检索结果-内蒙古大学图书馆

10th International Conference on Information Technology and Quantitative Management, ITQM 2023

作者： Fu, Saiji Tian, Yingjie Tang, Jingjing School of Economics and Management Beijing University of Posts and Telecommunications Beijing100876 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation UCAS Beijing100190 China School of Business Administration Faculty of Business Administration Southwestern University of Finance and Economics Sichuan 611130 China

Multi-view data is closely associated with privileged information, presenting opportunities for advancements in current studies. Firstly, they often overlook the dynamic nature of privileged information;Secondly, the current state-of-the-art privileged support vector machine, dSVM+, is primarily designed for single-view learning;Thirdly, some methods only address two-view classification problems;Finally, the performance enhancements achieved by these approaches remain unsatisfactory. To this end, this paper proposes a multi-view privileged support vector machine called MVdSVM+. The iterative learning strategy is put forward to update the privileged information dynamically. To our best knowledge, this is the first attempt of dSVM+ in multi-view learning. Meanwhile, it is designed for multiple views. Experiments show the effectiveness of MVdSVM+ over the benchmark methods. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative Management.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

HANE-SHC: Heterogeneous attributed network embedding with structural homophily contents

引用

Applied Intelligence 2025年第10期55卷 1-40页

作者： Fu, Yue Zhao, Shuliang Wu, Yongliang College of Information Engineering Hebei GEO University Hebei China College of Computer and Cyber Security Hebei Normal University Hebei China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security Hebei China Hebei Provincial Key Laboratory of Network and Information Security Hebei China School of Information Science and Technology Shijiazhuang Tiedao University Hebei China

Heterogeneous attributed networks (HANs) are ubiquitous in real-world, spanning domains from the academic network to the movie network. Heterogeneous attributed network embedding (HANE), a promising analytical technique in recent years, aims to generate low-dimensional dense vectors containing network structure and attribute content. Compared to the embedding approaches that only consider topology structure, researchers embed the network by leveraging both network topology and content to improve the quality of embedding vectors. However, when two nodes with a connected edge may have a small content similarity value, while two nodes without a connected edge may have a large content similarity value, so, in this situation, it is not appropriate to utilize the network topology and nodes’ content to generate embedding vectors. To overcome this challenge, we propose a novel approach of Heterogeneous Attributed Networks Embedding based on Structural Homophily Contents, abbreviated as HANE-SHC, which is based on convolutional neural networks to leverage both the network structure and the content of nodes connected with the embedded node to generate the representation vectors of the embedded node. To our knowledge, this is the first study that proposes the Structural Homophily Contents to enhance the heterogeneous attributed network embedding. Through comprehensive evaluations on downstream tasks including clustering, classification, link prediction, and visualization, the experimental results demonstrate that the HANE-SHC outperforms the baselines. On the artificial synthetic networks with various network structure-content dissimilarity scores, the HANE-SHC model consistently produces high-quality embedding vectors regardless of the network dissimilarity scores between structure and content, significantly outperforming existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Fusion Method Based on NSCT and Adaptive Sparse Representation 4

Image Fusion Method Based on NSCT and Adaptive Sparse Repres...

引用

4th International Conference on Video and Image Processing, ICVIP 2020

作者： Dong, Zhangyu Wei, Xin Wang, Mengyang School of Computer and Information Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei230009 China

ISBN: (纸本)9781450389075

ABSTRACT: Aiming at the imaging characteristics of multispectral and panchromatic image and the problem that the traditional image fusion methods cannot take into account the spectral quality and spatial resolution of the image at the same time, a novel fusion method based on the Non-subsampled Contourlet Transform (NSCT) domain and adaptive sparse representation (ASR) algorithm is presented in this paper. It combines the advantages of principal component substitution and multi-scale analysis, and uses the ASR model to encode the low-frequency components, which improves the shortcomings of the traditional SR-based approach applications. Firstly, NSCT transform is performed on thefirst principal component of multi-spectral image obtained by PCA transform and panchromatic image,and the low-pass and high-pass coefficients of the source image are obtained. Secondly, the Max-absolute' rule and the ASR model are used to fuse the separated high-pass and low-pass bands respectively. Finally, we obtained the final fused image by the corresponding inverse transformation reconstruction. The results show that the fusion algorithm proposed in this paper performs well in both spatial resolution and spectral performance;it not only improves the subjective visual effect, but also improves the objective evaluation index. © 2020 ACM.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Real-time Dense 3D Semantic Mapping Using RGB-D Camera

Real-time Dense 3D Semantic Mapping Using RGB-D Camera

引用

Chinese Control Conference (CCC)

