检索结果-内蒙古大学图书馆

5th International Conference on Intelligence Science and Big Data Engineering (IScIDE)

作者： Liu, Heng Liu, Hongshen Xun, Jing Anhui Univ Technol Sch Comp Sci & Technol Maanshan Peoples R China Hisense R&D Ctr Inst Syst Technol Qingdao Peoples R China

ISBN: (纸本)9783319239897;9783319239873

The main defect of traditional filtering based image dehazing approaches is huge time consuming, especially for large size image haze removal. In the work, a serial of practical computation acceleration strategies for bilateral filtering based haze removal are proposed. Our approach strength lies in its wide practicability: better dehazing with very fast computation speed even for large size images. Since our approach requires less time consuming corresponding to less CPU load, it will be promising for some real time application, such as smart TV image enhancement.

关键词： Image dehazing Bilateral filtering computation acceleration

来源：评论

学校读者我要写书评

暂无评论

An Interpretable Dynamic Feature Search Methodology for Accelerating computational Process of Control Rod Descent in Nuclear Reactors

引用

ENERGIES 2025年第7期18卷 1827-1827页

作者： Huang, Qingyu Xiao, Cong Zeng, Wei Xu, Le Liu, Jia Pang, Zhixin Lin, Yuanfeng Zhao, Mengwei Liu, Xiaobo Nucl Power Inst China Natl Key Lab Nucl Reactor Technol Chengdu 610213 Peoples R China

Within the operational dynamics of a nuclear reactor, the customary approach involves modulating the reactor's power output by means of control rod manipulation, which effectively alters the neutron density across the core. The descent behavior of the control rod drive lines pertains to the intricate motion exhibited by the control rod components within the reactor during its operational lifespan, characterized by conditions of heightened irradiation, temperature, pressure, and complex fluid dynamics. The precise calculation of the control rod descent process is an integral facet of reactor structural design to ensure the safe and reliable operation of the reactor. However, the current computational fluid dynamics-based simulation methods employed for this purpose necessitate extensive grid computations, imposing significant computational burdens in terms of resources and time. In light of this challenge, we present a novel and interpretative algorithm rooted in dynamic similarity feature search. Through comprehensive validation, this algorithm demonstrates remarkable precision, with the computational results exhibiting an error margin within 10% while simultaneously achieving a substantial enhancement of computational efficiency of nearly three orders of magnitude when compared to conventional computational fluid dynamics techniques and sequence-to-sequence machine learning algorithms. Notably, this algorithm showcases exceptional versatility, holding immense promise for broad applicability across various operational scenarios encountered during the intricate process of nuclear reactor design.

关键词： nuclear reactor control rod descent process computation acceleration dynamic feature search methodology CFD

来源：评论

学校读者我要写书评

暂无评论

The computation-Data Duality in Non-Deterministic Systems

The Computation-Data Duality in Non-Deterministic Systems

引用

作者： Dou, Xianzheng University of Michigan

学位级别：Ph.D.

Repeated computations and redundant data are pervasively invoked or generated in modern systems and software. These computations and data are mostly, but not exactly the same. For example, web servers invoke similar computations when displaying a common web page for different users, applications perform similar initialization during startups, and cloud storage services maintain past versions of user files with redundant data chunks shared among these versions. Consequently, many prior systems detect and deduplicate similar computations or data to reduce computation, network and storage costs. However, the non-determinism inherited in modern systems limits the effectiveness of existing approaches. Therefore, the thesis exploits the principle of equivalence between computation and data, i.e., the computation-data duality, to reduce redundancy for non-deterministic systems via two novel systematic supports. On the one hand, we can substitute computation for data to reduce storage and network costs for cloud-based storage services. In lieu of the actual file data, a file can be selectively represented as a description of the non-deterministic computation that is sufficient to re-create the same file data. Moreover, when the description of the computation is less costly than the file data, storage and communication costs are reduced. On the other hand, we can substitute data for computation to accelerate similar but non-deterministic computations, such as web server request processing and application startups. The computation is first memoized to disk, and then a predicated slice, which includes all instructions affected by non-deterministic inputs, is generated. For a subsequent execution of the same code region, the memoized outputs are applied to the program state and only these instructions in the predicated slice are re-evaluated to incorporate new non-deterministic inputs. As a result, the code region is significantly accelerated since most instructions are skipped

关键词： data redundancy computation redundancy computation acceleration equivalency between computation and data nondeterminism Thesis

来源：评论

学校读者我要写书评

暂无评论

A Novel Perturbed Matrix Inversion Based Method for the acceleration of Finite Element Analysis in Crack-Scanning Eddy Current NDT

