• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07a
• /
• pp.292-295
• /
• 2004

The SIT was introduced by Nishizawa. in 1972. When compared with high-voltage, power bipolar junction transistors, SITs have several advantages as power switching devices. They have a higher input impedance than do bipolar transistors and a negative temperature coefficient for the drain current that prevents thermal runaway, thus allowing the coupling of many devices in parallel to increase the current handling capability. Furthermore, the SIT is majority carrier device with a higher inherent switching speed because of the absence of minority carrier recombination, which limits the speed of bipolar transistors. This also eliminates the stringent lifetime control requirements that are essential during the fabrication of high-speed bipolar transistors. This results in a much larger safe operating area(SOA) in comparison to bipolar transistors. In this paper, vertical SIT structures are proposed to improve their electrical characteristics including the blocking voltage. Besides, the two dimensional numerical simulations were carried out using ISE-TCAD to verify the validity of the device and examine the electrical characteristics. A trench gate region oxide power SIT device is proposed to improve forward blocking characteristics. The proposed devices have superior electrical characteristics when compared to conventional device. Consequently, the fabrication of trench oxide power SIT with superior stability and electrical characteristics is simplified.

• International Journal of Highway Engineering
• /
• v.11 no.4
• /
• pp.17-23
• /
• 2009

Deformational characteristics of subgrade soils are very important input parameters for pavement design. It is necessary to make an amount of effort to estimate experimentally the modulus of subgrade soils. In case of designing simple (or lower level) pavement section, the estimation of the modulus based on experiments must cause an excessive cost. It has proposed various empirical correlation models to estimate the modulus from basic properties of the materials or more simple alternative tests. Seven subgrade soils in Korea were tested in this study. It was founded that the deformational characteristics of subgrade soils in Korea has a close relation to strength characteristics, the empirical correlation model was proposed. There was a close relation between cohesion value and modulus at low confining stress ($r^2=0.93$). By comparing with the measured modulus and the modulus determined by proposed correlation model from strength characteristics, the value of the coefficient of determination ($r^2$) is 0.75.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.9
• /
• pp.4095-4100
• /
• 2011

In this paper, a log periodic bow-tie dipole array (LPBDA) antenna for UWB communications is investigated. Bow-tie shaped dipole elements are used instead of general dipole elements for LPDA antennas and the input reflection coefficient and realized gain characteristics of the LPBDA as a function of a flare angle are analyzed. It turns out that as the flare angle of the bow-tie dipole elements is increased, the lowest operating frequency is shifted toward lower frequency and the operating frequency band is increased, but the average gain is decreased. However, the gain variation of the LPBDA is much decreased and the front-back ratio is improved compared to the LPDA. Standard LPDA and LPBDA with a flare angle of 13 degrees are fabricated on an FR4 substrate with a dielectric constant of 4.4 and a thickness of 1.6 mm. Measured gain for the LPDA ranges from 4 to 6.5 dBi at 3.1 to 10.6 GHz band, while that for the LPBDA is in the range of 4.2 to 5 dBi.

• Journal of Advanced Navigation Technology
• /
• v.24 no.4
• /
• pp.299-304
• /
• 2020

This paper proposes the design of circular sector shaped power divider-combiner with a planar structure. This structure can be constructed in series, and due to the circular sector shape, it is possible to simplify circuit configuration and improve the amplitude and phase balanced characteristics of the output. It has a simple input matching circuit and an RC parallel circuit was inserted between the output ports to improve the reflection coefficient and isolation of the output. Since the designed divider-combiner are structurally designed in a symmetrical shape of a sector, even if the output ports are composed of two or four output ports, they have excellent characteristics with an amplitude balance of ± 0.1 dB and a phase balance of ± 1o between outputs. To prove these characteristics, it was confirmed that the characteristics of the planar power divider-combiner fabricated at an operating frequency of 2 GHz are in good agreement with the simulation.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.7
• /
• pp.213-220
• /
• 2020

The convolutional neural network is composed of convolutional layers and fully connected layers. The nonlinear activation function is used in each layer of the convolutional layer and the fully connected layer. The activation function being used in a neural network is a function that simulates the method of transmitting information in a neuron that can transmit a signal and not send a signal if the input signal is above a certain criterion when transmitting a signal between neurons. The conventional activation function does not have a relationship with the loss function, so the process of finding the optimal solution is slow. In order to improve this, an agile activation function that generalizes the activation function is proposed. The agile activation function can improve the performance of the deep neural network in a way that selects the optimal agile parameter through the learning process using the primary differential coefficient of the loss function for the agile parameter in the backpropagation process. Through the MNIST classification problem, we have identified that agile activation functions have superior performance over conventional activation functions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.735-740
• /
• 2012

In this paper, we introduce design methodologies of polynomial radial basis function neural network classifier with the aid of Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA). By minimizing the information loss of given data, Feature data is obtained through preprocessing of PCA and LDA and then this data is used as input data of RBFNNs. The hidden layer of RBFNNs is built up by Fuzzy C-Mean(FCM) clustering algorithm instead of receptive fields and linear polynomial function is used as connection weights between hidden and output layer. In order to design optimized classifier, the structural and parametric values such as the number of eigenvectors of PCA and LDA, and fuzzification coefficient of FCM algorithm are optimized by Artificial Bee Colony(ABC) optimization algorithm. The proposed classifier is applied to some machine learning datasets and its result is compared with some other classifiers.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.537-547
• /
• 2010

