检索结果-内蒙古大学图书馆

2023 China Automation Congress, CAC 2023

作者： Li, Wenfei Li, Boyuan Hua, Wei Huang, Chao Du, Haiping Xing, Haitao Research Center for Intelligent Transportation Zhejiang Lab Hangzhou China The Hong Kong Polytechnic University Department of Industrial & Systems Engineering Hong Kong School of Electrical Computer and Telecommunications Engineering University of Wollongong Wollongong Australia

ISBN: (纸本)9798350303759

Tracking control has attracted significant attention because of its close link with industrial applications. Tracking control requires that a control algorithm can ensure that an actuator follows control commands, with a fast response anti-disturbance abilities and small chattering. A tracking-differentiator-based sliding-mode control approach for tracking control is proposed in this paper. A tracking differentiator has the ability to obtain the desired signal's differential signal, even when there is noise in the desired signal. A differential signal is often required in the design of sliding-mode controllers. When tracking differentiator is applied to a sliding-mode controller, the chattering of the control commands (caused by noise disturbance) can be reduced while the fast response of the sliding-mode controller can be maintained. The simulation results show that the proposed controller is effective. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

RoleScan: Enhancing Social Bot Detection Using Social Role Vector 19th

RoleScan: Enhancing Social Bot Detection Using Social Role V...

引用

19th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Wen, Wen Gao, Min Gong, Qingyuan Wang, Xin Chen, Yang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China

ISBN: (纸本)9789819623723

The increase in social media users has led to the rise of social bots, which can disrupt online environments and threaten user privacy. This study presents RoleScan, a novel framework that integrates Social Role Vector (SRV) and Graph Attention Network v2 (GATv2) to detect social bots more accurately. We are the first to formulate the social bot detection problem by considering users’ properties and social influence. RoleScan extracts user features and text features from user profiles and tweets, and uses SRV to capture the social features. SRV is based on node centrality measurement, structural hole theory, and social capital theory, offering a comprehensive view of the influence of a user within the network. By leveraging an attention mechanism, RoleScan focuses on pivotal features and connections, enhancing its ability to differentiate between bots and humans. The experimental results show that RoleScan outperforms existing models, achieving an AUC of 0.887. An ablation study further highlights the critical role of incorporating social features into the detection process. Our study not only enhances the social bot detection performance, but also offers new insights into the users’ diverse roles within social networks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

引用

computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq Muhammad Athar Javed Sethi Najib Ben Aoun Ala Saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance

arXiv

引用

arXiv 2024年

作者： Arrabi, Ahmad Zhang, Xiaohan Sultani, Waqas Chen, Chen Wshah, Safwan Vermont Artificial Intelligence Lab. Department of Computer Science University of Vermont United States Intelligent Machines Lab. Information Technology University Center for Research in Computer Vision University of Central Florida United States

Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibility. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird’s Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multi-modal cross-view dataset, namely VIGORv2, built upon VIGOR [66] with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and dataset are available at https://***/vail-uvm/gpg2a. Copyright © 2024, The Authors. All rights reserved.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

Real-Time monitoring of surface relief grating formation in azopolymer thin films

Real-Time monitoring of surface relief grating formation in ...

引用

Functional Material Applications: From Energy to Sensing 2023

作者： Pagliarulo, V. Calabuig, A. CNR-ISASI Institute of Applied Sciences & Intelligent Systems "e. Caianiello" Via Campi Flegrei 34 NA Pozzuoli80078 Italy ZEISS Vision Science Lab Institute for Ophthalmic Research University of Töbingen Elfriede-Aulhorn-Strasse 7 Töbingen72076 Germany

ISBN: (纸本)9781510668454

Azopolymers are unique materials with interesting optical properties due to the photoisomerization reaction, which induces large material motions at molecular, nanometrical and even microscopically scales. Several applications in different fields, in particular in photonics and biocompatible materials, have exploited the fabrication of surface relief gratings (SRG) by means the photo-form of azopolymers thin films. The phenomena from which has origin of the surface relief formation is still a matter of discussion and far away from a complete understanding. Consequently, the implementation of new characterization modalities could help to achieve the comprehension of this fundamental issue. So far, different methods as direct efficiency diffraction or Atomic Force Microscopy have been adopted to study the physical properties of such gratings structures as well to characterize the material. Nevertheless, for different reasons those techniques have inherent drawbacks. In this work, we report the results obtained by adopting a full-field interferometric method (in Digital Holographic modality) for monitoring in-situ, quasi-real time and with high spatial resolution the writing process of azopolymer structures on thin films. The micro-size patterns of SRG were fabricated by an interference lithography technique (i.e. Lloyd s mirror). The proposed method is an interesting diagnostic tool that could be useful for investigating the yet unclear origin and related mechanism of SRGs formation and their dynamic evolution. © 2023 SPIE. All rights reserved.