作者： Guanci Yang Xiaoyuan Wang Dongying Zhu Yang Li Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang China School of Mechanical Engineering Guizhou University Guiyang China State Key Laboratory of Public Big Data Guizhou University Guiyang China

Focusing on the poor real-time performance of 3D semantic mapping using RGB-D cameras in indoor environments, this paper investigates the Real-time Dense 3D Semantic Mapping (RD3DSM) using RGB-D camera. Firstly, a lightweight semantic point cloud acquisition algorithm based on keyframe is designed, which is used to segment scene images and obtain the semantic point cloud real-timely. Secondly, to address the loss of inter-frame tracking in the semantic mapping process, ORB-SLAM3 system is employed as the underlying architecture of the visual 3D semantic mapping system to provide stable camera pose. Thirdly, an information fusion mechanism of the visual 3D semantic mapping system is designed, and the OctoMap 3D scene reconstruction module is adopted to implement dense 3D map representation with semantic information, and then a visual 3D semantic mapping algorithm based on ORB-SLAM3 is proposed. Finally, the designed RD3DSM system is integrated into a robot platform. The tests were conducted on the TUM dataset and natural indoor scenes. The results show the effectiveness and real-time performance of the RD3DSM system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An improved teaching-learning optimization algorithm based on fully informed search

An improved teaching-learning optimization algorithm based o...

引用

Computer Technology and Information Science (ISCTIS), International Symposium on

作者： Xiao Wu Xinghe Jiang Shaobo Li Yanqiu Zhou School of Mechanical Engineering Guizhou University Guiyang China State Key Laboratory of Public Big Data Guizhou University Guiyang China Jiangnan Institute of Mechanical and Electrical Design Guizhou University Guiyang China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

As an advanced version of the Rao algorithm, the fully informed search algorithm (FISA) exhibits exceptional global search capabilities. However, its slow convergence rate somewhat limits its applicability in solving real-world problems. In contrast, the teaching-learning-based optimization (TLBO) algorithm is renowned for its rapid convergence but is highly susceptible to local optima entrapment. To capitalize on the robust global search prowess of FISA and the swift convergence characteristic of TLBO, while addressing optimization challenges, this study introduces an innovative proactive hybrid algorithm termed FISTLBO. Comparative experiments are conducted on the CEC2022 benchmark suite comprising 20dimensional test functions, pitting the FISTLBO algorithm against six classical algorithms. The results demonstrate that the FISTLBO algorithm not only achieves superior consistency and stability in benchmark function outcomes but also outperforms other comparative algorithms, securing the top rank in the Friedman rank sum test. Consequently, the proposed FISTLBO algorithm proves to be an effective solution for intricate optimization problems.

关键词： Information science Benchmark testing Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Adrc & Mpc for Gas Pressure Energy Recovery Systems

SSRN

引用

SSRN 2024年

作者： Zhao, RuoChen Wei, Dong Xiong, YaXuan Zuo, MingXin School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China The University of Sheffield United Kingdom School of Environmental and Energy Engineering Beijing University of Civil Engineering and Architecture China Beijing Key Laboratory of Intelligent Processing for Building Big Data China

The gas pressure needs to be regulated from high to low in transmitting certain industrial gases or natural gas according to the user's demand. To reduce the effects of disturbances caused by load fluctuations on the gas user side, this paper establishes a gas pressure energy recovery control system to generate electricity using an expander-driven generator. An Active Disturbance Rejection Controller (ADRC) is designed for the generator rotational speed process, and a model predictive controller (MPC) is developed for the torque/flux linkage process;they operate in a cascaded manner. The MPC in the secondary loop is used to overcome the system time delay characteristics, thus avoiding the generator torque and flux linkage deviation from their set-points caused by gas load variations. ADRC in the primary loop observes the system disturbances and compensates for them to determine the set-point of the torque, thus ensuring a stable generator rotational speed. The proposed control strategy is verified on a gas pressure energy recovery experimental platform. A comparison of experimental results with the five currently common generator control methods shows that the proposed strategy reduces the generator speed fluctuations and the harmonic components in the generator current. © 2024, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Marine Predator Algorithm for Thermal-aware Routing Scheme in Wireless Body Area Networks

引用

Journal of Bionic engineering 2023年第1期20卷 81-104页

作者： Tao Hai Jincheng Zhou Mohammad Masdari Haydar Abdulameer Marhoon School of Computer and Information Qiannan Normal University for NationalitiesDuyun558000GuizhouChina Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun558000GuizhouChina Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Universiti Teknologi MARA40450Shah AlamSelangorMalaysia Department of Computer Engineering Islamic Azad UniversityUrmia BranchUrmiaIran Information and Communication Technology Research Group Scientific Research CenterAl-Ayen UniversityThi-QarIraq College of Computer Sciences and Information Technology University of KerbalaKarbalaIraq

