检索结果-内蒙古大学图书馆

Adorym: a multi-platform generic x-ray image reconstruction framework based on automatic differentiation

OPTICS ExPRESS 2021年第7期29卷 10000-10035页

作者： Du, Ming Kandel, Saugat Deng, Junjing Huang, xiaojing Demortiere, Arnaud Tuan Tu Nguyen Tucoulou, Remi De Andrade, Vincent Jin, Qiaoling Jacobsen, Chris Argonne Natl Lab Adv Photon Source Lemont IL 60439 USA Northwestern Univ Appl Phys Program Evanston IL 60208 USA Brookhaven Natl Lab Natl Synchrotron Light Source II Upton NY 11973 USA Univ Picardie Jules Verne Lab Reactivite & Chim Solides LRCS CNRS UMR 7314 Hub Energie 15 Rue Baudelocque F-80039 Amiens France European Synchrotron Radiat Facil 71 Ave Martyrs F-38000 Grenoble France Northwestern Univ Dept Phys & Astron Evanston IL 60208 USA Northwestern Univ Chem Life Proc Inst Evanston IL 60208 USA

We describe and demonstrate an optimization-based x-ray image reconstruction framework called Adorym. Our framework provides a generic forward model, allowing one code framework to be used for a wide range of imaging methods ranging from near-field holography to fly-scan ptychographic tomography. By using automatic differentiation for optimization, Adorym has the flexibility to refine experimental parameters including probe positions, multiple hologram alignment, and object tilts. It is written with strong support for parallel processing, allowing large datasets to be processed on high-performance computing systems. We demonstrate its use on several experimental datasets to show improved image quality through parameter refinement. (C) 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： Astronomical interferometry image quality image reconstruction imaging techniques Three dimensional imaging x ray imaging

来源：评论

学校读者我要写书评

暂无评论

Analysis of parallel Graph applications

Analysis of Parallel Graph Applications

引用

International Conference on parallel and Distributed systems (ICPADS)

作者： Funda Atik Serif Yesil Hamza Ouarnoughi Smail Niar Ozcan Ozturk Computer Science and Engineering Department Washington University in St. Louis Doimukh MI USA NVidia Urbana IL USA Department of Computer Science Université Polytechnique Hauts-de-France Valenciennes France LAMIH/CNRS Université Polytechnique Hauts-de-France Valenciennes France Computer Science and Engineering Program Electronics Engineering Program Sabanci University Istanbul Turkey

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Despite the increasing computing power of shared memory systems with high core counts, parallel graph processing frameworks cannot exploit it effectively. The reason behind this is the inherent challenges in parallel graph algorithms, which are efficient management of dynamically created tasks and irregular data access patterns. In this paper, we categorize several popular design choices into three design dimensions: (i) execution mode, (ii) data access pattern, and (iii) work activation. We provide their high-level parallel implementations and analyze various implementations of three representative iterative graph algorithms by considering these design dimensions. To gain a better understanding of design choices, we examine their impacts on performance, communication, scalability, and work efficiency. We also investigate the communication characteristics of the design choices on two state-of-the-art shared-memory platforms by performing micro-architectural analysis. Our microarchitectural analysis reveals that a topology-driven, pull-based model gives up to $20 x$ better performance.

关键词： Analytical models Microarchitecture Scalability Heuristic algorithms Benchmark testing Throughput Iterative algorithms System-on-chip

来源：评论

学校读者我要写书评

暂无评论

A parallel and Optimized image Compressed Sensing Solution 5

A Parallel and Optimized Image Compressed Sensing Solution

引用

5th IEEE International Conference on Networking and Advanced systems, ICNAS 2021

作者： Bairi, Zakaria Bey, Kadda Beghdad Amamra, Abdennour Djamaa, Badis Ecole Militaire Polytechnique Algiers Algeria

ISBN: (纸本)9781665428217

Although there have been significant processor technology enhancements in terms of speed, data compression algorithms still do not accomplish the required task in a convenient time for voluminous data. The parallelism of the compression process could significantly improve not only the processing time but also the quality of the solution. In this paper, we propose a new Compressed Sensing (CS) solution based on parallel CSNet (PCSNet) while integrating the PSNR loss to improve the image reconstruction process. The proposal results in distributing data to be processed to different cores of the machine and could benefit a multitude of applications including autonomous driving, medical imaging, and face detection. At its core, PCSNet uses a parallel convolutional neural network that includes a sampling subnetwork and a reconstruction subnetwork. These two networks learn the sampling matrix from the input image then the reconstructed image from the CS measurements. Thus, the training is done in a parallel way in each iteration then optimized at the master level using PSNR loss in an end-to-end learning process. Obtained experimental results outperform state-of-the-art approaches in terms of both image reconstruction quality and processing time. © 2021 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

