• Communications for Statistical Applications and Methods
• /
• v.18 no.3
• /
• pp.319-331
• /
• 2011

In this paper, we propose automatic procedures for the model selection of various univariate time series data. Automatic model selection is important, especially in data mining with large number of time series, for example, the number (in thousands) of signals accessing a web server during a specific time period. Several methods have been proposed for automatic model selection of time series. However, most existing methods focus on linear time series models such as exponential smoothing and autoregressive integrated moving average(ARIMA) models. The key feature that distinguishes the proposed procedures from previous approaches is that the former can be used for both linear time series models and nonlinear time series models such as threshold autoregressive(TAR) models and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA-GARCH) models. The proposed methods select a model from among the various models in the prediction error sense. We also provide an R package autots that implements the proposed automatic model selection procedures. In this paper, we illustrate these algorithms with the artificial and real data, and describe the implementation of the autots package for R.

• 한국정보통신설비학회:학술대회논문집
• /
• 2002.08a
• /
• pp.199-207
• /
• 2002

A virtual laboratory for measurement and instrumentation must aim to realize an integrated environment. To achieve this goal, we designed and implemented a client/server distributed environment and developed a web-based virtual laboratory system for electronic circuits. Since our virtual laboratory system is implemented to describe the on-campus laboratory, the learners can obtain similar experimental data through it. The proposed virtual laboratory system is composed of four important components Principle Classroom, Virtual Experiment Classroom, Evaluation Classroom and Overall Management System. Through our virtual laboratory, the learners will be capable of teaming the concepts and theories related to electronic circuit experiments and how to operate the experimental equipments such as multimeters, function generators, digital oscilloscopes and DC power supplies. Also, every activity occurred in our virtual laboratory is recorded on database and Printed out on the preliminary report form. All of these can be achieved by the aid of the Management System. The database connectivity is made by PHP and the virtual laboratory environment is set up slightly differently for each learner. Finally, we have obtained several affirmative effects such as reducing the total experimental hours and the damage rate for experimental equipments and increasing Loaming efficiencies as well as faculty productivity.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.367-369
• /
• 2010

The purpose of this study is to develop a campus facility management system, construct 3D graphic data and attribute data of facilities on the Kumoh National Institute of Technology and then verificate the developed system's practicability. Utilized the existing campus facility data from the existing drawings, images, cadastre records and so forth, 3D position data of underground facilities surveyed with a total station and high-resolution aerial photos, 3D realistic models were produced by means of a XD2D software and a XDWORLD Builder Professional software of GIS engines. We intend to embody not only campus guide service in virtual reality space but visualization of 3D virtual campus by providing 2D and 3D data to web space using XDWORLD server soon after. It is expected that the campus facility management system is able to contribute to the integrated management of 3D facility data service, the support of prompt decision-making related to spatial affairs, the work simplification through data holding in common between the members of the staff and so forth.

• Genomics & Informatics
• /
• v.19 no.2
• /
• pp.16.1-16.14
• /
• 2021

Even in the current age of advanced medicine, the prognosis of malignant peritoneal mesothelioma (MPM) remains abysmal. Molecular mechanisms responsible for the initiation and progression of MPM are still largely not understood. Adopting an integrated bioinformatics approach, this study aims to identify the key genes and pathways responsible for MPM. Genes that are differentially expressed in MPM in comparison with the peritoneum of healthy controls have been identified by analyzing a microarray gene expression dataset. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses of these differentially expressed genes (DEG) were conducted to gain a better insight. A protein-protein interaction (PPI) network of the proteins encoded by the DEGs was constructed using STRING and hub genes were detected analyzing this network. Next, the transcription factors and miRNAs that have possible regulatory roles on the hub genes were detected. Finally, survival analyses based on the hub genes were conducted using the GEPIA2 web server. Six hundred six genes were found to be differentially expressed in MPM; 133 are upregulated and 473 are downregulated. Analyzing the STRING generated PPI network, six dense modules and 12 hub genes were identified. Fifteen transcription factors and 10 miRNAs were identified to have the most extensive regulatory functions on the DEGs. Through bioinformatics analyses, this work provides an insight into the potential genes and pathways involved in MPM.

• Information Systems Review
• /
• v.7 no.2
• /
• pp.117-128
• /
• 2005

This study proposes an integrated monitoring system for data reliability improvement in a steel manufacturing industry. The data obtained from existing steel manufacturing process is not micro data which is gathered at the occurring point, but average value (macro data) which is gathered from the occurring point to ending point. This kind of macro data is not only difficult for a detailed analysis for an error causing factor, but it might cause a fatal influence as well on the quality of produced goods even if the error is within an error tolerance. And during the process of steel production, thousands of data is produced in a second, thus requiring database plan to manage abundant amount of data. Therefore, the following proposed system is capable of collecting as well as analyzing all the data generated from the process of product production. And the system was able to raise the efficiency of the database server by planning the database to handle large capacity data. Also, by applying web-based technology, inquiries and analysis of data with no limit on time and space was possible with PC connected to the intranet. Hence, the system was able to work on effective quality improvement of manufactured products, plus able to raise the reliability of the product. Also, accumulated data from long period of time was used for fundamental material for new controlling model, operation technology, and new product development.

• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.287-294
• /
• 2017

This study attempted to develop a beacon scanner based ward monitoring service in order to respond to the new paradigm of medical environment which is trying to introduce ICT technology as medical service to track and manage the spread path of large infectious diseases such as MERS. The study also included beacon hardware development, firmware development for the beacon low-power bluetooth 4.0, and server and web-based dashboard UI development. Using these, we have developed a customized monitoring system that provides functions such as locating patients by location based service and monitoring based on web UI. It is possible to maximize the efficiency of offline hospital services and to value active infection control and patient safety by integrating online technology into the area where online technologies such as beacons are not properly integrated.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.2
• /
• pp.21-29
• /
• 2016

This study conducted a basic design of system and interface which provide both of spatial and non-spatial data for water hazard information management. This helps to decide directions of the future integrated water hazard information platform and possible technical examinations of the web-based system for the realization of the prototype. For user friendly system, this study did a survey to investigate the data format, service environment, image processing level and visualization type that users prefer. Also, authorization range was set up by type of the user group. In the water hazard information platform, the data and analysis algorithm were classified by the fields. Furthermore, the platform was consisted with six block systems according to the function and the interface and designed to flexibly mount or modify the additional functions. For a basic design of the data exchange method and protocols, a prototype was constructed by using the spatial information web service technology. The portal service system to visualize and provide spatial data was designed by the WMS/WFS type of OGC standard interface and the FTP/HTTP interface type through open source GIS software for server environment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.9
• /
• pp.527-535
• /
• 2004

Handling mixed workload in digital set-top box or streaming server becomes an important issue as integrated file system gets momentum as the choice for the next generation file system. The next generation file system is required to handle real-time audio/video playback while being able to handle text requests such as web page, image file, etc. Legacy file system provides only best effort I/O service and thus cannot properly support the QoS of soft real-time I/O. In this paper, we would like to present our experience in developing the file system which fan guarantee the QoS of multimedia stream. We classify all application I/O requests into two category: periodic I/O and sporadic I/O. The QoS requirement of multimedia stream could be guaranteed by giving a higher priority to periodic requests than sporadic requests. The proto-type file system(Qosfs) is developed on Linux Operating System.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.1C
• /
• pp.21-35
• /
• 2002

Nowadays, in accordance with increasing expectations of multimedia stream service on the internet, a lot of distributed applications are being required and developed. But the models of the existing systems have the problems that cannot support the extensibility and the reusability, when the QoS relating functions are being developed as an integrated modules which are suited on the centralized controlled specific-purpose application services. To cope with these problems, it is suggested in this paper to a distributed QoS management system on CORBA, an object-oriented middleware compliance. This systems we suggested can provides not only for efficient control of resources, various service QoS, and QoS control functions as the existing functions, but also QoS control real-time negotiation and dynamic adaptation in addition. This system consists of QoS Control Management Module(QoS CMM) in client side and QoS Management Module(QoS MM) in server side, respectively. These distributed modules are interfacing with each other via CORBA on different systems for distributed QoS management while serving distributed streaming applications. In phase of design of our system, we use UML(Unified Modeling Language) for designing each component in modules, their method calls and various detailed functions for controlling QoS of stream services. For implementation of our system, we used OrbixWeb 3.1c following CORBA specification on Solaris 2.5/2.7, Java language, Java Media Framework API 2.0 beta2, Mini-SQL 1.0.16 and the multimedia equipments, such as SunVideoPlus/Sun Video capture board and Sun Camera. Finally, we showed a numerical data controlled by real-time negotiation and adaptation procedures based on QoS map information to GUIs on client and server dynamically, while our distributed QoS management system is executing a given streaming service.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.2
• /
• pp.720-726
• /
• 2010

Haplotype-based research has become increasingly important in the field of personalized medicine since the haplotype reflects a set of SNPs (Single Nucleotide Polymorphisms) that are genetically associated and inherited together. Currently, the most widely used application softwares available for haplotype reconstruction, based on in silico method, include PL-EM, Haplotyper, PHASE and HAP. PL-EM, Haplotyper and PHASE are command-line application running on LINUX or Unix system and HAP is a web-based client-server application. This paper deals with an integrated haplotype reconstruction system that have been developed with PL-EM and Haplotyper selected from the accuracy test with experimentally verified data on public application softwares. This integrated system is a kind of client-sever one with user friendly web interface and can provide end-users with a high quality of haplotype analysis. SNPs genotype data with a length of 5 derived from 5 people and SNPs genotype data with a length of 13 derived from 15 people were used to test the analysis results of Haplotyper and PL-EM respectively. As a result, this system has been confirmed to provide the systematic and easy-to-understand analysis results that consist of two main parts, i.e. individual haplotype information and haplotype pool information. In this respect, the integration system will be utilized as a useful tool for the discovery of disease related genes and the development of personalized drugs through facilitating the reconstruction of haplotype maps.