检索结果-内蒙古大学图书馆

3rd International Conference on computer Vision, Image and Deep Learning and International Conference on computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Huo, Jiahao Qiao, Sijie Qian, Qicong Yang, Jiaxi School of Architectural Engineering Jinling Institute of Technology Nanjing China Xidian University School of Computer Science and Technology Xi'an China Wuhan University of Technology School of Naval Architecture Ocean and Energy Power Engineering Wuhan China Luoyang Normal University School of Information Technology Luoyang China

ISBN: (纸本)9781665459112

This paper mainly introduces an improved flower recognition method based on improved VGG Networks. There are problems with the existing flower recognition system. For example, recognition accuracy is poor for flowers with a similar appearance. Also, the model they use usually takes a long time for training. This study took into account the characteristics of the project and used the Mobile Network that is more lightweight than most of the other networks they normally used. In this case, this study ameliorates the network by adding the attentional mechanism. The proposed model adjusts the network architecture according to the learning results and expectations during the training process. The experiments show that the proposed model with the integration of the MobileNet is more accurate and efficient than other networks. The improved model with attention mechanism can be generalized to new flower datasets and correctly identify flower species in a noisy background, making it practical to apply the model in daily life. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

NOMA: A Novel Reliability Improvement Methodology for 3-D IC-based Neuromorphic Systems

引用

IEEE Transactions on Components, Packaging and Manufacturing Technology 2024年

作者： Nguyen, Ngo-Doanh Dang, Khanh N. Ahmed, Akram Ben Abdallah, Abderazek Ben Tran, Xuan-Tu The University of Aizu The Graduate School of Computer Science and Engineering Fukushima Aizu-Wakamatsu965-8580 Japan Vietnam National University The Information Technology Institute Hanoi10000 Viet Nam National Institute of Advanced Industrial Sciences and Technology The Digital Architecture Research Center 2-3-26 Aomi Koto-ku Tokyo Japan

Hardware is the foundation of trust for all real-time applications and is especially crucial in Artificial Intelligence (AI). The growing reliance on AI for various tasks has raised concerns about the reliability of the hardware. Extensive research has shown that hardware faults arising from the manufacturing process or device variation can significantly impact the precision and accuracy of AI applications. This also applies to 3-D IC (Three-Dimensional Integrated Circuit)-based Spiking Neural Networks (SNNs), despite their noise resilience, low-power, and low memory footprint advantages. This is because, in addition to the mentioned hardware faults, thermal dissipation on 3-D ICs can negatively affect the memory stacked on upper dies. Hence, this article proposes a methodology called NOMA (Network-of-Memory architecture) to enhance the reliability of 3-D IC-based SNNs by replacing the defective critical synaptic weights in high-priority layers with lower-priority ones. The method is assessed on multiple memory-on-logic architectures with various memory technologies such as SRAM, eDRAM, STT-RAM, and RRAM. As a result, for the 45nm SRAM library, the accuracy degradation improves by roughly 56% at a BER of 0.05 with a timing overhead of 3.538μs and a power overhead of 390.796nJ. © 2011-2012 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Mortar: Morphing the Bit Level Sparsity for General Purpose Deep Learning Acceleration

Mortar: Morphing the Bit Level Sparsity for General Purpose ...

引用

Asia and South Pacific Design Automation Conference

作者： Yunhung Gao Hongyan Li Kevin Zhang Xueru Yu Hang Lu School of Electronics Engineering and Computer Science Peking University Beijing China State Key Lab of Computer Architecture Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China Shanghai Integrated Circuits R&D Center Co. Ltd Shanghai China