关键词： Biocompatibility

来源：评论

学校读者我要写书评

暂无评论

Learning-based Relational Object Matching Across Views

Learning-based Relational Object Matching Across Views

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Cathrin Elich Iro Armeni Martin R. Oswald Marc Pollefeys Joerg Stueckler Embodied Vision Group Max Planck Institute for Intelligent Systems Tuebingen Germany Max Planck ETH Center for Learning Systems Computer Vision and Geometry Lab ETH Zurich Switzerland University of Amsterdam Netherlands Microsoft Mixed Reality and AI Lab Zurich Switzerland

intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can benefit from reasoning on the level of objects. While keypoint-based matching can yield strong results for finding correspondences for images with small to medium view point changes, for large view point changes, matching semantically on the object-level becomes advantageous. In this paper, we propose a learning-based approach which combines local keypoints with novel object-level features for matching object detections between RGB images. We train our object-level matching features based on appearance and inter-frame and cross-frame spatial relations between objects in an associative graph neural network. We demonstrate our approach in a large variety of views on realistically rendered synthetic images. Our approach compares favorably to previous state-of-the-art object-level matching approaches and achieves improved performance over a pure keypoint-based approach for large view-point changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning-based Relational Object Matching Across Views

arXiv

引用

arXiv 2023年

作者： Elich, Cathrin Armeni, Iro Oswald, Martin R. Pollefeys, Marc Stueckler, Joerg Embodied Vision Group Max Planck Institute for Intelligent Systems Tuebingen Germany The Max Planck ETH Center for Learning Systems The Computer Vision and Geometry Lab ETH Zurich Switzerland University of Amsterdam Netherlands Microsoft Mixed Reality and AI Lab Zurich Switzerland

关键词： intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps 38

Binding in hippocampal-entorhinal circuits enables compositi...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Kymn, Christopher J. Mazelet, Sonia Thomas, Anthony Kleyko, Denis Frady, E. Paxon Sommer, Friedrich T. Olshausen, Bruno A. Redwood Center for Theoretical Neuroscience Helen Wills Neuroscience Institute UC Berkeley Berkeley United States Université Paris-Saclay ENS Paris-Saclay Gif-sur-Yvette France Department of Electrical and Computer Engineering UC Davis Davis United States Centre for Applied Autonomous Sensor Systems Örebro University Örebro Sweden Intelligent Systems Lab Research Institutes of Sweden Kista Sweden Intel Labs Santa Clara United States Herbert Wertheim School of Optometry & Vision Science UC Berkeley Berkeley United States

We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a residue number system, with individual residues represented by high-dimensional, complex-valued vectors. These are composed into a single vector representing position by a similarity-preserving, conjunctive vector-binding operation. Self-consistency between the representations of the overall position and of the individual residues is enforced by a modular attractor network whose modules correspond to the grid cell modules in entorhinal cortex. The vector binding operation can also associate different contexts to spatial representations, yielding a model for entorhinal cortex and hippocampus. We show that the model achieves normative desiderata including superlinear scaling of patterns with dimension, robust error correction, and hexagonal, carry-free encoding of spatial position. These properties in turn enable robust path integration and association with sensory inputs. More generally, the model formalizes how compositional computations could occur in the hippocampal formation and leads to testable experimental predictions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characterization and Sensing of Milk Fat% in the Low GHz Band

Characterization and Sensing of Milk Fat% in the Low GHz Ban...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Omer, Ala Eldin Chong, Jessica Chen, Lisa Shaker, George University of Waterloo Centre for Intelligent Antenna and Radio Systems Electrical & Computer Engineering Canada Schlegel-University of Waterloo Research Institute for Aging Wireless Sensor and Devices Lab Waterloo Canada

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

This paper studies the dielectric properties of commercially available milk products of varying butterfat 0.1-3.25% in the low spectrum 1-10 GHz using an open-ended coaxial probe kit. Extracted properties have indicated an appreciably dielectric contrast between tested milks with a negative linear relationship between the dispersive complex permittivity and the fat content. A resonant sensor was developed to operate in one sensitive region to allow for non-invasive milk fat detection by monitoring changes in the resonance profile of the transmission coefficient S21. © 2022 IEEE.

关键词： Microwave resonators

来源：评论

学校读者我要写书评

暂无评论

Efficient learning of robust quadruped bounding usingpretrained neural networks

引用

IET Cyber-systems and Robotics 2022年第4期4卷 331-338页

作者： Zhicheng Wang Anqiao Li Yixiao Zheng Anhuan Xie Zhibin Li Jun Wu Qiuguo Zhu Institute of Cyber-Systems and Control Zhejiang UniversityZhejiangChina Intelligent Robot Research Center Zhejiang LabZhejiangChina Department of Computer Science University College LondonLondonUK State Key Laboratory of Industrial Control Technology Zhejiang UniversityZhejiangChina

Bounding is one of the important gaits in quadrupedal locomotion for negotiating *** authors proposed an effective approach that can learn robust bounding gaits more efficiently despite its large variation in dynamic body *** authors first pretrained the neural network(NN)based on data from a robot operated by conventional model-based controllers,and then further optimised the pretrained NN via deep reinforcement learning(DRL).In particular,the authors designed a reward function considering contact points and phases to enforce the gait symmetry and periodicity,which improved the bounding *** NN-based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully.A variety of environments are presented both indoors and outdoors with the authors’*** authors’approach shows efficient computing and good locomotion results by the Jueying Mini quadrupedal robot bounding over uneven *** cover image is based on the research Article Efficient learning of robust quadruped bounding using pretrained neural networks by Zhicheng Wang et al.,https://***/10.1049/csy2.12062.

关键词： legged locomotion reinforcement learning robot learning

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：