The importance of vegetation in studies of global climate and biogeochemical cycles is well recognized. Especially. the FPAR (fraction of photosynthetically active radiation) is one of the important parameters in ecosystem productivity and carbon budget models. Therefore, accurate estimates of vegetation parameters are increasingly important in environmental impact assessment studies. In this study, optical FPAR using the Terra MODIS (MODerate resolution Imaging Spectroradiometer), SPOT VEGETATION and ECOCLIMAP data reproduced on the Korean peninsula. We applied the empirical method which is usually estimated as a linear or nonlinear function of vegetation indices. As results, we estimated the accurate expression which is 0.9039 of $R^2$ in cropland and 0.7901 of $R^2$ in forest. Finally, this study could be demonstrated to calibrate that produced FPAR while the overall pattern and random noise through the comparative analysis of FPAR on the reference data. Optimal use of input parameter on the Korean peninsula should be helping the accuracy of output as well as the improved quality of research.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.398-398
• /
• 2015

To estimate and forecast runoff by using Aritifitial Neaural Networks model (ANNs). it has been studied in Thailand for the past 10 years. The model was developed in order to be conformed with the conditions in which the collected dataset is short and the amount of dataset is inadequate. Every year, the Northerpart of Thailand faces river overflow and flood inundation. The most important basin in this area is Yom basin. The purpose of this study is to forecast runoff at Y.14 gauge station (Si-Satchanalai district, Sukhothai province) for 3 days in advance. This station located at the upstream area of Yom River basin. Daily rainfall and daily runoff from Royal Irrigation Department and Meteorological Department during flood period 2000-2012 were used as input data. In order to check an accuracy of forecasting, forecasted runoff were compared with observed data by pursuing Nash Sutcliffe Efficiency (NSE) and Coefficient of Determination ($R^2$). The result of the first day gets the highest accuracy and then decreased in day 2 and day 3, consequently. NSE and $R^2$ values for frist day of runoff forecasting is 0.76 and 0.776, respectively. On the second day, those values are 0.61 and 0.65, respectively. For the third day, the aforementioned valves are 0.51 and 0.52, respectively. The results confirmed that the ANNs model can be used when the range of collected dataset is short and insufficient. In conclusion, the ANNs model is suitable for applying during flood incident because it is easy to use and does not require numerous parameters for simulating.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.259-259
• /
• 2016

This study examined Artificial Neurons Networks model (ANNs) for forecast flash discharge at Southern part of Thailand by using rainfall data and discharge data. The Sungai Kolok River Basin has meant the border crossing between Thailand and Malaysia which watershed drains an area lies in Thailand 691.88 square kilometer from over all 2,175 square kilometer. The river originates in mountainous area of Waeng district then flow through Gulf of Thailand at Narathiwat Province, which the river length is approximately 103 kilometers. Almost every year, flooding seems to have increased in frequency and magnitude which is highly non-linear and complicated phenomena. The purpose of this study is to forecast runoff on Sungai Kolok at X.119A gauge station (Sungai Kolok district, Narathiwat province) for 3 days in advance by using Artificial Neural Networks model (ANNs). 3 daily rainfall stations and 2 daily runoff station have been measured by Royal Irrigation Department and Meteorological Department during flood period 2000-2014 were used as input data. In order to check an accuracy of forecasting, forecasted runoff were compared with observed data by pursuing Coefficient of determination ($R^2$). The result of the first day gets the highest accuracy and then decreased in day 2 and day 3, consequently. $R^2$values for first day, second day and third day of runoff forecasting is 0.71, 0.62 and 0.49 respectively. The results confirmed that the ANNs model can be used when the range of collected dataset is short and real-time operated. In conclusion, the ANNs model is suitable to runoff forecasting during flood incident of Sungai Kolok river because it is straightforward model and require with only a few parameters for simulation.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.257-269
• /
• 2021

The purpose of this study is to collect biosignal data in a non-invasive and non-restrictive manner using a BCG (Ballistocardiogram) sensor, and utilize artificial intelligence machine learning algorithms in ICT and high-performance computing environments. And it is to present and study a method for developing and validating a data-based blood glucose prediction model. In the blood glucose level prediction model, the input nodes in the MLP architecture are data of heart rate, respiration rate, stroke volume, heart rate variability, SDNN, RMSSD, PNN50, age, and gender, and the hidden layer 7 were used. As a result of the experiment, the average MSE, MAE, and RMSE values of the learning data tested 5 times were 0.5226, 0.6328, and 0.7692, respectively, and the average values of the validation data were 0.5408, 0.6776, and 0.7968, respectively, and the coefficient of determination (R²) was 0.9997. If research to standardize a model for predicting blood sugar levels based on data and to verify data set collection and prediction accuracy continues, it is expected that it can be used for non-invasive blood sugar level management.