检索结果-内蒙古大学图书馆

International conference on Wireless Communications, signal processing and Networking

作者： K. Arunakumari I. Rexiline Sheeba Dept. of Electronics and Communication Engg. Sathyabama University Chennai India Dept. of Electronics and Communication Engg Sathyabama University Chennai India

ISBN: (纸本)9781467393393

The Field Programmable Gate Array (FPGA) technology is widely used in various applications such as Digital image processing (DIP), Digital signal processing (DSP), data processing, etc. As the active and the passive components are fabricated in a single chip the performance level of the applications, the overall speed, area, and power of the application systems can be minimized effectively. The identification of the circuit information is an important process in the Very Large Scale Integration (VLSI) design. The existing architectures such as neural network, and brute force approach, etc., improve the analytical model work and refine the model using the trial and error method. The use of these existing techniques for the circuit information identification is inefficient, inaccurate, highly complex, time consuming, power consuming, and produced minimal classification result quality. To address these issues we have proposed a FPGA based VLSI architecture. The proposed architecture collects the feature values of the circuit manually. The collected features are then applied the Discrete Fourier Transform (DFT) based feature extraction process for identifying the information for the required data base and the input selected circuit details. The classification process is performed using the Knowledge Based Neural Network (KBNN). The performance of the proposed architecture is compared with the existing neural network methodology. The comparison results show that the suggested architecture increases the speed, reduces the overall power consumption, overall delay time, and also improves the circuit details classification speed level.

关键词： Very Large Scale Integration (VLSI) Field Programmable Gate Array (FPGA) Discrete Fourier Transform (DFT) Knowledge Based Neural Network (KBNN) Digital image processing (DIP) Digital signal processing (DSP)

来源：评论

学校读者我要写书评

暂无评论

Building a research data science platform from industrial machines

Building a research data science platform from industrial ma...

引用

IEEE International conference on Big Data

作者： Fang Cherry Liu Fu Shen Duen Horng Chau Neil Bright Mehmet Belgin Partnership for An Advanced Computing Environment (PACE) Georgia Institute of Technology Atlanta Georgia School of Computational Science and Engineering Georgia Institute of Technology Atlanta Georgia

ISBN: (纸本)9781467390064

Data Science research has a long history in academia which spans from large-scale data management, to data mining and data analysis using technologies from database management systems (DBMS's). While traditional HPC offers tools on leveraging existing technologies with data processing needs, the large volume of data and the speed of data generation pose significant challenges. Using the Hadoop platform and tools built on top of it drew immense interest from academia after it gained success in industry. Georgia Institute of Technology received a donation of 200 compute nodes from Yahoo. Turning these industrial machines into a research Data Science Platform (DSP) poses unique challenges, such as: nontrivial hardware design decisions, configuration tool choices, node integration into existing HPC infrastructure, partitioning resource to meet different application needs, software stack choices, etc. We have 40 nodes up and running, 24 running as a Hadoop and Spark cluster, 12 running as a HBase and OpenTSDB cluster, the others running as service nodes. We successfully tested it against Spark Machine Learning algorithms using a 88GB image dataset, Spark DataFrame and GraphFrame with a Wikipedia dataset, and Hadoop MapReduce wordcount on a 300GB dataset. The OpenTSDB cluster is for real-time time series data ingestion and storage for sensor data. We are working on bringing up more nodes. We share our first-hand experience gained in our journey, which we believe will benefit and inspire other academic institutions.

关键词： Hardware Sparks Digital signal processing Ecosystems Distributed databases Cloud computing

来源：评论

学校读者我要写书评

暂无评论

A Cross Layer design for Performance Enhancements in LTE-A System

A Cross Layer Design for Performance Enhancements in LTE-A S...

