检索结果-内蒙古大学图书馆

IEEE Transactions on Biometrics, Behavior, and Identity Science 2024年第1期7卷 1-2页

作者： Naser Damer Weihong Deng Jianjiang Feng Vishal M. Patel Ajita Rattani Mark Nixon Smart Living & Biometric Technologies Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA Department of Computer Science and Engineering College of Engineering University of North Texas Denton TX USA

来源：评论

学校读者我要写书评

暂无评论

OPONeRF: One-Point-One NeRF for Robust Neural Rendering

arXiv

引用

arXiv 2024年

作者： Zheng, Yu Duan, Yueqi Zheng, Kangfu Yan, Hongru Lu, Jiwen Zhou, Jie Department of Automation Tsinghua University China Department of Electrical Engineering Tsinghua University China Department of Computer Science Tsinghua University China Weiyang College Tsinghua University China

In this paper, we propose a One-Point-One NeRF (OPONeRF) framework for robust scene rendering. Existing NeRFs are designed based on a key assumption that the target scene remains unchanged between the training and test time. However, small but unpredictable perturbations such as object movements, light changes and data contaminations broadly exist in real-life 3D scenes, which lead to significantly defective or failed rendering results even for the recent state-of-the-art generalizable methods. To address this, we propose a divide-and-conquer framework in OPONeRF that adaptively responds to local scene variations via personalizing appropriate point-wise parameters, instead of fitting a single set of NeRF parameters that are inactive to test-time unseen changes. Moreover, to explicitly capture the local uncertainty, we decompose the point representation into deterministic mapping and probabilistic inference. In this way, OPONeRF learns the sharable invariance and unsupervisedly models the unexpected scene variations between the training and testing scenes. To validate the effectiveness of the proposed method, we construct benchmarks from both realistic and synthetic data with diverse test-time perturbations including foreground motions, illumination variations and multi-modality noises, which are more challenging than conventional generalization and temporal reconstruction benchmarks. Experimental results show that our OPONeRF outperforms state-of-the-art NeRFs on various evaluation metrics through benchmark experiments and cross-scene evaluations. We further show the efficacy of the proposed method via experimenting on other existing generalization-based benchmarks and incorporating the idea of One-Point-One NeRF into other advanced baseline methods. Project Page: https://***/ OPONeRF/. Copyright © 2024, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learning 39

Modeling Inter-Intra Heterogeneity for Graph Federated Learn...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Movie sentiment analysis based on Long Short-Term Memory Network

Movie sentiment analysis based on Long Short-Term Memory Net...

引用

作者： Siyao Li Rui Qin Zijian Zhou College of Computer Science and Technology Harbin Engineering University Department of Automation Guangdong University of Technology Dundee International Institute Central South University

An important task in the study of Natural Language Processing(NLP) is the analysis of movie *** finishes the task of classifying movie review texts into sentiment,such as positive,negative or neutral *** works mainly follow the pipeline of LSTM(Long Short-Term Memory Network).The network model is a variant of Recurrent Neural Network(RNN) and particularly suitable for processing natural language *** existing LSTM-based works have improved the performance significantly,we argue that most of them deal with the problem of analyzing the sentiment of movie reviews while ignore analyze the model performance in different application scenarios,such as different lengths of the reviews and the frequency of sentiment adverbs in the *** alleviate the above issue,in this paper,we constructed a simple LSTM model containing an embedding layer,a batch normalization layer,a dropout layer,a one-dimensional convolutional layer,a maximal pooling layer,a bi-directional LSTM layer and a fully connected *** used the existing IMDB movie review dataset to train the model,and selected two research scenarios of movie review length and frequency of occurrence of sentiment adverbs to test the model,*** the experimental results,we proposed a model for the scenarios in which the LSTM model handles the problem of sentiment analysis with respect to the dataset construction,model stability and generalization ability,text fragment processing,data preprocessing and feature extraction,model optimization and improvement.

关键词： Sentiment Analysis LSTM Movie Review Different Application Scenarios

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Backstepping Trajectory Tracking Control for a Quadcopter with Experimental Validation

Nonlinear Backstepping Trajectory Tracking Control for a Qua...

