检索结果-内蒙古大学图书馆

2021 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), USNC-URSI 2021

作者： Teng, Kok-Hin Raju, Salahuddin Zhu, Di Lim, Jayce Lay Keng Chen, Daniel Ssu-Han Ching, Eva Wai Leong Jaibir, Sharma Joshua, Lee En-Yuan Ng, Eldwin Jiaqiang Chuan, Kevin Chai Tshun Lal, Amit ASTAR Institute of Microelectronics Singapore138634 Singapore Cornell University SonicMEMS Laboratory School of Electrical and Computer Engineering IthacaNY United States

ISBN: (纸本)9781946815101

A 2-dimensional discrete Fourier transform (2-D DFT) is a required preprocessing step for convolutional neural networks (CNNs) to perform matrix multiplication in convolutional layers. Here we present an ultrasonic wavefront-based architecture for CNNs that harness the wave propagation diffraction physic to perform Fourier transform (FT) effectively. The computation is improved to O(N) compare to Fast Fourier transform (FFT) with O(N(log2N). In addition, analysis of the proposed ultrasonic wavefront scheme is described in this paper. © 2021 USNC-URSI under licence to authors.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Rethinking Label-specific Features for Label Distribution Learning

arXiv

引用

arXiv 2025年

作者： Xu, Suping Dai, Chuyi Shang, Lin Shao, Changbin Yang, Xibei Pedrycz, Witold Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Department of Computer Science and Technology Nanjing University Nanjing210023 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Jiangsu University of Science and Technology Zhenjiang212003 China

Label distribution learning (LDL) is an emerging learning paradigm designed to capture the relative importance of labels for each instance. Label-specific features (LSFs), constructed by LIFT, have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label to re-characterize instances. However, directly introducing LIFT into LDL tasks can be suboptimal, as the prototypes it collects primarily reflect intra-cluster relationships while neglecting interactions among distinct clusters. Additionally, constructing LSFs using multi-perspective information, rather than relying solely on Euclidean distance, provides a more robust and comprehensive representation of instances, mitigating noise and bias that may arise from a single distance perspective. To address these limitations, we introduce Structural Anchor Points (SAPs) to capture inter-cluster interactions. This leads to a novel LSFs construction strategy, LIFT-SAP, which enhances LIFT by integrating both distance and direction information of each instance relative to SAPs. Furthermore, we propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution. Extensive experiments on 15 real-world datasets demonstrate the effectiveness of LIFT-SAP over LIFT, as well as the superiority of LDL-LIFT-SAP compared to seven other well-established algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Topological one-way Weyl fiber

引用

Physical Review B 2024年第22期110卷 224435-224435页

作者： Hao Lin Zitao Ji Yu Wang Yidong Zheng Jianfeng Chen Zhi-Yuan Li School of Physics and Optoelectronics South China University of Technology Guangzhou 510640 China Department of Electrical and Computer Engineering National University of Singapore Singapore 117583 Singapore State Key Laboratory of Luminescent Materials and Devices South China University of Technology Guangzhou 510640 China

Topological photonics enables unprecedented photon manipulation by realizing various topological states, such as corner, edge, and surface states. However, achieving a topological fiber state has remained elusive. Here, we demonstrate a topological fiber state in a Weyl gyromagnetic photonic crystal fiber. By applying an in-plane magnetic bias to a gyromagnetic photonic crystal fiber with broken parity-inversion symmetry, we create an asymmetrical Weyl band gap that supports one-way fiber states associated with type-II Weyl points. Dispersion and topological invariant calculations reveal a transition from Weyl surface states to one-way Weyl fiber states. Electromagnetic field simulations confirm the existence of these one-way Weyl fiber states and their robust transport, even in the presence of metallic obstacles along the transport path. Our findings offer an intriguing pathway for exploring topological states and guiding the design of topological fibers.

关键词： Photonic crystal fibers

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Learning and Control with Event-Triggered Measurements

引用

IEEE Transactions on Automatic Control 2025年

作者： Feng, Shilun Shi, Dawei Chen, Tongwen Shi, Ling Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Kowloon Hong Kong

Event-triggered control has attracted considerable attention for its effectiveness in resource-restricted applications. To make event-triggered control as an end-to-end solution, a key issue is how to effectively learn unknown system dynamics from event-triggered measurements and consequently, develop a learning-based event-triggered controller. Existing works learn system dynamics based on periodic time-triggered measurements, and it is yet to know how to learn a controller with performance guarantee based on event-triggered measurements. To address this issue, we consider the problem of learning an event-triggered state feedback controller for an unknown linear system based on event-triggered state measurements in this work. In particular, we first analyze the event-triggered measurements within a set-membership framework. We prove that the estimation error belongs to a bounded ellipsoid determined by the historical measurements and the event-triggering condition. Subsequently, we demonstrate that all admissible systems compatible with the collected data samples can be explicitly represented in the form of quadratic matrix inequalities using the state estimates. With the acquired set of admissible systems, a co-design problem for the data-driven controller and event-triggering condition is solved using the linear matrix inequality technique, with guaranteed closed-loop stability and L2-gain performance. Finally, numerical examples and comparisons are provided to illustrate the effectiveness of the proposed event-triggered learning and control approach. © 1963-2012 IEEE.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Addressing the regulatory gap: moving towards an EU AI audit ecosystem beyond the AI Act by including civil society

