检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Jiaojiao Zhu, Linglingzhi Johansson, Mikael Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-100 44 Sweden Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenges posed by DP noise and local updates with streaming non-iid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an (ϵ, δ)DP budget, we establish a dynamic regret bound over the entire time horizon, quantifying the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments confirm the efficacy of the proposed algorithm. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Distance-Based IoU Loss for Accurate and Efficient Bounding Box Regression

SSRN

引用

SSRN 2024年

作者： Gupta, Himanshu Verma, Sourabh Verma, Om Prakash Department of Computer Engineering-Artificial Intelligence Marwadi University Gujrat Rajkot360003 India Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India

Bounding box regression (BBR) has been considered the most decisive step in object detection, continues to make breakthroughs in wide real-time applications of computer vision and directly affects the localisation performance of deep learning models. Usually, existing BBR employs Intersection over Union (IoU)-based loss function, especially Complete IoU (CIoU). However, it shows inefficiency in depicting the objective of BBR, which leads to slow convergence and inaccurate regression performance due to poor aspect ratio penalty and normalised Euclidean distance in the denominator. To overcome these limitations, the present study proposes an Adaptive distance-based IoU (ADIoU) loss function by excluding the distance term in backpropagation and expanding the penalty in CIoU, which further improves the object detection accuracy. The effectiveness of the proposed ADIoU has been verified on the simulated data. Also, ADIoU has been incorporated into YOLOv5, YOLOv4, and RetinaNet to estimate its effectiveness on popular ground-view (COCO) and aerial-view (VisDrone, AU-AIR, and Airbus) object detection datasets. The experimental results reveal that relative to CIoU, ADIoU improves the mAPcoco by 0.68% to 1.66% for ground-view and 0.39% to 5.53% for aerial-view datasets, which demonstrates that ADIoU has strong robustness and can be considered a general BBR loss function. © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A two-stage HV-driven adaptive multi-objective evolutionary algorithm and its application in fixed polarity reed-muller circuits

引用

Expert Systems with Applications 2025年 288卷

作者： Yang, Lu Wang, Shengsheng Dong, Ruyi Fu, Zihao College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Information and Control Engineering Jilin Institute of Chemical Technology Changchun130012 China

To achieve a balance between convergence and diversity, we proposed a two-stage HV-driven adaptive multi-objective evolutionary algorithm (TSAMEA). TSAMEA employs a sinusoidal decreasing parameter adjustment method to enhance exploration pace in the first stage. An adaptive parameter control mechanism utilizes historical memory pools and an HV-driven degree adjustment strategy to achieve better exploitation in the second stage. Extensive experimental data demonstrate that TSAMEA outperforms nine other compared MOEAs. The component analysis illustrates the efficacy of each component of TSAMEA. In addition, area and power optimization are now the main limitations in chip design, TSAMEA is applied to area and power optimization for Fixed Polarity Reed-Muller (FPRM) logic circuits and perform well, which further verifies the ability of the TSAMEA to solve practical problems. © 2025

关键词： Cellular automata

来源：评论

学校读者我要写书评

暂无评论

A review of smartphones-based indoor positioning:Challenges and applications

引用

IET Cyber-Systems and Robotics 2021年第1期3卷 1-30页

作者： Khuong An Nguyen Zhiyuan Luo Guang Li Chris Watkins School of Computing Engineering and MathematicsUniversity of BrightonBrightonUK Computer Science Department Royal HollowayUniversity of LondonEghamUK Institute of Cyber-Systems and Control Zhejiang UniversityHangzhouChina

The continual proliferation of mobile devices has encouraged much effort in using the smartphones for indoor *** article is dedicated to review the most recent and interesting smartphones-based indoor navigation systems,ranging from electromagnetic to inertia to visible light ones,with an emphasis on their unique challenges and potential realworld applications.A taxonomy of smartphone sensors will be introduced,which serves as the basis to categorise different positioning systems for reviewing.A set of criteria to be used for the evaluation purpose will be *** each sensor category,the most recent,interesting,and practical systems will be examined,with detailed discussion on the open research questions for the academics,and the practicality for the potential clients.

关键词： client smart taxonomy

来源：评论

学校读者我要写书评

暂无评论

Leveraging protein-protein interactions in phenotype prediction through graph neural networks 21

Leveraging protein-protein interactions in phenotype predict...

引用

21st IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2024

作者： Smeriglio, Riccardo Rosell-Mirmi, Joana Radeva, Petia Abante, Jordi Universitat de Barcelona Dpt. of Physics Spain Politecnico di Torino Control and Computer Engineering Dpt. Turin Italy Headache Research Group Vall d'Hebron Institut de Recerca Catalonia Barcelona Spain Universitat de Barcelona Institute of Neurosciences Dpt. of Mathematics & Computer Science Catalonia Barcelona Spain Laboratory of Stem Cells & Regenerative Medicine Creatio Production & Validation Center of Advanced Therapies Spain Universitat de Barcelona Institute of Neurosciences Dpt. of Biomedical Sciences Spain Dpt. of Mathematics & Computer Science Catalonia Barcelona Spain