引用

International conference on Wireless Communications, signal processing and Networking

作者： V. Sharmila Gandhi B. Maheswaran Department of ECE Mepco Schlenk Engineering College Sivakasi India

ISBN: (纸本)9781467393393

Cross-layer design with respect to reference layered architecture is the design of algorithms, protocols and architectures that utilize an available set of interlayer exchanges a superset of the standard interfaces provided by the reference layered architecture. The cross layer approach transports feedback, dynamically via the layer margins to enable the remuneration for e.g. load, latency or other mismatch of requirements and resources by any deal with input to an additional layer. In the original OSI networking model, Layered communication approaches typically separate communication responsibilities into several layers, with a patent definition of the functionality of each layer. Cross layer optimization removes such strict restrictions to permit communication between layers to restore information and enable interfaces. For example, having knowledge of the existing physical condition will help a channel distribution offer at the MAC level in optimizing tradeoffs and achieve throughput maximization. The paper "A Cross Layer design for Performance Enhancement in LTE-A Systems" consists of four steps: i) Analyze the Various Optimization Techniques ii) Parameters Abstraction iii) Cross Layer Optimization iv) Performance Evaluation.

关键词： Automatic Repeat Request Long Term Evolution Advanced

来源：评论

学校读者我要写书评

暂无评论

design OF EFFECTIVE LOW POWER image COMPRESSION ALGORITHM

DESIGN OF EFFECTIVE LOW POWER IMAGE COMPRESSION ALGORITHM

引用

International conference on Wireless Communications, signal processing and Networking

作者： G. Epshi V. Saravanan B. Venkatalakshmi Velammal Engineering College Chennai- 600066 India

ISBN: (纸本)9781467393393

For satellite communication, large amount of data storage and transmission are involved as the satellites send data all the time, all day. Storing all these data and analyzing them for various purposes is possible using small low cost memory devices only with the help of image compression. image compression is the process of removing the redundant information from the image and it can be stored to reduce the storage size, transmission bandwidth and time. image compression aims at removing duplication from the source image and is essential for applications such as transmission and storage in an efficient form. The objective of the work is to develop an efficient low power image compression algorithm which compress it with higher compression ratio in such a way that the output compressed image becomes compatible for satellite communication. The proposed system should own a light weight algorithm which has the characteristics of minimum power consumption, less compression time and should meet a higher compression ratio. To do image compression, quad tree fractal image compression and an adaptive fractal wavelet image compression algorithm are selected and their performance in terms of mean square error, ratio of compression and peak signal to noise ratio are evaluated.

关键词： Fractal Range block image compression Quad tree

来源：评论

学校读者我要写书评

暂无评论

Conceptual design of a robotic assistant system based on projections onto flat surfaces for human-machine interaction applications

Conceptual design of a robotic assistant system based on pro...

引用

IEEE Colombian conference on Robotics and Automation (CCRA)

作者： J. G. Vargas Yepez A. Yepes Moreno S. Roa Prada Modeling and Simulation Research Group Universidad Autónoma de Bucaramanga SA Colombia Mechanical Engineering Department New York Institute of technology NY Colombia

ISBN: (纸本)9781509037889

The possibility of more intuitive human-machine interfaces has sparked the development of new visual technologies. The way humans interact with elements of their environment should not be limited to the screens of phones or computers. Other alternatives where a sensation of spatial freedom are under development. Projection systems, using continuous light on surrounding surfaces, represent a major area of exploration. The great level of development in artificial vision hardware and software tools enables the acquisition of data from the user and his/her environment, while in the background, a software can analyze in real time the variations of the scene without intervention of the user. This kind of data processing makes possible the integration between what the user is doing and seeing. The device proposed in this paper uses an arrangement of infrared sensors that capture the hand gestures from the user, and then points towards a projection surface in the user workspace. A gesture recognition software platform recreates the 3D environment of the user and analyzes the motion of the key points of the user hands. After obtaining these data, a process of comparison with previously established patterns determines if the user is performing some kind of preset command with his hands. If so, the system immediately converts this signal into a command that will be executed with the assistance of an Arduino platform. The embedded platform carries out a previously established protocol, in which, by making use of a mechatronic system of 2 degrees of freedom that supports a micro projector, it allows the user to adjust the position of the projected image over a surface, allowing the user to use a 360° virtual space. The main goal of this system is to generate an interface where the gestures of the hands of the user not only allow him/her to interact with software-level elements, but also with mechatronic components that may be physically present such as robots or home automation

关键词： Software Computers Robots Sensor systems Visualization Hardware

来源：评论

学校读者我要写书评

暂无评论

An Improved Faulting Detection Algorithm for Subway Tunnel Segment

An Improved Faulting Detection Algorithm for Subway Tunnel S...

