• The Journal of Korean Association of Computer Education
• /
• v.5 no.3
• /
• pp.37-44
• /
• 2002

Automatic text classification is a task of assigning predefined categories to free text documents. Its importance is increased to organize and manage a huge amount of text data. There have been some researches on automatic text classification based on machine learning techniques. While most of them was focused on proposal of a new machine learning methods and cross evaluation between other systems, a through evaluation or optimization of a method has been rarely been done. In this paper, we propose an improving method of kNN-based Korean text classification system using heuristic informations about decision function, the number of nearest neighbor, and feature selection method. Experimental results showed that the system with similarity-weighted decision function, global method in considering neighbors, and DF/ICF feature selection was more accurate than simple kNN-based classifier. Also, we found out that the performance of the local method with well chosen k value was as high as that of the global method with much computational costs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1562-1578
• /
• 2020

Vector data compression algorithm can meet requirements of different levels and scales by reducing the data amount of vector graphics, so as to reduce the transmission, processing time and storage overhead of data. In view of the fact that large threshold leading to comparatively large error in Douglas-Peucker vector data compression algorithm, which has difficulty in maintaining the uncertainty of shape features and threshold selection, a segmented Douglas-Peucker algorithm based on node importance is proposed. Firstly, the algorithm uses the vertical chord ratio as the main feature to detect and extract the critical points with large contribution to the shape of the curve, so as to ensure its basic shape. Then, combined with the radial distance constraint, it selects the maximum point as the critical point, and introduces the threshold related to the scale to merge and adjust the critical points, so as to realize local feature extraction between two critical points to meet the requirements in accuracy. Finally, through a large number of different vector data sets, the improved algorithm is analyzed and evaluated from qualitative and quantitative aspects. Experimental results indicate that the improved vector data compression algorithm is better than Douglas-Peucker algorithm in shape retention, compression error, results simplification and time efficiency.

• Journal of Korea Game Society
• /
• v.11 no.4
• /
• pp.143-149
• /
• 2011

This paper presents a novel camera tracking method based on model with multiple planes. The proposed algorithm detects QR code that is one of the most popular types of two-dimensional barcodes. A 3D model is imported from the detected QR code for augmented reality application. Based on the geometric property of the model, the vertices are detected and tracked using optical flow. A clipping algorithm is applied to identify each plane from model surfaces. The proposed method estimates the homography from coplanar feature correspondences, which is used to obtain the initial camera motion parameters. After deriving a linear equation from many feature points on the model and their 3D information, we employ DLT(Direct Linear Transform) to compute camera information. In the final step, the error of camera poses in every frame are minimized with local Bundle Adjustment algorithm in real-time.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.5-14
• /
• 1994

This paper is about an experiment of speaker-independent automatic Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The object words are 50 citynames of D.D.D local numbers. 43 of those are 2 syllables and the rest 7 are 3 syllables. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. That led independent result on the speech duration, and the PARCOR coefficients calculated from the frames using linear predictive analysis were employed as feature components. This paper tried to find out the optimum conditions through 4 differerent experiments which are comparison between total and pre-classified training, dependency of recognition rate on the number of frames and PAROCR order, recognition change due to the number of neurons in the hidden layer, and the comparison of the output pattern composition method of output neurons. As a result, the recognition rate of $89.6\%$ is obtaimed through the research.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.780-788
• /
• 2011

This paper suggests one model, which can be monitor and control target system at anytime and anywhere by a WAP and ME based personal cellular phone(Feature phone) and internet connection. The suggesting model tried to overcome constraints of distance and mobility of conventional methods, TCP/IP based remote data monitoring system, which combine PDA and WLAN technologies. For the experiments of suggesting model, the target systems are constructed with individual modules, which need AC or DC power control. The development software for the control and monitor of local system use NI Labview for the easy-programming and confidence. Also, web server use APM setup for the general user. The mobile connection environments of personal cellular phone are programmed by use WML and mHTML language for the general access. Through the experiments, we have showed that suggesting model can overcome constraints of distance and mobility of conventional system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.2
• /
• pp.117-128
• /
• 1999

A Simple tree-structured line simplification method, which exactly follows the Douglas-Peucker algorithm, has a strength for its simplification index to be involved into the hierarchical data structures. However, the hierarchy of simplification index, which is the core in a simple tree method, may not be always guaranteed. It is validated that the local property of line features in such global approaches as Douglas-Peucker algorithm is apt to be neglected and the construction of hierarchy with no thought of locality may entangle the hierarchy. This study designed a new approach, CALS(Convex hull Applied Line Simplification), a) to search critical points of line feature with convex hull search technique, b) to construct the hierarchical data structure based on these critical points, c) to simplify the line feature using multiple trees. CALS improved the spatial accuracy as compared with a simple tree method. Especially CALS was excellent in case of line features having the great extent of sinuosity.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.5 no.2 s.17
• /
• pp.37-44
• /
• 2005

It reflects well feature of slope that is characteristic of urban river basin of Busan local. In this study, process various hydrological data and basin details data which is collected through basin basis data, hydrological monitoring system(EMS-DEU) and automatic water level equipment(AWS-DEU) for urban flood disaster prevention and use as basin input data of ILLUDAS, SWMM and HEC-HMS in order to examine outflow feature of experiment basin and then use in reservoir design of experiment basin through calibration and verification about HEC-HMS. Inserted design rainfall for 30 years that is design criteria of creek into HEC-HMS and then calculated design floods according to change aspect of the impermeable rate. Capacity of reservoir was determined on the outflow mass curve. Designed detention pond(volume $54,000m^3$) at last outlet upper stream of experiment basin, after designing reservoir. It could be confirmed that the peak flow was reduced resulting from examining outflow aspect. Designing reservoir must decrease outflow of urban areas.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.756-763
• /
• 2013

Bilateral filter (BF), functioning by two Gaussian filters, domain and range filter is a nonlinear filter for sharpness enhancement and noise removal. In infrared (IR) small target detection field, the BF is designed by background predictor for predicting background not including small target. For this, the standard deviations of the two Gaussian filters need to be changed adaptively in background and target region of an infrared image. In this paper, the proposed bilateral filter make the standard deviations changed adaptively, using variance feature of mean values of surrounding block neighboring local filter window. And, in case the variance of mean values for surrounding blocks is low for any processed pixel, the pixel is classified to flat background and target region for enhancing background prediction. On the other hand, any pixel with high variance for surrounding blocks is classified to edge region. Small target can be detected by subtracting predicted background from original image. In experimental results, we confirmed that the proposed bilateral filter has superior target detection rate, compared with existing methods.

• The Journal of the Korea Contents Association
• /
• v.17 no.1
• /
• pp.436-443
• /
• 2017

This research aims to inquiry the present state of online game industry and related laws and investigate the nature and feature of the web-board game policy through the case of web-board game operation in China. We reviewed China local literature of online mobile game industry and inspected foreign entry, copyright protection, safety audit, distribution, and shop in China laws related to online game. We examined the game operation of the most famous 'Bianfeng' game company among China web-board game and considered how the charge and exchange for game money is made at issue. The result was revealed that money exchange was made in twilight zone neither legal nor illegal due to dual feature of China law. It is an ambiguous judgment that did not take a strong prohibition. However, we found that minium regulation was gone just in case social trouble happened. The result of this research will expect to help Korea regulation authorities and game company that have plans to enter China market the guideline for game operation policy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.