• Journal of the Korean GEO-environmental Society
• /
• v.14 no.9
• /
• pp.31-37
• /
• 2013

In this study installation diameter, interval, area replacement ratio and ground hardness of applicable ground in C.G.S method should be mastered through surrounding ground by conducting modeling. Optimum artificial neural network was selected through the study of the parameter of artificial neural network and prediction model was developed by the relationship with numerical analysis and artificial neural network. As this result, C.G.S pile settlement and ground settlement were found to be equal in terms of diameter, interval, area replacement ratio and ground hardness, presented in a single curve, which means that the behavior pattern of applied ground in C.G.S method was presented as some form, and based on such a result, learning the artificial neural network for 3D behavior was found to be possible. As the study results of artificial neural network internal factor, when using the number of neural in hidden layer 10, momentum constant 0.2 and learning rate 0.2, relationship between input and output was expressed properly. As a result of evaluating the ground behavior of C.G.S method which was applied to using such optimum structure of artificial neural network model, is that determination coefficient in case of C.G.S pile settlement was 0.8737, in case of ground settlement was 0.7339 and in case of ground heaving was 0.7212, sufficient reliability was known.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.65-75
• /
• 2022

Deep learning is used as a creative tool that could overcome the limitations of existing analysis models and generate various types of results such as text, image, and music. In this paper, we propose a method necessary to preprocess audio data using the Niko's MIDI Pack sound source file as a data set and to generate music using Bi-LSTM. Based on the generated root note, the hidden layers are composed of multi-layers to create a new note suitable for the musical composition, and an attention mechanism is applied to the output gate of the decoder to apply the weight of the factors that affect the data input from the encoder. Setting variables such as loss function and optimization method are applied as parameters for improving the LSTM model. The proposed model is a multi-channel Bi-LSTM with attention that applies notes pitch generated from separating treble clef and bass clef, length of notes, rests, length of rests, and chords to improve the efficiency and prediction of MIDI deep learning process. The results of the learning generate a sound that matches the development of music scale distinct from noise, and we are aiming to contribute to generating a harmonistic stable music.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.489-498
• /
• 2023

Advancements in hardware performance and computing technology have facilitated the progress of climate prediction models to address climate change. The Korea Meteorological Administration employs the GloSea6 model with supercomputer technology for operational use. Various universities and research institutions utilize the Low-GloSea6 model, a low-resolution coupled model, on small to medium-scale servers for weather research. This paper presents an analysis using Intel VTune Profiler on Low-GloSea6 to facilitate smooth weather research on small to medium-scale servers. The tri_sor_dp_dp function of the atmospheric model, taking 1125.987 seconds of CPU time, is identified as a hotspot. Nonlinear regression models, a machine learning technique, are applied and compared to existing functions conducting numerical operations. The K-Nearest Neighbors regression model exhibits superior performance with MAE of 1.3637e-08 and SMAPE of 123.2707%. Additionally, the Light Gradient Boosting Machine regression model demonstrates the best performance with an RMSE of 2.8453e-08. Therefore, it is confirmed that applying a nonlinear regression model to the tri_sor_dp_dp function during the execution of Low-GloSea6 could be a viable alternative.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Asian-Australasian Journal of Animal Sciences
• /
• v.22 no.5
• /
• pp.747-755
• /
• 2009

The feed resource for animals is a major cost determinant for profitability in livestock production enterprises, and thus any effort at improving the efficiency of feed use will help to reduce feed cost. Feed conversion ratio, expressed as feed inputs per unit output, is a traditional measure of efficiency that has significant phenotypic and genetic correlations with feed intake and growth traits. The use of ratio traits for genetic selection may cause problems associated with prediction of change in the component traits in future generations. Residual feed intake, a linear index, is a trait derived from the difference between actual feed intake and that predicted on the basis of the requirements for maintenance of body weight and production. Considerable genetic variation exists in residual feed intake for cattle and pigs, which should respond to selection. Phenotypic independence of phenotypic residual feed intake with body weight and weight gain can be obligatory. Genetic residual feed intake is genetically independent of its component traits (body weight and weight gain). Genetic correlations of residual feed intake with daily feed intake and feed conversion efficiency have been strong and positive in both cattle and pigs. Residual feed intake is favorably genetically correlated with eye muscle area and carcass weight in cattle and with eye muscle area and backfat in pigs. Selection to reduce residual feed intake (excessive intake of feed) will improve the efficiency of feed and most of the economically important carcass traits in cattle and pigs. Therefore, residual feed intake can be used to replace traditional feed conversion ratio as a selection criterion of feed efficiency in breeding programs. However, further studies are required on the variation of residual feed intake during different developmental stage of production.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.3
• /
• pp.9-19
• /
• 2015

