• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.07a
• /
• pp.37-40
• /
• 2001

This paper presents the modeling methodology of Zinc diffusion process applied for high-speed avalanche photodiode fabrication using neural networks. Three process factors (sealing pressure, amount of Zn$_3$P$_2$ source per volume, and doping concentration of diffused layer) are examined by means of D-optimal design experiment. Then, diffusion rate and doping concentration of Zinc in diffused layer are characterized by a static response model generated by training fred-forward error back-propagation neural networks. It is observed that the process models developed here exhibit good agreement with experimental results.

• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.4
• /
• pp.264-269
• /
• 2016

This paper reports a fundamental study of temperature characteristics of a solar pond with an insulation layer. Further, these characteristics were compared with those of a solar pond without the insulation layer. The governing equation was discretized via finite difference method. The governing equations are two-dimensional unsteady-state second-order partial differential equations. The conclusions of the study are as follows: 1) If the depth of the solar pond was increased, the desired effect of increase in temperature was not produced because the amount of solar insolation received by the bottom of the solar pond decreased. 2) As the temperature of the soil during winter is higher than the temperature of the water in a solar pond, heat was transferred from the soil to the solar pond. 3) For the case of the solar pond with insulation layer, it was estimated that the dependence rate of solar energy was 83.3% and that of the boiler was 16.7%.

• Journal of Practical Engineering Education
• /
• v.14 no.2
• /
• pp.279-285
• /
• 2022

In this paper, as a liberal arts course for non-majors, we developed a basic practice case for convolutional neural networks, which is essential for designing a basic convolutional neural network course curriculum. The developed practice case focuses on understanding the working principle of the convolutional neural network and uses a spreadsheet to check the entire visualized process. The developed practice case consisted of generating supervised learning method image training data, implementing the input layer, convolution layer (convolutional layer), pooling layer, and output layer sequentially, and testing the performance of the convolutional neural network on new data. By extending the practice cases developed in this paper, the number of images to be recognized can be expanded, or basic practice cases can be made to create a convolutional neural network that increases the compression rate for high-quality images. Therefore, it can be said that the utility of this convolutional neural network basic practice case is high.

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.193-200
• /
• 2019

The auto-encoder network which is a good candidate to handle the modeling of the signal strength attenuation is designed for denoising and compensating the distortion of the received data. It provides a non-linear mapping function by iteratively learning the encoder and the decoder. The encoder is the non-linear mapping function, and the decoder demands accurate data reconstruction from the representation generated by the encoder. In addition, the adaptive network width which supports the automatic generation of new hidden nodes and pruning of inconsequential nodes is also implemented in the proposed algorithm for increasing the efficiency of the algorithm. Simulation results show that the proposed method can improve the neural network training surface to achieve the highest possible accuracy of the signal modeling compared with the conventional modeling method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.310-313
• /
• 1996

In this paper, a neural control algorithm is proposed on the automation of adjustment process. The adjustment processes in camcoder production line are modelled, and the processes are adjusted automatically by means of off-line supervisory trained multi-layer neural network. We have made many experiments on the several adjustment processes by using the control algorithm. There are many unexpected troubles to achieve the desirable adjust time in the practical application. To overcome those, some auxiliary algorithms are demanded. As a result, our proposed algorithm has some advantages - simple architecture, easy extraction of the training data without expertises, adaptability to the varying systems, and wide application for the other resemble processes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.216-221
• /
• 2004

This paper describes an optimal synthesis method of binary neural network for pattern recognition. Our objective is to minimize the number of connections and the number of neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm (NETLA) for the multilayered neural networks. The synthesis method in NETLA uses the Expanded Sum of Product (ESP) of the boolean expressions and is based on the multilayer perceptron. It has an ability to optimize a given binary neural network in the binary space without any iterative learning as the conventional Error Back Propagation (EBP) algorithm. Furthermore, NETLA can reduce the number of the required neurons in hidden layer and the number of connections. Therefore, this learning algorithm can speed up training for the pattern recognition problems. The superiority of NETLA to other learning algorithms is demonstrated by an practical application to the approximation problem of a circular region.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.166-169
• /
• 1989

A study for the recognition of the Korean characters by a neural network is presented. To reduce the dimension of the input image data, DC components are extracted from each input image and used as input to the neural net. A multi-layer perceptron with one hidden layer was trained with back-error propagation training algorithm. Its performance is tested for 24 ${\times}$ 24 binary images of Korean characters and the results of several experiments are presented.

• Computers and Concrete
• /
• v.12 no.3
• /
• pp.285-301
• /
• 2013

This paper concentrates on the results of experimental work on tensile strength of self-compacting concrete (SCC) caused by flexure, which is called rupture modulus. The work focused on concrete mixes having water/binder ratios of 0.35 and 0.45, which contained constant total binder contents of 500 $kg/m^3$ and 400 $kg/m^3$, respectively. The concrete mixes had four different dosages of a superplasticizer based on polycarboxylic with and without silica fume. The percentage of silica fume that replaced cement in this research was 10%. Based upon the experimental results, the existing equations for anticipating the rupture modulus of SCC according to its compressive strength were not exact enough. Therefore, it is decided to use artificial neural networks (ANN) for anticipating the rupture modulus of SCC from its compressive strength and workability. The conclusion was that the multi layer perceptron (MLP) networks could predict the tensile strength in all conditions, but radial basis (RB) networks were not exact enough in some circumstances. On the other hand, RB networks were more users friendly and they converged to the final networks quicker.

• Advances in nano research
• /
• v.9 no.4
• /
• pp.237-250
• /
• 2020

An accurate plate theory for assessing sandwich structures is of interest in order to provide precise results. Hence, this paper develops Layer-Wise (LW) theory for reaching precise results in terms of buckling and vibration behavior of Functionally Graded Carbon Nanotube-Reinforced Composite (FG-CNTRC) annular nanoplates. Furthermore, for simulating the structure much more realistic, its edges are elastically restrained against in-plane and transverse displacement. The nano structure is integrated with piezoelectric layers. Four distributions of Single-Walled Carbon Nanotubes (SWCNTs) along the thickness direction of the core layer are investigated. The Differential Quadrature Method (DQM) is utilized to solve the motion equations of nano structure subjected to the electric field. The influence of various parameters is depicted on both critical buckling load and frequency of the structure. The accuracy of solution procedure is demonstrated by comparing results with classical edge conditions. The results ascertain that the effects of different distributions of CNTs and their volume fraction are significant on the behavior of the system. Furthermore, the amount of in-plane and transverse spring coefficients plays an important role in the buckling and vibration behavior of the nano-structure and optimization of nano-structure design.

• Journal of IKEEE
• /
• v.21 no.3
• /
• pp.244-247
• /
• 2017

In this paper, we implemented a convolution neural network using GP-GPU. After defining the structure, CNN performed inferencing using the GP-GPU with 256 threads, which was the previous study, using the weight obtained from the training. Training used Intel i7-4470 CPU and Matlab. Dataset used Daimler Pedestrian Dataset. The GP-GPU is controlled by the PC using PCIe and operates as an FPGA. We assigned a thread according to the depth and size of each layer. In the case of the pooling layer, we used over warpping pooling to perform additional operations on the horizontal and vertical regions. One inferencing takes about 12 ms.