检索结果-内蒙古大学图书馆

16th IEEE International Colloquium on Signal processing and its applications (CSPA)

作者： Islam, Rafiqul Islam, Md Shafiqul Islam, Md Shohidul Dhaka Univ Engn & Technol Dept Comp Sci & Engn Gazipur Bangladesh

ISBN: (纸本)9781728153100

In magnetic resonance imaging, high-quality images are demanded to diagnosis and analytical purposes. During the acquisition process, it takes a long time to generate fully sampled k-space data for producing a high-quality image. But reducing the acquisition time creates insufficient data that degrades the image quality. Compressed sampling is a widely used technique that allows faster acquisition by undersampling k-space measurements, and it is possible to reconstruct the high-quality image from these measurements using the nonlinear algorithm. However, existing non-linear algorithms incur a long delay in the reconstruction process. In this work, bivariate Gaussian mixture model-based reconstruction algorithm is proposed to properly reconstruct the MRI image in which Graphical processing unit enabled code is developed to accelerate the reconstruction process. Experimental results show the improved performance of proposed algorithm in terms of quality of the reconstructed image and GPU-enabled methods exhibit real-time performance in terms of reducing time up to 26x, 32x, and 30x more speedups over CPU based techniques for total variation, soft-thresholding, and the proposed algorithms respectively.

关键词： Compressed sampling Magnetic resonance imaging Graphical processing unit (GPU) parallel computing Reconstruction algorithm

来源：评论

学校读者我要写书评

暂无评论

A population balance method for simulation of particle-induced droplet breakup in spray flame synthesis and suspension spray combustion

APPLICATIONS IN ENERGY AND COMBUSTION SCIENCE

引用

applications IN ENERGY AND COMBUSTION SCIENCE 2023年 15卷

作者： Skenderovic, Ivan Juengst, Niklas Kaiser, Sebastian Arnold Kruis, Frank Einar Univ Duisburg Essen Inst Technol Nanostruct Duisburg Germany Univ Duisburg Essen Inst Energy & Mat Proc React Fluids Duisburg Germany Univ Duisburg Essen Ctr Nanointegrat Duisburg Essen CENIDE Duisburg Germany

A population balance method based on weighted Monte-Carlo droplets is used to investigate breakup phe-nomena in single droplet combustion and spray flame synthesis (SFS). Particle shell formation in conjunction with superheating of liquid components is shown to be a plausible cause for droplet breakup. The breakage rate is calculated based on temperature and particle concentration profiles inside individual droplets, whereas the breakage function was determined using shadowgraphy imaging of droplets and image analysis. This enabled the simulation of consecutive breakup events in single droplet combustion and SFS. Furthermore, in the context of population balance simulations, an adaptive grid method is introduced for the calculation of particle accumulation at the droplet surface. This method is applicable to quickly evaporating droplets where particle transport by advection is fast compared to transport by radial diffusion. The new adaptive grid method is evaluated by comparison with seven single droplet combustion experiments from literature. More than that, parallel algorithms for a computationally efficient implementation using graphics processing units (GPUs) are discussed.

关键词： Spray combustion Droplet breakup Shadowgraphy imaging Population balance simulation Graphics processing Unit (GPU) SpraySyn reactor

来源：评论

学校读者我要写书评

暂无评论

A comparison study on nonlinear dimension reduction methods with kernel variations: Visualization, optimization and classification

引用

INTELLIGENT DATA ANALYSIS 2020年第2期24卷 267-290页

作者： Kempfert, Katherine C. Wang, Yishi Chen, Cuixian Wong, Samuel W. K. Univ Florida Gainesville FL USA Univ North Carolina Wilmington Wilmington NC 28403 USA Univ Waterloo Waterloo ON Canada

Because of high dimensionality, correlation among covariates, and noise contained in data, dimension reduction (DR) techniques are often employed to the application of machine learning algorithms. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and their kernel variants (KPCA, KLDA) are among the most popular DR methods. Recently, Supervised Kernel Principal Component Analysis (SKPCA) has been shown as another successful alternative. In this paper, brief reviews of these popular techniques are presented first. We then conduct a comparative performance study based on three simulated datasets, after which the performance of the techniques are evaluated through application to a pattern recognition problem in face image analysis. The gender classification problem is considered on MORPH-ii and FG-NET, two popular longitudinal face aging databases. Several feature extraction methods are used, including biologically-inspired features (BIF), local binary patterns (LBP), histogram of oriented gradients (HOG), and the Active Appearance Model (AAM). After applications of DR methods, a linear support vector machine (SVM) is deployed with gender classification accuracy rates exceeding 95% on MORPH-ii, competitive with benchmark results. A parallel computational approach is also proposed, attaining faster processing speeds and similar recognition rates on MORPH-ii. Our computational approach can be applied to practical gender classification systems and generalized to other face analysis tasks, such as race classification and age prediction.

