• Journal of Korean Society for Atmospheric Environment
• /
• v.31 no.5
• /
• pp.430-436
• /
• 2015

Numerical air quality forecasting suffers from the large uncertainties of input data including emissions, boundary conditions, earth surface properties. Data assimilation has been widely used in the field of weather forecasting as a way to reduce the forecasting errors stemming from the uncertainties of input data. The present study aims at evaluating the effect of input data on the air quality forecasting results in Korea when data assimilation was invoked to generate the initial concentrations. The forecasting time was set to 36 hour and the emissions and initial conditions were chosen as tested input parameters. The air quality forecast model for Korea consisting of WRF and CMAQ was implemented for the test and the chosen test period ranged from November $2^{nd}$ to December $1^{st}$ of 2014. Halving the emission in China reduces the forecasted peak value of $PM_{10}$ and $SO_2$ in Seoul as much as 30% and 35% respectively due to the transport from China for the no-data assimilation case. As data assimilation was applied, halving the emissions in China has a negligible effect on air pollutant concentrations including $PM_{10}$ and $SO_2$ in Seoul. The emissions in Korea still maintain an effect on the forecasted air pollutant concentrations even after the data assimilation is applied. These emission sensitivity tests along with the initial condition sensitivity tests demonstrated that initial concentrations generated by data assimilation using field observation may minimize propagation of errors due to emission uncertainties in China. And the initial concentrations in China is more important than those in Korea for long-range transported air pollutants such as $PM_{10}$ and $SO_2$. And accurate estimation of the emissions in Korea are still necessary for further improvement of air quality forecasting in Korea even after the data assimilation is applied.

• The Korean Journal of Applied Statistics
• /
• v.15 no.1
• /
• pp.33-43
• /
• 2002

Various kinds of estimation methods have been developed for imputation of categorical missing data. They include category method, logistic regression, and association rule. In this study, we propose two fusions algorithms based on both neural network and voting scheme that combine the results of individual imputation methods. A Mont-Carlo simulation is used to compare the performance of these methods. Five factors used to simulate the missing data pattern are (1) input-output function, (2) data size, (3) noise of input-output function (4) proportion of missing data, and (5) pattern of missing data. Experimental study results indicate the following: when the data size is small and missing data proportion is large, modal category method, association rule, and neural network based fusion have better performances than the other methods. However, when the data size is small and correlation between input and missing output is strong, logistic regression and neural network barred fusion algorithm appear better than the others. When data size is large with low missing data proportion, a large noise, and strong correlation between input and missing output, neural networks based fusion algorithm turns out to be the best choice.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• IE interfaces
• /
• v.12 no.4
• /
• pp.551-556
• /
• 1999

In this paper, we compare the performance of three data mining classification algorithms(neural network, decision tree, logistic regression) in consideration of various characteristics of categorical input and output data. $2^{4-1}$. 3 fractional factorial design is used to simulate the comparison situation where factors used are (1) the categorical ratio of input variables, (2) the complexity of functional relationship between the output and input variables, (3) the size of randomness in the relationship, (4) the categorical ratio of an output variable, and (5) the classification algorithm. Experimental study results indicate the following: decision tree performs better than the others when the relationship between output and input variables is simple while logistic regression is better when the other way is around; and neural network appears a better choice than the others when the randomness in the relationship is relatively large. We also use Taguchi design to improve the practicality of our study results by letting the relationship between the output and input variables as a noise factor. As a result, the classification accuracy of neural network and decision tree turns out to be higher than that of logistic regression, when the categorical proportion of the output variable is even.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2415-2423
• /
• 1999

