• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.2
• /
• pp.224-233
• /
• 1991

The multilayer expanson of single layer NN (Neural Network) was needed to solve the linear seperability problem as shown by the classic example using the XOR function. The EBP (Error Back Propagation ) learning rule is often used in multilayer Neural Networks, but it is not without its faults: 1)D.Rimmelhart expanded the Delta Rule but there is a problem in obtaining Ca from the linear combination of the Weight matrix N between the hidden layer and the output layer and H, wich is the result of another linear combination between the input pattern and the Weight matrix M between the input layer and the hidden layer. 2) Even if using the difference between Ca and Da to adjust the values of the Weight matrix N between the hidden layer and the output layer may be valid is correct, but using the same value to adjust the Weight matrixd M between the input layer and the hidden layer is wrong. Recognitron III was proposed to solve these faults. According to simulation results, since Recognitron III does not learn the three layer NN itself, but divides it into several single layer NNs and learns these with learning patterns, the learning time is 32.5 to 72.2 time faster than EBP NN one. The number of patterns learned in a EBP NN with n input and output cells and n+1 hidden cells are 2**n, but n in Recognitron III of the same size. [5] In the case of pattern generalization, however, EBP NN is less than Recognitron III.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.10 no.3
• /
• pp.240-250
• /
• 2010

Double Gate MOSFETs (DG MOSFETs) with doping in one or two thin layers of an otherwise intrinsic channel are simulated to obtain the transport characteristics, threshold voltage and leakage current. Two different device structures- one with doping on two layers near the top and bottom oxide layers and another with doping on a single layer at the centre- are simulated and the variation of device parameters with a change in doping concentration and doping layer thickness is studied. It is observed that an n-doped layer in the channel reduces the threshold voltage and increases the drive current, when compared with a device of undoped channel. The reduction in the threshold voltage and increase in the drain current are found to increase with the thickness and the level of doping of the layer. The leakage current is larger than that of an undoped channel, but less than that of a uniformly doped channel. For a channel with p-doped layer, the threshold voltage increases with the level of doping and the thickness of the layer, accompanied with a reduction in drain current. The devices with doped middle layers and doped gate layers show almost identical behavior, apart from the slight difference in the drive current. The doping level and the thickness of the layers can be used as a tool to adjust the threshold voltage of the device indicating the possibility of easy fabrication of ICs having FETs of different threshold voltages, and the rest of the channel, being intrinsic having high mobility, serves to maintain high drive current in comparison with a fully doped channel.

• Journal of Mechanical Science and Technology
• /
• v.16 no.10
• /
• pp.1303-1313
• /
• 2002

Effects of the reduced frequency of upstream wake on downstream unsteady boundary layer flow were simulated by using a Wavier-Stokes code. The Wavier-Stokes code is based on an unstructured finite volume method and uses a low Reynolds number turbulence model to close the momentum equations. The geometry used in this paper is the MIT flapping foil experimental set-up and the reduced frequency of the upstream wake is varied in the range of 0.91 to 10.86 to study its effect on the unsteady boundary layer flow. Numerical solutions show that they can be divided into two categories. One is so called the low frequency solution, and behaves quite similar to a Stokes layer. Its characteristics is found to be quite similar to those due to either a temporal or spatial wave. The low frequency solutions are observed clearly when the reduced frequency is smaller than 3.26. The other one is the high frequency solution. It is observed for the reduced frequency larger than 7.24. It shows a sudden shift of the phase angle of the unsteady velocity around the edge of the boundary layer. The shift of phase angle is about 180 degree, and leads to separation of the boundary layer flow from corresponding outer flow. The high frequency solution shows the characteristics of a temporal wave whose wave length is half of the upstream frequency. This characteristics of the high frequency solution is found to be caused by the strong interaction between unsteady vortices. This strong interaction also leads to destroy of the upstream wake strips inside the viscous sublayer as well as the buffer layer.

• Journal of Navigation and Port Research
• /
• v.32 no.8
• /
• pp.589-596
• /
• 2008

In this paper, Artificial Neural Network(ANN) is applied to automatic berthing control for a ship. ANN is suitable for a maneuvering such as ship's berthing, because it can describe non-linearity of the system. Multi-layer perceptron which has more than one hidden layer between input layer and output layer is applied to ANN. Using a back-propagation algorithm with teaching data, we trained ANN to get a minimal error between output value and desired one. For the automatic berthing control of a containership, we introduced low speed maneuvering mathematical models. The berthing control with the structure of 8 input layer units in ANN is compared to 6 input layer units. From the simulation results, the berthing conditions are satisfied, even though the berthing paths are different.

• Ocean and Polar Research
• /
• v.27 no.2
• /
• pp.115-123
• /
• 2005

Recently, it has been observed in the East Sea that temperature increases below the thermocline, and dissolved oxygen increase in the intermediate layer but decrease below it. The layer of minimum dissolved oxygen deepens and the bottom homogeneous layer in oxygen becomes thinner. It emerges very probably that these changes are induced by the mode change of deep water formation associated with global warming. To further support this hypothesis, a one-dimensional model experiment is performed. First, a thermal profile is obtained by injecting a cold and high oxygen deep water into the bottom layer, say the bottom mode. Then, two thermal profiles are obtained from the bottom mode profile by assuming that either all the deep water introduce into the intermediate layer has been initiated, say the intermediate mode, or that only a part of the deep water has been initiated into the intermediate layer, say the intermediate-bottom mode. The results, from the intermediate-bottom mode experiment are closest to the observed results. They show quite well the tendency for oxygen to increase in the intermediate layer and the simultaneous thinning of the bottom homogeneous layer in oxygen. Therefore, it can be said that the recently observed slow variation of the thermal structure might be associated with changes in the deep water formation from the bottom mode to the intermediate-bottom mode.

