检索结果-内蒙古大学图书馆

18th International conference on Algorithms and architectures for Parallel processing (ICA3PP)

作者： Yang, Cheng Bao, Weidong Zhu, Xiaomin Wang, Ji Xiao, Wenhua Natl Univ Def Technol Changsha Peoples R China State Key Lab High Performance Comp Changsha Peoples R China Acad Mil Med Sci Beijing Peoples R China

ISBN: (纸本)9783030050573;9783030050566

In the field of signal process, Fast Fourier Transform (FFT) is a widely used algorithm to transform signal data from time to frequency. Unfortunately, with the exponential growth of data, traditional methods cannot meet the demand of large-scale computation on these big data because of three main challenges of large-scale FFT, i.e., big data size, real-time data processing and high utilization of compute resources. To satisfy these requirements, an optimized FFT algorithm in Cloud is deadly needed. In this paper, we introduce a new method to conduct FFT in Cloud with the following contributions: first, we design a parallel FFT algorithm for large-scaled signal data in Cloud;second, we propose a MapReduce-based mechanism to distribute data to compute nodes using big data processing framework;third, an optimal method of distributing compute resources is implemented to accelerate the algorithm by avoiding redundant data exchange between compute nodes. The algorithm is designed in MapReduce computation framework which contains three steps: data preprocessing, local data transform and parallel data transform to integrate processing results. The parallel FFT is implemented in a 16-node Cloud to process real signal data The experimental results reveal an obvious improvement in the algorithm speed. Our parallel FFT is approximately five times faster than FFT in Matlab in when the data size reaches 10 GB.

关键词： Fast fourier transform Cloud computing Apache spark Parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

ENDMEMBERS AS DIRECTIONAL DATA FOR ROBUST MATERIAL VARIABILITY RETRIEVAL IN HYPERSPECTRAL image UNMIXING

ENDMEMBERS AS DIRECTIONAL DATA FOR ROBUST MATERIAL VARIABILI...

引用

IEEE International conference on Acoustics, Speech and signal processing (ICASSP)

作者： Drumetz, L. Chanussot, J. Iwasaki, A. UBL IMT Atlantique Lab STICC F-29238 Brest France Univ Grenoble Alpes CNRS GIPSA Lab Grenoble INP Grenoble France Univ Tokyo Res Ctr Adv Sci & Technol Tokyo Japan

ISBN: (纸本)9781538646588

Hyperspectral image unmixing is a source separation problem aiming at recovering the spectra of the pure materials of the observed scene (called endmembers), as well as their relative proportions in each pixel of the image (called abundances). The variability of the materials has recently received a lot of attention in the community. In particular, a consequent number of models and algorithms have been proposed to estimate pixel-wise endmembers to account for their variability. These algorithms often rely on classical endmember extraction algorithms to provide reference spectra. In difficult scenarios with shadows and significant variability these algorithms may fail. In this paper, we address this issue in the Extended Linear Mixing Model framework by considering that an endmember is a direction in the feature space, rather than a single point. Under this paradigm, we show that using k-means clustering with the cosine similarity outperforms geometric endmember extraction algorithms. We also design an algorithm to refine the estimation of the endmember directions, and to account for both illumination and intrinsic variability effects. We show the potential of the proposed algorithm on a synthetic dataset using real world spectra with variability, and a challenging real dataset of a natural scene.

关键词： Hyperspectral unmixing endmember variability Extended Linear Mixing Model oblique manifold convex optimization

来源：评论

学校读者我要写书评

暂无评论

Molecular Synthesis for Probability Theory and Stochastic Process

引用

JOURNAL OF signal processing SYSTEMS FOR signal image AND VIDEO TECHNOLOGY 2018年第10期90卷 1479-1494页

作者： Shen, Ziyuan Ge, Lulu Wei, Wei Zhao, Jing Zhang, Zaichen You, Xiaohu Zhang, Chuan Southeast Univ Lab Efficient Architectures Digital Commun & Sign Natl Mobile Commun Res Lab Nanjing Jiangsu Peoples R China Nanjing Univ Sch Chem & Chem Engn State Key Lab Coordinat Chem Nanjing Jiangsu Peoples R China

It is common that probability theory and stochastic process, especially Markov chains, have long been used to study and explain the behaviors of chemical reaction networks (CRNs). Nonetheless, this paper sees things from a reverse angle, devoting itself in synthesizing common probability theory and stochastic process with CRNs. The main motivation is to imitate and explore the evolution of large-scale and complex practical systems based on CRNs, by making use of the inherent parallelism and randomness. In our conference paper, a preliminary but concise approach has been put forward to synthesize the stand-alone examples such as law of total probability, Bayes' theorem, and n-step transition of Markov chains. To make this methodology systematic and theoretically sound, we enrich and offer more solid foundation for the previous version. Rigorous stability analysis based on ordinary differential equations (ODEs) are provided. This paper further deeply discusses and distinguishes building stochastic models for CRNs and utilizing CRNs to solve stochastic problems. A joint distribution of Markov chains are implemented using molecular reactions as a showcase. In order to enhance the clearness of the results, all the simulations are done according to deterministic mass action. It is worth noting that an already mathematically proven conclusion, which states that nearly an arbitrary set of bimolecular or unimolecular reactions can be implemented by DNA strand displacement reactions, ensures the meaningfulness of our work. It is also believed that, though in its infancy, the proposed approach is also valid for other molecular synthesis than DNA, as long as the kinetics constraints are met.

