Lihua Yue

CCF-LRU: a new buffer replacement algorithm for flash memory

NAND flash memory has been widely used for storage in embedded systems and recently in enterprise computing environment, owing to its shock-resistance, nonvolatile, low energy consumption, and high I/O speed. In addition, flash memory has the characteristics of not-in-place update and asymmetric I/O costs among read, write, and erase operations, in which the cost of write/erase operations is much higher than that of read operation. Hence, the buffer replacement algorithms in flash-based systems should take the asymmetric I/O costs into account. Previous solutions to this issue, such as CFLRU and LRU-WSR, used a clean-first scheme to first evict clean pages from the buffer. Although they outperform the traditional LRU policy in performance, they do not consider the access frequency of clean page, which will consequently result in poor I/O performance. In order to solve this problem, we present a new buffering algorithm in this paper, called CCF-LRU, which enhances the previous CFLRU and LRU-WSR methods by differentiating clean pages into cold and hot ones, and evicting cold clean pages first and delaying the eviction of hot clean pages. We conduct a trace-driven experiment on a flash memory simulation environment, and use six types of synthesized traces as well as a real OLTP trace. The results show that the CCF-LRU algorithm outperforms LRU, CFLRU and LRUWSR in write count and runtime in all experiments. In particular, it provides more than 20% improvement over its competitors both in write count and runtime, when running the real OLTP trace.

An approach for image retrieval based on visual saliency

Considering the gap between low-level image features and the high-level semantic concept in content-based image retrieval (CBIR), a new approach is proposed for image retrieval based on visual saliency, by analyzing the human visual perception process. Visual information is introduced as the new feature which reflects high-level semantic concept objectively. First, the visual saliency model for image retrieval is established. The saliency features of intensity, color and texture are calculated. Second, integrated global saliency map is synthesized and its statistic histogram is used as a new feature in image retrieval. Finally, the similarity of color images is computed by combining the color feature and the histogram of integrated saliency map. Results of experiments show that our approach improves retrieval precision and recall when compared with the classical color feature approach.

Extracting Focused Locations for Web Pages

Most Web pages contain location information, which can be used to improve the effectiveness of search engines. In this paper, we concentrate on the focused locations, which refer to the most appropriate locations associated with Web pages. Current algorithms suffer from the ambiguities among locations, as many different locations share the same name (known as GEO/GEO ambiguity), and some locations have the same name with non-geographical entities such as person names (known as GEO/NON-GEO ambiguity). In this paper, we first propose a new algorithm named GeoRank, which employs a similar idea with PageRank to resolve the GEO/GEO ambiguity. We also introduce some heuristic rules to eliminate the GEO/NON-GEO ambiguity. After that, an algorithm with dynamic parameters to determine the focused locations is presented. We conduct experiments on two real datasets to evaluate the performance of our approach. The experimental results show that our algorithm outperforms the state-of-the-art methods in both disambiguation and focused locations determination.

An adaptive block-set based management for large-scale flash memory

With rapid increase of the capacity of flash-memory storage systems, it becomes critical to provide efficient management for large-scale flash-memory. Compared with FTL (Flash Translation Layer), NFTL (NAND Flash Translation Layer) provides less main-memory space requirements for large-scale flash memory. However, because each replacement block is exclusively used by a logical block, NFTL exhibits poor space utilization of flash memory. In this paper, we present an adaptive block-set based flash memory management. The presented scheme adopts shared and exclusive replacement blocks, and allocates replacement blocks according to the update loads of logical blocks. The experimental results show that the presented scheme yields a better performance in garbage collection than NFTL and FAST (fully associative sector translation), keeping space utilization of flash memory at high level.

Exploiting temporal information in Web search

Time plays important roles in Web search, because most Web pages contain temporal information and a lot of Web queries are time-related. How to integrate temporal information in Web search engines has been a research focus in recent years. However, traditional search engines have little support in processing temporal-textual Web queries. Aiming at solving this problem, in this paper, we concentrate on the extraction of the focused time for Web pages, which refers to the most appropriate time associated with Web pages, and then we used focused time to improve the search efficiency for time-sensitive queries. In particular, three critical issues are deeply studied in this paper. The first issue is to extract implicit temporal expressions from Web pages. The second one is to determine the focused time among all the extracted temporal information, and the last issue is to integrate focused time into a search engine. For the first issue, we propose a new dynamic approach to resolve the implicit temporal expressions in Web pages. For the second issue, we present a score model to determine the focused time for Web pages. Our score model takes into account both the frequency of temporal information in Web pages and the containment relationship among temporal information. For the third issue, we combine the textual similarity and the temporal similarity between queries and documents in the ranking process. To evaluate the effectiveness and efficiency of the proposed approaches, we build a prototype system called Time-Aware Search Engine (TASE). TASE is able to extract both the explicit and implicit temporal expressions for Web pages, and calculate the relevant score between Web pages and each temporal expression, and re-rank search results based on the temporal-textual relevance between Web pages and queries. Finally, we conduct experiments on real data sets. The results show that our approach has high accuracy in resolving implicit temporal expressions and extracting focused time, and has better ranking effectiveness for time-sensitive Web queries than its competitor algorithms.