引用

IEEE ACCESS 2020年 8卷 12438-12444页

作者： Huang, Ruochen Lu, Mingyang Peyton, Anthony Yin, Wuliang Tianjin Univ Sci & Technol Coll Elect Informat & Automat Tianjin 300222 Peoples R China Univ Manchester Sch Elect & Elect Engn Manchester M13 9PL Lancs England

Non-destructive testing (NDT) has a promising capability for crack detection. In this paper, a novel method for accelerating eddy current calculation for crack detection using the finite element method (FEM) is presented. This method exploits the fact that, due to the presence of a small defect, the stiffness matrix in FEM for a sample plate with the defect can be regarded as a summation of the stiffness matrix Q from the sample plate without the presence of the defect and the perturbation matrix D from the defect. The inversion of the stiffness matrix for a sample plate with the defect can, therefore, be obtained using the perturbed matrix inversion (PMI) method. PMI method only requires the inversion of a much smaller matrix and therefore improves the speed of the computation process. Numerical tests verified the effectiveness of the proposed method in shortening the computation time for crack scanning in FEM.

关键词： Finite-element method (FEM) eddy current calculation perturbed matrix inversion computation acceleration crack scanning

来源：评论

学校读者我要写书评

暂无评论

DFPT-CNN: A Dual Feature Extraction and Pretrained CNN Synergy for Minimal computational Overhead and Enhanced Accuracy in Multi-Class Medical Image Classification

引用

IEEE ACCESS 2024年 12卷 58573-58585页

作者： Varughese, Dinah Ann Sridevi, Sriadibhatla Vellore Inst Technol Vellore 632014 India

In the advanced computer vision era, Convolutional Neural Network (CNN) plays a pivotal role in image processing, as they excel at automatically extracting important patterns, and structures, for accurate analysis across diverse domains. However, achieving higher accuracy often leads to intensifying computational and timing demands. To address the challenge, this research introduces a novel dual feature extraction methodology. This approach is implemented using two distinct feature extraction modules, employed at different stages of the model: 1) Edge Gradient-Dimensionality Reduction (EGDR) module which encapsulates the extraction of pixel edge gradient features from the raw input frame, leading to a dimensionality reduction by a factor of 0.5;2) Subtle Local Feature Extraction (SLFE) pooling algorithm module, prioritizes the extraction of local and subtle features over maximum or average feature content. The combination of these two stages proves particularly effective in enhancing classification accuracy while minimizing computational overhead and training duration. Subsequently, comprehensive training, validation, and testing were conducted on a selected multi-class chest computed tomography medical image dataset using various state-of-the-art CNN architectures such as VGG-16, InceptionV3, ResNet50 to identify the most suitable model for further experimentation with the proposed method. The proposed CNN-SLFE framework with EGDR module achieved a significant reduction of 17.94% in computational time compared to non-EGDR module, and concurrently enhanced the classification accuracy with an improvement factor of 1.17 compared to existing CNN frameworks with EGDR module.

关键词： Classification accuracy computation acceleration convolutional neural network feature extraction medical images pooling algorithm

来源：评论

学校读者我要写书评

暂无评论

A cell agglomeration algorithm for accelerating detailed chemistry in CFD

引用

COMBUSTION THEORY AND MODELLING 2009年第4期13卷 721-739页

作者： Goldin, Graham M. Ren, Zhuyin Zahirovic, Selma Ansys Inc Lebanon NH 03766 USA Bioenergy 2020 GmbH A-8010 Graz Austria

A cell agglomeration algorithm is proposed to mitigate the computational cost of incorporating detailed chemical kinetics in multi-dimensional computational Fluid Dynamics (CFD) simulations. Cells that are close in species and energy composition space are agglomerated before calling the reaction integrator, substantially reducing the number of chemistry integrations. The algorithm is generalized and applicable to any reacting flow configuration, and the accuracy is fully controllable. A dynamic hash table is used to efficiently bin cells into high dimensional hyper-cubes in composition space. The method is applied to four different CFD simulations and the speed-up and incurred error are assessed for a range of agglomeration tolerances and table dimensions. The proposed approach exhibits up to an order of magnitude speed-up with a relatively moderate decrease in accuracy.

关键词： cell agglomeration detailed chemical kinetics CFD computation acceleration multi-zone and reactor network

来源：评论

学校读者我要写书评

暂无评论

Accelerated Information Processing Based on Deep Photonic Time-Delay Reservoir Computing

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2024年第24期42卷 8739-8747页

作者： Zhang, Jiahao Zhang, Lu Pang, Xiaodan Ozolins, Oskars Yu, Xianbin Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China KTH Royal Inst Technol Appl Phys Dept S-10691 Stockholm Sweden RISE Res Inst Sweden Networks Unit S-16440 Kista Sweden Riga Tech Univ Inst Photon Elect & Telecommun LV-1048 Riga Latvia

Photonic time-delay reservoir computing (TDRC) is an optical neural network structure known for its simple hardware implementation. However, this simplicity reduces information processing speed due to its sequential time multiplexing mechanism, such as the masking operation in practical experiments. To address this, we employ a deep photonic TDRC structure to enhance reservoir dynamics, effectively reducing the mask size to accelerate processing while maintaining high performance. An extended state matrix is proposed to leverage the enriched dynamics without additional hardware costs, combining different nonlinear intensities and memory lengths to augment node states without physically expanding the reservoir. Experimentally validated in a speech recognition task, our approach accelerates processing by 10 times with only a 2.4% decrease in recognition accuracy, compared to a 13.1% accuracy deterioration in the conventional scheme, indicating significant acceleration in TDRC information processing while maintaining performance.

