检索结果-内蒙古大学图书馆

Towards Privacy-Aware Causal Structure Learning in Federated Setting

IEEE Transactions on Big Data 2023年第6期9卷 1525-1535页

作者： Huang, Jianli Guo, Xianjie Yu, Kui Cao, Fuyuan Liang, Jiye Intelligent Interconnected Systems Laboratory of Anhui Province School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Taiyuan030006 China

Causal structure learning has been extensively studied and widely used in machine learning and various applications. To achieve an ideal performance, existing causal structure learning algorithms often need to centralize a large amount of data from multiple data sources. However, in the privacy-preserving setting, it is impossible to centralize data from all sources and put them together as a single dataset. To preserve data privacy, federated learning as a new learning paradigm has attached much attention in machine learning in recent years. In this paper, we study a privacy-aware causal structure learning problem in the federated setting and propose a novel federated PC (FedPC) algorithm with two new strategies for preserving data privacy without centralizing data. Specifically, we first propose a novel layer-wise aggregation strategy for a seamless adaptation of the PC algorithm into the federated learning paradigm for federated skeleton learning, then we design an effective strategy for learning consistent separation sets for federated edge orientation. The extensive experiments validate that FedPC is effective for causal structure learning in federated learning setting. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

引用

IEEE Transactions on Dependable and Secure Computing 2022年 1-14页

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China University of Texas at Dallas Dallas USA National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deliberate design of MOF-based pre-catalyst rationalizing the structural reconstruction toward efficient oxygen evolution reaction

引用

science China Chemistry 2025年第6期68卷 2388-2398页

作者： Yunhui Chen Meng Tian Zhongqi Zhang Guangzhao Wang Yan Guo Jing Wu Dawei Qi Zhenhua Yan Xiangyu Liu Xi Liu State Key Laboratory of High-efficiency Coal Utilization and Green Chemical Engineering College of Chemistry and Chemical EngineeringNingxia University Key Laboratory of Extraordinary Bond Engineering and Advanced Materials Technology of Chongqing School of Electronic Information Engineering Yangtze Normal University Frontiers Science Center for New Organic Matter Key Laboratory of Advanced Energy Materials Chemistry (Ministry of Education) State Key Laboratory of Advanced Chemical Power Sources College of Chemistry Nankai University School of Chemistry and Chemical Engineering In-situ Center for Physical Sciences Frontiers Science Center for Transformative MoleculesShanghai Jiao Tong University

Metal-organic frameworks（MOFs）, that have emerged as promising electrocatalysts in oxygen evolution reaction（OER）,usually undergo structural reconstruction to form metal hydroxides as active sites. However, it remains a great challenge to design and synthesize ideal MOF-based pre-catalysts for properly cognizing and utilizing the reconstruction process toward efficient OER activity. Herein, the well-defined MOF-808 is post-modified by 2-hydroxyphosphonoacetic acid（HPAA） to form a micro-adsorber that enables to capture of metal ions effectively. Fe3+and Ni2+ions are synergistically anchored into the microadsorber, developing a Fe/Ni-containing pre-catalyst that can be dynamically electrooxidized to be an active and stable dual-site electrocatalyst denoted by R-MOF-HPAA@Fe Ni with abundant metal sites. As a result, R-MOF-HPAA@Fe Ni exhibits an excellent OER performance with a low overpotential of 272 m V and Tafel slope of 35.9 m V dec-1, as well as long-term stability over 300 h at 10 m A cm-2. Experiments and theoretical calculations suggest the resulting catalyst mainly follows a lattice oxygen mechanism（LOM） of dual-metal-site mechanism（DMSM）. Owing to the chelating role of HPAA, the post-synthesized MOFHPAA behaves as a trap to uniformly and firmly adhere Fe3+and Ni2+ions, leading to a functionalized MOF-based pre-catalyst which can be structurally evolved into atomic level-distributed OER electrocatalysts.

关键词： metal-organic frameworks functionalization electrochemical reconstruction electrocatalyst oxygen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

The Journey/DAO/TAO of Embodied Intelligence: From Large Models to Foundation Intelligence and Parallel Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1313-1316页

作者： Tianyu Shen Jinlin Sun Shihan Kong Yutong Wang Juanjuan Li Xuan Li Fei-Yue Wang College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China School of Electrical and Information Engineering Jiangsu UniversityZhenjiang 212013China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Peng Cheng Laboratory Shenzhen 518000China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China IEEE

THE tremendous impact of large models represented by ChatGPT[1]-[3]makes it necessary to con-sider the practical applications of such models[4].However,for an artificial intelligence(AI)to truly evolve,it needs to possess a physical“body”to transition from the virtual world to the real world and evolve through interaction with the real *** this context,“embodied intelligence”has sparked a new wave of research and technology,leading AI beyond the digital realm into a new paradigm that can actively act and perceive in a physical environment through tangible entities such as robots and automated devices[5].

