检索结果-内蒙古大学图书馆

作者： Yan, Kai Gao, Hao Department of Information and Control Engineering Shenyang Institute of Science and Technology Liaoning Shenyang110000 China

The explosive growth of information on the internet poses great challenges to users. In response to the above issues, this article studies the construction of an intelligent recommendation system for internet information using a combination of deep learning and big data methods. This article adopts deep learning methods to model user behavior data and combines big data analysis to provide personalized recommendation services for users. This article compared the information recommendation accuracy of two other intelligent recommendation systems through experiments. The system designed in this article achieved an accuracy of 92.5% in this regard, far superior to the other two. Experimental results have shown that the system designed in this article not only improves recommendation accuracy, but also enhances user satisfaction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

C2P-Net: Comprehensive Depth Map to Planar Depth Conversion for Room Layout Estimation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5350-5367页

作者： Zhang, Weidong Zhou, Mengjie Cheng, Jiyu Liu, Ying Zhang, Wei Xi'an University of Posts & Telecommunications School of Communications and Information Engineering China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China

Room layout estimation seeks to infer the overall spatial configuration of indoor scenes using perspective or panoramic images. As the layout is determined by the dominant indoor planes, this problem inherently requires the reconstruction of these planes. Some studies reconstruct indoor planes from perspective images by learning pixel-level or instance-level plane parameters. However, directly learning these parameters has the problems of susceptibility to occlusions and position dependency. In this paper, we introduce the Comprehensive depth map to Planar depth (C2P) conversion, which reformulates planar depth reconstruction into the prediction of a comprehensive depth map and planar visibility confidence. Based on the parametric representation of planar depth we propose, the C2P conversion is applicable to both panoramic and perspective images. Accordingly, we present an effective framework for room layout estimation that jointly learns the comprehensive depth map and planar visibility confidence. Due to the differentiability of the C2P conversion, our network autonomously learns planar visibility confidence by constraining the estimated plane parameters and reconstructed planar depth map. We further propose a novel approach for 3D layout generation through sequential planar depth map integration. Experimental results demonstrate the superiority of our method across all evaluated panoramic and perspective datasets. © 1979-2012 IEEE.

关键词： Layout Three Dimensional Displays Image Reconstruction Estimation Cameras Floors Cognition Transforms Training Semantics Room Layout Estimation Monocular Depth Estimation Planar Depth Reconstruction Planar Visibility Confidence Function Of Depth Comprehensive Function Room Layout Depth Planes Depth Conversion Layout Estimation Sequence Mapping Integration Of Sequences Joint Learning Panoramic Images Planar Graphs Parameter Plane Visible Light Validation Set Intersection Over Union Probability Function Training Images Weight Coefficient Output Channels Depth Values Adjacent Walls Planar Regions Semantic Labels Pixel Coordinates Dice Loss Non Planar Surfaces Depth Estimation Global Vision Camera Pose Camera Coordinate System

来源：评论

学校读者我要写书评

暂无评论

Remote sensing image encryption algorithm based on novel hyperchaos and an elliptic curve cryptosystem

引用

Chinese Physics B 2024年第5期33卷 292-304页

作者：田婧希金松昌张晓强杨绍武史殿习 School of Computer Science National University of Defense TechnologyChangsha 410003China Intelligent Game and Decision Laboratory (IGDL) Beijing 100091China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China

Remote sensing images carry crucial ground information,often involving the spatial distribution and spatiotemporal changes of surface *** safeguard this sensitive data,image encryption technology is *** this paper,a novel Fibonacci sine exponential map is designed,the hyperchaotic performance of which is particularly suitable for image encryption *** encryption algorithm tailored for handling the multi-band attributes of remote sensing images is *** algorithm combines a three-dimensional synchronized scrambled diffusion operation with chaos to efficiently encrypt multiple ***,the keys are processed using an elliptic curve cryptosystem,eliminating the need for an additional channel to transmit the keys,thus enhancing *** results and algorithm analysis demonstrate that the algorithm offers strong security and high efficiency,making it suitable for remote sensing image encryption tasks.

关键词： hyperchaotic system elliptic curve cryptosystem(ECC) 3D synchronous scrambled diffusion remote sensing image unmanned aerial vehicle(UAV)

来源：评论

学校读者我要写书评

暂无评论

Open Circuit Fault Diagnosis Method for DC Microgrids Based on Improved Pearson Correlation Algorithm 2

Open Circuit Fault Diagnosis Method for DC Microgrids Based ...

