检索结果-内蒙古大学图书馆

PARAFAC algorithms for large-scale problems

NEUROCOMPUTING 2011年第11期74卷 1970-1984页

作者： Anh Huy Phan Cichocki, Andrzej RIKEN BSI Lab Adv Brain Signal Proc Wako Saitama Japan Polish Acad Sci Syst Res Inst PL-00901 Warsaw Poland

Parallel factor analysis (PARAFAC) is a tensor (multiway array) factorization method which allows to find hidden factors (component matrices) from a multidimensional data. Most of the existing algorithms for the PARAFAC, especially the alternating least squares (ALS) algorithm need to compute Khatri-Rao products of tall factors and multiplication of large matrices, and due to this require high computational cost and large memory and are not suitable for very large-scale-problems. Hence, PARAFAC for large-scale data tensors is still a challenging problem. In this paper, we propose a new approach based on a modified ALS algorithm which computes Hadamard products, instead Khatri-Rao products, and employs relatively small matrices. the new algorithms are able to process extremely large-scale tensors with billions of entries. Extensive experiments confirm the validity and high performance of the developed algorithm in comparison with other well-known algorithms. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Canonical polyadic decomposition (CP) Tensor factorization PARAFAC Large-scale dataset Multiway classification Parallel computing Alternating least squares Hierarchical ALS

来源：评论

学校读者我要写书评

暂无评论

A Bilinear Interpolation Mean Shift small Target Tracking Algorithm

A Bilinear Interpolation Mean Shift Small Target Tracking Al...

引用

5th International conference on signal processing and Communication Systems (ICSPCS)

作者： Kang, Yimei Wang, Guan Hu, Jiang Beihang Univ Software Sch BUAA Beijing 100191 Peoples R China Beijing Inst Comp Technol & Appl Beijing Peoples R China

ISBN: (纸本)9781457711800

It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7x7 pixels to 25x25 pixels. the algorithm included six steps: (1) enlarge the target and the surrounding region by bilinear interpolation;(2) enhance the target features of the enlarged region by histogram equalization;(3) expand the single grayscale video into three channel video by pixel gradient;(4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space;(5) obtain the target location in the enlarged image by mean shift method;and (6) transform the location of target from the enlarged image to the original image. the time complexity of the proposed algorithm is O(n). the experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. the deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. the time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.

关键词： small target tracking interpolation histogram equalization mean shift kernel density estimation

来源：评论

学校读者我要写书评

暂无评论

A bilinear interpolation mean shift small target tracking algorithm

A bilinear interpolation mean shift small target tracking al...

引用

International conference on signal processing and Communication Systems, ICSPCS

作者： Yimei Kang Guan Wang Jiang Hu Software School Beihang University Beijing China Beijing Institute of Computer Technology and Application Beijing China

It is difficult to track targets in grayscale videos especially for small targets because of the lack of the target image information. A tracking algorithm was proposed to track small targets in grayscale videos whose size was from 7×7 pixels to 25×25 pixels. the algorithm included six steps: (1) enlarge the target and the surrounding region by bilinear interpolation; (2) enhance the target features of the enlarged region by histogram equalization; (3) expand the single grayscale video into three channel video by pixel gradient; (4) establish the target model and the target candidates by kernel density estimation in the enlarged and equalized image space; (5) obtain the target location in the enlarged image by mean shift method; and (6) transform the location of target from the enlarged image to the original image. the time complexity of the proposed algorithm is O(n). the experimental results showed that the algorithm was able to track the small targets steadily, accurately and quickly. the deviation of target location was zero for most frames and no more than 2 pixels for a few frames in which the target rotated at a large angle. the time spent in tracking the small target in a frame was 15 or 16 ms for the two testing cases in this study.

关键词： Gray-scale Target tracking Histograms Interpolation Videos Algorithm design and analysis Kernel

来源：评论

学校读者我要写书评

暂无评论

A target detection algorithm based on peripheral anomaly

A target detection algorithm based on peripheral anomaly

引用

IEEE signal processing and Communications Applications (SIU)

作者： A. Onur Karalı Tayfun Aytaç Alper Yıldırım Ö. Nezih Gerek TÜBİTAK BİLGEM UEKAE İLTAREN Ankara Turkey Elektrik-Elektronik Mühendisliği Bölümü Anadolu Üniversitesi Eskisehir Turkey

Automatic target detection algorithms enable in military and civilian applications the detection of low-contrast and spatially small targets that can not be detected by a human operator and remove the requirement of permanent operator control for surveillance systems. Considering many different background patterns and target models, it is not possible to define a single target detection algorithm that succeeds in all scenarios. In this paper, a novel target detection algorithm is proposed for targets above sea-level and sky targets. Peripheral anomaly values are calculated for image blocks depending on the difference of the statistical data between target and background patterns and target and background regions are differentiated by comparing these values with scenario dependent threshold values. Experimental results show that the proposed method has high success rate in the detection of targets above sea-level and sky targets in visual band images.