引用

International conference on Wireless Communications, signal processing and Networking

作者： Zhengzhe Yang Xinwen Gao Haibing Xia School of Mechatronics Engineering and Automation Shanghai University Zhabei District China Technology Research and Development Center Shanghai Tunnel Engineering Rail Transit Design and Research Institute Xuhui District China

ISBN: (纸本)9781467393393

Novel security detection technology are needed to meet the growing demand of subway operation. In this paper, an improved faulting detection algorithm for subway tunnel segment is proposed. A combined denoising technique is used to convert the depth image of faulting acquired by Kinect into binary image of the height difference which can be processed by digital image. The obvious advantage of this method is that it can avoid the interference of environmental light and improve the detection speed. In addition, we focus on how to classify and identify different types of faulting line based on the idea of deep learning algorithm. And a fast CNN (convolution neural network) has been built to classify and identify faulting line. Finally, it shows that the proposed algorithm is effective through the experimental data.

关键词： Faulting Deep learning Depth image Classification and recognition Convolution operation

来源：评论

学校读者我要写书评

暂无评论

Automatic Segmentation of the Epicardium and Endocardium using convolutional neural network

Automatic Segmentation of the Epicardium and Endocardium usi...

引用

2016 IEEE 13th International conference on signal processing（ICSP2016）

作者： Zhao,Yue Li,Wenqiang Jin,Jing Jiang,Yu Shen,Yi Wang,Yan IEEE Control Theory and Engineering School of AstronauticsHarbin Institute of Technology

Automatic segmentation of the Epicardium and Endocardium plays an important role in the diagnosis of myocardial ischemia. Due to the speckle noise of ultrasound images and the complexity of cardiac tissue, the segmentation is still manual or semi-automatic. A fully automatic segmentation method based on Convolutional Neural Network(CNN) is proposed in this paper: localization segmentation method, which can obtain the position of the Epicardium and Endocardium based on the output of the network, then the segmentation is completed according to reprocessing based on the position. We concentrate the solutions of the following problems to supervised learning models: 1) the need of training images which have obvious features;2) the design of network;3) correlation between group images. The performance of our approach is evaluated using four different datasets containing 800 ultrasound images of Sprague-Dawley rats. The quality grades of the manual and automatic segmentation methods have been calculated, and the proportion of poor segmentation quality is decreased from 3.48% to 2.39%, which shows that our proposed method has improved segmentation accuracy and stability. The efficiency of our fully automatic segmentation method is higher than traditional segmentation strategies. The proposed method can optimize the clinical procedure and decrease the variability of manual segmentations.

关键词： echocardiography image automatic segmentation Epicardium and Endocardium convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

基于HCORDIC的浮点运算协处理器的设计

引用

电子测量与仪器学报 2020年第11期32卷 58-65页

作者：赵创张为天津大学微电子学院天津130072

通信硬件、信号和图像处理上需要进行大量数学运算,坐标旋转数字计算机(CORDIC)算法可以在硬件上快速计算三角、双曲线、自然对数和平方根函数,IEEE 754标准是目前最常用的浮点数标准,所以提出了一种处理浮点运算的协处理器。高基数自... 详细信息

