检索结果-内蒙古大学图书馆

Data compression Conference (DCC)

作者： Constantinescu, Cornel Schmidt, Gero IBM Almaden Res Ctr San Jose CA 95120 USA

ISBN: (纸本)9781538648834

Despite the large number of research papers and compression algorithms proposed for com- pressing FASTQ genomic data generated by sequencing machines, by far the most commonly used compression algorithm in the industry for FASTQ data is gzip. The main drawback of the proposed alternative special-purpose compression algorithms is the slow speed of either compression or de- compression or both, and also their brittleness by making various limiting assumptions about the input FASTQ format (for example, the structure of the headers or fixed lengths of the records [5]) in order to further improve their specialized compression. In this paper we propose using a simple modeling improvement combined with fast general purpose encoders, achieving 4X-40X speed improvements and 6%-11% more efficienct compression ratios for the compression and decompression of FASTQ genomic data compared to gzip and also being 5X faster than special-purpose FASTQ compressors like DSRC v2 and slimfastq.

关键词： Genomics Bioinformatics Sequential analysis compression algorithms Robustness Data compression Industries

来源：评论

学校读者我要写书评

暂无评论

Titan II: An IPcomp processor for 10-Gbps networks

引用

IEEE DESIGN & TEST OF COMPUTERS 2004年第6期21卷 514-523页

作者： Papaefstathiou, I Fdn Res & Technol Hellas Inst Comp Sci GR-71110 Iraklion Greece

Data compression techniques can alleviate low-bandwidth problems in multigigabit networks, and are especially useful when combined with encryption. The Titan II is a hardware compressor/decompressor core capable of speeds of up to 10 gigabits per second. Its compression algorithm is a variation of the Lempel-Ziv LZ) algorithm that uses part of the previous input stream as the dictionary.

关键词： Hardware Bandwidth compression algorithms Lithography Cams Very large scale integration Data compression Dictionaries Design optimization Silicon

来源：评论

学校读者我要写书评

暂无评论

TREE-STRUCTURED VECTOR QUANTIZATION OF CT CHEST SCANS - IMAGE QUALITY AND DIAGNOSTIC-ACCURACY

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 1993年第4期12卷 727-739页

作者： COSMAN, PC TSENG, C GRAY, RM OLSHEN, RA MOSES, LE DAVIDSON, HC BERGIN, CJ RISKIN, EA STANFORD UNIV SCH MEDDIV BIOSTATSTANFORDCA 94305 STANFORD UNIV SCH MEDDEPT DIAGNOST RADIOL & NUCL MEDSTANFORDCA 94305 STANFORD UNIV SCH MEDDIV DIAGNOST RADIOLSTANFORDCA UNIV WASHINGTON DEPT ELECT ENGNSEATTLEWA 98195

The quality of lossy compressed images is often characterized by signal-to-noise ratios, informal tests of subjective quality, or receiver operating characteristic (ROC) curves that include subjective appraisals of the value of an image for a particular application. We believe that for medical applications, lossy compressed images should be judged by a more natural and fundamental aspect of relative image quality: their use in making accurate diagnoses. We apply a lossy compression algorithm to medical images, and quantify the quality of the images by the diagnostic performance of radiologists, as well as by traditional signal-to-noise ratios and subjective ratings. Our study is unlike previous studies of the effects of lossy compression in that we consider non-binary detection tasks, simulate actual diagnostic practice instead of using paired tests or confidence rankings, use statistical methods that are more appropriate for non-binary clinical data than are the popular ROC curves, and use low-complexity predictive tree-structured vector quantization for compression rather than DCT-based transform codes combined with entropy coding. Our diagnostic tasks are the identification of nodules (tumors) in the lungs and lymphadenopathy in the mediastinum from computerized tomography (CT) chest scans. Radiologists read both uncompressed and lossy compressed versions of images. For the image modality, compression algorithm, and diagnostic tasks we consider, the original 12 bit per pixel (bpp) CT image can be compressed to between 1 bpp and 2 bpp with no significant changes in diagnostic accuracy. The techniques presented in this paper for evaluating image quality do not depend on the specific compression algorithm and are useful new methods for evaluating the benefits of any lossy image processing technique.

