• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.169-175
• /
• 2022

This paper introduces an interference elimination method using k-nearest neighbor (KNN) algorithm for precise distance estimation by reducing interference between ultrasonic sensors. Conventional methods compare current distance measurement result with previous distance measurement results. If the difference exceeds some thresholds, conventional methods recognize them as interference and exclude them, but they often suffer from imprecise distance prediction. KNN algorithm classifies input values measured by multiple ultrasonic sensors and predicts high accuracy outputs. Experiments of distance measurements are conducted where interference frequently occurs by multiple ultrasound sensors of same type, and the results show that KNN algorithm significantly reduce distance prediction errors. Also the results show that the prediction performance of KNN algorithm is superior to conventional voting methods.

• The Journal of Information Systems
• /
• v.31 no.2
• /
• pp.19-43
• /
• 2022

Purpose Due to the COVID-19 pandemic, many companies are building virtual workplaces based on virtual reality technology. Through this study, we intend to identify the trend of convergence and convergence research between virtual reality technology and work space, and suggest future promising fields based on this. Design/methodology/approach For this purpose, 12,250 bibliographic data of research papers related to Virtual Reality (VR) and Workplace were collected from Scopus from 1982 to 2021. The bibliographic data of the collected papers were analyzed using Text Mining and Pathfinder Network, Parallel Neighbor Clustering, Nearest Neighbor Centrality, and Triangle Betweenness Centrality. Through this, the relationship between keywords by period was identified, and network analysis and visualization work were performed for virtual reality-based workplace research. Findings Through this study, it is expected that the main keyword knowledge structure flow of virtual reality-based workplace convergence research can be identified, and the relationship between keywords can be identified to provide a major measure for designing directions in subsequent studies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.467-468
• /
• 2021

In order to improve the performance of the indoor positioning system using BLE beacons, a receiver that measures the angle of arrival among the direction finding technologies supported by BLE5.1 was manufactured and analyzed by machine learning to measure the optimal position. For the creation and testing of machine learning models, k-nearest neighbor classification and regression, logistic regression, support vector machines, decision tree artificial neural networks, and deep neural networks were used to learn and test. As a result, when the test set 4 produced in the study was used, the accuracy was up to 99%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.207-209
• /
• 2022

In the IoT environment, it is possible to collect life pattern data by recognizing human physical activity from smart devices. In this paper, the proposed model consists of a prediction stage and a recommendation stage. The prediction stage predicts the scale of anxiety and depression by using logistic regression and k-nearest neighbor algorithm through machine learning on the dataset collected from life pattern data. In the recommendation step, if the symptoms of anxiety and depression are classified, the principal component analysis algorithm is applied to recommend food and light exercise that can improve them. It is expected that the proposed anxiety/depression prediction and food/exercise recommendations will have a ripple effect on improving the quality of life of individuals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.12
• /
• pp.2343-2348
• /
• 2006

Image magnification is among the basic image processing operations. The most commonly used technique for image magnification are based on interpolation method(such as nearest neighbor, bilinear and cubic interpolation). However, the magnified images produced by the techniques that often appear a variety of undesirable image artifacts such as 'blocking' and 'blurring' or too takes the processing time into the several processing for image magnification. In this paper, we propose image magnification method which uses input image's sub-band information such as edge information to enhance the image magnification method. We use the whole image and not use the one's neighborhood pixels to detect the edge information of the image that isn't occurred the blocking phenomenon. And then we emphasized edge information to remove the blurring phenomenon which incited of edge information. Our method, which improves the performance of the traditional image magnification methods in the processing time, is presented. Experiment results show that the proposed method solves the drawbacks of the image magnification such as blocking and blurring phenomenon, and has a higher PSNR and Correlation than the traditional methods.

• The Korean Journal of Applied Statistics
• /
• v.19 no.2
• /
• pp.291-303
• /
• 2006

Data mining is the work to extract information from existing data file. So, the one of best important thing in data mining process is the quality of data to be used. In this thesis, we propose the data fusion technique using decision rule for data enrichment that one phase to improve data quality in KDD process. Simulations were performed to compare the proposed data fusion technique with the existing techniques. As a result, our data fusion technique using decision rule is characterized with low MSE or misclassification rate in fusion variables.

• Journal of the Korean Society for information Management
• /
• v.30 no.4
• /
• pp.241-264
• /
• 2013

This study compared and analyzed weighted network centrality measures supported by Opsahl's tnet and Lee's WNET, which are free softwares for weighted network analysis. Three node centrality measures including weighted degree, weighted closeness, and weighted betweenness are supported by tnet, and four node centrality measures including nearest neighbor centrality, mean association, mean profile association, triangle betweenness centrality are supported by WNET. An experimental analysis carried out on artificial network data showed tnet's high sensitiveness on linear transformations of link weights, however, WNET's centrality measures were insensitive to linear transformations. Seven centrality measures from both tools, tnet and WNET, were calculated on six real network datasets. The results showed the characteristics of weighted network centrality measures of tnet and WNET, and the relationships between them were also discussed.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.3
• /
• pp.561-568
• /
• 2015

In this study we predict apartment prices per unit in Daegu-Gyeongbuk areas by spatial lag and spatial error models, both of which belong to so-called spatial regression model. A spatial weight matrix is constructed by k-nearest neighbours method and then the models for the apartment prices in March, 2012 are fitted using the weight matrix. The apartment prices in March, 2013 are predicted by the fitted spatial regression models and then performances of two spatial regression models are compared by RMSE (root mean squared error), RRMSE (root relative mean squared error), MAE (mean absolute error).

• The Korean Journal of Applied Statistics
• /
• v.17 no.3
• /
• pp.605-617
• /
• 2004

One of the best important thing in data mining process is the quality of data used. When we perform the mining on data with excellent quality, the potential value of data mining can be improved. In this paper, we propose the data fusion technique for data enrichment that one phase can improve data quality in KDD process. We attempted to add k-NN technique to the regression technique, to improve performance of fusion technique through reduction of the loss of information. Simulations were performed to compare the proposed data fusion technique with the regression technique. As a result, the newly proposed data fusion technique is characterized with low MSE in continuous fusion variables.

• Journal of the Society of Naval Architects of Korea
• /
• v.46 no.6
• /
• pp.675-687
• /
• 2009

In general, the forming process of the curved hull plates consists of sub tasks, such as roll bending, line heating, and triangle heating. In order to complement the automated curved hull forming system, it is necessary to develop an algorithm to classify the curved hull plates of a ship into standard shapes with respect to the techniques of forming task, such as the roll bending, the line heating, and the triangle heating. In this paper, the curved hull plates are classified by four standard shapes and the combination of them, or saddle, convex, flat, cylindrical shape, and the combination of them, that are related to the forming tasks necessary to form the shapes. In preprocessing, the Gaussian curvature and the mean curvature at the mid-point of a mesh of modeling surface by Coon's patch are calculated. Then the nearest neighbor method to classify the input plate type is applied. Tests to verify the developed algorithm with sample plates of a real ship data have been performed.