检索结果-内蒙古大学图书馆

Hetu: a highly efficient automatic parallel distributed deep learning system

science China(Information sciences) 2023年第1期66卷 314-315页

作者： Xupeng MIAO Xiaonan NIE Hailin ZHANG Tong ZHAO Bin CUI School of Computer Science Peking University Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications

On July 18, 2021, the PKU-DAIR Lab1)(Data and Intelligence Research Lab at Peking University) openly released the source code of Hetu, a highly efficient and easy-to-use distributed deep learning(DL) framework. Hetu is the first distributed DL system developed by academic groups in Chinese universities, and takes into account both high availability in industry and innovation in academia. Through independent research and development, Hetu is completely decoupled from the existing DL systems and has unique characteristics. The public release of the Hetu system will help researchers and practitioners to carry out frontier MLSys(machine learning system) research and promote innovation and industrial upgrading.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Max-difference maximization criterion: a feature selection method for text categorization

引用

Frontiers of computer science 2023年第1期17卷 237-239页

作者： Lingbin JIN Li ZHANG Lei ZHAO School of Computer Science and Technology&Advanced Data Analysis Research Center Soochow UniversitySuzhou 215006China

1 IntroductionText categorization methods based on machine learning always encounter the curse of dimensionality. Therefore, it is crucial to perform feature selection to reduce dimensionality of text vectors. Methods based on the difference between document rate of a term in the positive class and that in the negative class have been widely studied in recent years, which is originated from balanced accuracy measures (ACC2) [1].

关键词： dimensionality difference criterion

来源：评论

学校读者我要写书评

暂无评论

Internet of Brain, Thought, Thinking, and Creation

引用

Chinese Journal of Electronics 2022年第6期31卷 1025-1042页

作者： ZHANG Zhimin YIN Rui NING Huansheng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing Engineering Research Center for Cyberspace Data Analysis and Applications

Thinking space came into being with the emergence of human civilization. With the emergence and development of cyberspace, the interaction between those two spaces began to take place. In the collision of thinking and technology, new changes have taken place in both thinking space and cyberspace. To this end, this paper divides the current integration and development of thinking space and cyberspace into three stages, namely Internet of brain(IoB), Internet of thought(IoTh), and Internet of thinking(IoTk). At each stage, the contents and technologies to achieve convergence and connection of spaces are discussed. Besides, the Internet of creation(IoC) is proposed to represent the future development of thinking space and cyberspace. Finally, a series of open issues are raised, and they will become thorny factors in the development of the Io C stage.

关键词： thinking space IoTk Internet of thinking IoTh Internet of thought cyberspace development Internet of Things Internet of brain cyber-physical systems IoB human civilization emergence

来源：评论

学校读者我要写书评

暂无评论

Learning to grade deterioration for ancient murals

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第2期15卷 1727-1734页

作者： Qian, Kun Zhang, Pengyu Huang, Rui Feng, Wei Sun, Jizhou School of Computer Science and Technology College of Intelligence and Computing Tianjin University Tianjin300350 China Key Research Center for Surface Monitoring and Analysis of Cultural Relics State Administration of Cultural Heritage Tianjin300350 China

Ancient murals recording histories and myths are suffering different types of deteriorations, which makes these valuable cultural heritage unrecoverable. For preventive protection of ancient murals, the researchers need to rate the grade of the mural deteriorations. However, the present grading is mainly rely on the experience of the cultural relics’ protection staff. In this paper, we propose to learn a mural deterioration grading network (MDGN) for generating robust and accurate mural deterioration grading. MDGN has similar architecture with AlexNet but with less network parameters. We built two small mural deterioration grading datasets on briquettes and real grottoes. We use image patches to generate enough training samples for MDGN. Dense pixel-level grading can be obtained by the means of sliding window. Extensive experiments on simulated data and real murals verify the effectiveness of the proposed ancient mural deterioration grading method. Our method achieves superior grading results on both quantitative and qualitative comparisons with baseline. © Springer-Verlag GmbH Germany, part of Springer Nature 2019.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Ghost Module Based Residual Mixture of Self-Attention and Convolution for Online Signature Verification

引用

computers, Materials & Continua 2024年第4期79卷 695-712页

作者： Fangjun Luan Xuewen Mu Shuai Yuan Department of Computer Technology School of Computer Science and EngineeringShenyang Jianzhu UniversityShenyang110168China Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang Jianzhu UniversityShenyang110168China Shenyang Branch of National Special Computer Engineering Technology Research Center Shenyang Jianzhu UniversityShenyang110168China