关键词： Vector quantization Computed tomography Image coding compression algorithms Biomedical imaging Medical diagnostic imaging Performance loss Signal to noise ratio Predictive models Medical simulation

来源：评论

学校读者我要写书评

暂无评论

PRIORITIZATION AND TRANSPORT IN THE ADTV DIGITAL SIMULCAST SYSTEM

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 1992年第3期38卷 319-324页

作者： JOSEPH, K NG, S SIRACUSA, R RAYCHAUDHURI, D ZDEPSKI, J SAINTGIRONS, R THOMSON CONSUMER ELECTR LOS ANGELES RES & DEV LABCULVER CITYCA 90230 DAVID SARNOFF RES CTR BROADBAND COMMUN RES GRPPRINCETONNJ 08543

This paper provides a technical overview of the prioritization and transport in the Advanced Digital Television system (ADTV). ADTV is the all-digital terrestrial simulcast system developed by the Advanced Television Research Consortium, ATRC, (Thomson Consumer Electronics, Philips North America, NBC, compression Labs, and the David Sarnoff Research Center.) ADTV incorporates an efficient MPEG-compatible compression algorithm at its central core, with application-specific data prioritization and transport features added as separable layers. The compression process is based on a 1440x960 (1050-line 2:1 interlaced) HDTV format, producing a selectable bit-rate in the region of 15-20 Mbps. The data prioritization layer of ADTV achieves robust delivery over an appropriate two-tier modem by separating compressed video data into high- and standard-priority bitstreams with appropriate bit-rates. This prioritized data is then formatted into fixed length "cells" (packets) with appropriate data-link level and service-specific adaptation level headers, designed to provide capabilities such as flexible service multiplexing, priority handling, efficient cell packing, error detection and graceful recovery from errors. (Issues related to the ADTV compression coding, receiver error recovery, and transmission are discussed in separate papers.[1,2,3])

关键词： HDTV Video compression Transform coding Error correction Consumer electronics Robustness Digital TV compression algorithms Decoding Cities and towns

来源：评论

学校读者我要写书评

暂无评论

Dynamic coding of visual information

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 1997年第3期7卷 489-500页

作者： Reusens, E Ebrahimi, T Kunt, M SWISS FED INST TECHNOL SIGNAL PROC LAB CH-1015 LAUSANNE SWITZERLAND

This paper introduces a novel approach to visual data compression. The approach, named dynamic coding, consists of an effective competition between several representation models used for describing data portions, The image data is represented as the union of several regions each approximated by a representation model locally appropriate, The dynamic coding concept leads to attractive features such as genericness, flexibility, and openness and is therefore particularly suited to a multimedia environment in which many types of applications are involved. Dynamic coding is a general proposal to visual data compression and many variations on the same theme may be designed. They differ by the particular procedure by which the data is segmented into objects and the local representation model selected, As an illustrative example, a video compression scheme based on the principles of dynamic coding is presented, This compression algorithm performs a joint optimization of the segmentation (restricted to a so-called generalized quadtree partition) together with the representation models associated with each data segment. Four representation models are competing namely, fractal, motion compensation, text and graphics, and background modes, Optimality is defined with respect to a rate-distortion tradeoff and the optimization procedure leads to a multicriterion segmentation.