Thermal-aware routing protocols in WBANs consider temperature factors in the routing process for preventing overheating of the tissues surrounding the sensor ***,providing an energy-efficient and thermal-aware routing in WBANs is a challenging *** deal with this problem,this article presents a novel temperature-aware routing protocol that applies Mamdani-based Fuzzy Logic Controllers(FLCs)for selecting the next forwarding node in routing data *** FLCs apply five important input factors such as the priority of the packet,and sensor node's remaining energy,temperature,distance,and link path ***,a new hybrid version of the Marine Predator Algorithm(MPA),named MPAOA is presented by combining the exploration and exploitation phases of the MPA and Arithmetic Optimization Algorithm(AOA).This algorithm is effectively applied for selecting the best possible set of fuzzy rules for FLCs and tuning their fuzzy *** experiments conducted in the Castalia simulator exhibit that the proposed temperature and priority-aware routing scheme can outperform other well-known routing schemes such as LATOR,TTRP,TAEO,ATAR,and EOCC-TARA in terms of metrics such as sensor nodes lifetime,the average temperature of the sensor nodes,and the percentage of the packets routed through non-overheated ***,it is shown that the MPAOA outperforms other algorithms such as Bat Algorithm(BA),Genetic Algorithm(GA),AOA,and MPA regarding the specified metrics.

关键词： WBANs Multi-hop routing Temperature Priority Fuzzy logic Bio-inspiration

来源：评论

学校读者我要写书评

暂无评论

Temporal Based Instance-Level Fusion for Video Object Detection 17th

Temporal Based Instance-Level Fusion for Video Object Detect...

引用

17th Chinese Intelligent Systems Conference, CISC 2021

作者： Cai, Qiang Kang, Nan Li, Haisheng Cao, Jian Liu, Wenqing Wan, Ruyi School of Computer Science and Engineering Beijing Technology and Business University Beijing100048 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing China National Engineering Laboratory For Agri-product Quality Traceability Beijing China Beijing zhiyunda Technology Co. Ltd. Beijing100085 China

ISBN: (纸本)9789811663277

Static image object detection is naively applied to videos in a frame-by-frame approach, and the prediction is often temporally inconsistent. Enhancement of every selected frame becomes a typical solution by aggregating temporal nearby frames features. But the solutions above just use features in pixel-level. In this work, we emphasize the importance of the temporal sequential relationship, which considers calibrating instance-level features on time line, and combining the pixel-level features with the calibrated instance-level features finally. In order to prevent mismatch in video boundary, pixel-level re-fusion is remained to amend above issue. Although the instance-level fusion gains more global motion cues for the pixel-level calibration’s sake of robustness to occlusion, using temporal information can further improve the robustness. Experiments on the large-scale ImageNet VID dataset state the improvement of the our work for object detection in videos. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

arXiv

引用

arXiv 2025年

作者： Liu, Bangzhen Zheng, Chenxi Xu, Xuemiao Xu, Cheng Zhang, Huaidong He, Shengfeng South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology The State Key Laboratory of Subtropical Building and Urban Science The Ministry of Education Key Laboratory of Big Data and Intelligent Robot The Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Singapore Management University Singapore

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

When liver disease diagnosis encounters deep learning:Analysis,challenges,and prospects

引用

iLIVER 2023年第1期2卷 73-87页

作者： Yingjie Tian Minghao Liu Yu Sun Saiji Fu School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Research Center on Fictitious Economy and Data Science Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of SciencesBeijing 100190China MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation at UCAS Beijing 100190China Tsinghua University Press Beijing 102611China School of Economics and Management Beijing University of Posts and TelecommunicationsBeijing 100876China

The liver is the second-largest organ in the human body and is essential for digesting food and removing toxic ***,obesity,alcohol use,and other factors can damage the liver and cause liver *** diagnosis of liver disease used to depend on the clinical experience of doctors,which made it subjective,difficult,and *** learning has made breakthroughs in various fields;thus,there is a growing interest in using deep learning methods to solve problems in liver research to assist doctors in diagnosis and *** this paper,we provide an overview of deep learning in liver research using 139 papers from the last 5 *** also show the relationship between data modalities,liver topics,and applications in liver research using Sankey diagrams and summarize the deep learning methods used for each liver topic,in addition to the relations and trends between these ***,we discuss the challenges of and expectations for deep learning in liver research.

关键词： Liver Deep learning data modality Liver topic Application

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：