引用

AI and Ethics 2024年 1-22页

作者： Hartmann, David de Pereira, José Renato Laranjeira Streitbörger, Chiara Berendt, Bettina Faculty of Electrical Engineering and Computer Science TU Berlin Berlin Germany Weizenbaum Institute for the Networked Society Berlin Germany LAPIN - Laboratory of Public Policy and Internet Public Policy Division Brasília Brazil Bonn Sustainable AI Lab University of Bonn Bonn Germany Kammergericht Berlin Berlin Germany Department of Computer Science KU Leuven Leuven Belgium

The European legislature has proposed the Digital Services Act (DSA) and Artificial Intelligence Act (AIA) to regulate platforms and Artificial Intelligence (AI) products. We review to what extent third-party audits are part of both laws and how is access to information on models and the data provided. By considering the value of third-party audits and third-party data access in an audit ecosystem, we identify a regulatory gap in that the AIA does not provide access to data for researchers and civil society. Our contributions to the literature include: (1) Defining an AI audit ecosystem incorporating compliance and oversight. (2) Highlighting a regulatory gap within the DSA and AIA regulatory framework, preventing the establishment of an AI audit ecosystem that has effective oversight by civil society and academia. (3) Emphasizing that third-party audits by research and civil society must be part of that ecosystem, we call for AIA amendments and delegated acts to include data and model access for certain AI products. Furthermore, we call for the DSA to provide NGOs and investigative journalists with data access to platforms by delegated acts and for adaptions and amendments of the AIA to provide third-party audits and data and model access, at least for high-risk systems. Regulations modeled after EU AI regulations should enable data access and third-party audits, fostering an AI audit ecosystem that promotes compliance and oversight mechanisms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CMOS Demonstration of Negative Capacitance HfO2-ZrO2 Superlattice Gate Stack in a Self-Aligned, Replacement Gate Process

CMOS Demonstration of Negative Capacitance HfO2-ZrO2 Superla...

引用

International Electron Devices Meeting (IEDM)

作者： N. Shanker M. Cook S.S. Cheema W. Li R. Rastogi D. Pipitone C. Chen M. Smith S. Meninger F. Bauer G. Pinelli J. Hunt S. Salahuddin M. Mohamed Deparment of Electrical Engineering and Computer Sciences University of California Berkeley Lincoln Laboratory Massachusetts Institute of Technology

ISBN: (纸本)9781665489607

We report on the successful integration of a low equivalent oxide thickness (EOT) negative capacitance (NC) gate stack – a 1.8 nm ferroelectric-antiferroelectric (FE-AFE) HfO 2 -ZrO 2 superlattice (HZH) [1] – into a 90 nm CMOS R&D technology, following a self-aligned, replacement gate process. The integrated gate oxides show an effective oxide thickness (EOT) of 7.5 Å on both p - and n-SOI MOSFETs. This amounts to a 2Å EOT lowering compared to conventional high-$\kappa$ dielectric HfO 2 due to the NC effect. Large intrinsic transconductance at $90\text{nm}L_{g},1.0\text{mS}/\mu\text{m}$ and $1.5\text{mS}/\mu\text{m}$ for p-FETs and n-FETs, respectively, exceeding L g scaling trends for industry benchmarks, are demonstrated. The low EOT also increases the $90\text{nm}L_{g}\text{ON}$-current to levels approaching reports of semiconductor foundry nodes at much lower $L_{g}(\sim 30\text{nm})$. Successful CMOS circuits are also demonstrated.

关键词： Radio frequency Thermal variables control Superlattices Logic gates Capacitance Time measurement Hafnium compounds

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition in Chinese Medical Texts Based on RoBERTa-WWM-IDCNN-CRF

Named Entity Recognition in Chinese Medical Texts Based on R...

引用

System Simulation Technology and its Application (CCSSTA), IEEE China Conference on

作者： Lan Tang Jie Kong Liang Xu School of Computer Xi‘an Shiyou University Xi‘an China Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

ISBN: (数字)9798350366600

ISBN: (纸本)9798350366617

Electronic medical records and doctor-patient conversations contain a wealth of useful information, such as disease symptoms, drug names, and cure cycles. Traditional deep learning approaches utilize bidirectional recurrent neural networks to encode text, which cannot effectively capture long-distance dependencies in text. In order to identify medical entity types in various texts more accurately, a named entity recognition approach based on RoBERTa-WWM-IDCNN-CRF is proposed. This approach introduces the RoBERTa-WWM pre-trained model, in order to improve the overall understanding of long Chinese texts for the first time. The model generates semantic representations containing prior knowledge. Then, the generated semantic representations are feed to the IDCNN to extract sentence level characteristics. Finally, the global optimal solution is obtained and the results of the named entity are produced through the CRF. The experiment indicates that the improvement of $F_{1}$ score, accuracy, and recall of RoBERTa-WWM-IDCNN-CRF model are 7.94%, 4.52% and 10.02% comparing with the classical BiLSTM-CRF model.

