Pei-Lun Suei

An Adaptive Endurance-Aware

This work is motivated by the strong demand for flash-friendly index designs to resolve reliability and performance concerns for data manipulation over flash memory. In comparison to previous work, we propose and explore the impact of hot-data access, sibling-link updates, and different workload types to a tree index structure over flash memory. In particular, a flash-friendly B+-tree, referred to as an Adaptive Durable B+-tree, is proposed to not only improve the endurance but also the performance of a tree index structure. The capability of the proposed methodology and index design is evaluated through a series of experiments, in which significant improvement on endurance was achieved in comparison to previous reports on the subject.

{B^+}

The forensics and anti-forensics of digital videos are investigated.An anti-forensic method to generate H.264 videos without abnormal coding modes and redundancies.The forensic methods based on the deblocking filter and checking the quantization parameters. This research investigates the forensics and anti-forensics of video editing operations, including shot insertion and deletion, which are common practices of content tampering. The proposed methodology is based on the fact that excessive prediction residuals in the H.264/AVC encoding may appear in the inter-coded frames that were intra-coded. For the anti-forensics, the relationships of coding modes in consecutive frames are employed to determine whether the intra-prediction can be applied during the re-encoding process of the tampered video. The correspondences of coding parameters and the bit-rates are then examined to predict the targeted distribution of quantization indices. Some nonzero indices are modified for satisfying the targeted distribution and generating a video that does not seem an edited one. Next, two forensic methods are presented. The first method evaluates the energy of resulting residuals after the deblocking filtering to reveal the editing operations that have been applied. The second method makes use of the rate control mechanism to check the quantization parameters. Although there exist certain limitations, the methods deserve more discussions under appropriate conditions.

-Tree for Flash Memory Storage Systems

As flash memory emerges as a high-performance and energy-efficient alternative for storage devices, how to accommodate disk-based storage servers with a flash-memory cache might provide a promising solution to resolve the energy-efficiency concerns of storage servers and their data centers. In this work, we propose a cache design method over flash memory without any additional hardware support for storage servers. In particular, a scalable set-associative flash-cache management design is proposed to significantly improve the flash endurance with excellent caching response time and hit rates. The capability of the proposed scheme was evaluated by extensive experiments over Microsofts server traces, in which significant improvement on endurance was achieved, compared to existing work.

Forensic and anti-forensic techniques for video shot editing in H.264/AVC

A large-scaled RFID application often needs a highly efficient database system in data processing. This research is motivated by the strong demand of an efficient index structure design for main-memory database systems of RFID applications. In this paper, a signature-based grid index structure is proposed for efficient data queries and storage. An efficient methodology is proposed to locate duplicates and to execute batch deletions and range queries based on application domain knowhow. The capability of the design is implemented in an open source main-memory database system H2 and evaluated by realistic workloads of RFID applications.

Endurance-Aware Flash-Cache Management for Storage Servers

A large-scale RFID application often requires a highly efficient database system in data processing. This research is motivated by the strong demand for an efficient index structure design for main-memory database systems of RFID applications. In this paper, a signature-based Grid index structure is proposed for efficient data queries and storage. An efficient methodology is proposed to locate duplicates and to execute batch deletions and range queries based on application domain knowhow. The capability of the design is implemented in an open source main-memory database system H2 and evaluated by realistic workloads of RFID applications.

A Signature-based Grid Index Design for RFID Main-Memory Databases

In recent years, many researchers and vendors have proposed their XML storage approaches based on relational databases (RDB), which are called XML-relational databases (XRDB). To manipulate XML data in XRDB, many excellent model-mapping schemas were proposed to provide schema definitions to translate various XML documents with different structures into relational tables. Such an approach can support any sophisticated applications and well-formed XML documents. When XML data stored in an XRDB, the user query must be translated into the corresponding SQL commands, then executed in the relational database. However, most model-mapping-schema-based approaches have a potential performance problem for retrieving XML data from an XRDB, because a large number of join operations are needed. In this paper, a novel query preprocessing technique will be proposed to reduce the number of join operations from the corresponding SQL commands. The rationale behind our approach is to replace join operations by predefined constant-mapping selection operations. By reducing the number of join operations, the performance of query processing can be greatly improved. The capability of our proposed approach was verified by experiments, for which we have some encouraging results.

A signature-based Grid index design for main-memory RFID database applications

Creates two new intra prediction modes through the concept of a finite state machine.Adaptively selects the template shape.Achieves 11% bit rate reduction when compared to H.264/AVC and 4% bit rate reduction when compared to HEVC. This paper presents a new approach that aims to improve the performance of the intra block coding of H.264/AVC and HEVC by using a finite state machine. Based on the high correlations between a frames neighboring blocks, the finite state machine is employed at both the encoder and decoder to reduce the number of bits required for intra encoding, improving the coding performance of videos. With the matching adaptive template, a better prediction block is found. Through the proposed extra intra prediction modes, the number of bits required to encode a block is reduced significantly, and thus a better intra coding performance is achieved. In addition, an early termination is proposed to speed-up the coding performance. Experimental results show that with the proposed method, the bit rate can be reduced 11% on average when compared to H.264/AVC and 4% on average when compared to HEVC.

A Novel Query Preprocessing Technique for Efficient Access to XML-Relational Databases

This work is motivated by the strong demands of flash-friendly index designs to resolve reliability and performance concerns for data manipulations over flash memory. Different from the past work, we propose and explore the impacts of hot-data access and sibling-link updates to a tree index structure over flash memory. In particular, a flash-friendly B+-tree, referred to as a Durable B+-tree, is proposed to not only improve the endurance but also the performance of a tree index structure over flash memory. The capability of the proposed methodology and index design was evaluated by a series of experiments, in which significant improvement on endurance was achieved, compared with the past work.

A new intra prediction with adaptive template matching through finite state machine

Multi-dimensional temporal data set is the common format in sensor network applications to store sampled temporal data. As time goes on, the size of the core tables in the data set may increase to enormous size and the tables become not managable. In order to reduce storage space and allow on-line query, how to trade off data compression effectiveness for on-line query performance is a challenge issue. In this paper, we are concerned with an effective framework for temporal data set that does not scarify on-line query performance and is specifically designed for very large sensor network database. The sampled data are compressed using several candidate approaches including dictionary-base compress and lossless vector quantization. In the mean time, on-line queries are conducted without decompressing the compressed data set so as to enhance the query performance. Experiments are conducted on a power meter database and sonoma database to evaluate the proposed methodologies in terms of data compression rate and data query speed. The results show that the compression rate ranges from 70% for numerical data to 20% for character data. In the mean time, the increased overhead for online query is limited up to 2%.

A flash-friendly B + -tree with endurance-awareness

With the advances of manufacturing technology and aggressive use of multi-level-cell (MLC) for flash memory, flash memory has faced a serious challenge on its device lifetime due to the fast-decreasing capacity caused by worn-out blocks. In contrast to existing works, we propose a block reinforcement scheme to optimize the guaranteed lifetime of flash storage devices by extending the useable period of flash blocks with limited performance degradation and space overhead. A serious of experiments was conducted to evaluate the efficacy of the proposed scheme and the results are very encouraging.