Dong-Ho Lee

A log buffer-based flash translation layer using fully-associative sector translation

Flash memory is being rapidly deployed as data storage for mobile devices such as PDAs, MP3 players, mobile phones, and digital cameras, mainly because of its low electronic power, nonvolatile storage, high performance, physical stability, and portability. One disadvantage of flash memory is that prewritten data cannot be dynamically overwritten. Before overwriting prewritten data, a time-consuming erase operation on the used blocks must precede, which significantly degrades the overall write performance of flash memory. In order to solve this “erase-before-write” problem, the flash memory controller can be integrated with a software module, called “flash translation layer (FTL).” Among many FTL schemes available, the log block buffer scheme is considered to be optimum. With this scheme, a small number of log blocks, a kind of write buffer, can improve the performance of write operations by reducing the number of erase operations. However, this scheme can suffer from low space utilization of log blocks. In this paper, we show that there is much room for performance improvement in the log buffer block scheme, and propose an enhanced log block buffer scheme, called FAST (full associative sector translation). Our FAST scheme improves the space utilization of log blocks using fully-associative sector translations for the log block sectors. We also show empirically that our FAST scheme outperforms the pure log block buffer scheme.

System software for flash memory: a survey

Recently, flash memory is widely adopted in embedded applications since it has several strong points: non-volatility, fast access speed, shock resistance, and low power consumption. However, due to its hardware characteristic, namely “erase before write”, it requires a software layer called FTL (Flash Translation Layer). This paper surveys the state-of-the-art FTL software for flash memory. This paper also describes problem definitions, several algorithms proposed to solve them, and related research issues. In addition, this paper provides performance results based on our implementation of each of FTL algorithms

HFTL: hybrid flash translation layer based on hot data identification for flash memory

For the last years, a number of flash translation layers (FTL) have been proposed for hiding erase-before-write architecture of NAND flash memory. However, although many conventional FTLs efficiently provide the logical to physical address remapping algorithms, they could not escape from the performance degradation when handling the hot data which tends to generate so many overwrites on the same logical address. In this paper, we propose a novel FTL algorithm called Hybrid Flash Translation Layer (HFTL) that adaptively exploits the sector mapping and log block based mapping schemes. To do so, HFTL first separates the hot data from the cold data by using the hot data identifier. And then it dynamically manages the former by using the sector mapping scheme showing an optimal performance for intensive overwrites at the same location, and the latter by using the log block based mapping scheme. By using this adaptive hybrid method, HFTL is always guaranteed to yield good performance for the pattern with the hot data as well as the pattern without it. Through a series of experiments, we show that HFTL yields better performance than conventional FTLs.

A New Edge-based Intra-field Interpolation Method for Deinterlacing Using Locally Adaptive-thresholded Binary Image

Traditional edge-based methods for de interlacing were poor at determining accurate edge direction which decides interpolation performance. The proposed method decides the direction and slope of edge based on locally adaptive-thresholded binary image, and it also increased the horizontal size of search window for better performance.

Ontology-based automatic video annotation technique in smart TV environment

Due to the recent explosive growth of smart TV and its applications, the need for multimedia contents analysis techniques for smart TV environment has dramatically increased. In particular, automatic video annotation and summarization technique is considered as one of the most important technique for smart TV because an enormous number of social videos are now becoming available as well as traditional digital videos such as TV programs and VODs. In this paper, we present an automatic video annotation technique which employs the ontologies to facilitate the video retrieval and sharing process in smart TV environment. In our work, ontologies are exploited to hierarchically describe the contents of video and facilitate the sharing of video contents among heterogeneous users or devices (e.g., smart phone, PDA, and so on). Through various experimental results, we show the effectiveness of the proposed approach.

