检索结果-内蒙古大学图书馆

Randomized tensor decomposition using parallel reconfigurable systems

JOURNAL OF SUPERCOMPUTING 2025年第4期81卷 1-32页

作者： Misra, Ajita Abdelgawad, Muhammad A. A. Jing, Peng Cheung, Ray C. C. Yan, Hong City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China City Univ Hong Kong Ctr Intelligent Multidimens Data Anal Kowloon Hong Kong Peoples R China

Tensor decomposition algorithms are essential for extracting meaningful latent variables and uncovering hidden structures in real-world data tensors. Unlike conventional deterministic tensor decomposition algorithms, randomized methods offer higher efficiency by reducing memory requirements and computational complexity. This paper proposes an efficient hardware architecture for a randomized tensor decomposition implemented on a field-programmable gate array (FPGA) using high-level synthesis (HLS). The proposed architecture integrates random projection, power iteration, and subspace approximation via QR decomposition to achieve low-rank approximation of multidimensional datasets. The proposed architecture utilizes the capabilities of reconfigurable systems to accelerate tensor computation. It includes three central units: (1) tensor times matrix chain (TTMc), (2) tensor unfolding unit, and (3) QR decomposition unit to implement a three-stage algorithm. Experimental results demonstrate that our FPGA design achieves up to 14.56 times speedup compared to the well-implemented tensor decomposition using software library Tensor Toolbox on an Intel i7-9700 CPU. For a large input tensor of size 512x512x512\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$512 \times 512 \times 512$$\end{document}, the proposed design achieves a 5.55 times speedup compared to an Nvidia Tesla T4 GPU. Furthermore, we utilize our hardware-based high-order singular value decomposition (HOSVD) accelerator for two real applications: background subtraction of dynamic video datasets and data compression. In both applications, our proposed design shows high efficiency regarding accuracy and computational time.

关键词： High-level synthesis (HLS) Field programmable gate array (FPGA) Randomized algorithm Low-rank tensor computing High order singular value decomposition (HOSVD)

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial network based on domain adaptation for crack segmentation in shadow environments

引用

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING 2025年第0期

作者： Zhang, Yingchao Liu, Cheng City Univ Hong Kong Dept Syst Engn Tat Chee Ave Hong Kong Peoples R China City Univ Hong Kong Ctr Intelligent Multidimens Data Anal Hong Kong Peoples R China

Precision segmentation of cracks is important in industrial non-destructive testing, but the presence of shadows in the actual environment can interfere with the segmentation results of cracks. To solve this problem, this study proposes a two-stage domain adaptation framework called GAN-DANet for crack segmentation in shadowed environments. In the first stage, CrackGAN uses adversarial learning to merge features from shadow-free and shadowed datasets, creating a new dataset with more domain-invariant features. In the second stage, the CrackSeg network innovatively integrates enhanced Laplacian filtering (ELF) into high-resolution net to enhance crack edges and texture features while filtering out shadow information. In this model, CrackGAN addresses domain shift by generating a new dataset with domain-invariant features, avoiding direct feature alignment between source and target domains. The ELF module in CrackSeg effectively enhances crack features and suppresses shadow interference, improving the segmentation model's robustness in shadowed environments. Experiments show that GAN-DANet improves the crack segmentation accuracy, with the mean intersection over union value increasing from 57.87 to 75.03, which surpasses the performance of existing state-of-the-art domain adaptation algorithms.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT RANDOMIZED ALGORITHMS FOR FIXED PRECISION PROBLEM OF APPROXIMATE TUCKER DECOMPOSITION

引用

SIAM JOURNAL ON MATRIX analYSIS AND APPLICATIONS 2025年第1期46卷 256-297页

作者： Che, Maolin Wei, Yimin Yan, Hong Ctr Intelligent Multidimens Data Anal Shatin Hong Sci Pk Hong Kong Peoples R China Fudan Univ Sch Math Sci Shanghai 200433 Peoples R China Fudan Univ Key Lab Math Nonlinear Sci Shanghai 200433 Peoples R China City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China City Univ Hong Kong Ctr Intelligent Multidimens Data Anal Kowloon Hong Kong Peoples R China