Online Signature Verification (OSV), as a personal identification technology, is widely used in various ***, it faces challenges, such as incomplete feature extraction, low accuracy, and computational heaviness. Toaddress these issues, we propose a novel approach for online signature verification, using a one-dimensionalGhost-ACmix Residual Network (1D-ACGRNet), which is a Ghost-ACmix Residual Network that combines convolutionwith a self-attention mechanism and performs improvement by using Ghost method. The Ghost-ACmix Residualstructure is introduced to leverage both self-attention and convolution mechanisms for capturing global featureinformation and extracting local information, effectively complementing whole and local signature features andmitigating the problem of insufficient feature extraction. Then, the Ghost-based Convolution and Self-Attention(ACG) block is proposed to simplify the common parts between convolution and self-attention using the Ghostmodule and employ feature transformation to obtain intermediate features, thus reducing computational ***, feature selection is performed using the random forestmethod, and the data is dimensionally reducedusing Principal Component analysis (PCA). Finally, tests are implemented on the MCYT-100 datasets and theSVC-2004 Task2 datasets, and the equal error rates (EERs) for small-sample training using five genuine andforged signatures are 3.07% and 4.17%, respectively. The EERs for training with ten genuine and forged signaturesare 0.91% and 2.12% on the respective datasets. The experimental results illustrate that the proposed approacheffectively enhances the accuracy of online signature verification.

关键词： Online signature verification feature selection ACG block ghost-ACmix residual structure

来源：评论

学校读者我要写书评

暂无评论

ControlVideo: conditional control for one-shot text-driven video editing and beyond

引用

science China(Information sciences) 2025年第3期68卷 150-162页

作者： Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML CenterTsinghua Laboratory of Brain and Intelligence Lab Tsinghua University ShengShu Technology Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Pazhou Laboratory (Huangpu)

This paper presents ControlVideo for text-driven video editing — generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions(such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing(e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous studies achieved. The code is available at https://***/thu-ml/controlvideo.

关键词： diffusion models controllable generation text-driven editing video editing long video editing

来源：评论

学校读者我要写书评

暂无评论

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures 39

FreeNet: Liberating Depth-Wise Separable Operations for Buil...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Hao Chen, Haoyu Peng, Wei Cheng, Xu Zhao, Guoying Center for Machine Vision and Signal Analysis University of Oulu Finland Department of Psychiatry and Behavioral Sciences Stanford University United States School of Computer Science Nanjing University of Information Science and Technology China Department of Computer Science Aalto University Finland

ISBN: (纸本)157735897X

In the pursuit of efficient vision architectures, substantial efforts have been devoted to optimizing operator efficiency. Depth-wise separable operators, such as DWConv, are found cheap in both FLOPs and parameters. As a result, they are increasingly incorporated into efficient backbones, trading for deeper and wider architectures to enhance performance. However, separable operators are not really fast on devices due to the discontinuous memory access requirements. In this paper, we propose FreeNets, a family of simple and efficient backbones that free the separable operation to further accelerate the running speed. We introduce sparse sampling mixers (S2-Mixer) to supersede existing separable token mixers. The S2-Mixer samples multiple segments of partially continuous signals across spatial and channel dimensions for convolutional processing, achieving extremely fast on-device speed. The sparse sampling also enables S2-Mixer to capture long-range pixel relationships from dynamic receptive fields. Furthermore, we introduce a Shift Feed-Forward Network (ShiftFFN) as a faster alternative to existing channel mixers. It utilizes a shift neck architecture that aggregates global information to shift features, enabling faster channel mixing while incorporating global pixel information. Extensive experiments demonstrate that FreeNet offers a superior accuracy-efficiency tradeoff compared to the latest efficient models. On ImageNet-1k, FreeNet-S2 outperforms the StarNet-S4 by 0.4% in top-1 accuracy, while running around 40% faster on desktop GPU and 15% faster on Mobile GPU. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in physiological characteristics recognition for internet of things authentication

