• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.269-271
• /
• 2022

In recent years, RNN networks with LSTM blocks have been used extensively in machine learning tasks that process sequential data. These networks have proven to be particularly good at sequential language processing tasks by being more able to accurately predict the next most likely word in a given sequence than traditional neural networks. This study trained an RNN / LSTM neural network on three different translations of 150 biblical Psalms - in both English and Korean. The resulting model is then fed an input word and a length number from which it automatically generates a new Psalm of the desired length based on the patterns it recognized while training. The results of training the network on both English text and Korean text are compared and discussed.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.6
• /
• pp.289-296
• /
• 2018

Drone detection in FMCW radar system needs complex techniques because a drone beat frequency is highly dynamic and unpredictable. Therefore, the current static signal processing algorithms cannot show appropriate detection accuracy. With dynamic signal fluctuation and environmental clutters, it can fail to detect a drone or make false detection. It affects to the radar system integrity and safety. Constant false alarm rate (CFAR), one of famous static signal process algorithm is effective for static environment. But for drone detection, it shows low detection accuracy. In this paper, we suggest neural network based FMCW radar system for detecting a drone. We use recurrent neural network (RNN) because it is the effective neural network for signal processing. In our FMCW radar system, one transmitter emits FMCW signal and four-way fixed receivers detect reflected drone beat frequency. The coordinate of the drone can be calculated with four receivers information by triangulation. Therefore, RNN only learns and inferences reflected drone beat frequency. It helps higher learning and detection accuracy. With several drone flight experiments, RNN shows false detection rate and detection accuracy as 21.1% and 96.4%, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.357-363
• /
• 2023

In underwater signal processing, separating individual signals from mixed signals has long been a challenge due to low signal quality. The common method using Short-time Fourier transform for spectrogram analysis has faced criticism for its complex parameter optimization and loss of phase data. We propose a Triple-path Recurrent Neural Network, based on the Dual-path Recurrent Neural Network's success in long time series signal processing, to handle three-dimensional tensors from multi-channel sensor input signals. By dividing input signals into short chunks and creating a 3D tensor, the method accounts for relationships within and between chunks and channels, enabling local and global feature learning. The proposed technique demonstrates improved Root Mean Square Error and Scale Invariant Signal to Noise Ratio compared to the existing method.

• Journal of Sensor Science and Technology
• /
• v.32 no.3
• /
• pp.174-179
• /
• 2023

Bulk trailers, used for the transportation of powdered materials, such as cement and fly ash, are crucial in the construction industry. The speedy exhaustion of powdered materials stored in the tank of bulk trailers is relevant to improving transportation efficiency and reducing transportation costs. The exhaust time can be reduced by developing an automatic control system to replace the manual exhaust operation. The instantaneous or accumulated exhausts of powdered materials must be measured for automatic control of the bulk trailer exhaust system. Accordingly, we previously proposed a recurrent neural network (RNN) model that estimated the instantaneous exhaust based on low-cost pressure sensor signals without an expensive flowmeter for powders. Although our previous study utilized only an RNN model, models such as multilayer perceptron (MLP) and convolutional neural network (CNN) are also widely utilized for time-series estimation. This study compares the performance of three neural network models (MLP, CNN, and RNN) in estimating instantaneous and accumulated exhausts. In terms of the instantaneous exhaust estimation, the difference in the performance of neural network models was insignificant (that is, 8.64, 8.62, and 8.56% for the MLP, CNN, and RNN, respectively, in terms of the normalized root mean squared error). However, in the case of the accumulated exhaust, the performance was excellent in the order of CNN (1.67%), MLP (2.03%), and RNN (2.20%).

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.1
• /
• pp.21-25
• /
• 1996

In this paper we suggest a general purpose RNN training algorithm which is derived on the optimal control concepts and variational methods. First, learning is regared as an optimal control problem, then using the variational methods we obtain optimal weights which are given by a two-point boundary-value problem. Finally, the modified gradient descent algorithm is applied to RNN for on-line training. This algorithm is intended to be used on learning complex dynamic mappings between time varing I/O data. It is useful for nonlinear control, identification, and signal processing application of RNN because its storage requirement is not high and on-line learning is possible. Simulation results for a nonlinear plant identification are illustrated.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Journal of Information Technology Applications and Management
• /
• v.24 no.1
• /
• pp.111-128
• /
• 2017

Existing studies for recommender have focused on recommending an appropriate item based on the customer preference. However, it has not yet been studied actively to recommend purchase timing for the repurchase product despite of its importance. This study aims to propose MLP and RNN models based on the only simple purchase history data to predict the timing of customer repurchase and compare performances in the perspective of prediction accuracy and quality. As an experiment result, RNN model showed outstanding performance compared to MLP model. The proposed model can be used to develop CRM system which can offer SMS or app based promotion to the customer at the right time. This model also can be used to increase sales for repurchase product business by balancing the level of order as well as inducing repurchase of customer.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.57-65
• /
• 2018

Conventional RF signal-based indoor localization techniques such as BLE or Wi-Fi based fingerprinting method show considerable localization errors even in small-scale indoor environments due to unstable received signal strength(RSS) of RF signals. Therefore, it is difficult to apply the existing RF-based fingerprinting techniques to large-scale indoor environments such as airports and department stores. In this paper, instead of RF signal we use the geomagnetic sensor signal for indoor localization, whose signal strength is more stable than RF RSS. Although similar geomagnetic field values exist in indoor space, an object movement would experience a unique sequence of the geomagnetic field signals as the movement continues. We use a deep neural network model called the recurrent neural network (RNN), which is effective in recognizing time-varying sequences of sensor data, to track the user's location and movement path. To evaluate the performance of the proposed geomagnetic field based indoor positioning system (IPS), we constructed a magnetic field map for a campus testbed of about $94m{\times}26$ dimension and trained RNN using various potential movement paths and their location data extracted from the magnetic field map. By adjusting various hyperparameters, we could achieve an average localization error of 1.20 meters in the testbed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.67-78
• /
• 2017

Traffic congestion cost is increasing annually. Specifically congestion caused by the CDB traffic contains more than a half of the total congestion cost. Recent advancement in the field of Big Data, AI paved the way to industry revolution 4.0. And, these new technologies creates tremendous changes in the traffic information dissemination. Eventually, accurate and timely traffic information will give a positive impact on decreasing traffic congestion cost. This study, therefore, focused on developing both recurrent and non-recurrent congestion prediction models on urban roads by adopting Recurrent Neural Network(RNN), a tribe in machine learning. Two hidden layers with scaled conjugate gradient backpropagation algorithm were selected, and tested. Result of the analysis driven the authors to 25 meaningful links out of 33 total links that have appropriate mean square errors. Authors concluded that RNN model is a feasible model to predict congestion.