In this paper, we focus on the fixed-precision problem for the approximate Tucker decomposition of any tensor. First, we modify several structured matrices for the adaptive randomized range finder algorithm in [W. Yu, Y. Gu, and Y. Li, SIAM J. Matrix anal. Appl., 39 (2018), pp. 1339--1359], when the standard Gaussian matrices are replaced by uniform random matrices, the Khatri--Rao product of the standard Gaussian matrices (or the uniform random matrices). Second, by using this modified algorithm for each mode unfolding of the input/intermediate tensor, we obtain the adaptive randomized variants for T-HOSVD and ST-HOSVD. Third, we propose theoretical properties for these adaptive randomized variants. Finally, numerical examples illustrate that for a given tolerance, the proposed algorithms are superior to other algorithms in terms of relative error, desired Tucker rank, and running time.

关键词： Tucker decomposition fixed-precision problem randomized algorithms standard Gaussian matrices continuous uniform distributions Khatri--Rao product adaptive T-HOSVD adap- tive ST-HOSVD

来源：评论

学校读者我要写书评

暂无评论

Q-Learning-Based Workload Consolidation for data Centers With Composable Architecture

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第3期21卷 2324-2333页

作者： Guo, Chao Li, Longfei Zukerman, Moshe Ctr Intelligent Multidimens Data Anal Ltd Hong Kong Peoples R China Suzhou Vocat Univ Sch Elect Informat Engn Suzhou 215104 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Composable or disaggregated architectures have emerged as a solution to address the drawbacks of server-based architectures in data centers, such as resource inefficiency and limited scalability. This article focuses on the workload consolidation problem where we aim to consolidate workloads that spread over many underutilized (resource) nodes onto fewer ones, with the two objectives of minimizing the number of active nodes and workload migrations, thereby enhancing energy efficiency and resource utilization. To address this problem, we propose a Q-learning-based reinforcement learning method that yields an approximate Pareto front, providing a set of (approximate) optimal solutions catering to different preferences for the two objectives. The performance of the proposed method is validated by comparing it to integer linear programming, simulated annealing, first fit, and first fit decreasing algorithms.

关键词： Resource management Q-learning data centers Informatics Costs Chaos Bandwidth Servers Scalability Memory management Composable or disaggregated data center (DC) Pareto front workload consolidation

来源：评论

学校读者我要写书评

暂无评论

On the generalized N-critical shock model

引用

QUALITY TECHNOLOGY AND QUANTITATIVE MANAGEMENT 2025年

作者： Goyal, Dheeraj Xie, Min Indian Inst Technol Kanpur Dept Math & Stat Kanpur 208016 Uttar Pradesh India Ctr Intelligent Multidimens Data Anal Ltd Pak Shek Kok Hong Kong Sci Pk Hong Kong Peoples R China City Univ Hong Kong Dept Syst Engn Hong Kong Peoples R China

According to the N-critical shock model, a system fails if the total number of critical shocks reaches N. The central assumption in this model is that after the arrival of a critical shock, the next shock will be critical with the same probability. This is a restrictive and unrealistic assumption in many natural situations. This paper defines a generalized N-critical shock model that overcomes this limitation. We study the model for two well-known shock arrival processes and derive reliability indices such as reliability function and mean remaining lifetime.

关键词： Reliability N-critical shock model phase-type distribution homogeneous Poisson generalized gamma process

来源：评论

学校读者我要写书评

暂无评论

Application of Adaptive Parallel Fast Marching Method in Automatic Submarine Cable Path Planning