关键词： Molecular synthesis Probability theory Stochastic process Bayes' Theorem Markov chains

来源：评论

学校读者我要写书评

暂无评论

LEARNING FROM WEAKLY-LABELED CLINICAL DATA FOR AUTOMATIC THYROID NODULE CLASSIFICATION IN ULTRASOUND imageS 25

LEARNING FROM WEAKLY-LABELED CLINICAL DATA FOR AUTOMATIC THY...

引用

25th IEEE International conference on image processing (ICIP)

作者： Wang, Jianxiong Li, Shuai Song, Wenfeng Qin, Hong Zhang, Bo Hao, Aimin Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing Peoples R China SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA Chinese Acad Med Sci Dept Ultrasound Beijing Peoples R China Peking Union Med Coll Hosp Beijing Peoples R China

ISBN: (纸本)9781479970612

This paper proposes a semi-supervised learning method based on weakly-labeled data to automatically classify ultrasound (US) thyroid nodules. Key to our new approach is the unification of multi-instance learning (MIL) with deep learning. Benefiting from that, our method can directly use off-the-shelf clinical data, which involves no labels to indicate nodule classes. To this end, we take the US images of a patient as a bag, and take the corresponding pathology report as the bag label. Specifically, we first propose a bag generating method, wherein the detected thyroid nodules are considered as instances corresponding to certain bag. After that, we design an effective EM algorithm to train a convolutional neural network (CNN) for nodule classification. We conduct extensive experiments and comprehensive evaluations on different datasets, and all the experiments confirm that, our method significantly outperforms state-of-the-art MIL algorithms, which exhibits great potential in clinical applications.

关键词： Weakly-labeled data Multi-instance learning (MIL) Convolutional neural network (CNN) Thyroid ultrasound image Automatic nodule classification

来源：评论

学校读者我要写书评

暂无评论

FPGA based real-time on-road stereo vision system

引用

JOURNAL OF SYSTEMS ARCHITECTURE 2017年 81卷 32-43页

作者： Dehnavi, M. Eshghi, M. Shahid Beheshti Univ EE Dept Tehran *** Iran

Accurate and Real-Time stereo vision is an essential need for many computer vision applications, such as On Road stereo vision system. In this paper, a fast and accurate system for On-Road stereo vision application is presented. In order to achieve this purpose, first, an algorithm is presented that is optimized for hardware implementation and On-Road application, then an appropriate hardware architecture for this algorithm is proposed. The approach uses gradient and Census transform as initial cost function, then cost is aggregate in cross-based supported reign. LR-check and disparity refinement is also utilized to improve final disparity. The proposed design is a standalone stereo vision system where all steps of algorithm is implemented on a hardware platform. Overall system is implemented on FPGA platform and it is tested on KITTI Database. The proposed system is also tested on Middlebury database without any changes in parameters. Experimental results show that the proposed system has high accuracy in KITTI and Middlebury database. In term of hardware resource, the system occupy %%66 of XC6VLX240T FPGA device for 1920 x 1080 image with 96 disparity levels that operated at 53.5 Fps.

关键词： FPGA Stereo vision On-road image Obstacle Hardware architecture

来源：评论

学校读者我要写书评

暂无评论

Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis 31

Unsupervised representation learning using convolutional and...

引用

31st conference on Graphics, Patterns and images (SIBGRAPI)

作者： Cavallari, Gabriel B. Ribeiro, Leonardo S. F. Ponti, Moacir A. Univ Sao Paulo Inst Math & Comp Sci ICMC Sao Carlos SP Brazil

ISBN: (纸本)9781538692646

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual domains are considered, methods that rely on large annotated datasets, such as Convolutional Neural Networks (CNNs), cannot be employed. In this paper we investigate different auto-encoder (AE) architectures, which require no labels, and explore training strategies to learn representations from images. The models are evaluated considering both the reconstruction error of the images and the feature spaces in terms of their discriminative power. We study the role of dense and convolutional layers on the results, as well as the depth and capacity of the networks, since those are shown to affect both the dimensionality reduction and the capability of generalising for different visual domains. Classification results with AE features were as discriminative as pre-trained CNN features. Our findings can be used as guidelines for the design of unsupervised representation learning methods within and across domains.

