检索结果-南通市图书馆

A hybrid attention model based on first-order statistical features for smoke recognition

Science China(Technological Sciences) 2024年第3期67卷 809-822页

作者： GUO Nan LIU JiaHui DI KeXin GU Ke QIAO JunFei Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing Artificial Intelligence InstituteBeijing 100124China Faculty of Information Technology Beijing University of TechnologyBeijing 100124China

Smoke and fire recognition are of great importance on foreseeing fire disasters and preventing environmental pollution by monitoring the burning process of objects(e.g., straw, fuels). However, since fire images suffer from problems like the variability of the features, complexity of scenarios, interference from background, changeable weather conditions as well as image quality problems, identifying smoke and fire accurately and promptly from a given image still remains a substantial challenge. Automatically learning the features of smoke images by CNNs has improved the target recognition ability compared to traditional approaches,nonetheless, convolutions and pooling operations in CNNs may cause severe information loss which may lead to *** tackle the above problems, this paper proposed a hybrid attention model based on the characteristics of smoke images. This model adopted multiple optimized attention mechanism in several stages to quickly and precisely capture the important features,achieving state-of-the-art performance on smoke and fire recognition in terms of accuracy and speed. Our proposed module mainly consists of two stages: pooling and attention. In the first stage, we conducted several newly proposed first-order pooling methods. Through traversing the data space in a larger scope, features are better reserved, thus constructing a more intact feature space of smoke and fire in an image. In the second stage, feature maps are aggregated together to perform channel and spatial attention. The channel and spatial dependencies allow us to quickly catch the important features presented in an image. By fully exploring the feature space and prominent salient features, characteristics of smoke and fire are better presented so as to obtain better smoke and fire detection results. Experiments have been conducted on public smoke detection dataset and new proposed fine-grained smoke and fire detection database. Experimental results revealed that the propose

关键词： hybrid attention first-order pooling smoke and fire detection deep convolutional neural networks

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Adaptive Sensor-Fault Tolerant Control of Unmanned Underwater Vehicles With Input Saturation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 907-918页

作者： Xuerao Wang Qingling Wang Yanxu Su Yuncheng Ouyang Changyin Sun the School of Artificial intelligence the Engineering Research Center of Autonomous Unmanned System Technologyand the Anhui Provincial Engineering Research Center for Unmanned System and Intelligent TechnologyMinistry of EducationAnhui UniversityHefei 230601China the School of Automation Southeast UniversityNanjing 210096China

This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean *** active sensor fault-tolerant control scheme is ***,the developed method only requires the inertia matrix of the UUV,without other dynamic information,and can handle both additive and multiplicative sensor ***,an adaptive fault-tolerant controller is designed to achieve asymptotic tracking control of the UUV by employing robust integral of the sign of error feedback *** is shown that the effect of sensor faults is online estimated and compensated by an adaptive *** the proposed controller,the tracking error and estimation error can asymptotically converge to ***,simulation results are performed to demonstrate the effectiveness of the proposed method.

关键词： Asymptotic stability fault-tolerant control input saturation robust integral of the sign of error unmanned underwater vehicle

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Multi-scale hash encoding based neural geometry representation

引用

Computational Visual Media 2024年第3期10卷 453-470页

作者： Zhi Deng Haoyao Xiao Yining Lang Hao Feng Juyong Zhang School of Mathematical Sciences University of Science and Technology of ChinaHefei 230026China Alibaba Artificial intelligence Governance Laboratory Alibaba GroupHangzhou 310017China

Recently, neural implicit function-basedrepresentation has attracted more and more attention,and has been widely used to represent surfacesusing differentiable neural networks. However, surfacereconstruction from point clouds or multi-view imagesusing existing neural geometry representations stillsuffer from slow computation and poor accuracy. Toalleviate these issues, we propose a multi-scale hashencoding-based neural geometry representation whicheffectively and efficiently represents the surface asa signed distance field. Our novel neural networkstructure carefully combines low-frequency Fourierposition encoding with multi-scale hash encoding. Theinitialization of the geometry network and geometryfeatures of the rendering module are accordinglyredesigned. Our experiments demonstrate that theproposed representation is at least 10 times faster forreconstructing point clouds with millions of *** also significantly improves speed and accuracyof multi-view reconstruction. Our code and modelsare available at https://***/Dengzhi-USTC/Neural-Geometry-Reconstruction.

