• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.4
• /
• pp.302-310
• /
• 2010

In this paper, we studied Bagging neural network for predicting defect size of steam generator(SG) tube in nuclear power plant. Bagging is a method for creating an ensemble of estimator based on bootstrap sampling. For predicting defect size of SG tube, we first generated eddy current testing signals for 4 defect patterns of SG tube with various widths and depths. Then, we constructed single neural network(SNN) and Bagging neural network(BNN) to estimate width and depth of each defect. The estimation performance of SNN and BNN were measured by means of peak error. According to our experiment result, average peak error of SNN and BNN for estimating defect depth were 0.117 and 0.089mm, respectively. Also, in the case of estimating defect width, average peak error of SNN and BNN were 0.494 and 0.306mm, respectively. This shows that the estimation performance of BNN is superior to that of SNN.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.11a
• /
• pp.489-493
• /
• 2004

[ $Ba_2NaNb_5O_{15}$ ]은 orthorhombic tungsten bronze 결정구조를 갖는 강유전체로서, 단결정의 경우 $LiNbO_3$에 비해 우수한 비선형 전광계수 값을 나타내는 것으로 알려져 있으며, 또한 주목할만한 초전, 압전, 강유전특성을 나타내고 있다. 본 연구에서는 다른 강유전체박막에 비하여 상대적으로 연구가 덜 이루어진 BNN 박막을 세라믹 타겟을 사용하여 이온빔 보조 증착법을 사용하여 제조하였으며, $Ar/O_2$ 분위기에서 증착된 BNN 박막에 대한 결정화 및 배향 특성을 고찰하였고, 이에 따른 전기적 특성의 변화를 살펴보았다. 연구에 사용된 기판은 $Pt(100)/TiO_2/SiO_2/Si(100)$이었으며, 이온빔 보조 증착법에서 보조 이온빔의 에너지를 $0{\sim}400eV$로 변화 시키며 BNN 박막을 증착한 후, 열처리하였다. BNN 박막의 전기적 특성은 MFM 박막 커패시터의 형태로 제조하여 강유전 특성에 대해 살펴보았다.

• Journal of Ceramic Processing Research
• /
• v.13 no.spc2
• /
• pp.270-273
• /
• 2012

x mol% (x = 0 ~ 20) Na2CO3 excess Bi2.5Na3.5Nb5O18 (BNN) particles were synthesized using molten salt as a flux. The secondary phases were observed at stoichiometric ratio of BNN precursors and their intensity decreased with increasing Na contents. The results of SEM images showed that all particles existed in a platelet shape and the particle increased in size with higher increasing Na contents. Plate-like NaNbO3 particles were developed using BNN precursor obtained by a topochemical microcrystal conversion. XRD analysis of NaNbO3 particles showed that a single perovskite phase and the intensity of (h00) peaks increased with increasing Na contents in BNN precursor. SEM images showed that the size of plate-like NaNbO3 was significantly changed by controlling Na contents in BNN precursors.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.07b
• /
• pp.739-743
• /
• 2003

[ $Ba_2NaNb_5O_{15}$ ], hereafter BNN, thin films are attractive candidates for nonvolatile memory and electro-optic devices. In the present work, thin films that have different contents of Ba, Nb and Na have been prepared by H-MOD technique on silicon and Pt substrates. XRD and SEM were used to investigate the phase evolution behavior and the microstructure of the films. It was found that the films of about 500nm thick were crack-free and uniform in microstructure. Nb content strongly influenced the phase formation of the films, where unwanted phases were always formed at the stoichiometric BNN composition. However, the unwanted phases decreased with the increase of excess Nb content, and the single phase (tetragonal tungsten bronze structure) BNN thin film was obtained when the niobium content reached some point. From this study, the sub-solidus phase diagram below $850^{\circ}C$ for $BaO-Na_2O-Nb_2O_5$ ternary system is proposed.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.08a
• /
• pp.98-102
• /
• 2003

$Ba_2NaNb_5O_{15}$, hereafter BNN, thin films are attractive candidates for nonvolatile memory and electro-optic devices. In the present work, thin films that have different contents of Ba, Na and Nb have been prepared by H-MOD technique on silicon and Pt substrates. XRD and SEM were used to investigate the phase evolution behavior and the microstructure of the films. It was found that the films of about 450nm thick were crack-free and uniform in microstructure. Nb content strongly influenced the phase formation of the films, where low temperature phase was always formed at the stoichiometric BNN composition. However, the amount of low temperature phase decreased with the increase of excess Nb content, and the single phase (orthorhombic tungsten bronze structure) BNN thin film was obtained at the temperature as low as $750^{\circ}C$ for samples with excess niobium. From this study, the sub-solidus phase diagram below $850^{\circ}C$ for $BaO-Na_2O-Nb_2O_5$ ternary system is proposed.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2726-2728
• /
• 2001