Internal air temperature of greenhouse is an important variable that can be influenced by the complex interaction between outside weather and greenhouse inside climate. This paper focuses on a data-based model approach to predict internal air temperature of the greenhouse. External air temperature, solar radiation, wind speed and wind direction were measured next to an experimental greenhouse supported by the Electronics and Telecommunications Research Institute and used as input variables for the model. Internal air temperature was measured at the center of three sections of the greenhouse and used as an output variable. The proposed model consisted of a transfer function including the four input variables and tested the prediction accuracy according to the sampling interval of the input variables, the orders of model polynomials and the time delay variable. As a result, a second-order model was suitable to predict the internal air temperature having the predictable time of 20-30 minutes and average errors of less than ${\pm}1K$. Afterwards mechanistic interpretation was conducted based on the energy balance equation, and it was found that the resulting model was considered physically acceptable and satisfied the physical reality of the heat transfer phenomena in a greenhouse. The proposed data-based model approach is applicable to any input variables and is expected to be useful for predicting complex greenhouse microclimate involving environmental control systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.1
• /
• pp.119-126
• /
• 2012

H.264/AVC can use three transforms depending on types of residual data which are to be coded. H.264/AVC always executes $4{\times}4$ DCT transform. In $16{\times}16$ intra mode only, $4{\times}4$ Hadamard transform for luma DC coefficients and $2{\times}2$ Hadamard transform for chroma DC coefficients are performed additionally. Quantization is carried out to achieve further data compression after transform coding is completed. In this paper, the hardware implementation for DCT transform, Hadamard transform and quantization is studied. Especially, the proposed architecture adopting the pipeline technique can output a quantized result per clock cycle after 33-clock cycle latency. The proposed architecture is coded in Verilog-HDL and synthesized using Xilinx 7.1i ISE tool. The operating frequency is 106MHz at SPARTAN3S-1000. The designed IP can process maximum 33-frame at $1920{\times}1080$ HD resolution.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1E
• /
• pp.30-38
• /
• 1995

In this paper, we evaluated the performance of vocoders for three-way conferencing using signal summation technique in digital mobile communication network. The signal summation technique yields natural mode of three-way conferencing, in shich the mixed voice signal from two speakers are transmitted to a third person, though there has been no useful speech coding technique for the mixed voice signal yet. We established Qualcomm code term prediction (RPE-LTP) vocoders to provide three-way conferencing using signal summation techinique. In addition, as the conventional speech quality measures are not applicable to the vocoders for mixed voice signals, we proposed two kinds of subjective quality measures. These are the sentence discrimination (SD) test and the modified degraded mean opinion score (MDMOS) test. The experimental results show that the output speech quality of the VSELP vocoder is superior to other two.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.38 no.5_2
• /
• pp.194-205
• /
• 2010

To predict urban growth according to changes in landcover, probability factors werecal culated and mapped. Topographic, geographic and social and political factors were used as prediction variables for constructing probability maps of urban growth. Urban growth-related factors included elevation, slope, aspect, distance from road,road ratio, distance from the main city, land cover, environmental rating and legislative rating. Accounting for these factors, probability maps of urban growth were constr uctedusing frequency ratio (FR) and logistic regression (LR) methods and the effectiveness of the results was verified by the relative operating characteristic (ROC). ROC values of the urban growth probability index (UGPI) maps by the FR and LR models were 0.937 and 0.940, respectively. The LR map had a slightly higher ROC value than the FR map, but the numerical difference was slight, with both models showing similar results. The FR model is the simplest tool for probability analysis of urban growth, providing a faster and easier calculation process than other available tools. Additionally, the results can be easily interpreted. In contrast, for the LR model, only a limited amount of input data can be processed by the statistical program and a separate conversion process for input and output data is necessary. In conclusion, although the FR model is the simplest way to analyze the probability of urban growth, the LR model is more appropriate because it allows for quantitative analysis.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.11
• /
• pp.1272-1280
• /
• 2008

In this paper, we have proposed a phase noise model of fast frequency hopping synthesizer with DDS Driven PLL architecture. To accurately model the phase noise contribution of noise sources in frequency hopping synthesizer, they were investigated using model of digital divider for PLL, DAC for DDS and Leeson's model for reference oscillator and VCO. Especially it was proposed that the noise component of low pass filter was considered together with the phase noise of VCO. Under assuming linear operation of a phase locked loop, the phase noise transfer functions from noise sources to the output of synthesizer was analyzed by superposition theory. The proposed phase noise prediction model was evaluated and its results were compared with measured data.