• Nutrition Research and Practice
• /
• v.17 no.6
• /
• pp.1255-1266
• /
• 2023

BACKGROUND/OBJECTIVES: This study aimed to predict the association between nutritional intake and diabetes mellitus (DM) by developing an artificial neural network (ANN) model for older adults. SUBJECTS/METHODS: Participants aged over 65 years from the 7th (2016-2018) Korea National Health and Nutrition Examination Survey were included. The diagnostic criteria of DM were set as output variables, while various nutritional intakes were set as input variables. An ANN model comprising one input layer with 16 nodes, one hidden layer with 12 nodes, and one output layer with one node was implemented in the MATLAB^® programming language. A sensitivity analysis was conducted to determine the relative importance of the input variables in predicting the output. RESULTS: Our DM-predicting neural network model exhibited relatively high accuracy (81.3%) with 11 nutrient inputs, namely, thiamin, carbohydrates, potassium, energy, cholesterol, sugar, vitamin A, riboflavin, protein, vitamin C, and fat. CONCLUSIONS: In this study, the neural network sensitivity analysis method based on nutrient intake demonstrated a relatively accurate classification and prediction of DM in the older population.

• Journal of Information Display
• /
• v.4 no.1
• /
• pp.29-33
• /
• 2003

We have investigated the effects of hole-injection buffer layer in organic light-emitting diodes using copper phthalocyanine (CuPc), poly(vinylcarbazole)(PVK), and Poly(3,4-ethylene dioxythiophene):poly(styrenesulfonate) (PEDOT: PSS) in a device structure of $ITO/bufferr/TPD/Alq_3/Al$. Polymer PVK and PEDOT:PSS buffer layer were produced using the spin casting method where as the CuPc layer was produced using thermal evaporation. Current-voltage characteristics, luminance-voltage characteristics and efficiency of device were measured at room temperature at various a thickness of the buffer layer. We observed an improvement in the external quantum efficiency by a factor of two, four, and two and half when the CuPc, PVK, and PEDOT:PSS buffer layer were used, respectively. The enhancement of the efficiency is assumed to be attributed to the improved balance of holes and elelctrons resulting from the use of hole-injection buffer layer. The CuPc and PEDOT:PSS layer function as a hole-injection supporter and the PVK layer as a hole-blocking one.

• 한국기계연구소 소보
• /
• s.9
• /
• pp.141-151
• /
• 1982

An iterative procedure for the calculation of the thick axisymmetric boundary layer and wake near the stern of a body of revolution is presented. Procedure consists of the potential flow calculation by a method of the integral equation of first kind and the calculation of boundary layer and wake by a differential me¬thod of the boundary layer theory. Additionally, higher order terms are included in the conventional momentum equations and continuity equation for the consider¬ation of the characteristics of axisymmetric flow different from the one of two dimentional flow and the thick boundary layer. These solutions are matched at the edge of boundary layer and wake. The results obtained by the present me¬thod are compared with the experimental data and it is found that the nominal wake distribution at the propeller plane of a axisymmetric body is in good agree¬ment with the experiment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.1
• /
• pp.17-32
• /
• 1996

In this paper, a model for two-layered video traffic is proposed. The performance analysis of the proposed model and the effects of two-layer coding scehemes in ATM networks are also studied. ATM-based networks give the possibility to support image codingat variable bit rate(VBR). Two layer coding is one of the very promising methods among many proposed methods to compensate the cell loss, the major drawback in ATM networks. From the experimental data of the 2-layer coded video traffics, it is observed that traffic patterns of base layer and enhanced layer are highly correlate to each other, when constant image quality is kept. With this observation, coded two layered video traffic can be modeled as 2-dimensional Markov chain. The model well fit the real experimental data. The model was used for the analysis of the performance of statistical multiplexer with priorites in ATM networks.

• Journal of the Korean Ceramic Society
• /
• v.36 no.10
• /
• pp.1087-1093
• /
• 1999

Bioglass which is one of the surface active bionmaterials has a good biocompatibility but a poor mechanical strength, In the present work therefore two types of fluoride-containing bioglasses were coated on an alumina to improve mechanical strength. Crystallization of the coating layer and the hydroxyapatite formation on the bioactive glass coatings in tris-buffer solution were studied. When bioactive glass coated alumina was heat-treated Na2CaSi3O8 crystal was formed on the layer at lower temperature while wollastonite(CaSIO3) was obtained at higher temperature. Hydroxyapatite forming rate on the coating layer with Na2CaSi3O8 crystal was delayed with SiO2 contents in glass composition. However the hydroxyapatite was developed in 20minutes regardless SiO2 contents when the coating layer crystallized into wollastonite. More amount of P3+ ions were leached out of the coating layer with wollastonite than that with Na2CaSi3O8 crystal while Na+ and Ca2+ ions were leached out more easily from the Na2CaSi3O8 crystal containing coating layer.