检索结果-内蒙古大学图书馆

ViF-SD2E: a robust weakly-supervised framework for neural decoding

Neural Computing and Applications 2025年第9期37卷 6645-6661页

作者： Feng, Jingyi Luo, Yong Song, Shuang Hu, Han National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

Neural decoding plays a vital role in the interaction between the brain and the outside world. Our task in this paper is to decode the movement track of a finger directly based on the neural data. Existing neural decoding solutions primarily perform some preprocessing operations on neural data before feeding them into existing models (such as LSTM) for decoding. However, these solutions either are prone to overfitting or cannot well exploit the spatial and temporal information. In our previous observations, there is a symmetrical phenomenon between the unsupervised decoded trajectory and the ground truth trajectory within the activity space. This precisely motivates us to propose (or derive) a robust weakly-supervised framework (or model structure), called ViF-SD2E, for neural decoding. In particular, it consists of a space-division (SD) module and an exploration–exploitation (2E) strategy, to effectively exploit both the spatial information of the outside world and the temporal information of neural activity, where the SD2E output is analogized with the weak 0/1 vision feedback (ViF) label for training. Extensive experiments demonstrate the effectiveness of our method, which can sometimes be comparable to supervised counterparts. Therefore, we redirect our attention to the information (hidden in data) ViF-SD2E conveys to us. In other words, we believe that the advantage of ViF-SD2E lies in the fact that its processing steps are objectively determined by the inherent attributes (i.e., symmetry) of the neural data, or rather, the model structure is fixed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Solar-Driven Interfacial Evaporation and Photo-Fenton Oxidation by Semiconducting Metal–Organic Framework From Waste Polyimide

引用

Energy & Environmental Materials 2025年第2期8卷 246-258页

作者： Lijie Liu Huajian Liu Zifen Fan Jie Liu Xueying Wen Huiyue Wang Yan She Guixin Hu Ran Niu Jiang Gong Key Laboratory of Material Chemistry for Energy Conversion and Storage Ministry of Education Hubei Key Laboratory of Material Chemistry and Service Failure Hubei Engineering Research Center for Biomaterials and Medical Protective Materials School of Chemistry and Chemical EngineeringHuazhong University of Science and Technology

The integrated technology of interfacial solar steam generation and photo-Fenton oxidation has emerged as a promising way to simultaneously mitigate freshwater scarcity and degrade organic ***,fabricating low-cost,multi-functional evaporators with high water evaporation and catalytic ability still presents a significant ***,we report the functional upcycling of waste polyimide into semiconducting Fe-BTEC and subsequently construct Fe-BTEC-based composite evaporators for simultaneous freshwater production and photo-Fenton degradation of ***,through a two-step solvothermal-solution stirring method,Fe-BTEC nanoparticles with the size of 20-100 nm are massively produced from waste polyimide,with a band gap energy of 2.2 *** composite evaporator based on Fe-BTEC and graphene possesses wide solar-spectrum absorption capacity,high photothermal conversion capacity,rapid delivery of water,and low enthalpy of *** from the merits above,the composite evaporator achieves a high evaporation rate of 2.72kgm-2h-1from tetracycline solution,as well as the photothermal conversion efficiency of 97% when exposed to irradiation of 1 Sun,superior to many *** is more,the evaporator exhibits the tetracycline degradation rate of 99.6% with good recycling stability,ranking as one of the most powerful heterogeneous Fenton *** Multiphysics and density functional theory calculation results prove the synergistic effect of the concentrated heat produced by interfacial solar steam generation and catalytic active sites of Fe-BTEC on promoting H2O2activation to form reactive oxidation *** work not only provides a green strategy for upcycling waste polyimide,but also proposes a new approach to fabricate multi-functional evaporators.