We propose a new optical method which conceals the data of authorized persons by encryption before they are stored or compared in the pattern recognition system for security systems. This proposed security system is made up of two subsystems : a proposed optical encryption system and a pattern recognition system based on the JTC which has been shown to perform well. In this system, each image of authorized persons as a reference image is stored in memory units through the proposed encryption system. And if a fingerprint image is placed in the input plane of this security system for access to a restricted area, the image is encoded by the encryption system then compared with the encrypted reference image. Therefore because the captured input image and the reference data are encrypted, it is difficult to decrypt the image if one does not know the encryption key bit stream. The basic idea is that the input image is encrypted by performing optical XOR operations with the key bit stream that is generated by digital encryption algorithms. The optical XOR operations between the key bit stream and the input image are performed by the polarization encoding method using the polarization characteristics of LCDs. The results of XOR operations which are detected by a CCD camera should be used as an input to the JTC for comparison with a data base. We have verified the idea proposed here with computer simulations and the simulation results were also shown.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.1073-1080
• /
• 1996

The impact of the input and output probability distributions on the performance of neural networks to forecast two year peak stream flow (cubic meters per second) is examined for two major river basins of the US. The neural network input consisted of drainage area(square kilometers ) and elevation (meters). When data are normally distributed , the neural networks predict much better than when the data are non-normal and have larger tails in their distributions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.2
• /
• pp.313-325
• /
• 1996

This paper presents a new architecture for full-search block-matching motion estimation. The architecture is based on linear systolic arrays. High speed operation is obtained by feeding reference data, search data, and control signals into the linear systolic array in a pipelined fashion. Input data are fed into the linear systolic array at a half of the processor speed, reducing the required data bandwidth to half. The proposed architecture has a good scalability with respect to the number of processors and input bandwidth when the size of reference block and search range change.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2019

The proposed model is developed to minimize the loss of information in incomplete data including missing data. The first step is to transform the learning data to compensate for the loss information using the data extension technique. In this conversion process, the attribute values of the data are filled with binary or probability values in one-hot encoding. Next, this conversion data is input to the deep learning model, where the number of entries is not constant depending on the cardinality of each attribute. Then, the entry values of each attribute are assigned to the respective input nodes, and learning proceeds. This is different from existing learning models, and has an unusual structure in which arbitrary attribute values are distributedly input to multiple nodes in the input layer. In order to evaluate the learning performance of the proposed model, various experiments are performed on the missing data and it shows that it is superior in terms of performance. The proposed model will be useful as an algorithm to minimize the loss in the ubiquitous environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.473-476
• /
• 2003

Nowaday, Internet is doing the role of a large distributed information service tenter and various information and database servers managing it are in distributed network environment. However, the we have several difficulties in deciding the server to disposal input data depending on data properties. In this paper, we designed server mining mechanism and Intellectual data mining system architecture for the best efficiently dealing with input data pattern by using neural network among the various data in distributed environment. As a result, the new input data pattern could be operated after deciding the destination server according to dynamic binding method implemented by neural network. This mechanism can be applied Datawarehous, telecommunication and load pattern analysis, population census analysis and medical data analysis.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.11
• /
• pp.1-9
• /
• 1996

In the following paper, new architectural algorithm of clock and data recovery circuit is proposed for 622.08 Mbps optical communication receiver. New algorithm makes use of charge pump PLL using voltage controlled ring oscillator and extracts 8-channel 77.76 MHz clock signals, which are delayed by i/8 (i=1,2, ...8), to convert and recover 8-channel parallel data from 662.08 Mbps MRZ serial data. This circuit includes clock genration block to produce clock signals continuously even if input data doesn't exist. And synchronization of data and clock is doen by the method which compares 1/2 bit delayed onput data and decided dta by extracted clock signals. Thus, we can stabilize frequency and phase of clock signal even if input data is distorted or doesn't exist and simplify receiver architecture compared to traditional receiver's. Also it is possible ot realize clock extraction, data decision and conversion simulataneously. Verification of this algorithm is executed by DESIGN CENTER (version 6.1) using test models which are modelized by analog behavior modeling and digital circuit model, modified to process input frequency sufficiently, in SPICE.