关键词： Intelligence DAO TAO

来源：评论

学校读者我要写书评

暂无评论

Analysis of Space Attitude Measurement Methods and Optical Design of Refractive Self-Collimator in Orbital Environment 11

Analysis of Space Attitude Measurement Methods and Optical D...

引用

11th International Symposium on Precision Mechanical Measurements

作者： Xing, Yuhang Li, Hong Cui, Xiwen Zhuang, Wei Zhu, Lianqing Guangzhou Nansha Intelligent Photonic Sensing Research Institute Guangzhou511462 China Beijing Laboratory of Optical Fiber Sensing and System Beijing Information Science & Technology University Beijing100016 China Beijing Engineering Research Center of Optoelectronic Information and Instruments Beijing Information Science & Technology University Beijing100016 China

ISBN: (纸本)9781510680296

To monitor the space attitude of the spacecraft key load under on-orbit conditions and obtain three-dimensional angular deflection data, a folding-reflecting self-collimator was designed based on the Cassegrain optical system, and the evaluation indexes and imaging quality of the optical system were systematically analyzed, with the MTF of 100 lp/mm being better than 0.4, aberration being less than 0.0368%, and diffraction-limited dispersion spot diameter within 8.6 um, which meets the requirements for monitoring on-orbit. The principle of using multiple devices to combine to measure the three-dimensional angular deflection of the target load is analyzed, and the correspondence between the spot change and the target deflection angle is deduced. It shows that this method has a good development prospect in the field of space attitude measurement. © 2024 SPIE.

关键词： Optical design

来源：评论

学校读者我要写书评

暂无评论

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 624-638页

作者： Chen, Yin Li, Jia Shan, Shiguang Wang, Meng Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. Firstly, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Structure evolution andτ_(f)influence mechanism of Bi_(1-x)Ho_(x)VO_(4)microwave dielectric ceramics for LTCC applications

引用

Journal of Materials science & technology 2024年第30期197卷 1-8页

作者： Huaicheng Xiang Yuheng Zhang Junqi Chen Yang Zhou Ying Tang Jinwu Chen Liang Fang Key Laboratory of Low-Dimensional Structural Physics and Application Education Department of Guangxi Zhuang Autonomous RegionCollege of Physics and Electronic Information EngineeringGuilin University of TechnologyGuilin541004China Guangxi Universities Key Laboratory of Non-Ferrous Metal Oxide Electronic Functional Materials and Devices Guangxi Key Laboratory of Optical and Electronic Materials and DevicesCollege of Materials Science and EngineeringGuilin University of TechnologyGuilin541004China School of Mechanical Engineering Guilin University of Aerospace TechnologyGuilin541004China

Bi_(1-x)Ho_(x)VO_(4)(0.1≤x≤0.9)ceramics were prepared via a solid-state reaction method,and all the ceram-ics could be well densified in the 920–980℃*** ceramics with 0.1≤x<0.4 were composed of both monoclinic scheelite(M)and tetragonal zircon(T)phases,and a single M phase could be obtained in the range of x≥*** measuredε_(r) decreased from 58.9(x=0.1)to 14.7(x=0.9),so do the calcu-lated values(ε_(r)(C−M)=34.3–12.1),and the main reason forε_(r)>ε_(r)(C−M)was the rattling of Ho^(3+)in the *** points with zeroτf appeared in Bi1–x Hox VO4(0≤x≤1)ceramics,and the best mi-crowave dielectric properties withε_(r)=16.6,Q×f=18,400 GHz(f=10.69 GHz),andτf=+3.29 ppm/℃were obtained in the Bi_(0.2)Ho_(0.8)VO_(4)*** change in temperature coefficient of ionic polarizability(τ_(αm))caused by the rattling effect of cations is the physical essence that affectsτ***,the rattling effect can be used as an effective mechanism to regulateτf in low-ε_(r) ***,there was no chemical reaction between Bi_(1-x)Ho_(x)VO_(4) and Ag electrode,which indicates potential applications in low-temperature co-fired ceramic(LTCC)technology.

关键词： Bi_(1–x)Ho_(x)VO_(4) Near-zeroτ_(f) Bond valence Rattling effect LTCC

来源：评论

学校读者我要写书评

暂无评论

Research on the Transient Temperature Field of the High-Speed Permanent-Magnet Motor for Dragging Pulsed Alternator 18th

Research on the Transient Temperature Field of the High-Spee...

