• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.86-94
• /
• 2010

In this paper, we propose spatially adaptive color demosaicing of noisy Bayer data. When sensor noises are not considered in demosaicing, they may degrade result image. In order to obtain high resolution image, sensor noises are considered in the color demosaicing step. We identify flat, edge and pattern regions at each pixel location to improve the performance of the algorithm and to reduce complexity. Based on the pre-classified regions, the demosaicing of the G channel is performed using the local statistics to reduce the interpolation error. The sensor noise is simultaneously removed by a modified version of non-local mean filter in the green and in the color difference domain. The R and B channels are interpolated easily using fully interpolated and denoised G and color difference values. Experimental results show that the proposed method achieves a significant improvement in terms of visual and numerical criteria, when compared to conventional methods.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1119-1126
• /
• 2002

In this paper, we propose two predictive spatial data mining based on spatial statistics and apply for predicting the forest fire hazardous area. These are conditional probability and likelihood ratio methods. In these approaches, the prediction models and estimation procedures are depending un the basic quantitative relationships of spatial data sets relevant forest fire with respect to selected the past forest fire ignition areas. To make forest fire hazardous area prediction map using the two proposed methods and evaluate the performance of prediction power, we applied a FHR (Forest Fire Hazard Rate) and a PRC (Prediction Rate Curve) respectively. In comparison of the prediction power of the two proposed prediction model, the likelihood ratio method is mort powerful than conditional probability method. The proposed model for prediction of forest fire hazardous area would be helpful to increase the efficiency of forest fire management such as prevention of forest fire occurrence and effective placement of forest fire monitoring equipment and manpower.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.525-531
• /
• 2009

Data mining is the process of extracting hidden patterns from collected data. At this time, for collected data which take important role as the basic information for prediction and recommendation, the process to discriminate incorrect data in order to enhance the performance of analysis result, is needed. The existing methods to discriminate unexpected data from collected data, mainly relies on methods which are based on statistics or simple distance between data. However, for these methods, the problematic point that even meaningful data could be excluded from analysis due that the environment and characteristic of the relevant data are not considered, exists. This study proposes a method to endow human heuristic knowledge with weight value through the comparison between collected data and human heuristic knowledge, and to use the value for creating a decision tree. The data discrimination by the method proposed is more credible as human knowledge is reflected in the created tree. The validity of the proposed method is verified through an experiment.

• Journal of the Korean Society for information Management
• /
• v.32 no.2
• /
• pp.221-236
• /
• 2015

This paper describes the process and methodology followed in developing the Android-based LG Sangnam Audiobook service and an evaluation of its usefulness to the public. The methods included a survey of user needs, analysis of usage statistics, and user interviews. The study found that visually impaired users: 1) were greatly interested and willing to use smartphones if there were no barrier in cost and access; 2) preferred downloads to streaming services; 3) did not mind performance differences between real and TTS (text-to-speech) voices; 4) showed marked differences in book preferences according to age, 5) made about 14,000 downloads in 2014; and 6) indicated bookmarking and moving between pages and tables of content as the most important functions in using audiobooks.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.741-750
• /
• 2011

In this paper, we derive an software mixed debugging model based on a Markov process, assuming that the length of time to perform the debugging is random and its distribution may depend on the fault type causing the failure. We assume that the debugging process starts as soon as a software failure occurs, and either a perfect debugging or an imperfect debugging is performed upon each fault type. One type is caused by a fault that is easily corrected and in this case, the perfect debugging process is performed. An Imperfect debugging process is performed to fix the failure caused by a fault that is difficult to correct. Distribution of the first passage time and working probability of the software system are obtained; in addition, an availability function of a software system which is the probability that the software is in working at a given time, is derived. Numerical examples are provided for illustrative purposes.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.179-188
• /
• 2008

This study was performed as part of the development of the payment adjustment regulations for ensuring high performance of concrete pavements. The objectives of this study were to develop the reasonable quality measurement approaches for the implementation of the payment adjustment regulations and to propose the methods to determine the quality dependent pay factors. First, by using the statistics the slab thickness measurement data was analyzed and the methods to determine the allowable measurement errors, the proper measurement spacing, and the selection of the measurement location were proposed. In addition, to suggest the reasonable methods to determine the pay factors, by using the data of the slab thickness and concrete flexural strength, the pay factors based on the PWL(Percent Within Limits) method used in the USA were compared with those obtained considering the normal probability distribution and t distribution. Finally, the most appropriate method to determine the pay factors was proposed.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.569-578
• /
• 2020