Vanilla Deep Neural Networks (DNN) after training are represented with native floating-point 32 (fp32) weights. We observe that the bit-level sparsity of these weights is very abundant in the mantissa and can be directly exploited to speed up model inference. In this paper, we propose Mortar, an off-line/on-line collaborated approach for fp32 DNN acceleration, which includes two parts: first, an off-line bit sparsification algorithm to construct the target formulation by “mantissa morphing”, which maintains higher model accuracy while increasing bit-level sparsity; second, the associating hardware accelerator architecture to speed up the on-line fp32 inference through manipulating the enlarged bit sparsity. We highlight the following results by evaluating various deep learning tasks, including image classification, object detection, video understanding, video & image super-resolution, etc.: We (1) increase bit-level sparsity up to 1.28~2.51x with only a negligible -0.09~0.23% accuracy loss, (2) maintain on average 3.55% higher model accuracy while increasing more bit-level sparsity than the baseline, (3)and our hardware accelerator outperforms up to 4.8x over the baseline, with an area of 0.031 mm 2 and power of 68.58mW.

关键词： Deep learning Training Mortar Superresolution Software algorithms Inference algorithms Software

来源：评论

学校读者我要写书评

暂无评论

Memory-facilitated Joint-space Shift Adaptation in Traffic Forecasting

Memory-facilitated Joint-space Shift Adaptation in Traffic F...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ye Wei He Haitao Gerald Schaefer Zhigang Ji Yifan Wang Hui Fang Department of Computer Science Loughborough University Loughborough UK The Alan Turing Institute London UK School of Architecture Building and Civil Engineering Loughborough University Loughborough UK National Key Laboratory of Science and Technology on Micro/Nano Fabrication Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Traffic forecasting, crucial for intelligent transport systems, faces significant challenges from distribution shifts due to the dynamic nature of traffic patterns. Although normalisation approaches have been proposed to address distribution shifts in other time-series forecasting tasks such as predicting electricity consumption load prediction or influenza-like illness patient number estimation, they fall short in handling the complex spatial and temporal shifts in traffic data. In this paper, we propose a novel memory-facilitated joint-space shift adaptation framework, ST-Align, to address this problem in traffic forecasting. ST-Align comprises two key components targeting the input and latent space, respectively: a memory-based data alignment module in the input space, and an end-to-end memory network structure dedicated to alignment within the latent space. This joint-space design enables our ST-Align framework to effectively capture and adapt to dynamic distribution shifts in both spatial and temporal dimensions, thus enhancing model performance. Extensive experiments on various real-world datasets and prediction backbones convincingly demonstrate the robustness and generalisability of our method.

关键词： Adaptation models Electricity Neural networks Estimation Traffic control Robustness Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evaluating Quantum Optimization for Dynamic Self-Reliant Community Detection

arXiv

引用

arXiv 2024年

作者： Bucher, David Porawski, Daniel Wimmer, Benedikt Nüßlein, Jonas O’Meara, Corey Mohseni, Naeimeh Cortiana, Giorgio Linnhoff-Popien, Claudia Aqarios GmbH Prinzregentenstraße 120 Munich81677 Germany Ludwig-Maximilians University Munich Institute for Computer Science Mobile and Distributed Systems Chair Germany E.ON Digital Technology GmbH Laatzener Str. 1 Hannover30539 Germany

Power grid partitioning is an important requirement for resilient distribution grids. Since electricity production is progressively shifted to the distribution side, dynamic identification of self-reliant grid subsets becomes crucial for operation. This problem can be represented as a modification to the well-known NP-hard Community Detection (CD) problem. We formulate it as a Quadratic Unconstrained Binary Optimization (QUBO) problem suitable for solving using quantum computation, which is expected to find better-quality partitions faster. The formulation aims to find communities with maximal self-sufficiency and minimal power flowing between them. To assess quantum optimization for sizeable problems, we apply a hierarchical divisive method that solves sub-problem QUBOs to perform grid bisections. Furthermore, we propose a customization of the Louvain heuristic that includes self-reliance. In the evaluation, we first demonstrate that this problem examines exponential runtime scaling classically. Then, using different IEEE power system test cases, we benchmark the solution quality for multiple approaches: D-Wave’s hybrid quantum-classical solvers, classical heuristics, and a branch-and-bound solver. As a result, we observe that the hybrid solvers provide very promising results, both with and without the divisive algorithm, regarding solution quality achieved within a given time frame. Directly utilizing D-Wave’s Quantum Annealing (QA) hardware shows inferior partitioning. © 2024, CC BY.