关键词： data compression fractals image representation image segmentation image sequences motion compensation multimedia communication optimisation quadtrees rate distortion theory video coding background modes compression algorithm data segmentation dynamic cod Video coding Rate distortion theory quaternary tree compression algorithms image representation dynamic encoding image sequences Data compression image segmentation Fractals Data partitioning Motion compensation background mode visual information

来源：评论

学校读者我要写书评

暂无评论

Fast Neural Representations for Direct Volume Rendering

引用

COMPUTER GRAPHICS FORUM 2022年第6期41卷 196-211页

作者： Weiss, S. Hermueller, P. Westermann, R. Tech Univ Munich Munich Germany

Despite the potential of neural scene representations to effectively compress 3D scalar fields at high reconstruction quality, the computational complexity of the training and data reconstruction step using scene representation networks limits their use in practical applications. In this paper, we analyse whether scene representation networks can be modified to reduce these limitations and whether such architectures can also be used for temporal reconstruction tasks. We propose a novel design of scene representation networks using GPU tensor cores to integrate the reconstruction seamlessly into on-chip raytracing kernels, and compare the quality and performance of this network to alternative network- and non-network-based compression schemes. The results indicate competitive quality of our design at high compression rates, and significantly faster decoding times and lower memory consumption during data reconstruction. We investigate how density gradients can be computed using the network and show an extension where density, gradient and curvature are predicted jointly. As an alternative to spatial super-resolution approaches for time-varying fields, we propose a solution that builds upon latent-space interpolation to enable random access reconstruction at arbitrary granularity. We summarize our findings in the form of an assessment of the strengths and limitations of scene representation networks for compression domain volume rendering, and outline future research directions. Source code:

关键词： volume rendering neural networks compression algorithms

来源：评论

学校读者我要写书评

暂无评论

Binary Outer Product Expansion of Convolutional Kernels

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2020年第4期14卷 871-883页

作者： Sun, Zhaohui H. Kitware Inc Clifton Pk NY 12065 USA

Convolutional neural networks (CNNs) have found great success in many artificial intelligence applications. At the heart of a CNN is the operation of convolution between multi-channel data and learned kernels. It is usually implemented as a floating-point large matrix multiplication, a major bottleneck of computational speed and memory usage. In this paper, we propose a binary outer product expansion (BOPE) method to represent a kernel matrix or tensor as a weighted sum of the outer products between binary vectors of values +1 or -1. This allows for network compression and simplified computation at the same time. Our theoretical analysis shows such a decomposition converges to the original matrix given a sufficient number of binary vectors. We present computational methods to estimate outer product weights using either optimized or random binary base vectors. Significant data compression can be achieved for a highly redundant matrix, since weights and binary vectors require less storage than array elements. In addition, most floating-point multiplication in matrix convolution can be replaced by addition and binary XOR, lessening computation and memory requirements. We propose a compact convolutional layer in which highly redundant convolutional kernels are projected onto binary vectors, and represented as a weighted sum of outer products. It is shown that the number of weights in AlexNet, VGG-19 and ResNet-50 can be reduced 3.45, 6.87 and 2.95 times respectively with less than a 1% loss in the top-1 and top-5 classification accuracy on ImageNet, and MobileNetV2 can be reduced 2.31 times with a 2% loss. Compared to the standard CNN, this compact convolutional network has fewer trainable weights, is better regularized, and is easier to train from fewer training samples. Therefore, it is particularly suited for devices with limited computation, memory, and battery power.

关键词： Convolution Matrix decomposition Kernel Standards Convolutional neural networks Data compression Training compression algorithms convolutional neural networks deep learning mobile computing

来源：评论

学校读者我要写书评

暂无评论

Video imagery transmission and compression method research on ocean monitor system

Video imagery transmission and compression method research o...

引用

23rd International Geoscience and Remote Sensing Symposium (IGARSS 2003)

作者： Li, MT Guo, JB Li, JH Ctr Space Sci & Appl Res Beijing 100080 Peoples R China

ISBN: (纸本)0780379292

A very useful real time ocean monitor system has been developing. In the ocean-satetellite-ground transmission subsystem of the system, suitable compression methods, right compression algorithms and efficient transmission methods have to be developed because of the real time transmission and the huge video imagery data as well as the limiting satellite channel bandwidth. In the real time ocean monitor system, there are three developed technologies: One is the ocean-satellite-ground transmission subsystem configuration and data transmission method. Another is the improved video image compression algorithm and the comparing method with other compression algorithms. Third is the data splitting and compounding method. Finally, some experiment results will be given.

