• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.2
• /
• pp.143-146
• /
• 2017

In this paper, a novel approach is proposed to improve the performance of speech/music classification using the recurrent neural network (RNN) in the enhanced voice services (EVS) of 3GPP for hearing aids. Feature vectors applied to the RNN are selected from the relevant parameters of the EVS for efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and large speech/music data. The proposed algorithm yields better results compared with the conventional scheme implemented in the EVS.

• Journal of the Korean Society of Visualization
• /
• v.19 no.1
• /
• pp.57-61
• /
• 2021

In order to determine erythrocyte sedimentation rate (ESR) indicating acute phase inflammation, a Westergren method has been widely used because it is cheap and easy to be implemented. However, the Westergren method requires quite a long time for 1 hour. In this study, a gated recurrent unit (GRU) neural network was used to reduce measurement time of ESR evaluation. The sedimentation sequences of the erythrocytes were acquired by the camera and data processed through image processing were used as an input data into the neural network models. The performance of a proposed models was evaluated based on mean absolute error. The results show that GRU model provides best accurate prediction than others within 30 minutes.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.399-402
• /
• 2007

뇌 속 뉴런들의 네트워크는 근본적으로 recurrent neural networks(RNNs)의 형태를 지닌다. 이 논문에서는 반복되는 뉴런 반응 패턴들 사이의 관계를 네트워크에 저장함으로써 생물의 기억이 생성된다는 가정하에, 이를 표현할 수 있는 RNN 모델을 제안하였고, evolutionary algorithm을 통해 이러한 여러 쌍의 기억들이 저장된 네트워크가 존재할 수 있음을 보였다.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.50-53
• /
• 2017

Not only growth of importance to understanding economic trends, but also the prediction to overcome the uncertainty is coming up for long-term maritime recession. This paper discussed about the prediction of BDI with artificial neural networks (ANN). ANN is one of emerging applications that can be the finest solution to the knotty problems that may not easy to achieve by humankind. Proposed a prediction by implementing neural networks that have recurrent architecture which are a Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). And for the reason of comparison, trained Multi Layer Perceptron (MLP) from 2009.04.01 to 2017.07.31. Also made a comparison with conventional statistics, prediction tools; ARIMA. As a result, recurrent net, especially RNN outperformed and also could discover the applicability of LSTM to specific time-series (BDI).

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.179-184
• /
• 2021

In this paper, we propose the deep learning-based neural network model to predict bunker price. In the shipping industry, since fuel oil accounts for the largest portion of ship operation costs and its price is highly volatile, so companies can secure market competitiveness by making fuel oil purchasing decisions based on rational and scientific method. In this paper, short-term predictive analysis of HSFO 380CST in Singapore is conducted by using three recurrent neural network models like RNN, LSTM, and GRU. As a result, first, the forecasting performance of RNN models is better than LSTM and GRUs using long-term memory, and thus the predictive contribution of long-term information is low. Second, since the predictive performance of recurrent neural network models is superior to the previous studies using econometric models, it is confirmed that the recurrent neural network models should consider nonlinear properties of bunker price. The result of this paper will be helpful to improve the decision quality of bunker purchasing.

• Journal of Information Technology Applications and Management
• /
• v.25 no.2
• /
• pp.73-90
• /
• 2018

Despite of increasing studies for product recommendation, the recommendation of product repurchase timing has not yet been studied actively. This study aims to propose deep neural network models usingsimple purchase history data to predict the repurchase timing of each customer and compare performances of the models from the perspective of prediction quality, including expected ROI of promotion, variability of precision and recall, and diversity of target selection for promotion. As an experiment result, a recurrent neural network (RNN) model showed higher promotion ROI and the smaller variability compared to MLP and other models. The proposed model can be used to develop a CRM system that can offer SMS or app-based promotionsto the customer at the right time. This model can also be used to increase sales for product repurchase businesses by balancing the level of ordersas well as inducing repurchases by customers.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.640-645
• /
• 2004

This paper proposes a direct adaptive control method using self-recurrent wavelet neural network (SRWNN) for stable path tracking of mobile robots. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). Unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN has the ability to store the past information of the wavelet. For this ability of the SRWNN, the SRWNN is used as a controller with simpler structure than the WNN in our on-line control process. The gradient-descent method with adaptive learning rates (ALR) is applied to train the parameters of the SRWNN. The ALR are derived from discrete Lyapunov stability theorem, which are used to guarantee the stable path tracking of mobile robots. Finally, through computer simulations, we demonstrate the effectiveness and stability of the proposed controller.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• Journal of Korea Water Resources Association
• /
• v.51 no.12
• /
• pp.1217-1227
• /
• 2018

This paper aims to evaluate the applicability of dam inflow prediction model using recurrent neural network theory. To achieve this goal, the Artificial Neural Network (ANN) model and the Elman Recurrent Neural Network(RNN) model were applied to hydro-meteorological data sets for the Soyanggang dam and the Chungju dam basin during dam operation period. For the model training, inflow, rainfall, temperature, sunshine duration, wind speed were used as input data and daily inflow of dam for 10 days were used for output data. The verification was carried out through dam inflow prediction between July, 2016 and June, 2018. The results showed that there was no significant difference in prediction performance between ANN model and the Elman RNN model in the Soyanggang dam basin but the prediction results of the Elman RNN model are comparatively superior to those of the ANN model in the Chungju dam basin. Consequently, the Elman RNN prediction performance is expected to be similar to or better than the ANN model. The prediction performance of Elman RNN was notable during the low dam inflow period. The performance of the multiple hidden layer structure of Elman RNN looks more effective in prediction than that of a single hidden layer structure.