• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.318-327
• /
• 2008

With the advance of information technologies and the spread of Internet use, the volume of usable information is increasing explosively. A content recommendation system provides the services of filtering out information that users do not want and recommending useful information. Existing recommendation systems analyze the records and patterns of Web connection and information demanded by users through data mining techniques and provide contents from the service provider's viewpoint. Because it is hard to express information on the users' side such as users' preference and lifestyle, only limited services can be provided. The semantic Web technology can define meaningful relations among data so that information can be collected, processed and applied according to purpose for all objects including images and documents. The present study proposes a content recommendation search system that can update and reflect personalized profiles dynamically in semantic Web environment. A personalized profile is composed of Collector that contains the characteristics of the profile, Aggregator that collects profile data from various collectors, and Resolver that interprets profile collectors specific to profile characteristic. The personalized module helps the content recommendation server make regular synchronization with the personalized profile. Choosing music as a recommended content, we conduct an experience on whether the personalized profile delivers the content to the content recommendation server according to a service scenario and the server provides a recommendation list reflecting the user's preference and lifestyle.

• Journal of the Korea Convergence Society
• /
• v.9 no.7
• /
• pp.1-7
• /
• 2018

Feature selection, one of data preprocessing techniques, is one of major research areas in many applications dealing with large dataset. It has been used in pattern recognition, machine learning and data mining, and is now widely applied in a variety of fields such as text classification, image retrieval, intrusion detection and genome analysis. The proposed method is based on a genetic algorithm which is one of meta-heuristic algorithms. There are two methods of finding feature subsets: a filter method and a wrapper method. In this study, we use a wrapper method, which evaluates feature subsets using a real classifier, to find an optimal feature subset. The training dataset used in the experiment has a severe class imbalance and it is difficult to improve classification performance for rare classes. After preprocessing the training dataset with SMOTE, we select features and evaluate them with various machine learning algorithms.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• Progress in Medical Physics
• /
• v.22 no.3
• /
• pp.155-162
• /
• 2011

The analog image based system consisted of a simulator and medical linear accelerator (LINAC) for radiotherapy was upgraded to digital medical image based system by exchanging the X-ray film with Computed Radiography (CR). With minimum equipments shift and similar treatment process, it was possible that the new digital image system was adapted by the users in short time. The film cassette and the film developer device were substituted with a CR cassette and a CR Reader, where the ViewBox was replaced with a small size PC and a monitor. The viewer software suitable for radiotherapy was developed to maximize the benefit of digital image, and as the result the convenience and the effectiveness was improved. It has two windows to display two different images in the same time and equipped various search capability, contouring, window leveling, image resizing, translation, rotation and registration functions. In order to avoid any discontinuance of the treatment while the transition to digital image, the film and the CR was used together for 1 week, and then the film developer was removed. Since then the CR System has been operated stably for 2 months, and the various requests from users have been reflected to improve the system.

• The Journal of Korean Academy of Prosthodontics
• /
• v.59 no.1
• /
• pp.146-152
• /
• 2021

Accurate transfer of the maxillo-mandibular relationship to an articulator (i.e., mounting) is critical in prosthetic treatment procedures. In the current study, a PubMed search was performed to review the influencing factors for the maxillo-mandibular relationship's accuracy. The search included digital mounting as well as conventional gypsum cast mounting. The results showed that a greater amount of displacement was introduced during positioning the maxillary and mandibular models to interocclusal records rather than the dimensional change of registration material. Most intraoral scanners resulted in an accurate reproduction of the maxillo-mandibular relationship for posterior quadrant scanning; however, the accuracy was declined as the scan area increased to a complete arch scan. The digital mounting accuracy was also influenced by the image processing algorithms and software versions, especially for complete arch scans.

• Journal of the Korean Society for information Management
• /
• v.19 no.4
• /
• pp.96-111
• /
• 2002

A lot of accumulated data of many quantity exist within a institution or an organization, but most data is remained in form of standardization as each institution or organization. There are difficulty in exchange and share of information. New concept of knowledge information resource management to overcome this disadvantage was introduced, and the digitization of knowledge information resources to share and manage accumulated data is been doing. Specially, in science technic or education scholarship it, the tendency that importing XML to process necessary data to exchange and share of knowledge information resources structurally, and limitation of back for search and indexing or reusability is happened according as expression of great many mathematics used inside electron document of these sphere is processed to nonstructural data of image or text and so on. There is interest converged in processing of mathematics that use MathML to overcome this, and we require the solution to be able to process MathML easily and efficiently on structural document. In this paper, designed and implemented of XML document editing system which easy structural process of electronic document for knowledge information resources, and create and express MathML easily on structural document without expert knowledge about MathML.