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 9498-9514页

作者： Wang, Xinyu Wang, Zengfu Zukerman, Moshe Ctr Intelligent Multidimens Data Anal Hong Kong Peoples R China Northwestern Polytech Univ Res & Dev Inst Shenzhen 518057 Peoples R China Northwestern Polytech Univ Sch Automat Xian 710072 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Submarine optical fiber communication cables (subsequently referred to as submarine cables) form the backbone of the Internet's infrastructure. Damage to these cables can precipitate Internet outages with far-reaching socio-economic impacts. The prevailing practice of manual cable routing is laborious, considering the thousands of kilometers these cables span. It also fails to strike an optimal balance between cost and risk due to its lack of scalability and precision. The Fast Marching Method (FMM), a non-iterative, precise numerical approach capable of solving the Eikonal equation, offers a viable alternative by optimizing the required path between source and destination, considering a summary objective function of costs and risk factors. An interpretation of its solution signifies the optimum value of the objective function between a starting point and all other points. However, the sequential nature of the FMM algorithm suffers from computational limitations and impedes direct parallelization. In this study, we introduce an Adaptive Parallel FMM (APFMM), an innovative approach utilizing adaptive domain decomposition and dynamic multi-resolution analysis. This scalable and widely applicable method can overcome the limitations of existing methods and achieve planning of high-precision, ultra-long-distance (over 14,000 km) submarine cable routes over the Earth's surface. Simulated experiment results corroborate that APFMM effectively overcomes the computational challenges posed by the sequential FMM when dealing with large datasets. Additionally, it reduces the running time by more than 81% compared to the traditional parallel FMM. This marks a substantial advancement in facilitating efficient, automated, high-precision planning for long-distance submarine cable paths. Note to Practitioners-This paper introduces APFMM, a novel technique based on adaptive domain decomposition and multi-resolution analysis, facilitating high-precision, ultra-long-distance (over 14,00

关键词： Underwater cables Cables Costs Path planning Planning Manuals Earth Computational efficiency Mathematical models Accuracy Submarine optical fiber cables path planning adaptive parallel FMM domain decomposition methods multi-resolution method cost-effectiveness survivability

来源：评论

学校读者我要写书评

暂无评论

Geometric programming for multilinear systems with nonsingular M-tensors

引用

APPLIED MATHEMATICS LETTERS 2025年 163卷

作者： Chen, Haibin Zhou, Guanglu Yan, Hong Qufu Normal Univ Sch Management Sci Rizhao 276800 Shandong Peoples R China Curtin Univ Curtin Ctr Optimisat & Decis Sci Sch Elect Engn Comp & Math Sci Bentley WA 6102 Australia Ctr Intelligent Multidimens Data Anal Shatin Hong Kong Sci Pk Hong Kong Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

We consider multilinear systems which arise in various applications, such as data mining and numerical differential equations. In this paper, we show that the multilinear system with a nonsingular M-tensor can be formulated equivalently into a geometric programming (GP) problem which can be solved by the barrier-based interior point method with a worst-case polynomial-time complexity. To the best of our knowledge, there is not a complexity analysis for the existing algorithms of the multilinear systems. Numerical results are reported to show the efficiency of the proposed GP method.

关键词： Multilinear system M-tensor Interior point algorithm Complexity

来源：评论

学校读者我要写书评

暂无评论

Image-based remaining useful life prediction through adaptation from simulation to experimental domain

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2025年 255卷

作者： Wang, Zhe Yang, Lechang Fang, Xiaolei Zhang, Hanxiao Xie, Min City Univ Hong Kong Dept Syst Engn Hong Kong Hong Kong Speci Peoples R China Ctr Intelligent Multidimens Data Anal Hong Kong Sci Pk Hong Kong Peoples R China Univ Sci & Technol Beijing Sch Mech Engn Beijing Peoples R China North Carolina State Univ Edward P Fitts Dept Ind & Syst Engn Raleigh NC USA Beijing Jiaotong Univ Sch Mech Elect & Control Engn Beijing Peoples R China

Degradation profoundly affects the performance of industrial systems, necessitating operational safety prognostics. However, the availability of run-to-failure data is often limited, and labels in real-world scenarios are scarce. To address the challenge, this work utilizes the simulation domain to extract degradation knowledge and then adaptively transfers this knowledge to the experimental domain, aiming at estimating the remaining useful life (RUL). The relative RUL in the simulation domain is adopted, focusing on the degradation trend and avoiding the determination of absolute RUL. The feature disentanglement technique captures degradation- relevant features. To improve model performance, Bayesian optimization is introduced to search for optimal hyperparameters, and a two-task learning approach is designed to achieve the objectives of both domains. A few labeled experimental samples are used to adjust the predictor to appropriate scale. The case study on infrared degradation image streams validates the effectiveness of this domain adaptation scheme. Further analysis and discussions demonstrate the superiority of the model and the associated optimization strategy.