引用

Chinese automation Congress (CAC)

作者： Siwei Xiang Ziying Yang Yao Yu Yi Shi Kairong Duan Weidong Zhang Wei Xie Department of Automation Shanghai Jiao Tong University Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This paper addresses the nonlinear control problem for a quadcopter. The proposed control strategy ensures effective trajectory tracking with ultimately bounded errors. A nonlinear controller employing a backstepping framework is designed to stabilize the quadcopter with damping effects. Simulation and experimental results demonstrate the controller's capability to maintain stability and accurately follow reference trajectory, validating the effectiveness of the proposed method.

关键词： Damping Backstepping Trajectory tracking Machine learning Stability analysis Robustness Trajectory Nonlinear dynamical systems Vehicle dynamics Quadrotors

来源：评论

学校读者我要写书评

暂无评论

New Results on Input Delay Tolerance for a Class of Nonlinear Control Systems

引用

IFAC-PapersOnLine 2023年第2期56卷 923-928页

作者： Xin Yu Wei Lin School of Electrical Engineering and Automation Jiangsu Normal University Xuzhou 221116 China Department of Electrical Computer and Systems Engineering Case Western Reserve University Cleveland Ohio 44106 USA

This paper studies the problem of when a globally asymptotically stabilizable (GAS) non-homogeneous system by state or output feedback is globally tolerant to input delay. With the aid of the new lemma on the combination of “linear growth and global Lipschitz” property in homogeneous norm reported by Yu and Lin [2023], we prove that for a class of non-homogeneous systems that are not locally exponentially stabilizable (LES) but dominated by a homogeneous system of degree zero, GAS by nonsmooth homogeneous state or output feedback implies GAS of the closed-loop system with input delay, i.e., the property of global input delay tolerance (GIDT). We then illustrate applications of the obtained GIDT results to a class of time-delay non-homogeneous systems with uncontrollable/unobservable linearization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

New Results in Stabilization of Uncertain Nonholonomic Systems:An Event-Triggered Control Approach

引用

Journal of Systems Science & Complexity 2021年第5期34卷 1953-1972页

作者： LIU Tengfei ZHANG Pengpeng WANG Mengxi JIANG Zhong-Ping State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110004China. Department of Electrical and Computer Engineering New York University370 Jay StreetBrooklynNY 11201USA

This paper reports latest developments in event-triggered and self-triggered control of uncertain nonholonomic systems in the perturbed chained *** order to tackle the effects of drift uncertain nonlinearities,nonholonomic constraints and nonsmooth aperiodic sampling in eventbased control,a novel systematic design scheme is proposed by integrating set-valued maps with stateseparation and state-scaling *** stability analysis of the closed-loop event-triggered control system is based on the cyclic-small-gain techniques that overcome the limitation of Lyapunov theory in the construction of Lyapunov functions for nonsmooth dynamical systems and enjoy inherent robustness properties due to the use of gain-based characterization of robust *** specifically,the closed-loop event-triggered control system is transformed into an interconnection of multiple input-tostate stable systems,to which the cyclic-small-gain theorem is applied for robust stability *** self-triggered mechanisms are also developed as natural extensions of the event-triggered control *** proposed event-based control design approach is new and original even when the system model is reduced to the ideal unperturbed chained ***,the proposed methodology is also applicable to a broader class of nonholonomic systems subject to state and input-dependent *** efficacy of the obtained event-triggered controllers is validated by a benchmark example of mobile robots subject to parametric uncertainties and a measurement noise such as bias in the orientation.

