• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07b
• /
• pp.960-964
• /
• 2004

[ $Ba_2NaNb_5O_{15}$ ](BNN) thin films have been prepared by the ion beam sputter deposition (IBSD) method on Pt coated Si substrate at temperature as low as $600^{\circ}C$ XRD, SEM were used to investigate the crystallization and microstructure of the films. It was found that the films were crack-free and uniform in microstructure. The electric properties of thin films were carried out by observation of D-E hysteresis loop, dielectric constant and leakage current. It was found the deposition rate strongly influenced the phase formation of the films, where the phase of $BaNb_2O_6$ was always formed when the deposition rate was high. However, the single phase (tungsten bronze structure ) BNN thin film was obtained with the deposition rate as low as $22{\AA}/min$. The remanent polarization Pr and dielectric constant are about 1-2 ${\mu}C/cm^2$ and $100\sim200$, respectively. It was also founded the electric properties of thin films were influenced by the deposition rate. The Pr and dielectric constant of films increased with the decrease of deposition rate. The effects of annealing temperature and annealing time to the crystallization behavior of films were studied. The crystallization of thin film started at about $600^{\circ}C$. The adequate crystallization was gotten at the temperature of $650^{\circ}C$ when the annealing time is 0.5 hour or at the temperature of $600^{\circ}C$ when the annealing time is long as 6 hours.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.397-404
• /
• 2024

This paper presents the design and implementation results of a Raspberry-Pi-based embedded system with an FPGA accelerator that can detect and classify objects using an FMCW radar sensor for preventing door collision accidents in vehicles. The proposed system performs a radar sensor signal processing and a deep learning processing that classifies objects into bicycles, automobiles, and pedestrians. Since the CNN algorithm requires substantial computation and memory, it is not suitable for embedded systems. To address this, we implemented a lightweight deep learning model, BNN, optimized for embedded systems on an FPGA, and verified the results achieving a classification accuracy of 90.33% and an execution time of 20ms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.201-207
• /
• 2012

A RAM-based neural network is a weightless neural network based on binary neural network(BNN) which is efficient neural network with a one-shot learning. RAM-based neural network has multiful information bits and store counts of training in BNN. Supervised learning based on the RAM-based neural network has the excellent performance in pattern recognition but in pattern categorization with unsupervised learning as unsuitable. In this paper, we propose a unsupervised learning algorithm in the RAM-based neural network to perform pattern categorization. By the proposed unsupervised learning algorithm, RAM-based neural network create categories depending on the input pattern by itself. Therefore, RAM-based neural network for supervised learning and unsupervised learning should proof of all possible complex models. The training data for experiments provided by the MNIST offline handwritten digits which is consist of 0 to 9 multi-pattern.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• 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 Advanced Navigation Technology
• /
• v.26 no.5
• /
• pp.365-372
• /
• 2022

Compared to sensors mainly used in human activity recognition (HAR) systems, inertial measurement unit (IMU) sensors are small and light, so can achieve lightweight system at low cost. Therefore, in this paper, we propose a binary neural network (BNN) based gait pattern analysis system using IMU sensor, and present the design and implementation results of an FPGA-based accelerator for computational acceleration. Six signals for gait are measured through IMU sensor, and a spectrogram is extracted using a short-time Fourier transform. In order to have a lightweight system with high accuracy, a BNN-based structure was used for gait pattern classification. It is designed as a hardware accelerator structure using FPGA for computation acceleration of binary neural network. The proposed gait pattern analysis system was implemented using 24,158 logics, 14,669 registers, and 13.687 KB of block memory, and it was confirmed that the operation was completed within 1.5 ms at the maximum operating frequency of 62.35 MHz and real-time operation was possible.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.103.2-103
• /
• 2002

1. Introduction 2. Structure of BNN 3. Decision of weight value and threshold value 4. Principle of Extension in the ETL algorithm 5. Approximation problem of one circular region 6. Problem of synthetic image having four class 7. Conclusion

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.356-361
• /
• 1998

Neural Networks, modeled succinctly from the real nervous system of a living body, can be categorized into two folds; artificial neural network(ANN) and biological neural network(BNN). While the former has been developed to solve practical problems using function approximation capability, pattern classification) clustering algorithm, etc, the latter has been focused on verifying the information processing capability to which brain research gives an impetus, by mimicking real biological systems. However, BNN suffers Iron severe nonlinearities dealt with. A bridge between two neural networks is chaotic neural network(CNN), which simply delineate the real nor-vous system and comprises almost all the ANN structures by selecting parameters. Main research theme of this area is to develop an explanation tool to clarify the information processing mechanism in biological systems and its extension to engineering applications. The CNN has a Gaussian-shaped refractory function with hysteresis effect and the chaotic responses of it have been observed fur a wide range of parameter space. Through the examination of the coupling effects of excitatory and inhibitory connections, the secrets of information processing and memory structure will appear.

• Proceedings of the Korean Ceranic Society Conference
• /
• 2003.04a
• /
• pp.98.2-98
• /
• 2003

• Proceedings of the Korean Ceranic Society Conference
• /
• 2003.10a
• /
• pp.112.1-112
• /
• 2003