关键词： Dimension reduction PCA LDA FDA KPCA KFDA SKPCA SVM parameter optimization gender classification MORPH-ii

来源：评论

学校读者我要写书评

暂无评论

Accelerated Edge Detection Algorithm for High-Speed applications

Accelerated Edge Detection Algorithm for High-Speed Applicat...

引用

Japan-Egypt International Conference on Electronics, Communications and Computers (JEC-ECC)

作者： Aya Saad Khloud Rafat Ahmed Soltan M. Saeed Darweesh School of Engineering and Applied Sciences Nile University Giza Egypt Nanoelectronics Integrated Systems Center (NISC) Nile University Giza Egypt Wireless Intelligent Networks Center (WINC) Nile University Giza Egypt

ISBN: (纸本)9781665482936

Digital image processing (DIP) is a growing field for various applications, such as autonomous vehicles and video surveillance. To improve the performance of DIP systems, image processing algorithms are implemented in hardware rather than software. The idea here is primarily to get a faster system than software imaging or other alternative hardware. Field-programmable gate arrays (FPGAs) have the advantages of parallel processing, low cost, and low power consumption. These semiconductor devices contain many logic blocks that can be programmed to perform everything from basic digital gate-level technology to complex image processing algorithms. This paper provides an enhancement pipeline system architecture using AxI interface to implement image processing algorithms such as Sobel edge detection and mean filters on the Zybo z7 Zynq 7010 board using Verilog HDL language. The system is implemented in a 512×512 image that takes 0.009ms in the processing system.

关键词： Performance evaluation image processing image edge detection Software algorithms Logic gates Filtering algorithms Software

来源：评论

学校读者我要写书评

暂无评论

PIM: A visualization-oriented web application for monitoring and debugging of large-scale image processing studies

PIM: A visualization-oriented web application for monitoring...

引用

SPIE Conference on Medical imaging - imaging Informatics for Healthcare, Research, and applications

作者： Kroes, Thomas Achterberg, Hakim Koek, Marcel Versteeg, Adriaan Niessen, Wiro van der Lugt, Aad van het Hof, Peter van Lew, Baldur Lelieveldt, Boudewijn Leiden Univ Div Image Proc Med Ctr NL-2333 ZA Leiden Netherlands Erasmus MC Biomed Imaging Grp Rotterdam Dept Radiol & Nucl Med NL-3015 GD Rotterdam Netherlands Erasmus MC Dept Med Informat NL-3015 GD Rotterdam Netherlands Univ Med Ctr Dept Biomed Data Sci Sequencing Anal Support Core NL-2333 ZA Leiden Netherlands

ISBN: (数字)9781510634046

ISBN: (纸本)9781510634039;9781510634046

Advances in computer hard- and software have enabled the automated extraction of biomarkers from large scale imaging studies by means of image processing pipelines. For large cohort studies, ample storage- and computing resources are required: pipelines are typically executed in parallel on one or more High Performance Computing Clusters (HPC). As processing is distributed, it becomes more cumbersome to obtain detailed progress and status information of large-scale experiments. Especially in a research-oriented environment, where image processing pipelines are often in an experimental stage, debugging is a crucial part of the development process that relies heavily on a tight collaboration between pipeline developers and clinical researchers. Debugging a running pipeline is a challenging and time-consuming process for seasoned pipeline developers, and nearly impossible for clinical researchers, often involving parsing of complex logging systems and text files, and requires special knowledge of the HPC environment. In this paper, we present the Pipeline Inspection and Monitoring web application (PIM). The goal of PIM is to make it more straightforward and less time-consuming to inspect complex, long running image processing pipelines, irrespective of the level of technical expertise and the workflow engine. PIM provides an interactive, visualization-based web application to intuitively track progress, view pipeline structure and debug running image processing pipelines. The level of detail is fully customizable, supporting a wide variety of tasks (e.g. quick inspection and thorough debugging) and thereby facilitating both clinical researchers and pipeline developers in monitoring and debugging.