This paper describes an optimal synthesis method of binary neural network(BNN) for an approximation problem of a circular region using a newly proposed learning algorithm[7] Our object is to minimize the number of connections and neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm(NETLA) for the multilayer BNN. The synthesis method in the NETLA is based on the extension principle of Expanded and Truncated Learning(ETL) and is based on Expanded Sum of Product (ESP) as one of the boolean expression techniques. And it has an ability to optimize the given BNN in the binary space without any iterative training as the conventional Error Back Propagation(EBP) algorithm[6] If all the true and false patterns are only given, the connection weights and the threshold values can be immediately determined by an optimal synthesis method of the NETLA without any tedious learning. Futhermore, the number of the required neurons in hidden layer can be reduced and the fast learning of BNN can be realized. The superiority of this NETLA to other algorithms was proved by the approximation problem of one circular region.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.585-594
• /
• 2007

The back propagation algorithm took a long time to learn the input patterns and was difficult to train the additional or repeated learning patterns. So Aleksander proposed the binary neural network which could overcome the disadvantages of BP Network. But it had the limitation of repeated learning and was impossible to extract a generalized pattern. In this paper, we proposed a dynamic 3 dimensional Neuro System which was consisted of a learning network which was based on weightless neural network and a feedback module which could accumulate the characteristic. The proposed system was enable to train additional and repeated patterns. Also it could be produced a generalized pattern by putting a proper threshold into each learning-net's discriminator which was resulted from learning procedures. And then we reused the generalized pattern to elevate the recognition rate. In the last processing step to decide right category, we used maximum response detector. We experimented using the MNIST database of NIST and got 99.3% of right recognition rate for training data.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2002.05a
• /
• pp.273-277
• /
• 2002

This paper describes an optimal synthesis method of binary neural network(BNN) for an approximation problem of a circular region and synthetic image having four class using a newly proposed learning algorithm. Our object is to minimize the number of connections and neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm(NETLA) based on the multilayer BNN. The synthesis method in the NETLA is based on the extension principle of Expanded and Truncated Learning (ETL) learning algorithm using the multilayer perceptron and is based on Expanded Sum of Product (ESP) as one of the boolean expression techniques. The number of the required neurons in hidden layer can be reduced and fasted for learning pattern recognition.. The superiority of this NETLA to other algorithms was proved by simulation.

• Journal of Advanced Navigation Technology
• /
• v.25 no.5
• /
• pp.426-432
• /
• 2021

Continuous wave (CW) Doppler radar has the advantage of being able to solve the privacy problem unlike camera and obtains signals in a non-contact manner. Therefore, this paper proposes a human activity recognition (HAR) system using CW Doppler radar, and presents the hardware design and implementation results for acceleration. CW Doppler radar measures signals for continuous operation of human. In order to obtain a single motion spectrogram from continuous signals, an algorithm for counting the number of movements is proposed. In addition, in order to minimize the computational complexity and memory usage, binarized neural network (BNN) was used to classify human motions, and the accuracy of 94% was shown. To accelerate the complex operations of BNN, the FPGA-based BNN accelerator was designed and implemented. The proposed HAR system was implemented using 7,673 logics, 12,105 registers, 10,211 combinational ALUTs, and 18.7 Kb of block memory. As a result of performance evaluation, the operation speed was improved by 99.97% compared to the software implementation.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.211-218
• /
• 2022

Continuous wave (CW) radar has the advantage of reliability and accuracy compared to other sensors such as camera and lidar. In addition, binarized neural network (BNN) has a characteristic that dramatically reduces memory usage and complexity compared to other deep learning networks. Therefore, this paper proposes binarized neural network based human identification and motion classification system using CW radar. After receiving a signal from CW radar, a spectrogram is generated through a short-time Fourier transform (STFT). Based on this spectrogram, we propose an algorithm that detects whether a person approaches a radar. Also, we designed an optimized BNN model that can support the accuracy of 90.0% for human identification and 98.3% for motion classification. In order to accelerate BNN operation, we designed BNN hardware accelerator on field programmable gate array (FPGA). The accelerator was implemented with 1,030 logics, 836 registers, and 334.904 Kbit block memory, and it was confirmed that the real-time operation was possible with a total calculation time of 6 ms from inference to transferring result.