• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.12
• /
• pp.1345-1354
• /
• 2015

This paper, information communication code standard($KS{\times}1001$, confirmation in 2004), as definded in Hangul Character Code Hangul AMI/HDB-3 the code set for the new system Hangul consonant and vowel tables presented. The result of the existing system and the code set ($4{\times}4$) bit source coding rules for comparing the frequency of use Hangul consonant and vowel tables(The National Institute of The Korea Language) and statistices showed that 44% of the data processing efficiency is improved.

• Transactions of Materials Processing
• /
• v.32 no.6
• /
• pp.352-359
• /
• 2023

Recently, independent suspension systems have been applied not only to passenger cars but also to large commercial vehicles. Therefore, the need for research to domestically produce such independent suspensions for large commercial vehicles is gradually increasing. In this paper, we conducted research on the manufacturing technology of the relay lever, which are integral components of independent suspension systems for large commercial vehicles. Our goal was to reduce the flash volume generated during the forging process. The shape variables of the initial billet were adjusted to find proper forming conditions that could minimize flash volume while performing product forming smoothly. Shape variables were set as input variables and the flash volume was set as an output variable, and simulations were carried out to analytically predict the volume of the flash area for each variable condition. Based on the data obtained through numerical simulations, a regression model and an artificial neural network model were used to develop a prediction model that can easily predict the flash volume for variable conditions. For the corresponding prediction model, a goodness of-fit test was performed to confirm a high level of fit. By comparing and analyzing the two prediction models, the high level of fit of the ANN model was confirmed.

• Journal of Korean Society of Transportation
• /
• v.29 no.1
• /
• pp.125-134
• /
• 2011

In order to reconstruct vehicle-pedestrian collision accidents, this paper presents a fuzzy tool to estimate accurately the impact velocity of the vehicle using parameters which could be easily collectable at the accident scene. The fuzzy rules and membership functions were set up using number of over 200 domestic and foreign data from accidents and empirical tests and 700 data from multibody simulation experiments. The developed fuzzy tool deduces the category of pedestrian trajectory and impact speed of the vehicle using 4 membership functions and 2 logic rules. The membership function of throw distance was differently set according to the deduced category of trajectories. The implemented fuzzy program was validated through comparing with the domestic and foreign empirical data. The output results agree very well in impact velocities of vehicle resulting the accuracy and usefulness of the developed tool in the reconstruction analysis of vehicle-pedestrian collision accidents.

• Journal of Digital Convergence
• /
• v.11 no.10
• /
• pp.255-262
• /
• 2013

Data envelopment analysis(DEA) is a linear programming procedure designed to evaluate the relative efficiency of a set of peer entities called decision making units which use the same inputs to produce the same outputs. It has been widely employed in a variety of disciplines as an efficiency or performance measurement tool for comparing a set of entities such as firms, banks, hospitals, nations and organizations. The method, however, cant's make the priority of their performance when many units have efficiency score of unity or 100 percent. In this paper, we propose a new approach which combine qualitative method(graphical approach using network analysis) and quantitative method(super-efficient analysis using DEA), and present the results of an empirical analysis using the data of the Korean professional baseball players. As a result, there were 12 DMU that priority is hardly realized through DEA. However, this problem could be solved with super-efficiency analyzing. Also, more in-depth interpretation was able through integrating results of dendrogram and super-efficiency analyzing and prospecting it in qualitative, quantitative ways.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.12
• /
• pp.901-906
• /
• 2015

It is difficult to measure aircraft noise at many points, because the noise measurement is need to long time, 24 hours and consecutive 7 days, which results in high costs. As an alternative, movement measuring points are set to measure aircraft noise for less than 24 hours, and so it is needed to overcome the limitation of shorter measuring time. Thus, this study measured military aircraft noise on movement measuring points and conducted a comparative analysis on the data according to each measuring time. The data of measuring noise for 24 hours and less than 24 hours were compared to suggest appropriate measuring time on the movement measuring points. As a result of comparing data of measuring noise, an error was within 3 dB in case of measuring time of 3 hours, and an error was within 1 dB in case of 6 hours of measurement.

• Journal of Korean Society of Rural Planning
• /
• v.5 no.1 s.9
• /
• pp.26-34
• /
• 1999

This study, a sub-one of comprehensive research works titled under "Rural Resources Evaluation System", tried to verify utility/applicability of the developed model system through the case study works on 3 sample villages, Backya, Uyan and Suyu, representing the lowland, upland and seashore villages respectively. From the various surveying and collecting works including the official/statistical data collection, map analysis, in-situ investigation, field survey and written material review, the original data set were obtained and manipulated into final input data for resources grading. After then, by the automatized calculation procedure of "Rural Resources Evaluation System", score results for resources evaluation were finally produced with the total maximum score being 1,000. Through comparing works among score results of 3 case villages and between score results and areal characteristics of each case village, the applicability of the system developed in this study was well confirmed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.179-185
• /
• 2010

In this paper, we present a performance evaluation for face recognition algorithm using feature feedback according to the Feature mask. In the face recognition method using feature feedback, important region is extracted from original data set by using the reverse mapping from the extracted features to the original space. In this paper, we evaluate the performance of feature feedback according to shape of Feature Mask for Yale data. Comparing the result using Important part and unimportant part, we show the validity and applicability of the pattern recognition method based on feature feedback.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.226-228
• /
• 2005

Predicting the cellular location of an unknown protein gives valuable information for inferring the possible function of the protein. For more accurate Prediction system, we need a good feature extraction method that transforms the raw sequence data into the numerical feature vector, minimizing information loss. In this paper we propose new methods of extracting underlying features only from the sequence data by computing pairwise sequence alignment scores. In addition, we use composition based features to improve prediction accuracy. To construct an SVM ensemble from separately trained SVM classifiers, we propose specificity based weighted majority voting . The overall prediction accuracy evaluated by the 5-fold cross-validation reached $88.53\%$ for the eukaryotic animal data set. By comparing the prediction accuracy of various feature extraction methods, we could get the biological insight on the location of targeting information. Our numerical experiments confirm that our new feature extraction methods are very useful forpredicting subcellular localization of proteins.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.24 no.2
• /
• pp.226-235
• /
• 2019

Soluble silica profiles of the East Sea were described by comparing the 1970 Japanese data with the 1999-2000 ONR-JES data set, which is the most extensive collection of data currently available. Considering the ventilation mode change happened/ongoing and the features of the soluble silica to phosphate ratio we suggest a hypothesis that a utilization of soluble silica by the primary production might be exacerbated in the future. According to the silica limitation hypothesis composition of primary producers will be altered and followed by a weaker contribution of ballast against aggregates in the export production. Since the silicate cycle is deeply intertwined with the carbon cycle whether the warmed future ocean would behave like the East Sea appears to a potentially promising study theme.

• Journal of Korean Association for Spatial Structures
• /
• v.18 no.4
• /
• pp.69-80
• /
• 2018

In this study, an algorithm applying deep learning to the truss structures was proposed. Deep learning is a method of raising the accuracy of machine learning by creating a neural networks in a computer. Neural networks consist of input layers, hidden layers and output layers. Numerous studies have focused on the introduction of neural networks and performed under limited examples and conditions, but this study focused on two- and three-dimensional truss structures to prove the effectiveness of algorithms. and the training phase was divided into training model based on the dataset size and epochs. At these case, a specific data value was selected and the error rate was shown by comparing the actual data value with the predicted value, and the error rate decreases as the data set and the number of hidden layers increases. In consequence, it showed that it is possible to predict the result quickly and accurately without using a numerical analysis program when applying the deep learning technique to the field of structural analysis.