• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.58-66
• /
• 2003

In this paper. an image compression of embedded zerotree structure using multiwavelet filter banks is proposed. Multiwavelet is used DGHM(Donovan, Geronimo, Hardin, and Massopust) scaling functions and wavelet functions of a new method with two channel fillet banks. The important properties of the DGHM multiwavelet are orthogonality and approximation order. The DCHM muitiwavelet using the this paper preserves the approximation order=2 for better energy compaction and perfect reconstruction. Image compression using the preposed DGHM multiwavelet is better PSNR for compression ratio than single Daubechies wavelet(D4), Biorthogoanl wavelet, and GHM(Geronimo, Hardin, and Massopust) multi wavelet.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.65-78
• /
• 2009

The most commonly adopted approach to find valuable information from tree data is to extract frequently occurring subtree patterns from them. Because mining frequent tree patterns has a wide range of applications such as xml mining, web usage mining, bioinformatics, and network multicast routing, many algorithms have been recently proposed to find the patterns. However, existing tree mining algorithms suffer from several serious pitfalls in finding frequent tree patterns from massive tree datasets. Some of the major problems are due to (1) modeling data as hierarchical tree structure, (2) the computationally high cost of the candidate maintenance, (3) the repetitious input dataset scans, and (4) the high memory dependency. These problems stem from that most of these algorithms are based on the well-known apriori algorithm and have used anti-monotone property for candidate generation and frequency counting in their algorithms. To solve the problems, we base a pattern-growth approach rather than the apriori approach, and choose to extract maximal frequent subtree patterns instead of frequent subtree patterns. The proposed method not only gets rid of the process for infrequent subtrees pruning, but also totally eliminates the problem of generating candidate subtrees. Hence, it significantly improves the whole mining process.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.6
• /
• pp.521-531
• /
• 2009

Flash memory has physical characteristics different from hard disk where two costs of a read and write operations differ each other and an overwrite on flash memory is impossible to be done. In order to solve these restrictions with software, storage systems equipped with flash memory deploy FTL(Flash Translation Layer) software. Several FTL algorithms have been suggested so far and most of them prefer sequential write pattern to random write pattern. In this paper, we provide a new technique to efficiently store and maintain the B-tree index on flash memory. The operations like inserts, deletes, updates of keys for the B-tree generate random writes rather than sequential writes on flash memory, leading to inefficiency to the B-tree maintenance. In our technique, we convert random writes generated by the B-tree into sequential writes and then store them to the write-buffer on flash memory. If the buffer is full later, some sequential writes in the buffer will be issued to FTL. Our diverse experimental results show that our technique outperforms the existing ones with respect to the I/O cost of flash memory.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.77-79
• /
• 2012

본 논문에서는 임베디드 시스템으로의 적용을 위한 균형이진트리 방식의 허프만 코딩 복호화 방법에 대하여 논한다. 그리고 구현된 전체 시스템의 간단한 코드 최적화(code optimization)를 추가하여 시스템 전체의 처리 속도를 감소시키고자 하였다. 본문에서는 구현된 복호화 성능 향상의 정확한 측정을 위하여 하드웨어 시뮬레이터를 사용했다. 이를 통해서 실질적인 환경에서 어느 정도의 duration으로 동작될 수 있는지, 그리고 해당 환경에서 얼마나 성능을 향상시킬 수 있을지를 비교적 정확하게 판단할 수 있도록 했다. 본문의 마지막에 명시된 대로, 최적화의 결과로, 허프만 코드를 표에서 찾는 기존의 방법에 비하여, 복호화 부분과 복호화 부분을 제외한 시스템 코드 최적화 각각 36%, 2%의 duration 횟수의 감소를 확인할 수 있었다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.2
• /
• pp.79-86
• /
• 2019

For decades, in-memory data structures have been designed for DRAM-based main memory that provides symmetric read/write performances and has no limited write endurance. However, such data structures provide sub-optimal performance for NVM as it has different characteristics to DRAM. With this motivation, we rethink a conventional red-black tree in terms of its efficacy under NVM settings. The original red-black tree constantly rebalances sub-trees so as to export fast access time over dataset, but it inevitably increases the write traffic, adversely affecting the performance for NVM with a long write latency and limited endurance. To resolve this problem, we present a variant of the red-black tree called a hierarchical balanced binary search tree. The proposed structure maintains multiple keys in a single node so as to amortize the rebalancing cost. The performance study reveals that the proposed hierarchical binary search tree effectively reduces the write traffic by effectively reaping the high capacity of NVM.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.67-73
• /
• 2023