引用

Digital Communications and Networks 2024年第3期10卷 740-755页

作者： Zhimin Zhang Huansheng Ning Fadi Farha Jianguo Ding Kim-Kwang Raymond Choo School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Faculty of Informatics Engineering Aleppo UniversityAleppoSyria Department of Computer Science Blekinge Institute of Technology37179KarlskronaSweden Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Effective user authentication is key to ensuring equipment security,data privacy,and personalized services in Internet of Things(IoT)***,conventional mode-based authentication methods(e.g.,passwords and smart cards)may be vulnerable to a broad range of attacks(e.g.,eavesdropping and side-channel attacks).Hence,there have been attempts to design biometric-based authentication solutions,which rely on physiological and behavioral *** characteristics need continuous monitoring and specific environmental settings,which can be challenging to implement in ***,we can also leverage Artificial Intelligence(AI)in the extraction and classification of physiological characteristics from IoT devices processing to facilitate ***,we review the literature on the use of AI in physiological characteristics recognition pub-lished after *** use the three-layer architecture of the IoT(i.e.,sensing layer,feature layer,and algorithm layer)to guide the discussion of existing approaches and their *** also identify a number of future research opportunities,which will hopefully guide the design of next generation solutions.

关键词： Physiological characteristics recognition Artificial intelligence Internet of things Biological-driven authentication

来源：评论

学校读者我要写书评

暂无评论

Winter wheat phenology classification using stacking ensemble learning algorithm based on Sentinel-1A SAR images 5

Winter wheat phenology classification using stacking ensembl...

引用

5th International Conference on Geoscience and Remote Sensing Mapping, ICGRSM 2023

作者： Duan, Haoxin Yang, Huijin Zhao, Jianhui Li, Ning School of Computer and Information Engineering Henan University Kaifeng China Henan Province Engineering Research Center of Spatial Information Processing Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9781510672789

Crop monitoring and phenology estimation based on the satellite systems have become an important research area due to high demand on crops. Synthetic Aperture Radar (SAR) is a kind of microwave remote sensing equipment, which has the advantage of all-weather and all-day, and can realize large-scale and periodic crop phenological monitoring. Besides, thanks to the high temporal resolution of new generation space-based sensors, it has been possible to monitor growth cycle of crops by classification algorithms. A stacking ensemble learning algorithm using time series Sentinel-1A SAR images for winter wheat phenology classification was proposed in this paper based on multiple machine learning models, including Random Forest (RF), Support Vector Machine (SVM), K-nearest Neighbor(K-NN), Naive Bayes (NB) and BP Neural Network (BP) models. The experimental results showed that, comparing with each single model, the stacking ensemble learning algorithm proposed in this paper had the optimal performance, with the highest overall recognition accuracy of 81.40%, demonstrating its effectiveness and application potential for winter wheat phenology identification. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Cognitive Computing Model for Data Security on a Cloud Platform

引用

computers, Materials & Continua 2023年第12期77卷 3305-3323页

作者： Xiangmin Guo Guangjun Liang Jiayin Liu Xianyi Chen Department of Computer Information and Cyber Security Jiangsu Police InstituteNanjing210031China Jiangsu Electronic Data Forensics and Analysis Engineering Research Center Jiangsu Police InstituteNanjing210031China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China

Cloud storage is widely used by large companies to store vast amounts of data and files,offering flexibility,financial savings,and ***,information shoplifting poses significant threats,potentially leading to poor performance and privacy ***-based cognitive computing can help protect and maintain information security and privacy in cloud platforms,ensuring businesses can focus on business *** ensure data security in cloud platforms,this research proposed a blockchain-based Hybridized Data Driven Cognitive Computing(HD2C)***,the proposed HD2C framework addresses breaches of the privacy information of mixed participants of the Internet of Things(IoT)in the ***2C is developed by combining Federated Learning(FL)with a Blockchain consensus algorithm to connect smart contracts with Proof of ***“Data Island”problem can be solved by FL’s emphasis on privacy and lightning-fast processing,while Blockchain provides a decentralized incentive structure that is impervious to *** with Blockchain allows quick consensus through smart member selection and *** HD2C paradigm significantly improves the computational processing efficiency of intelligent *** analysis results derived from IIoT datasets confirm HD2C *** compared to other consensus algorithms,the Blockchain PoA’s foundational cost is *** accuracy and memory utilization evaluation results predict the total benefits of the *** comparison to the values 0.004 and 0.04,the value of 0.4 achieves good *** to the experiment results,the number of transactions per second has minimal impact on memory *** findings of this study resulted in the development of a brand-new IIoT framework based on blockchain technology.

关键词： Blockchain Internet of Things(IoT) blockchain based cognitive computing Hybridized Data Driven Cognitive Computing(HD2C) Federated Learning(FL) Proof of Authority(PoA)

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：