关键词： Drugs Recurrent neural networks Semantics Named entity recognition Oral communication Medical services Systems simulation Feeds Electronic medical records Diseases

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Multi-Stream Adaptive Graph Convolutional Network for Indoor Scene Action Recognition

Skeleton-Based Multi-Stream Adaptive Graph Convolutional Net...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Jiazhuo Chen, Luefeng Li, Min Wu, Min Pedrycz, Witold Hirota, Kaoru The School of Automation The Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems The Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Wuhan430074 China The Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada The Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland The Department of Computer Engineering Istinye University Sariyer Istanbul34396 Turkey The Tokyo Institute of Technology Tokyo226-8502 Japan

ISBN: (纸本)9798350303759

With the rapid advances in computer vision, human action recognition has gradually received attention, but the current methods still exhibit some problems in indoor environments. The human skeleton, as the framework of human motion, contains high-quality actional feature information, and the skeleton-based action recognition method effectively avoid the interference of interior background noise and has advantages in indoor action recognition. The outstanding effect of graph convolutional networks on graph structure data processing has led to its rapid development and wide application in skeleton-based action recognition. Second-order skeletal information also contains a large number of actional features but is not effectively utilized. The artificial predefined topology of the human skeleton map has limitations, and cannot reflect the interaction between limbs. To solve the above problems, this article designs an adaptive weighted multi-stream graph convolutional network (AM-GCN) based on skeletal information, using an attention mechanism to enhance the network's ability to extract actional features, and an adaptive layer to make the construction graph more flexible, incorporating second-order skeletal features through a dual-stream architecture. In this article, the NTU-RGB+D dataset has been used for the experiments, the results show that the method in this article has good results. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Support-Query Prototype Fusion Network for Few-shot Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Wu, Xiaoxiao Gao, Zhenguo Chen, Xiaowei Wang, Yakai Qu, Shulei Li, Na Department of Computer Science and Technology Huaqiao University No.668 Jimei Avenue Fujian Xiamen361021 China Department of Mechanical Engineering and Automation Huaqiao University No.668 Jimei Avenue Fujian Xiamen361021 China Key Laboratory of Computer Vision and Machine Learning Fujian Provincial Universities Fujian Xiamen361021 China

In recent years, deep learning based on Convolutional Neural Networks (CNNs) has achieved remarkable success in many applications. However, their heavy reliance on extensive labeled data and limited generalization ability to unseen classes pose challenges to their suitability for medical image processing tasks. Few-shot learning, which utilizes a small amount of labeled data to generalize to unseen classes, has emerged as a critical research area, attracting substantial attention. Currently, most studies employ a prototype-based approach, in which prototypical networks are used to construct prototypes from the support set, guiding the processing of the query set to obtain the final results. While effective, this approach heavily relies on the support set while neglecting the query set, resulting in notable disparities within the model classes. To mitigate this drawback, we propose a novel Support-Query Prototype Fusion Network (SQPFNet). SQPFNet initially generates several support prototypes for the foreground areas of the support images, thus producing a coarse segmentation mask. Subsequently, a query prototype is constructed based on the coarse segmentation mask, additionally exploiting pattern information in the query set. Thus, SQPFNet constructs highquality support-query fused prototypes, upon which the query image is segmented to obtain the final refined query mask. Evaluation results on two public datasets, SABS and CMR, show that SQPFNet achieves state-of-the-art performance. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

NEAR-OPTIMAL REWARD-FREE EXPLORATION FOR LINEAR MIXTURE MDPS WITH PLUG-IN SOLVER 10

NEAR-OPTIMAL REWARD-FREE EXPLORATION FOR LINEAR MIXTURE MDPS...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Chen, Xiaoyu Hu, Jiachen Yang, Lin F. Wang, Liwei Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University China Electrical and Computer Engineering Department University of California Los Angeles United States International Center for Machine Learning Research Peking University China

Although model-based reinforcement learning (RL) approaches are considered more sample efficient, existing algorithms are usually relying on sophisticated planning algorithm to couple tightly with the model-learning procedure. Hence the learned models may lack the ability of being re-used with more specialized planners. In this paper we address this issue and provide approaches to learn an RL model efficiently without the guidance of a reward signal. In particular, we take a plug-in solver approach, where we focus on learning a model in the exploration phase and demand that any planning algorithm on the learned model can give a near-optimal policy. specifically, we focus on the linear mixture MDP setting, where the probability transition matrix is a (unknown) convex combination of a set of existing models. We show that, by establishing a novel exploration algorithm, the plug-in approach learns a model by taking Õ(d2H3/∊2) episodes with the environment and any ∊-optimal planner on the model gives an O(∊)-optimal policy on the original model. This sample complexity matches our lower bound for non-plug-in approaches and is statistically optimal. We achieve this result by leveraging a careful maximum total-variance bound using Bernstein inequality and properties specified to linear mixture MDPs. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Learning algorithms

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：