关键词： neural geometry representation hash encoding point cloud reconstruction multi-view reconstruction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

UAV image target localization method based on outlier filter and frame buffer

引用

Chinese Journal of Aeronautics 2024年第7期37卷 375-390页

作者： Yang WANG Hongguang LI Xinjun LI Zhipeng WANG Baochang ZHANG Institute of Unmanned system Beihang UniversityBeijing 100191China School of Electronics and Information Engineering Beihang UniversityBeijing 100191China Institute of Artificial intelligence Beihang UniversityBeijing 100191China

With rapid development of UAV technology,research on UAV image analysis has gained *** the existing techniques of UAV target localization often rely on additional equipment,a method of UAV target localization based on depth estimation has been ***,the unique perspective of UAVs poses challenges such as the significant field of view variations and the presence of dynamic objects in the *** a result,the existing methods of depth estimation and scale recovery cannot be directly applied to UAV ***,there is a scarcity of depth estimation datasets tailored for UAV perspectives,which makes supervised algorithms *** address these issues,an outlier filter is introduced to enhance the applicability of depth estimation networks to target localization.A frame buffer method is proposed to achieve more accurate scale recovery,so as to handle complex scene textures in UAV *** proposed method demonstrates a 14.29%improvement over the *** with the average recovery results from UAV perspectives,the difference is only 0.88%,approaching the performance of scale recovery using ground truth ***,to overcome the limited availability of traditional UAV depth datasets,a method for generating depth labels from video sequences is *** to state-of-the-art methods,the proposed approach achieves higher accuracy in depth estimation and stands for the first attempt at target localization using image *** algorithm and dataset are available at https://***/uav-tan/uav-object-localization.

关键词： Object localization Deep learning Depth estimate Scale recovery Unmanned Aerial Vehicle(UAV)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Sparse convolutional model with semantic expression for waste electrical appliances recognition

引用

Science China(Technological Sciences) 2024年第9期67卷 2881-2893页

作者： HAN HongGui LIU YiMing LI FangYu DU YongPing Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational intelligence and Intelligent system Beijing 100124China Engineering Research Center of Digital Community Ministry of EducationBeijing 100124China Beijing Artificial intelligence Institute and Beijing Laboratory for Intelligent Environmental Protection Beijing 100124China

Deep neural networks play an important role in the recognition of waste electrical appliances. However, deep neural network components still lack reliability in decision-making features. To address this problem, a sparse convolutional model with semantic expression(SCMSE) is proposed. First, a low-rank sparse semantic expression component, combining the benefits of residual networks and sparse representation, is adapted to enhance sparse feature extraction and semantic expression. Second, a reliable network architecture is obtained by iterating the optimal sparse solution, enhancing semantic expression. Finally, the results of visualization experiments on the waste electrical appliances dataset demonstrate that the proposed SCMSE can obtain excellent semantic performance.

关键词： sparse convolutional model deep neural network semantic expression visualization computer vision

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Identity-Preserving Adversarial Training for Robust Network Embedding

引用

Journal of Computer Science & Technology 2024年第1期39卷 177-191页

作者：岑科廷沈华伟曹婍徐冰冰程学旗 Data intelligence system Research Center Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 101480China Beijing Academy of Artificial intelligence Beijing 100000China Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link ***,existing network embed-ding models are vulnerable to random or adversarial perturbations,which may degrade the performance of network em-bedding when being applied to downstream *** achieve robust network embedding,researchers introduce adversari-al training to regularize the embedding learning process by training on a mixture of adversarial examples and original ***,existing methods generate adversarial examples heuristically,failing to guarantee the imperceptibility of generated adversarial examples,and thus limit the power of adversarial *** this paper,we propose a novel method Identity-Preserving Adversarial Training(IPAT)for network embedding,which generates imperceptible adversarial exam-ples with explicit identity-preserving *** formalize such identity-preserving regularization as a multi-class classification problem where each node represents a class,and we encourage each adversarial example to be discriminated as the class of its original *** experimental results on real-world datasets demonstrate that our proposed IPAT method significantly improves the robustness of network embedding models and the generalization of the learned node representations on various downstream tasks.

关键词： network embedding identity-preserving adversarial training adversarial the example

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

TSC prediction and dynamic control of BOF steelmaking with state-of-the-art machine learning and deep learning methods

引用

Journal of Iron and Steel Research International 2024年第1期31卷 174-194页

作者： Tian-yi Xie Cai-dong Zhang Quan-lin Zhou Zhi-qiang Tian Shuai Liu Han-jie Guo Material Technology Research Institute Hesteel GroupShijiazhuang050023HebeiChina Tangsteel Company Hesteel GroupTangshan063611HebeiChina School of Artificial intelligence Beijing Technology and Business UniversityBeijing100048China School of Metallurgical and Ecological Engineering University of Science and Technology BeijingBeijing100083China

Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC)test,including temperature of molten steel(TSC-Temp),carbon content(TSC-C)and phosphorus content(TSC-P),which made prepa-ration for eliminating the TSC *** maximize the prediction accuracy of the proposed approach,various models with different inputs were implemented and compared,and the best models were applied to the production process of a Hesteel group steelmaking plant in China in the *** number of tabular features(hot metal information,scrap,additives,blowing practices,and preset values)was expanded,and time series(off-gas profiles and blowing practice curves)that could reflect the entire steelmaking process were introduced as ***,the latest machine learning models(LightGBM,CatBoost,TabNet,and NODE)were used to make predictions with tabular features,and the best coefficient of determination R^(2)values obtained for TSC-P,TSC-C and TSC-Temp predictions were 0.435(LightGBM),0.857(Cat-Boost)and 0.678(LightGBM),respectively,which were higher than those of classic models(backpropagation and support vector machine).Then,making predictions was performed by using SOTA time series regression models(SCINet,DLinear,Informer,and MLSTM-FCN)with original time series,SOTA image regression models(NesT,CaiT,ResNeXt,and GoogLeNet)with resized time series,and the proposed Concatenate-Model and Parallel-Model with both tabular features and time *** optimization and comparisons,it was finally determined that the Concatenate-Model with MLSTM-FCN,SCINet and Informer as feature extractors performed the best,and its R^(2)values for predicting TSC-P,TSC-C and TSC-Temp reached 0.470,0.858 and 0.710,*** field test accuracies for TSC-P,TSC-C and TSC-Temp were 0.459,0.850 and 0.685,respectively.A related importance analysis was carri