关键词： Population imaging Graph Visualization Monitoring Debugging Workflow Engine Level of detail Distributed Computing

来源：评论

学校读者我要写书评

暂无评论

Multicore processors and GPUs: the power of parallel computing in the Cloud 2

Multicore processors and GPUs: the power of parallel computi...

引用

Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations applications ii Part of SPIE Defense + Commercial Sensing Conference

作者： Bennett, Kelly W. Robertson, James US Army Res Lab Sensors & Electron Devices Directorate Adelphi MD 20783 USA Clearhaven Technol LLC Severna Pk MD 21146 USA

ISBN: (纸本)9781510636040

Sensors used in intelligence, surveillance and reconnaissance (ISR) operations and activities have the ability to generate vast amounts of data. High-volume analytical capabilities are needed to process data from multi-modal sensors to develop and test complex computational and deep learning models in support of the U.S. Army Multi-Domain Operations (MDO). The Army Research Laboratory designs, develops and tests Artificial Intelligence and Machine Learning (AI/ML) algorithms employing large repositories of in-house data. To efficiently process the data as well as design, build, train and deploy models, parallel and distributed algorithms are needed. Deep learning frameworks provide language-specific, container-based building blocks associated with deep learning neural networks applied to specific target applications. This paper discusses applications of AI/ML deep learning frameworks and Software Development Kits (SDKs) and demonstrates and compares specific multi-core processor and NVidia Graphics processing Unit (GPU) implementations for desktop and Cloud environments. Frameworks selected for this research include PyTorch and Matlab. Amazon Web Services (AWS) SageMaker was used to launch Machine Learning instances ranging from general purpose computing to GPU instances. Detailed processes, example code, performance enhancements, best practices and lessons learned are included for publicly available acoustic and image datasets. Research results indicate parallel implementations of data preprocessing steps saved significant time but more expensive GPUs did not provide any processing time advantages for the machine learning algorithms tested.

关键词： Amazon Web Services Cloud Computing AL/ML algorithms Cloud-based GPU platform Big data Disruptive Computing Technologies AWS SageMaker

来源：评论

学校读者我要写书评

暂无评论

x-ray-induced acoustic computed tomography (xACT) imaging with single-shot nanosecond x-ray

引用

APPLIED PHYSICS LETTERS 2021年第18期119卷 183702-183702页

作者： Wang, Siqi Ivanov, Vassili Pandey, Prabodh Kumar xiang, Liangzhong Univ Calif Irvine Dept Biomed Engn Irvine CA 92617 USA PhotoSound Technol Inc Houston TX 77036 USA Univ Calif Irvine Dept Radiol Sci Irvine CA 92617 USA Univ Calif Irvine Beckman Laser Inst Irvine CA 92612 USA Univ Calif Irvine Med Clin Irvine CA 92612 USA

x-ray-induced acoustic computed tomography (xACT) has emerged as a promising imaging modality with broad applications in both biomedicine and nondestructive testing. The previous xACT imaging systems require thousands of averages to achieve reasonable images. Here, we report the experimental demonstration of single-shot xACT imaging of a metal object using a single-shot 50 ns x-ray pulse. A two-stage dedicated amplification and a 128-channel parallel data acquisition configuration were introduced for xACT imaging to enable sufficient acoustic signal amplification and maintain an overall low noise level for single-shot xACT imaging. Details of the system design are presented;the improved signal-to-noise ratio (> 23 dB) and image reconstruction have been demonstrated with a ring ultrasound transducer array imaging system. The study paves the way for realizing real-time xACT imaging and its potential applications in image-guided intervention.