关键词： Video compression Image coding Oceans Satellites Real time systems Data communication Remote monitoring Data compression Transmitting antennas compression algorithms

来源：评论

学校读者我要写书评

暂无评论

Compressed Linear Algebra for Declarative Large-Scale Machine Learning

引用

COMMUNICATIONS OF THE ACM 2019年第5期62卷 83-91页

作者： Elgohary, Ahmed Boehm, Matthias Haas, Peter J. Reiss, Frederick R. Reinwald, Berthold Univ Maryland College Pk MD 20742 USA IBM Res Almaden San Jose CA USA Univ Massachusetts Amherst MA 01003 USA

Large-scale Machine Learning (ML) algorithms are often iterative, using repeated read-only data access and I/O-bound matrix-vector multiplications. Hence, it is crucial for performance to fit the data into single-node or distributed main memory to enable fast matrix-vector operations. General-purpose compression struggles to achieve both good compression ratios and fast decompression for block-wise uncompressed operations. Therefore, we introduce Compressed Linear Algebra (CIA) for lossless matrix compression. CIA encodes matrices with lightweight, value-based compression techniques and executes linear algebra operations directly on the compressed representations. We contribute effective column compression schemes, cache-conscious operations, and an efficient sampling-based compression algorithm. Our experiments show good compression ratios and operations performance close to the uncompressed case, which enables fitting larger datasets into available memory. We thereby obtain significant end-to-end performance improvements.

关键词： compression ratio compression algorithms Access to Information Machine Learning COMPRESSED Artificial Intelligence operating performance Iterative Linear algebra information retrieval Surgery

来源：评论

学校读者我要写书评

暂无评论

Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2021年第8期39卷 2572-2589页

作者： Cui, Laizhong Su, Xiaoxin Zhou, Yipeng Pan, Yi Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Macquarie Univ Fac Sci & Engn Dept Comp Sydney NSW 2109 Australia Peng Cheng Lab Shenzhen 518000 Peoples R China Chinese Acad Sci Fac Comp Sci & Control Engn Shenzhen Inst Adv Technol Shenzhen 518053 Peoples R China

Federated Learning (FL) is an emerging decentralized learning framework through which multiple clients can collaboratively train a learning model. However, a major obstacle that impedes the wide deployment of FL lies in massive communication traffic. To train high dimensional machine learning models (such as CNN models), heavy communication traffic can be incurred by exchanging model updates via the Internet between clients and the parameter server (PS), implying that the network resource can be easily exhausted. Compressing model updates is an effective way to reduce the traffic amount. However, a flexible unbiased compression algorithm applicable for both uplink and downlink compression in FL is still absent from existing works. In this work, we devise the Model Update compression by Soft Clustering (MUCSC) algorithm to compress model updates transmitted between clients and the PS. In MUCSC, it is only necessary to transmit cluster centroids and the cluster ID of each model update. Moreover, we prove that: 1) The compressed model updates are unbiased estimation of their original values so that the convergence rate by transmitting compressed model updates is unchanged;2) MUCSC can guarantee that the influence of the compression error on the model accuracy is minimized. Then, we further propose the boosted MUCSC (B-MUCSC) algorithm, a biased compression algorithm that can achieve an extremely high compression rate by grouping insignificant model updates into a super cluster. B-MUCSC is suitable for scenarios with very scarce network resource. Ultimately, we conduct extensive experiments with the CIFAR-10 and FEMNIST datasets to demonstrate that our algorithms can not only substantially reduce the volume of communication traffic in FL, but also improve the training efficiency in practical networks.

关键词： Computational modeling Training Adaptation models Convergence Data models compression algorithms Uplink Federated learning model update compression convergence rate clustering

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：