BioNetExplorer: Architecture-Space Exploration of Biosignal processing Deep Neural Networks for Wearables

引用

IEEE INTERNET OF THINGS JOURNAL 2021年第17期8卷 13251-13265页

作者： Prabakaran, Bharath Srinivas Akhtar, Asima Rehman, Semeen Hasan, Osman Shafique, Muhammad Tech Univ Wien Inst Comp Engn A-1040 Vienna Austria Natl Univ Sci & Technol Sch Elect Engn & Comp Islamabad 44000 Pakistan Tech Univ Wien Inst Comp Technol A-1040 Vienna Austria New York Univ Abu Dhabi Div Engn Abu Dhabi U Arab Emirates

Deep learning (DL) has been shown to be highly effective in solving various problems across numerous applications and domains, such as autonomous driving and image recognition. Due to the advent of DL, plenty of research works have explored the applicability of DL, more specifically deep neural networks (DNNs), to solve pattern recognition and computer vision challenges. More recently, researchers have focused on the topic of automated generation and exploration of DNN architectures, which tend to mostly focus on image recognition or visual data sets, primarily, due to the computer vision-related DL advancements. In this work, we propose the BioNetExplorer framework to systematically generate and explore multiple DNN architectures for biosignal processing in wearable devices. Our framework varies key neural architecture parameters to search for an embedded DNN architecture with a low hardware overhead, which can be deployed in wearable edge devices to analyze the biosignal data and to extract the relevant information, such as arrhythmia and seizure. Furthermore, BioNetExplorer reduces the exploration time by deploying genetic algorithms, such as NSGA-ii, SPEA-2, etc. Our framework also enables the hardware-aware DNN architecture search by imposing user requirements and hardware constraints (storage, FLOPs, etc.) during the exploration stage, thereby limiting the number of networks explored. Moreover, BioNetExplorer can also be used to search for DNNs based on the user-required output classes;for instance, a user might require a specific output class, attributed toward ventricular fibrillation, due to genetic predisposition or a preexisting heart condition. The use of genetic algorithms reduces the exploration time, on average, by 9x, compared to exhaustive exploration. We are successful in identifying Pareto-optimal designs, which can reduce the storage overhead of DNN by similar to 30 MB for a quality loss of less than 0.5%. To enable low-cost embedded DNNs, BioNet

关键词： Bio-signals convolution deep neural networks (DNNs) efficiency embedded systems exploration healthcare long short-term memory (LSTM) performance wearables

来源：评论

学校读者我要写书评

暂无评论

Optimizing and Scaling the 3D Reconstruction of Single-Particle imaging

Optimizing and Scaling the 3D Reconstruction of Single-Parti...

引用

International Symposium on parallel and Distributed processing (IPDPS)

作者： Niteya Shah Christine Sweeney Vinay Ramakrishnaiah Jeffrey Donatelli Wu-Chun Feng Dept. of Computer Science Virginia Tech Blacksburg VA USA Applied Computer Science Group Los Alamos National Laboratory Los Alamos NM USA Center for Advanced Mathematics for Energy Research Applications Lawrence Berkeley National Laboratory Berkeley CA USA

ISBN: (数字)9798350387117

ISBN: (纸本)9798350387124

An x-ray free electron laser (xFEL) facility can produce on the order of 1,000,000 extremely bright x-ray light pulses per second. Using an xFEL to image the atomic structure of a molecule requires fast analysis of an enormous amount of data, estimated to exceed one terabyte per second and requiring petabytes of storage. The SpiniFEL application provides such analysis by determining the 3D structure of proteins from single-particle imaging (SPI) experiments performed using xFELs, but it needs significantly better performance and efficiency to scale and keep up with the terabyte-per-second data production. Thus, this paper addresses the high-performance computing optimizations and scaling needed to improve this 3D reconstruction of SPI data. First, we optimize data movement, memory efficiency, and algorithms to improve the per-node computational efficiency and deliver a 5.28× speedup over the baseline GPU *** addition, we achieved a 485× speedup for the post-analysis reconstruction resolution, which previously took as long as the 3D reconstruction of SPI data. Second, we present a novel distributed shared-memory computational algorithm to hide data latency and load-balance network traffic, thus enabling the processing of 128× more orientations than previously possible. Third, we conduct an exploratory study over the hyperparameter space for the SpiniFEL application to identify the optimal parameters for our underlying target hardware, which ultimately led to an up to 1.25× speedup for the number of streams. Overall, we achieve a 6.6× speedup (i.e., 5.28×1.25) over the previous fastest GPUMPI-based SpiniFEL realization.

