• The Korean Journal of Applied Statistics
• /
• v.23 no.1
• /
• pp.197-206
• /
• 2010

In this paper, we propose boosting algorithms when data are very large or coming in batches sequentially over time. In this situation, ordinary boosting algorithm may be inappropriate because it requires the availability of all of the training set at once. To apply to large scale data or data batch stream, we modify the AdaBoost and Arc-x4. These algorithms have good results for both large scale data and data batch stream with or without concept drift on simulated data and real data sets.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1283-1291
• /
• 2014

In this paper, we propose forward stagewise algorithm when data are very large or coming in batches sequentially over time. In this situation, ordinary boosting algorithm for large scale data and data batch stream may be greedy and have worse performance with class noise situations. To overcome those and apply to large scale data or data batch stream, we modify the forward stagewise algorithm. This algorithm has better results for both large scale data and data batch stream with or without concept drift on simulated data and real data sets than boosting algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.904-913
• /
• 2020

As the data volumes and complexity rapidly increase, data-intensive science handling large-scale scientific data needs to investigate new techniques for intelligent storage and data distribution over networks. Recently, Named Data Networking (NDN) and data-intensive science communities have inspired innovative changes in distribution and management for large-scale experimental data. In this article, analysis on NDN testbeds for large-scale scientific data such as climate science data and High Energy Physics (HEP) data is presented. This article is the first attempt to analyze existing NDN testbeds for large-scale scientific data. NDN testbeds for large-scale scientific data are described and discussed in terms of status, NDN-based application, and features, which are NDN testbed instance for climate science, NDN testbed instance for both climate science and HEP, and the NDN testbed in SANDIE project. Finally various issues to prevent pitfalls in NDN testbed establishment for large-scale scientific data are analyzed and discussed, which are drawn from the descriptions of NDN testbeds and features on them.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.780-793
• /
• 2022

Large-scale ontology management is one of the main issues when using ontology data practically. Although many approaches have been proposed in relational database management systems (RDBMSs) or object-oriented DBMSs (OODBMSs) to develop large-scale ontology management systems, they have several limitations because ontology data structures are intrinsically different from traditional data structures in RDBMSs or OODBMSs. In addition, users have difficulty using ontology data because many terminologies (ontology nodes) in large-scale ontology data match with a given string keyword. Therefore, in this study, we propose a (graph database-based ontology management system (GOMS) to efficiently manage large-scale ontology data. GOMS uses a graph DBMS and provides new query templates to help users find key concepts or instances. Furthermore, to run queries with multiple joins and path conditions efficiently, we propose GOMS encoding as a filtering tool and develop hash-based join processing algorithms in the graph DBMS. Finally, we experimentally show that GOMS can process various types of queries efficiently.

• Journal of Cadastre & Land InformatiX
• /
• v.45 no.1
• /
• pp.169-179
• /
• 2015

Recently, as the amount of data increases rapidly, the development of IT technology entered the 'Big Data' era, dealing with large-volume of data at once. In the spatial field, a spatial data service technology is required to use that various and big amount of data. In this study, firstly, we explained the technology of typical spatial information data services abroad, and then we have developed large KML data processing techniques those can be applied as KML format to VWorld desktop. The test was conducted using a large KML data in order to verify the development KML partitioned methods and tools. As a result, the index file and the divided files are produced and it was visible in VWorld desktop.

• Journal of Sensor Science and Technology
• /
• v.26 no.1
• /
• pp.1-6
• /
• 2017

The advanced driver assistant system (ADAS) requires the collection of a large amount of information including road conditions, environment, vehicle status, condition of the driver, and other useful data. In this regard, large-scale sensor networks can be an appropriate solution since they have been designed for this purpose. Recent advances in sensor network technology have enabled the management and monitoring of large-scale tasks such as the monitoring of road surface temperature on a highway. In this paper, we consider the estimation and fusion problems of the large-scale sensor networks used in the ADAS. Hierarchical fusion architecture is proposed for an arbitrary topology of the large-scale sensor network. A robust cluster estimator is proposed to achieve robustness of the network against outliers or failure of sensors. Lastly, a robust hierarchical data fusion scheme is proposed for the communication channel between the clusters and fusion center, considering the non-Gaussian channel noise, which is typical in communication systems.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.303-311
• /
• 1999

The amount of financial information in today's sophisticated large data bases is huge and makes comparisons between company performance difficult or at least very time consuming. The purpose of this paper is to investigate whether neural networks in the form of self-organizing maps can be used to manage the complexity in large data bases. This paper structures and analyzes accounting numbers in a large data base over several time periods. By using self-organizing maps, we overcome the problems associated with finding the appropriate underlying distribution and the functional form of the underlying data in the structuring task that is often encountered, for example, when using cluster analysis. The method chosen also offers a way of visualizing the results. The data base in this study consists of annual reports of more than 80 Korean companies with data from the year 1998.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.361-366
• /
• 2022

There are several ways to process large amounts of data. Depending on the processing method, there is a big difference in processing speed to create a large data list. Typically, to make a large data list, large data is converted into a normalized query, and the result of the query is stored in a List Map and converted into a printable form. This process occurs as a cause of lowering the processing speed step by step. In the process of storing the results of the created query as a List Map, the processing speed differs because the data is stored in a different format for each type of data. Through the simultaneous processing of GO language, we want to solve the problem of the existing difference in processing speed. In other words, it compares the results of GO language concurrency processing by providing how different and how it proceeds between the format contained in the existing List Map and the method of processing using concurrency in large data lists for faster processing. do.

• Journal of the Semiconductor & Display Technology
• /
• v.11 no.2
• /
• pp.85-91
• /
• 2012

In this paper, the large data processing and suitable FAT32 file system for industrial system using a PLC and CF memory was implemented. Most of PLC can't save the large data in user data memory. So it's required to the external devices of CF memory or NAND flash memory. The CF memory is used in order to save the large data of PLC system. The file system using the CF memory is NTFS, FAT, and FAT32 system to configure in various ways. Typically, the file system which is widely used in industrial data storage has been implemented as modified FAT32. The conventional FAT 32 file system was not possible for multiple writing and high speed data accessing. The proposed file system was implemented by the large data processing module can be handled that the files are copied at the 40 bytes for 1msec speed logging and creating 8 files at the same time. In a sudden power failure, high reliability was obtained that the problem was solved using a power fail monitor and the non-volatile random-access memory (NVSRAM). The implemented large data processing system was applied the modified file system as FAT32 and the good performance and high reliability was showed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.3
• /
• pp.1-9
• /
• 2014

This study deals with development of Integrated Transportation Analysis System for Large-scale event. Based on case studies, the requirements of the system were defined and the direction of development was established. The large-scale events that require fast and accurate transportation policy were selected. The data warehouse and data mart were developed by integrating the large-scale event data and the traffic data. Business intelligence system was designed and developed users to allow timely decisions.