关键词： Topics: Electromagnetic interference Nondestructive testing techniques Electronic noise Acoustic signal processing Ultrasound Data acquisition Optical imaging Data processing Graphical user interface Computed tomography

来源：评论

学校读者我要写书评

暂无评论

Towards an Efficient CNN Inference Architecture Enabling In-Sensor processing

引用

SENSORS 2021年第6期21卷 1955-1955页

作者： Pantho, Md Jubaer Hossain Bhowmik, Pankaj Bobda, Christophe Univ Florida Elect & Comp Engn Dept Gainesville FL 32603 USA

The astounding development of optical sensing imaging technology, coupled with the impressive improvements in machine learning algorithms, has increased our ability to understand and extract information from scenic events. In most cases, Convolution neural networks (CNNs) are largely adopted to infer knowledge due to their surprising success in automation, surveillance, and many other application domains. However, the convolution operations' overwhelming computation demand has somewhat limited their use in remote sensing edge devices. In these platforms, real-time processing remains a challenging task due to the tight constraints on resources and power. Here, the transfer and processing of non-relevant image pixels act as a bottleneck on the entire system. It is possible to overcome this bottleneck by exploiting the high bandwidth available at the sensor interface by designing a CNN inference architecture near the sensor. This paper presents an attention-based pixel processing architecture to facilitate the CNN inference near the image sensor. We propose an efficient computation method to reduce the dynamic power by decreasing the overall computation of the convolution operations. The proposed method reduces redundancies by using a hierarchical optimization approach. The approach minimizes power consumption for convolution operations by exploiting the Spatio-temporal redundancies found in the incoming feature maps and performs computations only on selected regions based on their relevance score. The proposed design addresses problems related to the mapping of computations onto an array of processing elements (PEs) and introduces a suitable network structure for communication. The PEs are highly optimized to provide low latency and power for CNN applications. While designing the model, we exploit the concepts of biological vision systems to reduce computation and energy. We prototype the model in a Virtex UltraScale+ FPGA and implement it in Application Specific Inte

关键词： CNN embedded vision FPGA pixel-parallel processing

来源：评论

学校读者我要写书评

暂无评论

Implementation and comparison of binary thinning algorithms on GPU

引用

COMPUTING 2019年第8期101卷 1091-1117页

作者： Ben Boudaoud, Lynda Solaiman, Basel Tari, Abdelkamel Univ Bejaia Fac Sci Exactes LIMED Lab Informat Med Bejaia Algeria IMT Atlantique Inst Image & Informat Proc Dept Brest France

Thinning algorithms have been widely applied in many applications such as computer graphics, computer vision and medical imaging. The performances of thinning algorithms are hampered by the increase of image's size and image's content. By employing graphics processing units (GPUs), the calculation of thinning algorithms can be accelerated. In this paper, we present GPU parallel versions of well-known binary thinning algorithms namely the ZS algorithm, the GH algorithm, the AW algorithm and the hybrid algorithm belonging to different classes for an efficient implementation using CUDA as a parallel programming model. These thinning algorithms are then evaluated and compared according to quality and runtime measures. The obtained results show that the GPU multithreaded implementations of the selected algorithms present high computational speed outperforming the central processing unit sequential implementations achieving the best average speedup when executing the AW algorithm.

关键词： Thinning algorithm Binary image Performance evaluation CUDA GPU

来源：评论

学校读者我要写书评

暂无评论

Editorial: Special issue on Advancing on Approximate Computing: Methodologies, Architectures and algorithms

引用

FUTURE GENERATION COMPUTER systems-THE INTERNATIONAL JOURNAL OF ESCIENCE 2021年 124卷 54-55页

作者： Barbareschi, Mario Bosio, Alberto Sekanina, Lukas Braun, Claus Univ Naples Federico II Via Claudio 21 I-80125 Naples NA Italy Univ Lyon 36 Ave Guy Collongue F-69134 Ecully France Brno Univ Technol FIT Bozetechova 2 Brno 61266 Czech Republic Robert Bosch GmbH Stuttgart Germany

In the modern computing era, characterized by saturated performance and high production costs, Approximate Computing has been representing the most attractive breakthrough for efficient system design. Such an innovative paradigm leverages the intrinsic error resilience of applications to inaccuracy in their inner calculations, in order to trade output result quality, under a certain maximum acceptable error threshold, off for system performance gain, such as calculation time and power demanding. In particular, for audio, image and video processing, data mining and information retrieval, approximate results turn out hard to distinguish from perfect ones, while their computation is less expensive. In recent years, Approximate Computing applicability is broadening in many scientific areas since suitable solutions come from approximate arithmetic operators, implemented both at hardware and software level, but from unreliable memory architectures, integrated circuit test, compilers and many others too. This special issue is dedicated to original research results and achievements by researcher community working on challenges and issues related to Approximate Computing. (C) 2021 Published by Elsevier B.V.

关键词： Approximate computing Approximate circuit Inherent error resiliency Error modeling and propagation

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：