关键词： Proteins Three-dimensional displays imaging x-ray lasers Telecommunication traffic Production x-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Exploring the use of Optical Domain Information for Automated Target Detection and Recognition 2

Exploring the use of Optical Domain Information for Automate...

引用

Conference on Virtual, Augmented, and Mixed Reality (xR) Technology for Multi-Domain Operations ii

作者： Hickman, Duncan L. Tektonex Ltd Argyll Rd Kilcreggan Argyll & Bute Scotland

ISBN: (数字)9781510643567

ISBN: (纸本)9781510643567

Automated Target Detection and Recognition (ATD/R) of targets in a cluttered background presents major challenges for the designers of military sensor systems. To achieve acceptable levels of detection and recognition performance, extensive use is often made of complex image processing techniques such as neural network architectures which attempt to replicate the capabilities of the human vision system. Although such methods generate good levels of performance, they are often not suitable for those applications where smaller and lower cost sensor systems are used across a more diverse range of scene content and imaging conditions. A new approach is proposed here where system performance is achieved through a more effective balance between optical domain and post-detection processing. Specifically, the Signal to Clutter Ratio (SCR) is maximised by using broadband spectral and polarisation information to offset performance deficiencies associated with simple image and data processing functions. It is shown that this approach offers a basis for introducing ATD/R functionality in low cost imaging systems such as those flown on drones. A simple imaging system is used to demonstrate the concept, which compromises two broadband cameras operating in the visible and near infrared bands, and with one of the sensors additionally providing polarimetric information. The concept of a joint spectral polarisation weight map is proposed and the potential performance gain is illustrated using targets in moderate to high clutter situations. The results obtained indicate potential benefits for future ATD/R systems and it is hoped that this will encourage future design engineers to consider the wider use of optical domain information.

关键词： Target detection and recognition ATD/R spectral processing polarimetry colour weight map polarisation weight map joint weight map signal to clutter optical domain processing

来源：评论

学校读者我要写书评

暂无评论

Abstract: Implementation of a Real-time 3D-thermometry Pipeline in Gadgetron for Easy Clinical Integration

Abstract: Implementation of a Real-time 3D-thermometry Pipel...

引用

Bildverarbeitung für die Medizin Workshop, BVM 2023

作者： Horstmann, Dominik zu Hartlage, Karen Meyer Reimert, Daniel Löning Caballero, Joaquin J. Belker, Othmar Wacker, Frank Hensen, Bennet Gutberlet, Marcel Hannover Medical School Germany STIMULATE-Solution Centre for Image Guided Local Therapies Germany

ISBN: (纸本)9783658416560

MR thermometry as measure for guiding thermal ablation of tumor tissue makes realtime imaging and arbitrary slice positioning possible while assuring precise knowledge of the size of the ablation zone. However, difficult clinical integration currently hamper the success of clinical thermometry. Purpose of this work was to implement a real-time 3D MR thermometry pipeline for easy clinical integration. The pipeline starts with fast data acquisition by a multigradient echo 3D stack-of-stars sequence. The acquired data is then sent to an external server where images temperature maps as well as necrosis maps are calculated from it via a modular Gadgetron pipeline running in a Docker container. Using Docker guarantees multi-platformportability and reproducibility of our pipeline whereas the ISMRMRD format makes it vendor independent. parallel imaging, compressed sensing (PICS) as well as GPU accelerated reconstruction are implemented. Apart from that, the pipeline contains correction algorithms for noise, gradient delay, phase drift and phase errors. To test the pipeline, microwave ablations on nine static bioprotein phantoms were performed on a 1.5 T scanner. Fiber optical temperature sensors were used for gaining reference temperatures. Retrospectively, the calculated necrosis zones were compared to a ground truth. The pipeline yielded temperature accuracies of 1.15 °C ± 0.69 °C compared to the temperature sensors. The comparison of the ablation zone with the ground truth yielded dice scores of 84.02 % ± 2.36 %. For a 3D volume with 24 slices and 8 echoes the processing time was about 26 s. The experiments show that the thermometry pipeline is already close to real-time 3D thermometry. Further research will focus on optimizing it for moving phantoms as, in the future, it is planned to be used for clinical applications in moving organs such as the liver. The modular and opensource character of the pipeline makes future improvements and extensions easy to integrate [1]. ©

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Design of Approximate Tree Multiplier Using Approximate Compressor for image processing applications

引用

IETE JOURNAL OF RESEARCH 2024年第10期70卷 7899-7910页

作者： Venkatnarayanan, C. Somasundaram, D. Univ Coll Engn Arni Dept Elect & Commun Engn Thatchur India Sri Shakthi Inst Engn & Technol Dept Electronics& Commun Engn Coimbatore India

