检索结果-内蒙古大学图书馆

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Heng Zhou Bing Wu Huan Cheng Jinpeng Liu Taoming Lei Dan Feng Wei Tong Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology School of Computer Science and Technology Huazhong University of Science and Technology Ministry of Education of China

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

The memristive Computing-in-Memory (CIM) sys-tem can efficiently accelerate matrix-vector multiplication (MVM) operations through in-situ computing. The data layout has a significant impact on the communication performance of CIM systems. Existing software-level communication opti-mizations aim to reduce communication distance by carefully designing static data layouts, while wear-leveling (WL) and error mitigation methods use dynamic scheduling to enhance system reliability, resulting in randomized data layouts and increased communication overhead. Besides, existing CIM compilers di-rectly map data to physical crossbars and generate instructions, which causes inconvenience for dynamic scheduling. To address these challenges of balancing communication performance and reliability while coordinating existing CIM compilers and dy-namic scheduling, we propose a disorder-resistant computation translation layer (DRCTL), which improves system lifetime and communication performance through co-optimization of data layout and dynamic scheduling. It consists of three parts: (1) We propose an address conversion method for dynamic scheduling, which updates the addresses in the instruction stream after dynamic scheduling, thereby avoiding recompilation. (2) Dynamic scheduling strategy for reliability improvement. We propose a hierarchical wear-leveling (HWL) strategy, which reduces communication by increasing scheduling granularity. (3) Communication optimization for dynamic scheduling. We propose data layout-aware selective remapping (LASR), which helps dynamic scheduling methods improve communication lo-cality and reduce latency by exploiting data dependencies. The experiments demonstrate that HWL extends lifetime by 100.3-205.9 x compared to not using WL. Even with a slight lifetime decrease compared to the state-of-the-art WL (TIWL), it still supports continuous neural network training for 7 years. After applying LASR to HWL, the number of execution cycles, energy consumption

关键词： Training Energy consumption Processor scheduling Layout Dynamic scheduling In-memory computing Common information Model (computing) System-on-chip Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

Cointegration Identification with Metric Learning 5

Cointegration Identification with Metric Learning

引用

5th International Conference on Computer information science and Artificial Intelligence, CISAI 2022

作者： Xia, Zeyu Lin, Changle Department of Economics Shenzhen University Shenzhen China China Aerospace Academy of Systems Science and Engineering Beijing China Institute for Interdisciplinary Information Core Technology Xi’an China

ISBN: (纸本)9781510662520

Cointegration is an important topic for time series analysis, especially in finance pair trading and hedging area. Cointegration is a kind of structure in which a linear combination of two (or more) time series is stationary. Traditional way to identify cointegration is to use the OLS estimator, firstly run a regression and secondly run a unit root test on residuals. But such method is easy to lead to ambiguous and unstable result. Therefore, we developed a dimensionality reduction model based on automatically calculated common factors, and adopted the Metric Learning method to find a method that can quickly reduce the dimensionality and test the cointegration relationship of stock pairs. © 2023 SPIE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Theoretical study on the morphology of cobalt nanoparticles modulated by alkali metal promoters

引用

International Journal of Minerals,Metallurgy and Materials 2023年第10期30卷 2006-2013页

作者： Xiaobin Geng Hui Yang Wenping Guo Xiaotong Liu Tao Yang Jinjia Liu National Energy Center for Coal to Liquids Synfuels China Co.LtdBeijing 101400China State Key Laboratory of Coal Conversion Institute of Coal ChemistryChinese Academy of SciencesTaiyuan 030001China University of Chinese Academy of Sciences Beijing 100049China Beijing Advanced Innovation Center for Materials Genome Engineering Beijing Information Science and Technology UniversityBeijing 100101China School of Computer Beijing Information Science and Technology UniversityBeijing 100101China College of Chemistry and Environmental Science Inner Mongolia Key Laboratory of Green CatalysisInner Mongolia Normal UniversityHohhot 010022China

Cobalt nanoparticles(NPs)catalysts are extensively used in heterogeneous catalytic reactions,and the addition of alkali metal promoters is a common method to modulate the catalytic performance because the catalyst's surface structures and morphologies are sensitive to the addition of ***,the underlying modulation trend remains ***,the adsorption of alkali metal promoters(Na and K)on the surfaces of face-centered-cubic(FCC)and hexagonal-closest packed(HCP)polymorphous cobalt was systematically investigated using density functional ***,the effect of alkali promoters on surface energies and nanoparticle morphologies was revealed on the basis of Wulff *** FCC-Co,the exposed area of the(111)facet in the nanoparticle increases with the adsorption coverage of alkali metal ***,the(311),(110),and(100)facets would disappear under the higher adsorption coverage of alkali *** HCPCo,the Wulff morphology is dominated by the(0001)and(1011)facets and is independent of the alkali metal adsorption *** work provides insights into morphology modulation by alkali metal promoters for the rational design and synthesis of cobalt-based nanomaterials with desired facets and morphologies.

