• Journal of Korea Spatial Information System Society
• /
• v.8 no.2 s.17
• /
• pp.39-52
• /
• 2006

With the recent the use of spatio-temporal data mining which can extract various knowledge such as movement patterns of moving objects in history data of moving object gets increasing. However, the existing movement pattern extraction methods create lots of candidate movement patterns when the minimum support is low. Therefore, in this paper, we suggest the STMPE(Spatio-Temporal Movement Pattern Extraction) algorithm in order to efficiently extract movement patterns of moving objects from the large capacity of spatio-temporal data. The STMPE algorithm generalizes spatio-temporal and minimizes the use of memory. Because it produces and keeps short-term movement patterns, the frequency of database scan can be minimized. The STMPE algorithm shows more excellent performance than other movement pattern extraction algorithms with time information when the minimum support decreases, the number of moving objects increases, and the number of time division increases.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.9
• /
• pp.3-11
• /
• 2013

Recently, a plenty of researches have been conducted using the massively parallel processing of GPU for the implementation of communication system. In this paper, we tried to reduce software simulation time applying GPU with sliding block method to Viterbi decoder in DVB-T system which is one of European DTV standards. First of all, we implement DVB-T system by CPU and estimate cost time whereby the system processes one OFDM symbol. Secondly, we implement Viterbi decoder by software using NVIDIA's massive GPU processor. In our work, stream process method is applied to reduce the overhead for data transfer between CPU and GPU, as well as coalescing method to lower the global memory access time. In addition, data structure design method is used to maximize the shared memory usage. Consequently, our proposed method is approximately 11 times faster in 2K mode and 60 times faster in 8K mode for the process in Viterbi decoder.

• Journal of Digital Contents Society
• /
• v.14 no.1
• /
• pp.15-23
• /
• 2013

In response to the demands of large-scale data processing with low-power and new application, a storage system using SSD (Solid State Disk/Drive) with fast input-output performance instead of hard disc has appeared as storage device. Studies on methods to overcome specific problems of SSD such as various processing data units, out-place-update and limited delete count have been actively conducted. However, declining performance and stability have not been resolved yet when storing case specific data with small scale that causes frequent random write in hard disc or SSD. This thesis suggests a system structure that stores index requesting frequent random write in NVRAM capable of byte access by using characteristics such as byte unit fast read / write of NVRAM, non-volatile and smaller size of actual changed data size in index page than block size.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.8
• /
• pp.1998-2004
• /
• 2009

Recently, due to technical developments of various storage devices and networks, the amount of data increases rapidly. The large volume of data streams poses unique space and time constraints on the data mining process. The continuous characteristic of streaming data necessitates the use of algorithms that require only one scan over the stream for knowledge discovery. Most of the researches based on the support are concerned with the frequent itemsets, but ignore the infrequent itemsets even if it is crucial. In this paper, we propose an efficient method WSFI-Mine(Weighted Support Frequent Itemsets Mine) to mine all frequent itemsets by one scan from the data stream. This method can discover the closed frequent itemsets using DCT(Data Stream Closed Pattern Tree). We compare the performance of our algorithm with DSM-FI and THUI-Mine, under different minimum supports. As results show that WSFI-Mine not only run significant faster, but also consume less memory.

• The KIPS Transactions:PartA
• /
• v.13A no.2 s.99
• /
• pp.137-146
• /
• 2006

Shared Memory Multiprocessor (SMP) systems adopting Chip-level MultiThreading (CMT) technology are becoming mainstream servers in commercial applications and High Performance Computining (HPC) applications as well. OpenMP has become the standard paradigm to parallelize applications for SMP mostly because of its ease of use. As the demand for more computing power in HPC applications is growing rapidly, obtaining high performance and scalability for these applications parallelized using OpenMP API's will become more important. In this paper, we study the performance and scalability of HPC applications parallelized using OpenMP, SPEC OMPL (standard OpenMP benchmark suite), on the Sun Fire E25K server which adopts CMT technology. We also study the effect of CMT on SPEC OMPL.