By estimating conditional quantile functions of the response, quantile regression (QR) can provide comprehensive information of the relationship between the response and the predictors. In addition, kernel quantile regression (KQR) estimates a nonlinear conditional quantile function in reproducing kernel Hilbert spaces generated by a positive definite kernel function. However, it is infeasible to use the KQR in analysing a massive data due to the limitations of computer primary memory. We propose a divide and conquer based KQR (DC-KQR) method to overcome such a limitation. The proposed DC-KQR divides the entire data into a few subsets, then applies the KQR onto each subsets and derives a final estimator by aggregating all results from subsets. Simulation studies are presented to demonstrate the satisfactory performance of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.9B
• /
• pp.908-913
• /
• 2009

Mobile phones became important household appliance that cannot be without in our daily lives. And the short messaging service (SMS) in these mobile phones is 1.5 to 2 times more than the voice service. However, the spam filtering functions installed in mobile phones take a method to receive specific number patterns or words and recognize spam messages when those numbers or words are present. However, this method cannot properly filters various types of spam messages currently dispatched. This paper proposes a more powerful and more adaptive spam filtering system using SVM and thesaurus. The system went through a process of isolating words from sample data through pro-processing device and integrating meanings of isolated words using a thesaurus. Then it generated characteristics of integrated words through the chi-square statistics and studied the characteristics. The proposed system is realized in a Window environment and the performance is confirmed through experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.6C
• /
• pp.480-486
• /
• 2008

The high peak-to-average power ratio (PAPR) of the transmitted signals is one of major drawbacks of the orthogonal frequency division multiplexing (OFDM). A partial transmit sequences (PTS) technique can improve the PAPR statistics of OFDM signals. However, in a PTS technique, the search complexity to select phase weighting factors increases exponentially with the number of sub-blocks. In this paper, a PTS technique with low computational complexity is presented, which adopts micro-genetic algorithm(${\mu}$-GA) as a search algorithm. A search on the phase weighting factors starts with a population of five randomly generated individuals. An elite having the largest fitness value and the other four individuals selected through the tournament selection strategy are determined, and then the next generation members are generated through the crossover operations among those. If the new generation converges, all the four individuals except the elite are randomly generated again. The search terminates when there has been no improvements on the PAPR during the predefined number of generations, or the maximum number of generations has been reached. To evaluate the performance of the proposed PTS technique, the complementary cumulative distribution functions (CCDF) of the PAPR are compared with those of the conventional PTS techniques.

• Korean Journal of Clinical Pharmacy
• /
• v.3 no.1
• /
• pp.79-88
• /
• 1993

Bioequivalence(BE) test of commercially available sustained release tablets of diltiazem hydrochloride(DTZ) was performed to give some guidelines to BE test in korea in case of which drugs with low oral bioavaiiability(BA) due to substantial first-pass hepatic loss form pharmacologically active metabolites. In such cases, the pharmacologic activity after oral administration is greater than anticipated from BA data, based on chemical assay of drug alone. Therefore, this paper explores the use and meaning of area under the plasma concentration-time(AUC) data of parent and its metabolites to access BA if sustained release tablets. Normal healthy male volunteers(n=14) were randomly divided into 2 groups, and sustained release reference$(Herbesser^{(R)})$ and test$(Herben^{(R)})$ tablets of DTZ-30mg were given orally by balanced two-period cross-over dosing schedule. The plasma concentration of DTZ and and its active metabolite, desacetyldiitiazem(DAD), were determined by high performance liquid chromatography, and, $AUC_{DTZ},\;AUC_{DAD},\;AUC_{DTZ+DAD},\;C_{max}\;and\;T_{max}$ obtained. Analysis of varlance(ANOVA) showed that $AUC_{DTZ}\;and\;C_{max}$ passed the standard $(\alpha=0.05,\;1-\beta\geq0.8,\;\Delta\leq0.2)$ of BE test of korea, but $AUC_{DAD}$ was not satisfied from the standpoint of power. On the other hand, $AUC_{DTZ\midDAD}$ may be more avaliable than $AUC_{DAD}$ from the standpoint of statistics and pharmacologic equivalence.