关键词： Feature extraction Decoding Training Convolutional codes image reconstruction Visualization Task analysis

来源：评论

学校读者我要写书评

暂无评论

SVM-based real-time hyperspectral image classifier on a manycore architecture

引用

JOURNAL OF SYSTEMS ARCHITECTURE 2017年 80卷 30-40页

作者： Madronal, D. Lazcano, R. Salvador, R. Fabelo, H. Ortega, S. Callico, G. M. Juarez, E. Sanz, C. Univ Politecn Madrid Ctr Software Technol & Multimedia Syst CITSEM Madrid Spain ULPGC Res Inst Appl Microelect IUMA Las Palmas Gran Canaria Spain

This paper presents a study of the design space of a Support Vector Machine (SVM) classifier with a linear kernel running on a manycore MPPA (Massively Parallel Processor Array) platform. This architecture gathers 256 cores distributed in 16 clusters working in parallel. This study aims at implementing a real-time hyperspectral SVM classifier, where real-time is defined as the time required to capture a hyperspectral image. To do so, two aspects of the SVM classifier have been analyzed: the classification algorithm and the system parallelization. On the one hand, concerning the classification algorithm, first, the classification model has been optimized to fit into the MPPA structure and, secondly, a probability estimation stage has been included to refine the classification results. On the other hand, the system parallelization has been divided into two levels: first, the parallelism of the classification has been exploited taking advantage of the pixel-wise classification methodology supported by the SVM algorithm and, secondly, a double-buffer communication procedure has been implemented to parallelize the image transmission and the cluster classification stages. Experimenting with medical images, an average speedup of 9 has been obtained using a single-cluster and double-buffer implementation with 16 cores working in parallel. As a result, a system whose processing time linearly grows with the number of pixels composing the scene has been implemented. Specifically, only 3 mu s are required to process each pixel within the captured scene independently from the spatial resolution of the image. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Support Vector Machine Hyperspectral imaging Massively parallel processing Real-time processing Energy consumption awareness Embedded system

来源：评论

学校读者我要写书评

暂无评论

FIR Filter design Based On FPGA 10

FIR Filter Design Based On FPGA

引用

10th International conference on Measuring Technology and Mechatronics Automation (ICMTMA)

作者： Zheng Jiayu Wei Zhenhua East China Univ Technol Sch Informat Engn Nanchang 330013 Jiangxi Peoples R China

ISBN: (纸本)9781538651148

FIR (Finite Impulse Response) filters: the finite impulse response filter is the most basic components in digital signal processing systems and are widely used in communications, image processing, and pattern recognition. Based on FPGA (editable logic device) to achieve FIR filter, not only take into account the fixed-function DSP-specific chip real-time, but also has the DSP processor flexibility. The combination of FPGA and DSP technology can further improve integration, increase work speed and expand system capabilities.

关键词： FIR FPGA MODELSIM simulation Verilog HDL

来源：评论

学校读者我要写书评

暂无评论

3rd International conference on Intelligent Computing and Applications, ICICA 2016

3rd International Conference on Intelligent Computing and Ap...

引用

3rd International conference on Intelligent Computing and Applications, ICICA 2016

ISBN: (纸本)9789811055195

The proceedings contain 59 papers. The special focus in this conference is on Intelligent Computing and Applications. The topics include: Parallel palm print identification using fractional coefficients of palm edge transformed images on GPU;a secure spatial domain image steganography using genetic algorithm and linear congruential generator;Three-dimensional MRI brain image analysis on hadoop platform;performance evaluation of fingerprint trait authentication system;graphical password using an intuitive approach;a model of legal and procedural framework for cybercrime investigation in India using digital image forensics;comparative study of android-based M-Apps for farmers;Feature extraction of DICOM images using canny edge detection algorithm;design of 2-bit parallel asynchronous self-timed adder and 2-bit parallel adder using radix adder;block compressive sampling and wiener curvelet denoising approach for satellite images;efficient image secret sharing using parallel processing for row-wise encoding and decoding;TXGR: A reverse engineering tool to convert design patterns and application software into graph;Comparative analysis of image fusion using DCT, DST, DWT, walsh transform and kekre’s wavelet transform;ioT-based smart garbage management system;Event-driven SOA-based IoT architecture;FPGA implementation of AES algorithm for image, audio, and video signal;power extraction from small hydropower plant;enhancement of digital distance protection scheme with novel transducer;A hierarchical underwater wireless sensor network design for tracking ships approaching harbors using an aerial mobile sink (AMS) node;development of single and multi-jet conical nozzle based open jet facility for cold jet simulation;Neural deployment algorithm for WSN: A concept;energy-aware multi-objective differential evolution in cloud computing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

conference on design and architectures for signal and image processing, dasip

Conference on Design and Architectures for Signal and Image ...

引用

conference on design and architectures for signal and image processing, dasip 2015

ISBN: (纸本)9791092279108

The proceedings contain 24 papers. The topics discussed include: real-time correlation for locating systems utilizing heterogeneous computing architectures;FPGA based system for real-time structure from motion computation;exploring custom heterogeneous MPSoCs for real-time neural signal decoding;compa backend: a dynamic runtime for the execution of dataflow programs onto multi-core platforms;demonstrating an FPGA implementation of a full HD real-time HEVC decoder with memory optimizations for range extensions support;fast and accurate power estimation for application-specific instruction set processors using FPGA emulation;selecting most profitable instruction-set extensions using ant colony heuristic;hardware implementation of a soft cancellation decoder for polar codes;and FPGA-based real-time MFCC extraction for automatic audio indexing on FM broadcast data.

关键词：

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：