关键词： Reservoirs Task analysis Hardware Information processing Photonics Neural networks Multiplexing computation acceleration optical neural network reservoir computing speech recognition

来源：评论

学校读者我要写书评

暂无评论

Fast Sky to Sky Interpolation for Radio Interferometric Imaging 29

Fast Sky to Sky Interpolation for Radio Interferometric Imag...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Monnier, Nicolas Orieux, Francois Gac, Nicolas Tasse, Cyril Raffin, Erwan Guibert, David Univ Paris Saclay Lab Signaux & Syst CNRS Cent Supelec F-91190 Gif Sur Yvette France Univ Paris Diderot GEPI Observ Paris F-92190 Meudon France CEPP Ctr Excellence Performance Programming Rennes France

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Reconstruction of radio interferometric images requires the processing of data in Fourier space that dot not have regular coordinates, preventing direct use of the Fast Fourier Transform. The most common solution is to rely on interpolation algorithms, called gridding, that are computationally expensive. In this paper, we propose an algorithmic reinterpretation, named sky to sky method, to reduce the computation cost of the gridding operation and its adjoint, the degridding, when used successively. We analyze the impact of interpolation step size regarding the computation cost and the reconstruction error. We also illustrate this optimization on a full reconstruction with gradient descent and CLEAN algorithm. Finally, we obtain acceleration factors between 1.2 and 16.4 without additional approximation.

关键词： Interpolation inverse problem gridding computation acceleration

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Assisted Malware Detection Framework for Mobile Devices

A Cloud-Assisted Malware Detection Framework for Mobile Devi...

引用

International Computer Symposium (ICS)

作者： Hung, Shih-Hao Tu, Chia-Heng Yeh, Chi Wei Natl Taiwan Univ Taipei 10617 Taiwan Natl Cheng Kung Univ Tainan 70101 Taiwan

ISBN: (纸本)9781509034383

While mobile applications make our lives more convenient, security concerns may arise when the mobile applications contain malicious code that would harm the mobile devices and their users financially and physically. In this article, we propose a malware detection framework to protect the mobile devices with the help of the cloud, where the cloud is equipped with the facilities for automatic analysis of large amount of new malware generated everyday, and the device is able to detect malicious intents of running software in real-time based on the knowledge of the analyzed malware. We evaluate the performance of our framework with Android-based systems as case studies. In particular, we study the impact of different system configurations on the time required for malware detection, including detecting algorithms (i.e., CNN and SVM), mobile processors (i.e., ARM CPU and NVIDIA GPU), and wireless networks (i.e., Wi-Fi and 3G for the communication between the device and the cloud). To the best of our knowledge, we are not aware of any other work studying performance impacts of the system configurations of the malware detection systems using the physical machines. As the widespread of malware, we believe that our empirical study is useful when designing antivirus software and can be applied to different application domains, such as automotive, and smart home.

关键词： Malware detection Android systems Convolutional Neural Network Support Vector Machines computation acceleration mobile cloud computing

来源：评论

学校读者我要写书评

暂无评论

MULTI-CORE COMPUTING UNIT FOR ARTIFICIAL NEURAL NETWORKS IN FPGA CHIP

MULTI-CORE COMPUTING UNIT FOR ARTIFICIAL NEURAL NETWORKS IN ...

引用

6th International Conference on Informatics in Control, Automation and Robotics

作者： Bohrn, Marek Fujcik, Lukas Brno Univ Technol Dept Microelect Brno Czech Republic

ISBN: (纸本)9789898111999

This article describes a design and features of a multi-core unit for performing computing operations required for artificial neural network functioning. Its purpose is to speed up computing operations of the neural network. The number of computing cores can be altered as needed to achieve the required performance. VHDL language has been used to build this module. It has been optimized for the Spartan-3 family FPGA chips from Xilinx. These chips are favorable because of their low price and a high number of on-chip multipliers and block memory units. Spartan-3 chips facilitate parallel computing operations within neural networks to a very high level and thus help to achieve high computing power.

关键词： Artificial neural networks computation acceleration FPGA VHDL Spartan-3

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：