通信硬件、信号和图像处理上需要进行大量数学运算,坐标旋转数字计算机(CORDIC)算法可以在硬件上快速计算三角、双曲线、自然对数和平方根函数,IEEE 754标准是目前最常用的浮点数标准,所以提出了一种处理浮点运算的协处理器。高基数自适应性CORDIC(HCORDIC)算法具有收敛速度快的优点,通过设计用于该算法的浮点乘法器和浮点加法器,进而设计出计算多种三角函数和超越函数的浮点运算协处理器架构。该架构可以实现更快的收敛,同时减少了输出延时并具有低误差精度。设计已在现场可编程逻辑门阵列(FPGA)上实现,结果表明,相比于Xilinx CORDIC IP和其他CORDIC架构,在输出延迟、最大工作频率、关键路径和计算精度等方面有更好的表现,该设计可以应用于多种计算场景,具有较强的工程价值。

关键词： IEEE 754 FPGA CORDIC HCORDIC 吠陀算法协处理器

来源：评论

学校读者我要写书评

暂无评论

从U-Net到Transformer:深度模型在医学图像分割中的应用综述

引用

计算机应用 2024年第S1期44卷 204-222页

作者：张玮智于谦苏金善乎西旦·居马洪林玲伊犁师范大学网络安全与信息技术学院新疆伊宁835000 伊犁师范大学智能计算研究与应用重点实验室新疆伊宁835000 山东女子学院数据科学与计算机学院济南255300 伊犁师范大学电子与工程学院新疆伊宁835000 伊犁师范大学振动信号俘获及智能处理实验室新疆伊宁835000

精准分割医学图像中的病灶对医生探寻病因和制定诊疗方案起关键作用,计算机视觉技术的发展促使深度学习在医学图像分割领域衍生出多种模型架构。U-Net架构以其巧妙的跳跃连接、易于优化的模块设计成为这一领域的基准模型。然而,U-Net以... 详细信息

精准分割医学图像中的病灶对医生探寻病因和制定诊疗方案起关键作用,计算机视觉技术的发展促使深度学习在医学图像分割领域衍生出多种模型架构。U-Net架构以其巧妙的跳跃连接、易于优化的模块设计成为这一领域的基准模型。然而,U-Net以卷积神经网络(CNN)为主干,在长期建模依赖关系方面只擅长获取局部特征,基于CNN的各项方法在执行分割任务中缺乏对图像长期相关性的解释,无法提取全局特征。为帮助本领域学者了解U-Net的发展历程及研究现状,以问题为导向对2016-2023年U-Net改进工作进行综述。首先,从改进结构位置的角度对U-Net及其各项改进模型进行叙述,探讨各工作的研究目的和创新设计及不足之处;其次,对Transformer与U-Net的结合方式进行分析,从中获取改进工作的研究动向;最后,在Synapse和ACDC数据集上进行对比实验,通过实验分析和可视化结果表明,Transformer方法在分割精度方面有显著优势,特别是混合网络子块的结合方式,在确保模型性能的同时兼顾效率,证明了该类工作有着广阔的发展前景和研究价值。

关键词：医学图像分割 U-Net 结构改进 Transformer 深度神经网络

来源：评论

学校读者我要写书评

暂无评论

image processing, Computer Vision, and Deep Learning: new approaches to the analysis and physics interpretation of LHC events

引用

Journal of Physics: conference Series 2016年第1期762卷

作者： A. Schwartzman M. Kagan L Mackey B. Nachman L. De Oliveira SLAC National Accelerator Laboratory Stanford University 2575 Sand Hill Road Menlo Park CA 94025 USA Department of Statistics Stanford University Stanford CA 94305 USA Institute for Computational and Mathematical Engineering Stanford University Stanford CA 94305 USA

This review introduces recent developments in the application of image processing, computer vision, and deep neural networks to the analysis and interpretation of particle collision events at the Large Hadron Collider (LHC). The link between LHC data analysis and computer vision techniques relies on the concept of jet-images, building on the notion of a particle physics detector as a digital camera and the particles it measures as images. We show that state-of-the-art image classification techniques based on deep neural network architectures significantly improve the identification of highly boosted electroweak particles with respect to existing methods. Furthermore, we introduce new methods to visualize and interpret the high level features learned by deep neural networks that provide discrimination beyond physics- derived variables, adding a new capability to understand physics and to design more powerful classification methods at the LHC.

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：