引用

2nd International Conference on Cyber-Energy Systems and Intelligent Energy, ICCSIE 2024

作者： Zhuo, Hangyi Yang, Yang He, Siming Li, Ka Pu, Xuebin Yang, Houhua School of Electronic Information Engineering Changchun Science University China School of Electrical and Information Engineering Changchun Institute of Technology China School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China

ISBN: (纸本)9798350373318

A fault diagnosis method based on improved Pearson correlation algorithm and Convolutional Neural Network (CNN) is proposed to address the issue of high diagnostic speed and high proportion of semiconductor power transistor faults in DC-DC converters in DC microgrids. This method uses the triangular wave algorithm to convert the PWM fault signal output by the power electronic controller into a triangular wave signal, and performs a rolling window correlation operation with the DC bus voltage ripple characteristic signal. Subsequently, the calculated correlation coefficients are combined with convolutional neural networks (CNN) to achieve fast and accurate diagnosis of open circuit faults in semiconductor power transistors. The simulation test results based on MATLAB/Simulink show that the proposed fault diagnosis method can quickly and accurately identify the open circuit fault of semiconductor power transistors in DC microgrids. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Graph Dual Adversarial Network for Hyperspectral Image Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 922-932页

作者： Cheng, Yuhu Chen, Yang Kong, Yi Philip Chen, C.L. Wang, Xuesong China University of Mining and Technology Engineering Research Center of Intelligent Control for Underground Space Ministry of EducationSchool of Information and Control Engineering Xuzhou221116 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China

An end-to-end unsupervised domain adaptation method for hyperspectral image (HSI) classification based on a graph dual adversarial network is proposed in this article. First, in order to extract the domain-invariant features of the source and target domains, the rich spectral information and spatial position of HSI are used to construct a spectral-spatial nearest neighbor graph, which is input into the graph convolutional network. Then, a prototype adversarial strategy is proposed, which uses the labeled data of the source domain to reliably calculate the feature prototypes of different classes. Through the prototype adversarial strategy, the distances between different prototypes are appropriately extended, so that the clusters of different classes are far away from their respective decision boundaries, and the discriminability of features are also enhanced. The dual adversarial strategy is composed of the prototype adversarial strategy and the domain adversarial strategy. It is worth noting that the dual adversarial strategy does not require feature extractor and discriminator to work in turn, which can be implemented through a gradient reversal layer. Finally, on the basis of adapting the overall features of both the domains via the domain adversarial strategy, the source- and target-domain features are further adapted by minimizing the correlation alignment loss of each class of samples. Experimental results on two real HSI datasets of Botswana and Kennedy Space Center show the effectiveness of our proposed method. © 2020 IEEE.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Teachers cooperation:team-knowledge distillation for multiple cross-domain few-shot learning

引用

Frontiers of Computer Science 2023年第2期17卷 91-99页

作者： Zhong JI Jingwei NI Xiyao LIU Yanwei PANG School of Electrical and Information Engineering Tianjin UniversityTianjin 300072China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjin 300308China Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin 300072China

Although few-shot learning(FSL)has achieved great progress,it is still an enormous challenge especially when the source and target set are from different domains,which is also known as cross-domain few-shot learning(CD-FSL).Utilizing more source domain data is an effective way to improve the performance of ***,knowledge from different source domains may entangle and confuse with each other,which hurts the performance on the target ***,we propose team-knowledge distllation networks(TKD-Net)to tackle this problem,which explores a strategy to help the cooperation of multiple ***,we distill knowledge from the cooperation of teacher networks to a single student network in a meta-learning *** incorporates task-oriented knowledge distillation and multiple cooperation among teachers to train an efficient student with better generalization ability on unseen ***,our TKD-Net employs both response-based knowledge and relation-based knowledge to transfer more comprehensive and effective *** experimental results on four fine-grained datasets have demonstrated the effectiveness and superiority of our proposed TKD-Net approach.

关键词： cross-domain few-shot learning meta-learning knowledge distillation multiple teachers

来源：评论

学校读者我要写书评

暂无评论

Low Latency Soft Fiberoptic Choledochoscope Robot control System

引用

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 43-52页

作者： ZHOU Hanwei ZHU Xinping MA Youwei WANG Kundong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University200240ShanghaiChina Shanghai Aerospace Control Technology Institute Shanghai 201109China

Soft fiberoptic choledochoscope is an important tool for the diagnose and surgical treatment of biliary ***,the traditional soft fiberoptic choledochoscope is hard to operate,due to the low position *** on the conventional soft fiberoptic choledochoscope,an electrical soft fiberoptic choledochoscope robot with a low latency was *** order to improve the controllability of the conventional choledochoscope,the wire traction mechanism and the rotation mechanism are used to bend and rotate the scope,so as to control its movement *** dead band compensation model and control algorithm of the wire traction mechanism are developed to improve the accuracy of the orientation *** human-computer interaction system and complex motion control system are developed based on ARM embedded system and *** to the high-speed synchronization channel between FPGA and peripheral,the design of low latency whole-procedure surgical mode was established and *** with a micro image sensor,real-time video back transmission was *** performance of the robot prototype was verified by animal experiment in vivo on a *** robot has an extremely low operating latency of no more than 0.402 ms,and a high bending positioning accuracy of±1.43°error margin within 99.7%confidence interval,which guarantees the safety of biliary surgery.