关键词： Object detection Marine vehicles signal processing algorithms signal processing conferences Histograms Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Performance Characterization of a High-Purity Germanium Detector for small-Animal SPECT

Performance Characterization of a High-Purity Germanium Dete...

引用

IEEE Nuclear Science Symposium/Medical Imaging conference (NSS/MIC)/18th International Workshop on Room-Temperature Semiconductor X-Ray and Gamma-Ray Detectors

作者： Johnson, Lindsay C. Campbell, Desmond L. Ovchinnikov, Oleg S. Peterson, Todd E. Vanderbilt Univ Dept Biomed Engn Inst Imaging Sci 221 Kirkland Hall Nashville TN 37232 USA Vanderbilt Univ Dept Phys Astro Inst Imaging Sci Nashville TN 37232 USA

ISBN: (纸本)9781467301206

We present an initial evaluation of a mechanically-cooled, high-purity germanium double-sided strip detector as a potential gamma camera for small-animal SPECT. It is 90 mm in diameter and 10 mm thick with two sets of 16 orthogonal strips that have a 4.75 mm width with a 5 mm pitch. A sub-strip interpolation method is used to bin the data at a pixel size of 0.53mm x 0.53mm, while it is also possible to estimate the depth of interaction based on CFD time differences between the anode and cathode. the system has an energy resolution of 0.92% at 140 keV and an intrinsic efficiency of 55.40% at 122 keV. Simulations suggest that increases in the efficiency should be possible by altering signal processing to include Compton events in which charge is collected on more than one strip. Integral uniformity in the central field of view for strips was found to be less than 1% in a flood-corrected flood while pixel-level uniformity was 2.98%. Due to the excellent energy resolution, the presence of a scattering medium did not greatly alter the FWHM or FWTM of a pinhole projection when compared to an acquisition without a scattering medium. this high-purity germanium system offers many desirable properties for small-animal SPECT.

关键词： CFD time differences Collimators Detectors Energy resolution Ge Image resolution computational fluid dynamics efficiency 55.4 percent electron volt energy 122 keV electron volt energy 140 keV flood-corrected flood gamma camera germanium detector germanium double-sided strip detector germanium radiation detectors interpolation scattering medium single photon emission computed tomography size 0.53 mm size 10 mm size 4.75 mm size 90 mm small-animal SPECT substrip interpolation method

来源：评论

学校读者我要写书评

暂无评论

Hierarchical exact symbolic analysis of large analog integrated circuits by symbolic stamps 11

Hierarchical exact symbolic analysis of large analog integra...

引用

Asia and South Pacific Design Automation conference

作者： Hui Xu Guoyong Shi Xiaopeng Li School of Microelectronics Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781424475162

Linearized small-signal transistor models share the common circuit structure but may take different parameter values in the ac analysis of an analog circuit simulator. this property can be utilized for symbolic circuit analysis. this paper proposes to use a symbolic stamp for all device models in the same circuit for hierarchical symbolic analysis. Two levels of binary decision diagrams (BDDs) are used for maximum data sharing, one for the symbolic device stamp and the other for modified nodal analysis. the symbolic transadmittances of the device stamp share one BDD for storage saving. the modified nodal analysis (MNA) matrix formulated using symbolic stamp is of much lower dimension, hence it can be solved by a determinant decision diagram (DDD) with significantly reduced complexity. A circuit simulator is implemented based on the proposed partitioning architecture. It is able to analyze an op-amp circuit containing 44 MOS transistors exactly for the first time.

关键词： data structures Boolean functions Integrated circuit modeling Benchmark testing Transistors Analytical models Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Firmware Upgrade for the data Acquisition System of the LabPET small Animal PET Scanner

Firmware Upgrade for the Data Acquisition System of the LabP...