关键词： Domain adaptation Feature disentanglement Prognostics Remaining useful life Thermal image

来源：评论

学校读者我要写书评

暂无评论

Joint optimization of condition-based production and maintenance with mutual production-deterioration dependencies

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2025年 256卷

作者： Zhang, Hanxiao Wang, Zhe Liu, Xingchen Gaudoin, Olivier Xie, Min Beijing Jiaotong Univ Sch Mech Elect & Control Engn Beijing Peoples R China City Univ Hong Kong Dept Syst Engn Hong Kong Peoples R China Ctr Intelligent Multidimens Data Anal Hong Kong Sci Pk Hong Kong Peoples R China Hong Kong Polytech Univ Dept Ind & Syst Engn Hong Kong Peoples R China Univ Grenoble Alpes Lab Jean Kuntzmann Grenoble France City Univ Hong Kong Shenzhen Res Inst Shenzhen Peoples R China

Production control and maintenance scheduling are the two major cost-effective methodologies in the manufacturing systems. The existing literature considers these processes in isolation or with unidirectional dependencies. To fill this gap, we propose an integrated control model of maintenance and production process considering the mutual influence between production and deterioration in a single-machine system. By leveraging condition monitoring data, we enhance decision-making effectiveness and develop a comprehensive framework based on an infinite-horizon Markov decision process. We establish and prove the monotonic structural properties of total profit and maintenance actions relative to machine state, and develop an improved value iteration algorithm to reduce the computational space. Numerical experiments demonstrate the performance of our model in maximizing profits compared to traditional condition-based maintenance and condition-based production approaches. Sensitivity analysis further highlights key parameters influencing optimal policies, providing valuable insights for practical applications.

关键词： Condition-based maintenance Condition-based production Reliability Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Fast-Adaptive Permanent Magnetic Positioning-based Navigation Framework for Continuum Robots in Colonoscopic Biopsy

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2025年

作者： Yao, Shilong Luo, Peiyu Liu, Li Yan, Hong Meng, Max Q. -H. Shenzhen Key Lab Robot Percept Intelligence Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen 518055 Peoples R China Great Bay Univ Sch Engn Dongguan 523000 Peoples R China Dongguan Great Bay Inst Adv Study Dongguan 523000 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong 999077 Peoples R China City Univ Hong Kong Ctr Intelligent Multidimens Data Anal Hong Kong 999077 Peoples R China

The potential of continuum robots in medical applications is considerable, due to their flexibility and capacity to navigate complex anatomical environments. This article introduces a novel framework based on the Fast-Adaptive Permanent Magnetic Tracking method, which has been designed with the objective of enhancing the accuracy and autonomy of colonoscopic biopsies. The system incorporates a permanent magnet positioning methodology, enabling the robot to maintain a trajectory tracking root mean square error of less than 4 mm, with magnet speeds up to 150 mm/s and positioning errors under 2 mm. Furthermore, the framework includes an adaptive obstacle avoidance strategy, allowing the robot to navigate around obstacles and adjust its posture in response to dynamic movement. Extensive experimental validations in both simulation and real-world environments demonstrate the system's effectiveness in delivering precise, responsive, and continuous operation. This work represents a significant advancement in autonomous navigation based on permanent magnetic localization techniques, with the potential to enhance the efficacy and safety of robotic-assisted surgeries.

关键词： Robots Magnetometers Robot sensing systems Continuum robots Biopsy Navigation Shape Location awareness Accuracy Magnetic resonance imaging Continuum robot magnetic positioning robot-assisted endoscopic biopsy

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：