• Journal of Biomedical Engineering Research
• /
• v.24 no.6 s.81
• /
• pp.481-486
• /
• 2003

This paper describes the implementation of the toolkit software for the DICOM. the international standards of medical imaging. Well known toolkits do not have the functions related to imaging or ported to Windows OS after developed at UNIX OS or do not have mechanism for the speed and memory management or have complicated structure comes from DICOMI complexity. The toolkit introduced in this paper was designed for the hospital environments. It handles mass images at Windows based PC system. supports multi-threading to enhance the efficiency. supports every functions in Object Oriented Programming style needed at clinical application which makes the rapid development of the DICOM related applications. The results says that the toolkit can display 50 CT, 50 MR, 10 CR and 10 DX images in 12 seconds and occupy small quantity of physical memory at usual PC system.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.33-39
• /
• 2022

A storage device used in the mobile computing field should have low power, light weight, durability, etc., and should be able to effectively store and manage large-capacity data generated by users. NAND flash memory is mainly used as a storage device in the field of mobile computing. Due to the structural characteristics of NAND flash memory, it is impossible to overwrite in place when a data update request is made, so it can be solved by accurately separating requests that frequently request data update and requests that do not, and storing and managing them in each block. The classification method for such a data update request is called a hot data identification method, and various studies have been conducted at present. This paper continuously records the occurrence of data update requests using a counting filter for more accurate hot data validation, and also verifies hot data by considering how often the requested update requests occur during a specific time.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.593-598
• /
• 2022

Recently, data production has seen explosive growth, and the storage systems to store these big data safely and quickly is evolving in various ways. A typical configuration of storage systems is the use of SSDs with fast data processing speed as a RAID group that can maintain reliable data. However, since NAND flash memory, which composes SSD, has the feature that deterioration if writes more than a certain number of times are repeated, can increase the likelihood of simultaneous failure on multiple SSDs in a RAID group. And this can result in serious reliability problems that data cannot be recovered. Thus, in order to solve this problem, we propose a method of throttling IOs so that each SSD within a RAID group leads to a different life-end. The technique proposed in this paper utilizes SMART to control the state of each SSD and the number of IOs allocated according to the data pattern used step by step. In addition, this method has the advantage of preventing large amounts of concurrency defects in RAID because it induces differential lifetime finishes of SSDs.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.1-12
• /
• 2024

Deep learning with faster and more accurate results requires large amounts of storage space and large computations. Accordingly, many studies are using hardware accelerators for quick and accurate calculations. However, the performance bottleneck is due to data movement between the hardware accelerators and the CPU. In this paper, we propose a data prefetch strategy that can efficiently reduce such operational bottlenecks. The core idea of the data prefetch strategy is to predict the data needed for the next task and upload it to local memory while the hardware accelerator (Matrix Multiplication Unit, MMU) performs a task. This strategy can be enhanced by using a dual buffer to perform read and write operations simultaneously. This reduces latency and execution time of data transfer. Through simulations, we demonstrate a 24% improvement in the performance of hardware accelerators by maximizing parallel processing with dual buffers and bottlenecks between memories with data prefetch.

• Journal of KIISE:Software and Applications
• /
• v.26 no.8
• /
• pp.939-954
• /
• 1999

데이타마이닝 분야에서는 대용량의 트랜잭션 데이타베이스와 같은 하나의 데이타베이스로부터 연관 규칙을 찾는 연구가 많이 수행되어왔다. 그러나, 창고형 할인매장이나 백화점 같이 고객 카드를 이용하는 판매점의 등장으로, 단지 트랜잭션에 대한 분석 뿐만이 아니라, 트랜잭션과 고객과의 관계에 대한 분석 또한 요구되고 있다. 즉, 두 개의 데이타베이스로부터 연관 규칙을 찾는 연구가 필요하다. 이 논문에서는 두 데이타베이스 사이에 링크를 생성하여 연관 항목집합을 찾는 알고리즘을 제안한다. 실험 결과, 링크를 이용한 알고리즘은 고객 데이타베이스가 메모리에 거주가능한 크기라면 시간에 따른 분석에 유용함을 보여주었다.Abstract There have been a lot of researches of mining association rules from one database such as transaction database until now. But as the large discount store using customer card emerges, the analysis is not only required about transactions, but also about the relation between transactions and customer data. That is, it is required to search association rules from two databases. This paper proposes an efficient algorithm constructing links from one database to the other. Our experiments show the algorithm using link is useful for temporal analysis of memory-resident customer database.