A fast content-based indexing and retrieval technique by the shape information in large image database

Abstract In this paper, we present an efficient content-based image retrieval (CBIR) system which employs the shape information of images to facilitate the retrieval process. For efficient feature extraction, we extract the shape feature of images automatically using edge detection and wavelet transform which is widely used in digital signal processing and image compression. To facilitate speedy retrieval, we also propose the Spherical Pyramid-Technique (SPY-TEC), a new indexing method for similarity search in high-dimensional data space. The SPY-TEC is based on a special space partitioning strategy, which is to divide the d-dimensional data space first into 2d spherical pyramids, and then cut the single spherical pyramid into several spherical slices. This partition provides a transformation of d-dimensional space into 1-dimensional space. Thus, we are able to use a B+-tree to manage the transformed 1-dimensional data. We show that our image indexing method supports faster retrieval than other multi-dimensional indexing methods such as the R*-tree through various experiments. Finally, we show the retrieval effectiveness of our CBIR system using the measure proposed by the QBIC (C. Faloutsos et al., 1994) system.

Alleviation of rheumatoid arthritis by cell-transducible methotrexate upon transcutaneous delivery

Rheumatoid arthritis (RA) is a systemic autoimmune disease that is initiated and maintained by various inflammatory/immune cells and their cytokines, leading to cartilage degradation and bone erosion. Despite its potent therapeutic efficacy on RA, the oral administration of methotrexate (MTX) provokes serious adverse systemic complications, thus necessitating the local application of MTX. Here, we show that transcutaneous MTX (TC-MTX) can efficiently penetrate joint skin ex vivo and in vivo, and that TC-MTX can significantly improve the various inflammatory symptoms associated with RA. Further, TC-MTX preserved the joint-structures in mice with collagen-induced arthritis (CIA), which was also confirmed by three-dimensional micro-computed tomography scan. TC-MTX markedly decreased the secretion of inflammatory cytokines both in the serum and in inflamed joints of CIA mice. Further, its therapeutic potential is comparable to that of etanercept, a biological agent that block tumor necrosis factor (TNF)-α. Importantly, the systemic cytotoxicity of TC-MTX was not detected. Thus, TC-MTX can be a new therapeutic modality for RA patients without systemic complications.

Editorial: An efficient index buffer management scheme for implementing a B-tree on NAND flash memory

Recently, NAND flash memory has been one of the best storage mediums for various embedded systems such as MP3 players, mobile phones and laptops because of its shock-resistant, low-power consumption, and none-volatile properties. However, since it has very distinct characteristics including erase-before-write and asymmetric read/write speed, the performance of disk based systems and applications may degrade dramatically when directly adopting them on the flash memory storage systems. Especially when a B-tree is constructed on NAND flash memory, intensive overwrite operations may be caused by record inserting, deleting, and reorganizing. These may result in severe performance degradation when building the B-tree. In this paper, we propose an efficient index buffer management scheme, called IBSF, which eliminates redundant index units in the index buffer and then delays the time that the index buffer requires to become full. Consequently, IBSF significantly reduces the number of write operations to a flash memory when constructing a B-tree. We also show that IBSF yields a better performance on a flash memory by comparing it to the related technique through various experiments.

Compact video signatures for near-duplicate detection on mobile devices

In this paper, we focus on generating compact but efficient video signatures on mobile devices so that users quickly know whether there are near-duplicates in the social network systems when they upload a video. For this, the proposed method employs the idea of inverted index that is one of the most popular text retrieval methods. Experimental results show that our method can achieve similar results compared with state-of-the-art method whereas it requires low memory and computation cost.

OLYBIA: ontology-based automatic image annotation system using semantic inference rules

One of the big issues facing current content-based image retrieval is how to automatically extract the high-level concepts from images. In this paper, we present an efficient system that automatically extracts the high-level concepts from images by using ontologies and semantic inference rules. In our method, MPEG-7 visual descriptors are used to extract the visual features of image, and the visual features are mapped to semi-concepts via the mapping algorithm. We also build the visual and animal ontologies to bridge the semantic gap. The visual ontology allows the definition of relationships among the classes describing the visual features and has the values of semi-concepts as the property values. The animal ontology can be exploited to identify the highlevel concept in an image. Also, the semantic inference rules are applied to the ontologies to extract the high-level concept. Finally, we evaluate the proposed system using the image data set including various animal objects and discuss the limitations of our system.