关键词： freshwater production interfacial solar steam generation metal–organic framework photo-Fenton oxidation waste polyimide

来源：评论

学校读者我要写书评

暂无评论

Masked hybrid attention with Laplacian query fusion and tripartite sequence matching for medical image segmentation

引用

Neural Computing and Applications 2025年第8期37卷 5891-5911页

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Wang, Xiangxiang Ukot, Akpanika Robert Cai, Jingye School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Medical image segmentation is pivotal in computer-aided diagnosis systems, demanding high precision and contextual understanding. Vision Transformer-based approaches have gained much attention recently due to their excellent performance and ability to capture long-range dependencies in medical images. However, research shows they suffer from inadequate multi-scale feature integration, poor object localization, and inconsistent mask predictions, leading to sub-optimal segmentation performance. This paper addresses these challenges by redefining semantic medical image segmentation through learnable object queries within an enhanced transformer framework with a masked hybrid attention querying mechanism, optimizing multi-scale feature fusion, object localization, and instance-specific segmentation. First, this study presents a novel transformer-based masked hybrid attention mechanism using Laplacian query fusion on learnable query features and incorporating a novel tripartite sequence matching technique as part of the enhanced decoder block to improve the consistency of mask predictions and optimize decoder queries. The designed hybrid multi-head self- and cross-attention mechanisms aim to selectively integrate multi-scale features, ensuring optimal feature combinations for precise segmentation. Secondly, multiple class tokens are incorporated to improve object localization and capture class-specific characteristics within the transformer framework, leveraging the transformer decoders’ ability to learn distinct instance representations. Experimental results and extensive ablation studies demonstrate the effectiveness of the proposed approach on three publicly available datasets, obtaining better segmentation results compared to various state-of-the-art approaches using various evaluation metrics. Specifically, the proposed model achieves a Dice Score of 95.25%, 92.75%, and 85.25% on LUNA, ISIC, and DRIVE datasets, respectively. © The Author(s), under exclusive licence

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

research on the Performance of a Mooring Platform Under the Collision of Icebergs

引用

China Ocean engineering 2025年第1期39卷 43-57页

作者： ZHANG Yan ZHANG Song-bao WANG Yi-tao ZHAO Wei-dong GUI Hong-bin School of Ocean Engineering Harbin Institute of TechnologyWeihaiWeihai 264209China China Ship Scientific Research Center(CSSRC) Wuxi 214082China College of Shipbuilding Engineering Harbin Engineering UniversityHarbin 150001China State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentDalian University of TechnologyDalian 116024China

In the process of developing oil and gas resources in the Arctic,the impact of icebergs can pose a considerable threat to the structural safety of semi-submersible mooring platforms in ice *** the basis of the arbitrary Lagrangian Eulerian(ALE)algorithm,a numerical model for the interaction between an iceberg and a semi-submersible mooring platform is built in this ***,a mooring system with a link element is designed and *** ice material model for the target iceberg is built and validated.A numerical model for the interaction between an iceberg and a semi-submersible mooring platform is then built.A parametric study(cable angle,tension angle and number of cables)is carried out to study the performance of the mooring *** collision process between the semi-submersible mooring platform and the iceberg in the polar marine environment can be predicted by the present numerical model,and then the optimal mooring arrangement scheme can be *** research results in this work can provide a reference for the design of mooring systems.

关键词： ALE algorithm semi-submersible platform iceberg collision mooring system

来源：评论

学校读者我要写书评

暂无评论

Dynamic Certificateless Outsourced Data Auditing Mechanism Supporting Multi-Ownership Transfer via Blockchain Systems

引用

IEEE Transactions on Network and service Management 2025年第2期22卷 2017-2030页

作者： Zhang, Xiaojun Liu, Qing Liu, Bingyun Zhang, Yuan Xue, Jingting Southwest Petroleum University School of Computer Science and Software Engineering Research Center for Cyber Security Chengdu610500 China Chengdu Neusoft University School of Computer and Software Chengdu611844 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu610054 China