引用

16th IEEE/NPSS Real-Time conference

作者： Tetrault, M. -A. Bergeron, M. Lecomte, R. Fontaine, R. Univ Sherbrooke Dept Elect & Comp Engn Sherbrooke PQ J1K 2R1 Canada Univ Sherbrooke Dept Med Nucl & Radiobiol Sherbrooke PQ J1K 2R1 Canada CHUS Sherbrooke Mol Imaging Ctr Sherbrooke PQ J1K 2R1 Canada

ISBN: (纸本)9781424444557

the LabPET scanner is based on avalanche photodiodes individually read out by free running analog to digital converters, giving it the ability to reach high count rates for individual detection crystals. the actual rate performance depends on the supporting firmware that implements the detection, sampling and processing steps in the host programmable devices. the initial firmware version for the LabPET provided the target performance, but was written for functionality rather than maximum throughput. the upgraded firmware optimizes several parts of the analysis flow and uses pipelining techniques to increase count rate performance by 50%, while utilizing 24% less FPGA logic resources and no hardware modifications.

关键词： FPGA pipelining positron emission tomography (PET) real time signal processing

来源：评论

学校读者我要写书评

暂无评论

UWB Microwave Monopulse Radar System for Breast Cancer Detection

UWB Microwave Monopulse Radar System for Breast Cancer Detec...

引用

4th International conference on signal processing and Communication Systems (ICSPCS)/12th International Symposium on DSP and Communication Systems (DSPCS)/9th Workshop on the Internet, Telecommunications and signal processing (WTSP)

作者： Bialkowski, Marek E. Wang, Yifan Abbosh, Amin Univ Queensland Sch Informat Technol & Elect Engn St Lucia Qld 4072 Australia

ISBN: (纸本)9781424479078

the concept of an Ultra Wideband (UWB) Monopulse Microwave Radar System for detection and location of breast cancer is described. the system uses a two-element Tapered Slot Antenna (TSA) array accompanied by a UWB 180 degrees hybrid which scans the breast. When the breast tissue features symmetry with respect to the array axis and the hybrid enables the 180 degrees out phase feeding operation, the array automatically eliminates background while extracting information about an off axis target. the data obtained from the scan is post-processed using a novel imaging algorithm to locate the target. the design of the required 2-element UWB array antenna and the 180 degrees hybrid is presented. the validity of the proposed breast cancer detection method is demonstrated in an example of a simple breast phantom formed by a cylindrical plastic container filled with a vegetable oil and small cylindrical targets.

关键词： UWB microwave monopulse radar system biomedical imaging breast cancer detection breast cancer location breast tissue cancer imaging algorithm microwave antenna arrays microwave imaging radar imaging small cylindrical targets tapered slot antenna array ult

来源：评论

学校读者我要写书评

暂无评论

Firmware Upgrade for the data Acquisition System of the LabPET small Animal PET Scanner

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 2010年第2期57卷 556-560页

关键词： FPGA pipelining positron emission tomography (PET) real time signal processing

来源：评论

学校读者我要写书评

暂无评论

On optimal timer-based distributed selection for rate-adaptive multi-user diversity systems

On optimal timer-based distributed selection for rate-adapti...

引用

16th National conference on Communications, NCC 2010

作者： Suresh, Ananda theertha Mehta, Neelesh B. Shah, Virag Madras India Bangalore India

ISBN: (纸本)9781424463855

We develop an optimal, distributed, and low feedback timer-based selection scheme to enable next generation rateadaptive wireless systems to exploit multi-user diversity. In our scheme, each user sets a timer depending on its signal to noise ratio (SNR) and transmits a small packet to identify itself when its timer expires. When the SNR-to-timer mapping is monotone non-decreasing, timers of users with better SNRs expire earlier. thus, the base station (BS) simply selects the first user whose timer expiry it can detect, and transmits data to it at as high a rate as reliably possible. However, timers that expire too close to one another cannot be detected by the BS due to collisions. We characterize in detail the structure of the SNR-to-timer mapping that optimally handles these collisions to maximize the average data rate. We prove that the optimal timer values take only a discrete set of values, and that the rate adaptation policy strongly influences the optimal scheme's structure. the optimal average rate is very close to that of ideal selection in which the BS always selects highest rate user, and is much higher than that of the popular, but ad hoc, timer schemes considered in the literature. ©2010 IEEE.

关键词： signal to noise ratio

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：