关键词： Event-triggered control nonholonomic systems self-triggered control stabilization

来源：评论

学校读者我要写书评

暂无评论

The Evaluation of Milling Processes Based on Fuzzy Logic

The Evaluation of Milling Processes Based on Fuzzy Logic

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Liu Qinghua Cai Yishu Tong Xiaomeng ShiPeng School of Automation Science and Electrical Engineering Beihang University(BUAA) Beijing China Department of computer science University of Liverpool Liverpool United Kingdom

ISBN: (数字)9798331517021

ISBN: (纸本)9798331517038

Process evaluation and optimization are critical aspects of manufacturing, however research in this area faces challenges due to the complexity of parameter variability, strong coupling effects, and significant randomness in the machining process. To address these challenges, this paper proposes a method for assessing machining risks using fuzzy logic. First, a Type-2 fuzzy logic system was applied to fuzzify machining parameters, enabling the knowledge-based expression of these parameters. Next, an expert knowledge base for machining risks was established, with rule weights determined by an expert confidence index. The Analytic Hierarchy Process (AHP) was then used to identify primary and secondary risk indicators, and a fuzzy comprehensive evaluation method was employed to assess overall machining risks. Finally, a machining experiment was designed to validate the effectiveness of the risk assessment system. The experimental results demonstrate that the fuzzy logic approach effectively identifies and categorizes various machining risks, providing robust support for optimizing machining parameters and enhancing process safety.

关键词： Fuzzy logic Knowledge based systems Machining Milling Analytic hierarchy process Market research Safety Risk management Indexes Optimization

来源：评论

学校读者我要写书评

暂无评论

The relevance of IT Security awareness in Renewable Energy facilities

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2022年 20卷 530-535页

作者： Lourenço, Justino Zanghi, Eric Morais, José Neves, Nelson Vasques, César Figueiredo, Fernando Department of Computer Science Engineering Instituto Superior Politécnico Gaya Avenida dos Descobrimentos 333 Vila Nova de Gaia Portugal Department of Electronics and Automation Engineering Instituto Superior Politécnico Gaya Avenida dos Descobrimentos 333 Vila Nova de Gaia Portugal Department of Mechanical Engineering ISPGAYA Instituto Superior Politécnico Gaya Avenida dos Descobrimentos 333 Vila Nova de Gaia Portugal

In recent years several efforts have being made in bringing smart network connectivity to the Renewable Energy Plant (REP) environment. On the other hand, REP is extending in scale from specialized points where the energy provider acts as a supplier to home REP (self-energy producers). This enables new important features such as: process automation, monitoring, control and optimizations. On the other hand, and in particular during and after the Covid19 pandemics the cybersecurity menace is a massive concern. The digital literacy of a worker of such an infrastructure is relevant to the correct implementation of adequate security policies. This article describes the threats and challenges on the field and conducts an enquire for perceiving the awareness of automation and Mechanics engineering students for this relevant problem, as future player in the field. © 2022, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation Based on Transformer and Spatial Recursive Convolution

Medical Image Segmentation Based on Transformer and Spatial ...

引用

International Conference on Control, Mechatronics and automation (ICCMA)

作者： Shanshan Li Xuefeng Liu Fouad Khelifi College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao China Computer Information Sciences Department Northumbria University Newcastle UK

ISBN: (数字)9798331517519

ISBN: (纸本)9798331517526

Artificial intelligence-assisted automated medical image segmentation plays a vital role in helping clinicians make accurate diagnoses and develop effective treatment plans. However, as a significant machine learning model in medical image processing, a U-shaped network (U-Net) faces challenges in capturing long-range dependencies, particularly in medical images with complex textures where structures often blend into the background. To address these challenges, we propose the Transformer and Spatial Recursive U-Net (TSU-Net), a novel architecture that integrates the transformer technology and the spatial recursive convolution, building upon the U-Net framework. The main contribution of TSU-Net lies in the adaptive transformer (AT) block, which integrates transformer mechanisms with adaptive pooling to effectively capture long-range dependencies and enhance multi-level abstract features. Furthermore, we introduce the spatial recursive convolution (SRC) block, which iteratively updates features across layers, thereby improving the network’s capacity to model spatial correlations and describe intricate features in medical images. Experimental results on a cardiac segmentation dataset demonstrate that TSU-Net can enhance segmentation accuracy, underscoring its potential for medical image segmentation tasks.

关键词： Image segmentation Technological innovation Accuracy Correlation Sensitivity Mechatronics Convolution Machine learning Transformers Medical diagnostic imaging

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：