유한상태기계나 그래프 기반의 방식들에서 벗어나 딥러닝을 이용한 동작 생성 방식이 많이 연구되고있다. 동작 학습에 요구되는 네트워크의 표현력은 학습해야하는 동작의 단순한 길이보다는 그 안에 포함된 동작의 다양성에 더 큰 영향을 받는다. 본 연구는 이처럼 학습해야하는 동작의 종류가 다양한 경우에 효율적인 네트워크 구조를 찾는것을 목표로 한다. 기본적인 fully-connected 구조, 여러개의 fully-connected 레이어를 병렬적으로 사용하는 mixture of experts구조, seq2seq처리에 널리 사용되는 순환신경망(RNN), 그리고 최근 시퀀스 형태의 데이터 처리를 위해 자연어 처리 분야에서 사용되고있는 transformer구조의 네트워크들을 각각 학습하고 비교한다.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• Structural Engineering and Mechanics
• /
• 제76권3호
• /
• pp.311-324
• /
• 2020

Until now, a comparative study on fully and partially-connected steel shear walls leading to enhancing strength and stiffness reduction of partially-connected steel plate shear wall structures has not been reported. In this paper a number of 4-story and 8-story steel plate shear walls, are considered with three different connection details of infill plate to surrounding frame. The specimens are modeled using nonlinear finite element method verified excellently with the experimental results and analyzed under monotonic loading. A comparison between initial stiffness and shear strength of models as well as percentage of shear force by model boundary frame and infill plate are performed. Moreover, a comparison between energy dissipation, ductility factor and distribution of Von-Mises stresses of models are presented. According to the results, the initial stiffness, shear resistance, energy dissipation and ductility of the models with beam-only connected infill plates (SSW-BO) is found to be about 53%, 12%, 15% and 48% on average smaller than those of models with fully-connected infill plates (SPSW), respectively. However, performance characteristics of semi-supported steel shear walls (SSSW) containing secondary columns by simultaneously decreasing boundary frame strength and increasing thickness of infill plates are comparable to those of SPSWs. Results show that by using secondary columns as well as increasing thickness of infill plates, the stress demands on boundary frame decreases substantially by as much as 35%. A significant increase in infill plate share on shear capacity by as much as 95% and 72% progress for the 4-story SSW-BO and 8-story SSSW8, respectively, as compared with non-strengthened counterparts. A similar trend is achieved by strengthening secondary columns of 4-story SSSW leading to an increase of 50% in shear force contribution of infill plate.

• ETRI Journal
• /
• 제40권5호
• /
• pp.582-591
• /
• 2018

In this paper, we present a performance analysis of large-scale multi-input multi-output (MIMO) systems for wireless backhaul networks. We focus on fully connected N nodes in a wireless meshed and multi-hop network topology. We also consider a large number of antennas at both the receiver and transmitter. We investigate the transmission schemes to support fully connected N nodes for half-duplex and full-duplex transmission, analyze the achievable ergodic sum rate among N nodes, and propose a closed-form expression of the achievable ergodic sum rate for each scheme. Furthermore, we present numerical evaluation results and compare the resuts with closed-form expressions.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.1007-1010
• /
• 1999

This paper describes the recognition of totally unconstrained handwritten numerals using neural networks. Neural networks with multiple output nodes have been successfully used to classify complex handwritten numerals. The recognition system consists of the preprocessing stage to extract features using Kirsch mask and the classification stage to recognize the numerals using the fully-connected recurrent neural networks (RNN). Simulation results with the numeral database of Concordia university, Montreal, Canada, are presented. The recognition system proposed in this paper outperforms other recognition systems reported on the same database.

• 한국음향학회지
• /
• 제37권1호
• /
• pp.60-65
• /
• 2018

본 논문에서는 양서류 울음소리 구별을 CNN(Convolutional Neural Network)에 적용하기 위한 방법으로 공분산 행렬과 모듈로그램(modulogram)을 제안한다. 먼저, 멸종 위기 종을 포함한 양서류 9종의 울음소리를 자연 환경에서 추출하여 데이터베이스를 구축했다. 구축된 데이터를 CNN에 적용하기 위해서는 길이가 다른 음향신호를 정형화하는 과정이 필요하다. 음향신호를 정형화하기 위해서 분포에 대한 정보를 나타내는 공분산 행렬과 시간에 대한 변화를 내포하는 모듈로그램을 추출하여, CNN의 입력으로 사용했다. CNN은 convolutional layer와 fully-connected layer의 수를 변경해 가며 실험하였다. 추가적으로, CNN의 성능을 비교하기 위해 기존에 음향 신호 분석에서 쓰이는 알고리즘과 비교해보았다. 그 결과, convolutional layer가 fully-connected layer보다 성능에 큰 영향을 끼치는 것을 확인했다. 또한 CNN을 사용하였을 때 99.07 % 인식률로, 기존에 음향분석에 쓰이는 알고리즘 보다 높은 성능을 보인 것을 확인했다.

• 방송공학회논문지
• /
• 제26권6호
• /
• pp.758-765
• /
• 2021

최근 딥러닝 기술을 비디오 부호화에 적용하는 다양한 연구가 진행되고 있다. 본 논문은 차세대 비디오 코덱인 VVC(Versatile Video Coding)에 채택된 신경망 기반의 기술인 MIP(Matrix-based Intra Prediction)를 확장한 완전연결계층(Fully Connected Layer) 기반의 다중 모델을 이용하는 화면내 예측 부호화 기법을 제시한다. 또한 다중 화면내 예측 모델을 위한 효율적인 학습기법을 제안한다. HEVC(High Efficiency Video Coding)에서의 성능검증을 위해 VVC의 MIP와 제안하는 완전연결계층 기반 다중 화면내 예측 모델을 HEVC의 참조 소프트웨어인 HM16.19에 추가적인 화면내 예측모드로 구현하였다. 실험결과 제안하는 방법이 HM16.19와 VVC MIP 대비 각각 0.47%과 0.19% BD-rate 성능향상이 있음을 확인하였다.

• 방송공학회논문지
• /
• 제20권6호
• /
• pp.938-949
• /
• 2015

본 논문에서는 외부압력에 의한 외형 손상이나 빛의 방향에 따른 색상 대비변화 등에 견고한 영상기반 속도 제한 표지판 인식 시스템 설계를 제안한다. 속도 제한 표지판 인식을 위해서 최근 패턴 인식 분야에서 뛰어한 성능을 보여주고 있는　CNN (Convolutional neural network)을 사용한다. 하지만 기존의 CNN은 특징 추출을 위해 다수의 은닉층이 사용되고 추출된 결과에 대해 MLP(Multi-layer perceptron) 등과의 완전 연결(fully-connected) 방식을 사용함으로 학습과 테스트 시간이 많이 걸리는 단점이 있다. 본 논문에서는 이러한 단점을 줄이기 위해 2계층의 CNN을 구성하고 패턴 분류를 위해 랜덤 포레스트(Random forest)를 결합하여 완전 연결이 아닌 랜덤 연결 방식을 적용하였다. GTSRB(German Traffic Sign Recognition Benchmark)데이터의 교통안전표지판 중에서 8개 속도 제한 표지판 데이터를 사용하여 제안하는 방식이 SVM (Support Vector Machine)이나 MLP 분류기를 적용할 때 보다 성능이 우수함을 입증하였다.