Data auditing contributes to checking the integrity of outsourced data, promoting the vigorous development of cloud storage services. In actual scenarios, such as migration of electronic medical records or data transfer of enterprise mergers and acquisitions, it always require data auditing to help clients with dynamic data migration and integrity checking. In this paper, we present an efficient dynamic certificateless outsourced data auditing mechanism supporting multi-ownership transfer (CDA-MOT), addressing the issue of key escrow and without needing complex certificate management. By integrating a certificateless multi-signature on the same data file into the construction of a homomorphic authenticator based on the Lagrange inverse Multinomial theorem, CDA-MOT not only achieves integrity verification but also enables clients to transfer ownership rights and responsibilities for multi-ownership data in collaboration with cloud servers. Utilizing blockchain systems to store necessary data conversion and update records, as well as smart contracts to fulfill auditing tasks, CDA-MOT owns the characteristics of openness, transparency, accountability, and decentralized public auditing. Besides, CDA-MOT could be further applied in the extension of dynamic update operations, even if outsourced data have been transferred. The security analysis and performance evaluation have demonstrated the feasibility of CDA-MOT in the secure deployment of cloud storage. © 2004-2012 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Modeling Method for Hybrid Ripple Estimation of General PWM Converters Based on KBM Theory

Modeling Method for Hybrid Ripple Estimation of General PWM ...

引用

2025 International Conference on Electrical Automation and Artificial Intelligence, ICEAAI 2025

作者： Sun, Zhaoxuan Chen, Liping Ding, Jianwan National CAD Support Software Engineering Technology Research Center Huazhong University of Science and Technology Wuhan China Organization: National CAD Support Software Engineering Technology Research Center Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798331506797

To address the problem of balancing the accuracy and efficiency of simulation models of PWM converters, a hybrid ripple estimation modeling method for general Pulse-Width-Modulated (PWM) converters is proposed. The method is to apply the Krylov-Bogoliubov-Mitropolsky (KBM) theory to the Piecewise State Space Averaging (PSSA) model of PWM converter, and to address the defects of the first-order ripple estimation model, an upgrade criterion of the ripple estimation model is proposed, so as to realize the variable-order ripple estimation of state variables. Modeling simulations of the three cases are performed based on the system modeling language Modelica, and the results indicate that the hybrid ripple estimation model provides the best fitting effect and the model run efficiency is improved compared with the detailed model. © 2025 IEEE.

关键词： component Krylov-Bogoliubov-Mitropolsky Modelica Pulse-Width-Modulated Ripple estimation Simulation model

来源：评论

学校读者我要写书评

暂无评论

MambaTalk: Speech-Driven 3D Facial Animation with Mamba 31st

MambaTalk: Speech-Driven 3D Facial Animation with Mamba

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Zhu, Deli Xu, Zhao Yang, Yunong Chongqing Normal University Chongqing China Chongqing Digital Agricultural Service Engineering Technology Research Center Chongqing China

ISBN: (纸本)9789819620609

3D facial animation has been widely applied in entertainment, virtual reality, education, and advertising. Achieving coordination between lip movements, facial expressions, and speech content is crucial for enhancing the realism of animations. Existing research often focuses on directly driving 3D facial animations using audio signals, failing to fully process the complex relationship between audio signals and facial expressions, and overlooking the critical role of lip shape constraints in improving lip synchronization accuracy. This paper proposes MambaTalk, a speech-driven 3D lip synchronization method. MambaTalk, based on the Mamba architecture, generates more refined and natural 3D facial animations by separately and independently handling lip movements strongly correlated with speech information and upper facial expressions weakly correlated with speech information. Additionally, the introduction of lip shape constraints further enhances the naturalness and synchronization of lip movements in 3D facial animations. Quantitative evaluation demonstrates that MambaTalk produces animations of higher quality than existing state-of-the-art methods on the VOCASET and MeshTalk dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Against Mobile Collusive Eavesdroppers: Cooperative Secure Transmission and Computation in UAV-Assisted MEC Networks

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5280-5297页

作者： Zhao, Mingxiong Wang, Zirui Guo, Kun Zhang, Rongqian Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China Yunnan University Yunnan Key Laboratory of Software Engineering Kunming650091 China East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing School of Communications and Electronics Engineering Shanghai200241 China Yunnan University School of Information Science and Engineering Kunming650500 China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore

In Uncrewed Aerial Vehicle (UAV)-assisted Mobile Edge Computing (MEC) networks, the security of transmission faces significant challenges due to the vulnerabilities of line-of-sight links and potential eavesdropping on two-hop links. This paper addresses these challenges with an innovative Cooperative Secure Transmission and Computation strategy (CSTC), specifically engineered for time-slotted UAV-assisted MEC networks plagued by mobile collusive eavesdroppers. These eavesdroppers significantly bolster their interception capabilities through coordinated and optimized movements, escalating the security threats. To neutralize these risks, the proposed CSTC employs the UAV and remote devices as helper nodes to emit jamming signals, thereby thwarting eavesdropping activities, while simultaneously facilitating the efficient relay of users’ tasks to the base station for advanced processing. The CSTC aims to maximize the sum Secrecy Transmission Rate (STR) satisfying task latency constraints. It involves a joint optimization of UAV trajectory, jamming beamformers, transmit power, and data offloading strategy to expedite task transmission. Additionally, a real-time computation scheduling approach is developed based on a newly defined metric, the Urgency Degree of Users (UDoU), to enhance task processing efficiency. Our extensive simulations validate that the CSTC not only elevates the sum STR but also consistently meets latency constraints, demonstrating its robustness against advanced mobile eavesdropping techniques. © 2002-2012 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

Invisible Warning Line: Efficient and Generic Regulation for Anonymous Cryptocurrencies

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2022-2036页

作者： Gao, Rui Wan, Zhiguo Wang, Huaqun Luo, Shaoteng Nanjing University of Posts and Telecommunications College of Computer Jiangsu Cryptographic Technology Engineering Research Center Nanjing210023 China Zhejiang Lab Hangzhou310000 China UCAS School of Software Engineering Hangzhou Institute for Advanced Study Hangzhou310024 China

Decentralized finance based on blockchain has experienced rapid development. To safeguard the privacy of participants, decentralized anonymous payment (DAP) systems such as ZCash and Zether have emerged. These systems employ cryptographic techniques to conceal the trader addresses and payment amounts. However, this anonymity presents challenges in terms of regulation. To address this issue, we propose the Walsh-DAP (WDAP) scheme, an efficient and generic regulation scheme for decentralized anonymous payments that strikes a balance between regulation and privacy preservation. Our scheme introduces two regulation policies: first, users who have exceeded their spending limits within a certain period will be identified during the regulation process;second, the supervisor possesses the capability to trace any anonymous transaction. To implement regulation effectively, we have designed an innovative commitment scheme, Walsh commitment, which leverages the orthogonal properties of Walsh codes to achieve the features of aggregatability and extractability. The supervisor in WDAP only needs to deal with the aggregation result of the Walsh commitments instead of the huge amount of raw transactions information, which greatly increases the efficiency. In a DAP system with 256 users, 10 transactions per second and 30 days as a regulation period, we reduced the communication cost for regulation from 14 GB to 94.20 KB, and the computing cost from 1.6 × 105 s to 2.17s. Both improvement is of over five orders of magnitude. We formally discussed the security of the whole system, and verified its feasibility and practicability in the ZCash system. © 2004-2012 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Event-enhanced synthetic aperture imaging

引用

Science China(Information Sciences) 2025年第3期68卷 388-390页

作者： Siqi LI Shaoyi DU Jun-Hai YONG Yue GAO Beijing National Research Center for Information Science and Technology School of SoftwareTsinghua University Institute for Brain and Cognitive Sciences Beijing Laboratory of Brain and Cognitive IntelligenceTsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsInstitute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Synthetic aperture imaging(SAI) methods aim to see through dense occlusions and reconstruct the target scene behind occlusions. Traditional frame-based SAI methods,e.g., DeOccNet [1], take the occluded light field ima...

关键词：

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：