关键词： cobalt nanoparticles alkali promoter density functional theory crystal morphology Wulff construction

来源：评论

学校读者我要写书评

暂无评论

Online Optimization in Power systems With High Penetration of Renewable Generation:Advances and Prospects

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 839-858页

作者： Zhaojian Wang Wei Wei John Zhen Fu Pang Feng Liu Bo Yang Xinping Guan Shengwei Mei Key Laboratory of System Control and Information Processing Ministry of Education of ChinaDepartment of AutomationShanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Power System and the Department of Electrical Engineering Tsinghua UniversityBeijing 100084China Institute of High Performance Computing(IHPC) Agency for Science Technology and Research(A*STAR)Singapore 138632Singapore

Traditionally,offline optimization of power systems is acceptable due to the largely predictable loads and reliable *** increasing penetration of fluctuating renewable generation and internet-of-things devices allowing for fine-grained controllability of loads have led to the diminishing applicability of offline optimization in the power systems domain,and have redirected attention to online optimization ***,online optimization is a broad topic that can be applied in and motivated by different settings,operated on different time scales,and built on different theoretical *** paper reviews the various types of online optimization techniques used in the power systems domain and aims to make clear the distinction between the most common techniques *** particular,we introduce and compare four distinct techniques used covering the breadth of online optimization techniques used in the power systems domain,i.e.,optimization-guided dynamic control,feedback optimization for single-period problems,Lyapunov-based optimization,and online convex optimization techniques for multi-period ***,we recommend some potential future directions for online optimization in the power systems domain.

关键词： optimization Lyapunov optimization online convex optimization online optimization optimization-guided control

来源：评论

学校读者我要写书评

暂无评论

Mode-Dependent H ∞ Tracking Control for Semi-Markov Jumping Robotic Manipulators Under Random Disturbances

Mode-Dependent H ∞ Tracking Control for Semi-Markov Jumping...

引用

International Conference on Image, Vision and Intelligent systems, ICIVIS 2023

作者： Ji, Yidao Cao, Wenhua Zhou, Cheng Wu, Wei School of Mechanical Engineering University of Science and Technology Beijing100083 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9789819708543

In our manuscript, we study the issue of output tracking control of a semi-markovian jumping robot manipulator with random disturbances. Specifically, a novel mode-dependent ouput tracking control strategy is designed to our robotic manipulator hence the robotic manipulator can track the reference system and achieve the H∞ performance index. The mode-dependent Lyapunov function is used to obtain sufficient stability conditions and control parameters to complete the tracking control target of the manipulator through the linear matrix inequality (LMI) algorithm. Lastly, this designed method have been demonstrated by numerical simulation, as this robotic manipulator system achieves capable tracking in the presence of time-varying state jumps (Weibull Distribution) and random disturbances. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Deformable Cross Attention for Learning Optical Flow 48

Deformable Cross Attention for Learning Optical Flow

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Abdein, Rokia Xiang, Xuezhi Lv, Ning Saddik, Abdulmotaleb El Harbin Engineering University School of Information and Communication Engineering Harbin150001 China Ministry of Industry and Information Technology Key Laboratory of Advanced Marine Communication and Information Technology Harbin150001 China School of Electrical Engineering and Computer Science University of Ottawa OttawaONK1N 6N5 Canada

ISBN: (纸本)9781728163277

Optical flow is the process of estimating motion in scenes. Each object in the scene has a homogeneous motion, i.e., moves in the same direction with the same velocity. Therefore, connecting the parts of an image globally provides an essential cue for learning accurate motion. Convolution-based methods estimate the motion features from the local regions, which miss this important cue. Recently, some methods used Transformer to model global dependencies to improve optical flow. However, Transformer suffers from excessive attention computations and still brings irrelevant parts into the region of interest. Therefore, we propose a deformable cross-attention for optical flow estimation, which provides two important advantages: connecting the parts of the image globally while deforming the attention to the objects' shapes in the image and reducing the memory consumption. Our proposed method achieved competitive performance on Sintel and KITTI 2015 datasets in terms of accuracy and efficiency. © 2023 IEEE.

关键词： Deep learning Deformable cross-attention Optical flow Transformer

来源：评论

学校读者我要写书评

暂无评论

Infrared image enhancement algorithm based on improved wavelet threshold function and weighted guided filtering 2

Infrared image enhancement algorithm based on improved wavel...

引用

2nd International Conference on Electronic information and Communication engineering, EICE 2023

作者： Yang, Haitao Tong, Yaonan Cao, Zhiqi Chen, Zhenguang School of Information Science and Engineering Hunan Institute of Technology Yueyang414000 China Hunan Provincial University Key Laboratory of Complex Networks and Embedded Systems Yueyang414000 China Dongguan Zhenhai Electronic Technology Co. Ltd. Dongguan523000 China