A reliable B-tree implementation over flash memory

Flash memory has been widely used in various embedded computing systems and portable devices in recent years because of its small size, shock-resistance, low-power consumption and non-volatile properties. To hide the disadvantages of flash memory such as out-of-place update, a flash translation layer (FTL) is usually used for providing transparent block-device emulation. But when index structures are implemented over FTL, intensive overwrite operations caused by record inserting, deleting, modifying and index reorganizing could not only degrade the performance significantly but also reduce the life of flash memory. To address the problem, BFTL and IBSF are proposed. However, neither of them could avoid the loss of records and incompatibilities when system crash occurs. In this paper, a reliable B-tree implementation called RBFTL is presented for flash-memory storage systems. It is placed between the application layer and FTL. RBFTL could minimize the loss of data and eliminate incompatibilities effectively and efficiently when system crashes. The experimental results also show that RBFTL yields a better performance than FTL.

Continuous Dynamic Constrained Optimization With Ensemble of Locating and Tracking Feasible Regions Strategies

Dynamic constrained optimization problems (DCOPs) are difficult to solve because both objective function and constraints can vary with time. Although DCOPs have drawn attention in recent years, little work has been performed to solve DCOPs with multiple dynamic feasible regions from the perspective of locating and tracking multiple feasible regions in parallel. Moreover, few benchmarks have been proposed to simulate the dynamics of multiple disconnected feasible regions. In this paper, first, the idea of tracking multiple feasible regions, originally proposed by Nguyen and Yao, is enhanced by specifically adopting multiple subpopulations. To this end, the dynamic species-based particle swam optimization (DSPSO), a representative multipopulation algorithm, is adopted. Second, an ensemble of locating and tracking feasible regions strategies is proposed to handle different types of dynamics in constraints. Third, two benchmarks are designed to simulate the DCOPs with dynamic constraints. The first benchmark, including two variants of G24 (called G24v and G24w), could control the size of feasible regions. The second benchmark, named moving feasible regions benchmark (MFRB), is highly configurable. The global optimum of MFRB is calculated mathematically for experimental comparisons. Experimental results on G24, G24v, G24w, and MFRB show that the DSPSO with the ensemble of strategies performs significantly better than the original DSPSO and other typical algorithms.

A Novel Algorithm for Ship Detection Based on Dynamic Fusion Model of Multi-feature and Support Vector Machine

Ship detection is one of the most important applications of target recognition based on optical remote sensing images. In this paper, we propose an uncertain ship target extraction algorithm based on dynamic fusion model of multi-feature and variance feature of optical remote sensing image. We choose several geometrical features, such as length, wide, rectangular ratio, tightness ratio and so on, using SVM to train and predict the uncertain ship targets extracted by our algorithm automatically. Experiments show that our algorithm is very robust, and the recognition rate of our algorithm can reach or even better than 95%, with the false alarm rate is kept at 3%.

Flash memory management based on predicted data expiry-time in embedded real-time systems

Flash memory based embedded systems are becoming increasingly prevalent. Garbage collection mechanism is a critical issue in these systems, especially in embedded real-time systems. Therefore, in this article, we discuss the influence of the capacity utilization (percentage of fullness) of the flash memory on allocating and recycling, and propose a new flash memory management technique, namely PETFM. The proposed technique improves the performance of garbage collection mechanism by allocating free pages from different allocated-blocks for data to be updated, based on their predicted expiry-time. The analytical and experimental results show that garbage collection of PETFM is more efficient and effective under high capacity utilization in embedded real-time systems.

Negative Iris Recognition

Elements of a persons biometrics are typically stable over the duration of a lifetime, and thus, it is highly important to protect biometric data while supporting recognition (it is also called secure biometric recognition). However, the biometric data that are derived from a person usually vary slightly due to a variety of reasons, such as distortion during picture capture, and it is difficult to use traditional techniques, such as classical encryption algorithms, in secure biometric recognition. The negative database (NDB) is a new technique for privacy preservation. Reversing the NDB has been demonstrated to be an NP-hard problem, and several algorithms for generating hard-to-reverse NDBs have been proposed. In this paper, first, we propose negative iris recognition, which is a novel secure iris recognition scheme that is based on the NDB. We show that negative iris recognition supports several important strategies in iris recognition, e.g., shifting and masking. Next, we analyze the security and efficiency of negative iris recognition. Experimental results show that negative iris recognition is an effective and secure iris recognition scheme. Specifically, negative iris recognition can achieve a highly promising recognition performance (i.e., GAR = 98.94% at FAR = 0.01%, EER = 0.60%) on the typical database CASIA-IrisV3-Interval.