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Approximating Geometric Knapsack via L-packings

Approximating Geometric Knapsack via L-packings

引用

作者： Gálvez, Waldo Grandoni, Fabrizio Ingala, Salvatore Heydrich, Sandy Khan, Arindam Wiese, Andreas Department of Computer Science Technical University of Munich Garching Germany Chair of Approximation Algorithms IDSIA USI-SUPSI via la Santa 1 Lugano-Viganello6962 Switzerland Department of Optimization Fraunhofer Institute for Industrial Mathematics Kaiserslautern Germany Department of Computer Science and Automation Indian Institute of Science Bangalore India Department of Industrial Engineering Center for Mathematical Modeling Universidad de Chile Chile

We study the two-dimensional geometric knapsack problem, in which we are given a set of n axis-aligned rectangular items, each one with an associated profit, and an axis-aligned square knapsack. The goal is to find a (non-overlapping) packing of a maximum profit subset of items inside the knapsack (without rotating items). The best-known polynomial-time approximation factor for this problem (even just in the cardinality case) is 2+ϵ [Jansen and Zhang, SODA 2004]. In this article we present a polynomial-time 17/9+ϵ © 2021 Association for Computing Machinery.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

High Performance Computing for CS-InSAR Data Processing

High Performance Computing for CS-InSAR Data Processing

引用

2021 SAR in Big Data Era, BIGSARDATA 2021

作者： Zhang, Weikang You, Haihang Tang, Yixian Wang, Chao Zhang, Hong Chinese Academy of Sciences State Key Laboratory of Computer Architecture Institute of Computing Technology Beijing China Chinese Academy of Sciences Key Laboratory of Digital Earth Science Aerospace Information Research Institute Beijing China

ISBN: (纸本)9781665401234

In this paper, we have developed a highperformance data processing system for big SAR data based on parallel and distributed computation using supercomputer. Aiming at the pipeline of InSAR, we mainly focus on the parallelization and optimization of computing hotspot to accelerate the operation. Furthermore, we take advantage of the technology of distributed computation and multitask automation to get higher performance - process more data in less time. With the high-performance system, we obtained the nationwide measurement of China's surface movement from September 2018 to February 2020 and from January to December in 2020 using 20-30 computing nodes, processing nearly 1PB of data in total. The calculation time of the two images of national scale surface movement is completed in only 7 and 5 days, respectively. © 2021 IEEE.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Support vector machine regression(SVR)-based nonlinear modeling of radiometric transforming relation for the coarse-resolution data-referenced relative radiometric normalization(RRN)

引用

Geo-Spatial Information science 2020年第3期23卷 237-247,I0004页

作者： Jing Geng Wenxia Gan Jinying Xu Ruqin Yang Shuliang Wang School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Beijing Institute of Technology BeijingChina School of Civil Engineering and Architecture Wuhan Institute of TechnologyWuhanChina Wuhan Natural Resources and Planning Information Center WuhanChina

Radiometric normalization,as an essential step for multi-source and multi-temporal data processing,has received critical *** Radiometric Normalization(RRN)method has been primarily used for eliminating the radiometric *** radiometric trans-forming relation between the subject image and the reference image is an essential aspect of *** at accurate radiometric transforming relation modeling,the learning-based nonlinear regression method,Support Vector machine Regression(SVR)is used for fitting the complicated radiometric transforming relation for the coarse-resolution data-referenced *** evaluate the effectiveness of the proposed method,a series of experiments are performed,including two synthetic data experiments and one real data *** the proposed method is compared with other methods that use linear regression,Artificial Neural Network(ANN)or Random Forest(RF)for radiometric transforming relation *** results show that the proposed method performs well on fitting the radiometric transforming relation and could enhance the RRN performance.