Tree routing is one of appropriate routing schemes in wireless sensor network because the complexity of this approach is relatively low. But, congestion at a specific node may happen because a parent node toward a sink node is usually selected in one hop way, specially where large number of node are deployed. As feasible solution for this problem, multiple paths and sinks schemes can be applied. However, the performance of these schemes are not proved and analyzed yet. In this paper, we conduct diverse simulaton scenarios performance evaluation for these cases to identify the improvement and analyze the impact of schemes. The performance is measured in the aspects of packet transmission rate, throughput, and end-to-end delay as a function of amount of network traffic.

• The Journal of the Korea Contents Association
• /
• v.11 no.1
• /
• pp.16-25
• /
• 2011

Some context is characterized by a single event in computing environment, but many other contexts are determined by a lot of things which occur with a space and a time. The Realtime Embedded System context-awareness service that interacts with the physical space can have property such as time. The exceptional behaviors of the system that interact with physical space can result in critical damage and cause danger to the operation of an embedded system. we propose an approach which should include spatio-temporal property and exceptional management in the context model, and verify its effectiveness using an expanded Petri-Net. The context-awareness service modeling of an embedded system is discussed the properties of model such as basic Petri-Net, patterned Petri-Net, or Spatio-temporal Petri-Net for the exceptional behaviors of the system. The proposed methodology demonstrated using an example that is emergency medical service. The use of expanded Petri-Net will contribute not only to develop the application but also to model the spatio-temporal context awareness for the exceptional handling.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.185-188
• /
• 1998

본 논문에서는 새로운 예측 방법을 사용한 웨이브릿 영상 압축 방식을 제안한다. 에지는 시각적으로 매우 중요한 성분이며 밴드간에도 높은 상관도를 가지고 있다. 또한 에지는 각 밴드의 성질에 맞는 일정한 방향을 가지고 있다. 본 논문에서는 자식 계수들의 배열이 밴드 방향에 따라 방향성을 가진다는 것을 예측에 이용하여 새로운 트리를 통해 영상을 압축하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3227-3235
• /
• 2011

In this paper, a relational embedded DBMS was designed and a prototype 'Miracle' RDBMS (MDB) was developed. MDB is written in C and works on Unix, Linux and Windows platforms locally. It accesses database through SQL interfaces and API functions and uses $B^+$ tree index. It guarantees ACID in transactions and supports low concurrency control and processes SQL statements on a single table. To evaluate the performance of MDB on an ARM board EZ-S3C6410 and to compare the performance of MDB with that of SQLite, an experiment was carried out to estimate processing times for insertion, selection, update and deletion operations. The result shows that the average times for selections and insertions in MDB were 38.46% and 22.86% faster than those in SQLite, respectively, but the average times for updates and deletions in SQLite were 28.33% and 26.00% faster than MDB, respectively, This experiment shows that fetching data from database and sending data to database in MDB is faster than in SQLite, but $B^+$ tree index is implemented more effectively in SQlite than in MDB.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.1-12
• /
• 2015

NAND flash memory has being used for storage systems widely, because it has good features which are low-price, low-power and fast access speed. However, NAND flash memory has an in-place update problem, and therefore it needs FTL(flash translation layer) to run for applications based on hard disk storage. The FTL includes complex functions, such as address mapping, garbage collection, wear leveling and so on. Futhermore, implementation of the FTL on low-power embedded systems is difficult due to its memory requirements and operation overhead. Accordingly, many index data structures for NAND flash memory have being studied for the embedded systems. Overall performances of the index data structures are enhanced by a decreasing of page write counts, whereas it has increased page read counts, as a side effect. Therefore, we propose an index management method using a page mapping log table in $B^+$-Tree based on NAND flash memory to decrease page write counts and not to increase page read counts. The page mapping log table registers page address information of changed index node and then it is exploited when retrieving records. In our experiment, the proposed method reduces the page read counts about 61% at maximum and the page write counts about 31% at maximum, compared to the related studies of index data structures.