• Journal of the Korean Operations Research and Management Science Society
• /
• v.27 no.1
• /
• 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)
• /
• v.15 no.1
• /
• 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.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.73-79
• /
• 2021

Recently, in the field of computer animation, a method for generating motion using deep learning has been studied away from conventional finite-state machines or graph-based methods. The expressiveness of the network required for learning motions is more influenced by the diversity of motion contained in it than by the simple length of motion to be learned. This study aims to find an efficient network structure when the types of motions to be learned are diverse. In this paper, we train and compare three types of networks: basic fully-connected structure, mixture of experts structure that uses multiple fully-connected layers in parallel, recurrent neural network which is widely used to deal with seq2seq, and transformer structure used for sequence-type data processing in the natural language processing field.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• 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
• /
• v.76 no.3
• /
• 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
• /
• v.40 no.5
• /
• 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.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.60-65
• /
• 2018

In this paper, a covariance matrix and modulogram are proposed for realizing amphibian sound classification using CNN (Convolutional Neural Network). First of all, a database is established by collecting amphibians sounds including endangered species in natural environment. In order to apply the database to CNN, it is necessary to standardize acoustic signals with different lengths. To standardize the acoustic signals, covariance matrix that gives distribution information and modulogram that contains the information about change over time are extracted and used as input to CNN. The experiment is conducted by varying the number of a convolutional layer and a fully-connected layer. For performance assessment, several conventional methods are considered representing various feature extraction and classification approaches. From the results, it is confirmed that convolutional layer has a greater impact on performance than the fully-connected layer. Also, the performance based on CNN shows attaining the highest recognition rate with 99.07 % among the considered methods.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.758-765
• /
• 2021

Recently, various research on the application of deep learning to video encoding for enhancing coding efficiency are being actively studied. This paper proposes a deep learning based intra prediction which uses multiple models by extending Matrix-based Intra Prediction(MIP) that is a neural network-based technology adopted in VVC. It also presents an efficient learning method for the multi-model intra prediction. To evaluate the performance of the proposed method, we integrated the VVC MIP and the proposed fully connected layer based multi-model intra prediction into HEVC reference software, HM16.19 as an additional intra prediction mode. As a result of the experiments, the proposed method can obtain bit-saving coding gain up to 0.47% and 0.19% BD-rate, respectively, compared to HM16.19 and VVC MIP.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).