关键词： Support Vector machine Regression(SVR) non-linear radiometric transforming relation Relative Radiometric Normalization(RRN) multi-source data

来源：评论

学校读者我要写书评

暂无评论

Automated Disassembly Sequence Prediction for Industry 4.0 Using Enhanced Genetic Algorithm

引用

computers, Materials & Continua 2021年第11期69卷 2531-2548页

作者： Anil Kumar Gulivindala M.V.A.Raju Bahubalendruni R.Chandrasekar Ejaz Ahmed Mustufa Haider Abidi Abdulrahman Al-Ahmari Department of Mechanical Engineering Industrial Robotics and Manufacturing Automation LaboratoryNational Institute of TechnologyKariakal609609India Department of Computer Science Engineering National Institute of TechnologyKariakal609609India Raytheon Chair for Systems Engineering Advanced Manufacturing InstituteKing Saud UniversityRiyadh11421Saudi Arabia Industrial Engineering Department College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia

The evolution of Industry 4.0 made it essential to adopt the Internet of Things(IoT)and Cloud Computing(CC)technologies to perform activities in the new age of *** technologies enable collecting,storing,and retrieving essential information from the manufacturing *** collected at sites are shared with others where execution automatedly *** obtained information must be validated at manufacturing to avoid undesirable data losses during the de-manufacturing ***,information sharing from the assembly level at the manufacturing stage to disassembly at the product end-of-life state is a major *** current research validates the information optimally to offer a minimum set of activities to complete the disassembly *** optimal disassembly sequence plan(DSP)can possess valid information to organize the necessary actions in ***,finding an optimal DSP is complex because of its combinatorial *** genetic algorithm(GA)is a widely preferred artificial intelligence(AI)algorithm to obtain a near-optimal solution for the DSP *** converging nature at local optima is a limitation in the traditional *** study improvised the GA workability by integrating with the proposed priori crossover *** optimality function is defined to reduce disassembly effort by considering directional changes as *** enhanced GA method is tested on a real-time product to evaluate the *** obtained results reveal that diversity control depends on the operators employed in the disassembly *** proposed method’s solution can be stored in the cloud and shared through IoT devices for effective resource allocation and disassembly for maximum recovery of the *** effectiveness of the proposed enhanced GA method is determined by making a comparative assessment with traditional GA and other AI methods at different population sizes.

关键词： Automation internet of things disassembly sequence planning priori cross over operator enhanced GA disassembly predicates

来源：评论

学校读者我要写书评

暂无评论

$\mathcal {H}_{2}$ and $\mathcal {H}_\infty$ Suboptimal Distributed Filters Design for Linear Systems

引用

IEEE Transactions on Automatic Control 2022年第4期68卷 2560-2567页

作者： Junjie Jiao Harry L. Trentelman M. Kanat Camlibel Chair of Information-Oriented Control TUM School of Computation Information and Technology Technical University of Munich Munich Germany Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen The Netherlands

This article investigates the $\mathcal {H}_{2}$ and $\mathcal {H}_\infty$ suboptimal distributed filtering problems for continuous-time linear systems. We consider a linear system monitored by a number of filters, where each of the filters receive only part of the measured output of the system. Each filter can communicate with the other filters according to a priori given strongly connected weighted directed graph. The aim is to design filter gains that guarantee the $\mathcal {H}_{2}$ or $\mathcal {H}_\infty$ norm of the transfer matrix from the disturbance input to the output estimation error to be smaller than a priori given upper bound, while all local filters reconstruct the full system state asymptotically. We provide a centralized design method for obtaining such $\mathcal {H}_{2}$ and $\mathcal {H}_\infty$ suboptimal distributed filters. The proposed design method is illustrated by a simulation example.

关键词： Filtering theory Linear systems Filtering Observers Matrix decomposition Nonlinear filters Maximum likelihood detection

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：