Approximate computing enables high performance and efficiency of execution by using the overhead on compute units of a processor to give high speed. The speed and system delay are inversely proportional, necessitating massive parallel processes with massive hardware and power dissipation. Energy and area-efficient systems can be realized by reducing system accuracy and dependability. Approximate computing techniques can be used to reduce the number of computing resources needed for a given task and improve the performance of a system. This can be accomplished by lowering a computational model's accuracy and decreasing complexity, reducing power consumption, latency, and area requirements. This study examines an electrical circuit that performs multiplication of two equal integers and it proposes the use of a carry-in adder with two approximation compressors to reduce the size, latency, and power consumption while maintaining the same level of accuracy as current designs. The suggested algorithms were implemented in xilinx Vivado and their effectiveness was evaluated using numerical performance metrics, including error rate, power consumption, delay, and power delay product in output result. The compressors suggested are used to implement 8 x 8 and 16 x 16 Dadda multipliers that perform comparably to state-of-the-art approximation multipliers.

关键词： Approximate compressors Approximate computing Dadda multiplier approximation Lower complexity Reduced accuracy

来源：评论

学校读者我要写书评

暂无评论

140 Frames-per-Second Ionoacoustic imaging Detector for Real-Time Particle Therapy Monitoring 29

140 Frames-per-Second Ionoacoustic Imaging Detector for Real...

引用

29th IEEE International Conference on Electronics, Circuits and systems (IEEE ICECS)

作者： Vallicelli, Elia A. Cosmi, Mattia Oliver Tambaro, Mattia Baschirotto, Andrea De Matteis, Marcello Univ Milano Bicocca Milan Italy Univ Padua Padua Italy

ISBN: (数字)9781665488235

ISBN: (纸本)9781665488235

This work presents the development and experimental validation of a ionacoustic detector that uses a multi-channel sensor, a dedicated ASIC in 28nm CMOS and hardware DSP to reduce the input-referred noise power by 1-2 orders of magnitude compared to state of the art ionacoustic detectors. The most interesting application of the ionacoustic technique is the real-time monitoring with sub-millimeter precision of hadron therapy treatments, but the main limitation of current detectors lies in their high latency and noise power, not compatible with clinical treatments. The hereby presented High-Resolution Proton Sound Detector exploits the parallel acquisition and processing of 64 channels to obtain a 2D acoustic image of the source with 256x256 pixel resolution, 140 fps and 70 mPaRMS input-referred noise, resulting in 34 dB SNR with 0.8 Gy dose deposition.

关键词： Circuits and systems for Biomedical applications Analog Integrated Circuits Radiation Therapy

来源：评论

学校读者我要写书评

暂无评论

Understanding the Impact of Synchronous, Asynchronous, and Hybrid In-Situ Techniques in Computational Fluid Dynamics applications 18

Understanding the Impact of Synchronous, Asynchronous, and H...

引用

IEEE 18th International Conference on E-Science (E-Science)

作者： Ju, Yi Perez, Adalberto Markidis, Stefano Schlatter, Philipp Laure, Erwin Max Planck Comp & Data Facil Garching Germany KTH Royal Inst Technol Stockholm Sweden

ISBN: (数字)9781665461245

ISBN: (纸本)9781665461245

High-Performance Computing (HPC) systems provide input/output (IO) performance growing relatively slowly compared to peak computational performance and have limited storage capacity. Computational Fluid Dynamics (CFD) applications aiming to leverage the full power of Exascale HPC systems, such as the solver Nek5000, will generate massive data for further processing. These data need to be efficiently stored via the IO subsystem. However, limited IO performance and storage capacity may result in performance, and thus scientific discovery, bottlenecks. In comparison to traditional post-processing methods, in-situ techniques can reduce or avoid writing and reading the data through the IO subsystem, promising to be a solution to these problems. In this paper, we study the performance and resource usage of three in-situ use cases: data compression, image generation, and uncertainty quantification. We furthermore analyze three approaches when these in-situ tasks and the simulation are executed synchronously, asynchronously, or in a hybrid manner. In-situ compression can be used to reduce the IO time and storage requirements while maintaining data accuracy. Furthermore, in-situ visualization and analysis can save Terabytes of data from being routed through the IO subsystem to storage. However, the overall efficiency is crucially dependent on the characteristics of both, the in-situ task and the simulation. In some cases, the overhead introduced by the in-situ tasks can be substantial. Therefore, it is essential to choose the proper in-situ approach, synchronous, asynchronous, or hybrid, to minimize overhead and maximize the benefits of concurrent execution.

关键词： CFD in-situ HPC

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：