Aiming at the problems such as the poor visual effect of infrared thermal imaging under low illumination conditions, an enhanced infrared image recognition method based on wavelet decomposition is proposed for this paper. First, according to wavelet decomposition, the infrared image is divided into a low-frequency sub-band (LFS) and high-frequency sub-band (HFS) in each orientation, and HFS in each orientation is denoised using a modified wavelet threshold function to strengthen the denoising effect of the infrared image;Second, the multi-scale Retinex (MSR) algorithm based on weighted guided filtering (WGIF) is used to evaluate the component of illumination in the basic layer of the LFS, and the WGIF-segmented detail layer images are fused with the MSR processed ones to effectively highlight the texture details of the LFS;Finally, the LFS and the HFS are wavelets reconstructed (WR) to obtain the infrared enhanced images. This paper applies the algorithm to a low-resolution (resolution 32x32 pixels) infrared thermal imaging module, and the results of combining subjective and objective evaluation indexes show that the overall property index of the algorithm in this paper is superior to other contrasting algorithms and can effectively improve the infrared image quality. © Published under licence by IOP Publishing Ltd.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Helmet Detection Algorithm of Electric Bicycle Riders Based on YOLOv5 with CBAM Attention Mechanism Integration 8th

Helmet Detection Algorithm of Electric Bicycle Riders Based ...

引用

8th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2023

作者： Fu, Si-Yue Wei, Dong Zhou, Liu-Ying School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing Municipal Science and Technology Commission Beijing100044 China

ISBN: (纸本)9789819975921

Object detection algorithms can assist in detecting the helmet-wearing status of electric bicycle riders, thereby saving regulatory manpower costs. However, there is currently a lack of standardized and publicly available datasets. Additionally, the basic YOLOv5s object detection algorithm, due to its limited feature extraction capabilities, may lead to numerous instances of both false negative and false positive. To enhance the model’s focus on critical information within the feature maps, this paper introduces the CBAM attention mechanism module into the Backbone section of YOLOv5s. This module sequentially infers attention maps from the input feature maps along both channel and spatial dimensions independently, and then multiplies these attention maps with the input feature maps to achieve adaptive feature optimization. This paper have established self-built dataset for experimental research, and the results indicate that compared to the original YOLOv5s model, the proposed method has improved the model’s overall mAP score by 1.89%. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Historical Arabic Images Classification and Retrieval Using Siamese Deep Learning Model

引用

Computers, Materials & Continua 2022年第7期72卷 2109-2125页

作者： Manal M.Khayyat Lamiaa A.Elrefaei Mashael M.Khayyat Computer Science Department Umm Al-Qura UniversityMakkahSaudi Arabia Computer Science Department King Abdulaziz UniversityJeddahSaudi Arabia Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairoEgypt Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia

Classifying the visual features in images to retrieve a specific image is a significant problem within the computer vision field especially when dealing with historical faded colored ***,there were lots of efforts trying to automate the classification operation and retrieve similar images *** reach this goal,we developed a VGG19 deep convolutional neural network to extract the visual features from the images ***,the distances among the extracted features vectors are measured and a similarity score is generated using a Siamese deep neural *** Siamese model built and trained at first from scratch but,it didn’t generated high evaluation ***,we re-built it from VGG19 pre-trained deep learning model to generate higher evaluation ***,three different distance metrics combined with the Sigmoid activation function are experimented looking for the most accurate method formeasuring the similarities among the retrieved *** that the highest evaluation parameters generated using the Cosine distance ***,the Graphics Processing Unit(GPU)utilized to run the code instead of running it on the Central Processing Unit(CPU).This step optimized the execution further since it expedited both the training and the retrieval time *** extensive experimentation,we reached satisfactory solution recording 0.98 and 0.99 F-score for the classification and for the retrieval,respectively.

关键词： Visual features vectors deep learning models distance methods similar image retrieval

来源：评论

学校读者我要写书评

暂无评论

Impact Monitoring and Positioning Method of Steel Plate Based on Piezoelectric Acoustic Sensor Array 17

Impact Monitoring and Positioning Method of Steel Plate Base...

引用

17th Symposium on Piezoelectricity, Acoustic Waves, and Device Applications, SPAWDA 2023

作者： Huang, Xuanxuan Sun, Changhe Zeng, Chenrui Hu, Zijian School of Electronic Information and Electrical Engineering Yangtze University Jingzhou434023 China Chongqing University Key Laboratory of Optoelectronic Technology & Systems Ministry of Education Chongqing400044 China

ISBN: (纸本)9798350394740

In this paper, an impact stress wave analysis method to indirectly represent the impact force is introduced by using a high-sensitivity quartz crystal piezoelectric acoustic sensor array. The finite element simulation method is used to establish an acoustic-solid coupling model. The difference in the flight time of array sensors is calculated to locate the impact position. Besides, a multi-channel acoustic wave signal acquisition and processing system has been developed in the LabVIEW platform, where a MATLAB based signal processing model is combined to perform the Fourier transform and calculate the flight time difference. The simulated annealing algorithm is adopted to optimize the experimental scheme and accurately monitor the impact location. The impact experiment results are compared with the actual impact coordinates, offering the maximum absolute error of less than 3 cm. The impact monitoring and positioning system has a broad application prospect in the field of structural health monitoring. © 2023 IEEE.

关键词： Acoustic waves

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：