引用

18th Annual Conference of China Electrotechnical Society, ACCES 2023

作者： Wan, Yuan Zhang, Xu Jia, Yuqi Guo, Jian Li, Wenlong School of Automation Nanjing University of Science and Technology Nanjing10094 China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration AVIC Nanjing Engineering Institute of Aircraft System Nanjing211102 China

ISBN: (纸本)9789819710713

For dragging the pulsed alternator, the high-speed permanent-magnet synchronous motor (HSPMSM) is required with a high-power density. Considering the specific working condition that the speed and load both change with time, the steady-state thermal analysis is not applicable to check the effectiveness of thermal design for the dragging motor. This paper studies the characteristics of the losses of a 300 kW, 12000 rpm dragging motor with the variation of time. Then based on the fluid-solid coupling analysis method, the transient temperature field analysis was then carried out. The variation of temperature field distribution over the time and the influence of discharging times are both discussed. With the pulsed alternator discharging 20 bursts continuously, that is 60 shorts, the temperature rise of the dragging motor is 60.9% of that of the steady-state with the highest speed and maximum power. This paper lays the foundation for the later design and optimization of the dragging motor. © Beijing Paike Culture Commu. Co., Ltd. 2024.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Construction of mesoporous silica-implanted tungsten oxides for selective acetone gas sensing

引用

Chinese Chemical Letters 2024年第11期35卷 492-498页

作者： Jichun Li Zhengren Wang Yu Deng Hongxiu Yu Yonghui Deng Xiaowei Cheng Kaiping Yuan Department of Chemistry Shanghai Stomatological Hospital&School of StomatologyState Key Laboratory of Molecular Engineering of PolymersShanghai Key Laboratory of Molecular Catalysis and Innovative MaterialsiCHEMFudan UniversityShanghai 200433China Frontier Institute of Chip and System State Key Laboratory of ASIC and SystemFudan UniversityShanghai 200433China State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai 200050China

As a key biomarker for noninvasive diagnosis of diabetes,the selective detection of trace acetone in exhaled gas using a portable and low-cost device remains a great *** metal oxide(SMO)based gas sensors have drawn signification attention due to their potential in miniaturization,user-friendliness,high cost-effectiveness and selective real-time detection for noninvasive clinical ***,we propose a one-pot solvent evaporation induced tricomponent co-assembly strategy to design a novel ordered mesoporous SMO of silica-implanted WO_(3)(Si O_(2)/WO_(3))as sensing materials for trace acetone *** controlled co-assembly of silicon and tungsten precursors and amphiphilic diblock copolymer poly(ethylene oxide)-block-polystyrene(PEO-b-PS),and the subsequent thermal treatment enable the local lattice disorder of WO_(3)induced by the amorphous silica and the formation of ordered mesoporous Si O_(2)/WO_(3)hybrid walls with a unique metastableε-phase WO_(3)*** obtained mesoporous SiO_(2)/WO_(3)composites possess highly crystalline framework with large uniform pore size(12.0-13.3 nm),high surface area(99-113 m^(2)/g)and pore volume(0.17-0.23 cm^(3)/g).Typically,the asfabricated gas sensor based on mesoporous 2.5%Si O_(2)/WO_(3)exhibits rapid response/recovery rate(5/17 s),superior sensitivity(R_(air)/R_(gas)=105 for 50 ppm acetone),as well as high selectivity towards *** limit of detection is as low as 0.25 ppm,which is considerably lower than the thresh value of acetone concentration(>1.1 ppm)in the exhaled breath of diabetic patients,demonstrating its great prospect in real-time monitoring in diabetes ***,the mesoporous 2.5%Si O_(2)/WO_(3)sensor is integrated into a wireless sensing module connected to a smart phone,providing a convenient real-time detection of acetone.

关键词： Mesoporous materials ε-Tungsten oxide Silica-implanted Acetone sensing Real-time detection

来源：评论

学校读者我要写书评

暂无评论

A Probe Set Determination Method Based on Spanning Tree Algorithm 23

A Probe Set Determination Method Based on Spanning Tree Algo...

引用

7th International Conference on High Performance Compilation, Computing and Communications, HP3C 2023

作者： Hongxing, Hao Ronghuan, Yu Jing, Guo Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781450399883

With the rapid development of network technologies such as the Internet of Things, the scale of networks has gradually increased. The P2P networks have been gradually studied, and fault detection and localization for large-scale networks have become a hot research topic. Generally, probes are usually used to quickly locate the fault nodes, but the ability to locate network faults is determined by the choice of probes. This paper studies the probe set determination problem and proposes the criteria named segmentation entropy to judge the probe set. Then a probe set determination method is proposed which does not require a candidate set and performs better than the random probe selection algorithm. Experimental results proves that the proposed algorithm can quickly obtain excellent probe sets. © 2023 ACM.

关键词： Probes

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：