关键词： soft fiberoptic choledochoscope electrical control low latency in vivo animal experiment

来源：评论

学校读者我要写书评

暂无评论

Turbulent drag reduction by sector-shaped counter-flow dielectric barrier discharge plasma actuator

引用

Chinese Physics B 2025年第2期34卷 362-370页

作者： Borui Zheng Shaojie Qi Minghao Yu Jianbo Zhang Linwu Wang Dongliang Bian School of Automation and Information Engineering Xi’an University of TechnologyXi’an 710048China School of Mechanical and Precision Instrument Engineering Xi’an University of TechnologyXi’an 710048China Science and Technology on Plasma Dynamics Laboratory Air Force Engineering UniversityXi’an 710038China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an 710048China Shaanxi University Key Laboratory of Photonic Power Devices and Discharge Regulation Xi’an 710048China

The primary objective in aircraft transportation is to minimize turbulent drag, thereby conserving energy and reducing emissions. We propose a sector-shaped counter-flow dielectric barrier discharge plasma actuator, which leverages jet synthesis for drag reduction. A drag control experiment was conducted in a low-speed wind tunnel with a controlled flow velocity of 9.6 m/s(Re = 1.445 × 10^(4)). This study investigated the effects of varying pulse frequencies and actuation voltages on the turbulent boundary layer. Using a hot-wire measurement system, we analyzed the pulsating and time-averaged velocity distributions within the boundary layer to evaluate the streamwise turbulent drag reduction. The results show that the local TDR decreases as the pulse frequency increases, reaching a maximum reduction of approximately 20.97% at a pulse frequency of 50 Hz. In addition, as the actuation voltage increases, the friction coefficient decreases, increasing the drag reduction rate. The maximum drag reduction of approximately 33.34% is achieved at an actuation voltage of 10 kV.

关键词： plasma flow control turbulent boundary layer turbulent drag reduction

来源：评论

学校读者我要写书评

暂无评论

SEMANTIC PRESERVATION AND STYLISTIC DECOUPLING IN TEXTUAL STYLE MIGRATION

SEMANTIC PRESERVATION AND STYLISTIC DECOUPLING IN TEXTUAL ST...

引用

2024 International Conference on Electrical engineering and Intelligent control, EEIC 2024

作者： Chen, Hengzhen Department of Information and Control Engineering Shenyang Institute of Science and Technology Shenyang110167 China

ISBN: (纸本)9781837242672

With the continuous progress of text style transfer technology, its importance in natural language processing is becoming more and more prominent, especially in machine translation, literary creation and other fields with a wide range of applications. This study builds on the work of Tikhonov et al. and provides insights into the problems with their proposed method for assessing textual style migration. Through experiments, this study validates Tikhonov's model architecture and further explores the applicability and limitations of the assessment criteria. The study uses a model that combines an autoencoder (AE) architecture with a Gated Recurrent Unit Recurrent Neural Network (GRU RNN) generator and optimizes the performance by introducing a dedicated discriminator and a shifted autoencoder (SAE). The experimental results demonstrate significant improvements in semantic retention and style migration accuracy thanks to the refined model. However, this study also found that Bilingual Evaluation Understudy (BLEU) scores have limitations in assessing style migration tasks and may not fully reflect the semantic accuracy and fluency of the migrated text. Therefore, this study proposes a reflection on the existing evaluation metrics and suggests exploring a comprehensive evaluation system that is more applicable to style migration tasks. In addition, this study discusses the model's ability to generalize over different styles and domains of data, highlighting the need for further validation and optimization. This study provides valuable insights into the field of textual style migration by validating state-of-the-art models while providing insights into their limitations. © The Institution of engineering & technology 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Extraction of Complex Sentence Relationships Based on Formalized Chinese Clause Structures 7

Extraction of Complex Sentence Relationships Based on Formal...

引用

7th International Conference on Machine Learning and Natural Language Processing, MLNLP 2024

作者： Hao, Wen School of Information and Control Engineering Xi'an University of Architecture Technology Xi'an710055 China

ISBN: (纸本)9798350354973

In the field of relation extraction (RE) from text, English clause structures have recently emerged as a promising method with significant practical value. However, applying this approach to Chinese clauses presents challenges due to the absence of formal structural representation. Our research shows that Chinese clauses follow a conditional probability function of the core relation P, which can be expressed as C = (S|P, O|P, SO|P), demonstrating a formal structural characteristic of discrete complementary synthesis. Notably, the O|P structure, with a high conditional probability, accounts for 79% of cases, serving as the core of complex sentence relations in Chinese. This sharply contrasts with the structural features of English clauses. Building on this, we propose the Discrete Complementary Synthesis Formal Structure (DCSFS) clause unit model. This model is employed to analyze and verify the role of the clause unit as the fundamental encoding element in Chinese sentences. Accordingly, we develop a method for automatically extracting semantic relations from complex Chinese sentences using this formalized clause unit model. Experimental results show that our approach outperforms existing punctuation-based clause determination methods and effectively addresses the challenges of extracting complex sentence relations from Chinese texts. © 2024 IEEE.

关键词： Semantics

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：