关键词： BOF steelmaking In-blow prediction TSC test Machine learning Deep learning Field application

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

SG-NeRF:Sparse-Input Generalized Neural Radiance Fields for Novel View Synthesis

引用

Journal of Computer Science & Technology 2024年第4期39卷 785-797页

作者： Kuo Xu Jie Li Zhen-Qiang Li Yang-Jie Cao School of Cyber Science and Engineering Zhengzhou UniversityZhengzhou 450002China Intelligent Big Data system(iBDSys)Lab Shanghai Jiao Tong UniversityShanghai 200240China School of Computer and Artificial intelligence Zhengzhou UniversityZhengzhou 450001China

Traditional neural radiance fields for rendering novel views require intensive input images and pre-scene optimization,which limits their practical *** propose a generalization method to infer scenes from input images and perform high-quality rendering without pre-scene optimization named SG-NeRF(Sparse-Input Generalized Neural Radiance Fields).Firstly,we construct an improved multi-view stereo structure based on the convolutional attention and multi-level fusion mechanism to obtain the geometric features and appearance features of the scene from the sparse input images,and then these features are aggregated by multi-head attention as the input of the neural radiance *** strategy of utilizing neural radiance fields to decode scene features instead of mapping positions and orientations enables our method to perform cross-scene training as well as inference,thus enabling neural radiance fields to generalize for novel view synthesis on unseen *** tested the generalization ability on DTU dataset,and our PSNR(peak signal-to-noise ratio)improved by 3.14 compared with the baseline method under the same input *** addition,if the scene has dense input views available,the average PSNR can be improved by 1.04 through further refinement training in a short time,and a higher quality rendering effect can be obtained.

关键词： Neural Radiance Fields(NeRF) multi-view stereo(MVS) new view synthesis(NVS)

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

PEPFL:A framework for a practical and efficient privacy-preserving federated learning

引用

Digital Communications and Networks 2024年第2期10卷 355-368页

作者： Yange Chen Baocang Wang Hang Jiang Pu Duan Yuan Ping Zhiyong Hong State Key Laboratory of Integrated Service Networks Xidian UniversityXi'an710071China School of Information Engineering Xuchang UniversityXuchang461000China School of Telecommunications Engineering Xidian UniversityXi'an710071China Secure Collaborative intelligence Laboratory Ant GroupHangzhou310000China Facility of intelligence Manufacture Wuyi UniversityJiangmen529020China

As an emerging joint learning model,federated learning is a promising way to combine model parameters of different users for training and inference without collecting users’original ***,a practical and efficient solution has not been established in previous work due to the absence of efficient matrix computation and cryptography schemes in the privacy-preserving federated learning model,especially in partially homomorphic *** this paper,we propose a Practical and Efficient Privacy-preserving Federated Learning(PEPFL)***,we present a lifted distributed ElGamal cryptosystem for federated learning,which can solve the multi-key problem in federated ***,we develop a Practical Partially Single Instruction Multiple Data(PSIMD)parallelism scheme that can encode a plaintext matrix into single plaintext for encryption,improving the encryption efficiency and reducing the communication cost in partially homomorphic *** addition,based on the Convolutional Neural Network(CNN)and the designed cryptosystem,a novel privacy-preserving federated learning framework is designed by using Momentum Gradient Descent(MGD).Finally,we evaluate the security and performance of *** experiment results demonstrate that the scheme is practicable,effective,and secure with low communication and computation costs.

关键词： Federated learning Partially single instruction multiple data Momentum gradient descent ElGamal Multi-key Homomorphic encryption

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 18-36页

作者： Ding Wang Ning Gao Derong Liu Jinna Li Frank L.Lewis IEEE the Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing Laboratory of Smart Environmental Protectionand Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China the School of system Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518055China the Department of Electrical and Computer Engineering University of Illinois at ChicagoChicago IL 60607 USA the School of Information and Control Engineering Liaoning Petrochemical UniversityFushun 113001China the UTA Research Institute the University of Texas at ArlingtonArlington TX 76118 USA

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, ***, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation ***, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

关键词： Adaptive dynamic programming(ADP) advanced control complex environment data-driven control event-triggered design intelligent control neural networks nonlinear systems optimal control reinforcement learning(RL)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：