ISBN: (纸本)9798350356632

Current genotype-to-phenotype models, such as polygenic risk scores, only account for linear relationships between genotype and phenotype and ignore epistatic interactions, limiting the complexity of the diseases that can be properly characterized. Protein-protein interaction networks have the potential to improve the performance of the models. Moreover, interactions at the protein level can have profound implications in understanding the genetic etiology of diseases and, in turn, for drug development. In this article, we propose a novel approach for phenotype prediction based on graph neural networks (GNNs) that naturally incorporates existing protein interaction networks into the model. As a result, our approach can naturally discover relevant epistatic interactions. We assess the potential of this approach using simulations and comparing it to linear and other non-linear approaches. We also study the performance of the proposed GNN-based methods in predicting Alzheimer's disease, one of the most complex neurodegenerative diseases, where our GNN approach outperform state of the art methods. In addition, we show that our proposal is able to discover critical interactions in the Alzheimer's disease. Our findings highlight the potential of GNNs in predicting phenotypes and discovering the underlying mechanisms of complex diseases. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Vision Transformers(ViT) Pretraining on 3D ABUS Image and Dual-CapsViT: Enhancing ViT Decoding via Dual-Channel Dynamic Routing

Vision Transformers(ViT) Pretraining on 3D ABUS Image and Du...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingwang Xu Wei Wang Kuanquan Wang Suyu Dong Pengzhong Sun Jinwei Sun Gongning Luo Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China College of Computer and Control Engineering Northeast Forestry University Harbin China School of Instrumentation Science and Engineering Harbin Institute of Technology Harbin China

Breast cancer continues to be a pressing global health concern, emphasizing the essential need for effective diagnostic techniques. Automated Breast Ultrasound Systems (ABUS) provide a promising advance in breast tumor detection, yet they require significant expertise in interpreting 3D ABUS images, a task fraught with distinctive challenges. Although Vision Transformers (ViT) display remarkable potential for image processing, their low inductive bias and significant data requirements pose obstacles, particularly in the data-constrained medical field. To mitigate these issues, we introduce a Mask-Recover strategy for pretraining Transformer models on 3D ABUS images, enhancing model adaptability and reducing the data demands of the ViT model. Moreover, recognizing the risk that ViTs’ average pooling approach may unintentionally mask small but vital features, we propose Dual-CapsViT, an inventive model combining Transformers and Capsule Networks. This integration affords efficient token routing while preserving fine-grained details. To reconcile potential inconsistencies between capsules and tokens, we engineer a novel dual-channel routing algorithm, strengthening the decoder’s performance. We benchmarked our models against well-known standards such as ResNet and ViT for classifying breast tumors in ABUS images. Our models exhibited superior performance, as evidenced by improved accuracy, specificity, and Area Under the Receiver Operating Characteristic Curve (AUC) metrics, thereby affirming Dual-CapsViT’s potential to enhance breast cancer diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Vein Segmentation Method Based on Improved U-Net 12

A Vein Segmentation Method Based on Improved U-Net

引用

12th International Conference of Information and Communication Technology, ICTech 2023

作者： Wang, Hongliang Zhu, Liang Deng, Changyi Xiu, Pengfei Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Institute of Software China Industrial Control Systems Cyber Emergency Response Team Beijing100040 China

ISBN: (纸本)9798350332919

Recently, medical research has revealed that diffusion weighted imaging (DWI) is less sensitive than susceptibility-weighted imaging (SWI) for acute ischemic stroke. Brain vein analysis in SWI is very important for personalised therapy, quantitative diagnosis, and prognosis of acute ischemic stroke. Therefore, the accurate segmentation of veins in SWI images has important significance in supplementary diagnosis and medical research. However, vein segmentation in SWI is a challenging task because different veins show distinct variability and uneven intensity and are difficult to manually split. This paper proposes an improvement method based on U-net, by using dense connection and mixing loss function, the best Dice coefficient and the ASSD were obtained by other comparison methods. The method presented in this article can be used as a potential tool to accurately measure SWI cerebral veins and help physicians in decision making. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Ensemble-Learning Approach for Renewable Energy Resources Evaluation in Algeria

引用

computers, Materials & Continua 2022年第6期71卷 5837-5854页

作者： El-Sayed M.El-Kenawy Abdelhameed Ibrahim Nadjem Bailek Kada Bouchouicha Muhammed A.Hassan Basharat Jamil Nadhir Al-Ansari Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansouraEgypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura 35712Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansouraEgypt Energies and Materials Research Laboratory Faculty of Sciences and TechnologyUniversity of Tamanghasset10034TamanghassetAlgeria URERMS Centre de Developpement des Energies Renouvelables(CDER)01000AdrarAlgeria Mechanical Power Engineering Department Faculty of EngineeringCairo UniversityGiza12613GizaEgypt Department Computer Sciences Universidad Rey Juan CarlosMostoles28933MadridSpain Department of Civil Environmental and Natural Resources EngineeringLulea University of Technology97187LuleaSweden

In order to achieve a highly accurate estimation of solar energy resource potential,a novel hybrid ensemble-learning approach,hybridizing Advanced Squirrel-Search Optimization Algorithm(ASSOA)and support vector regression,is utilized to estimate the hourly tilted solar irradiation for selected arid regions in ***-term measured meteorological data,including mean-air temperature,relative humidity,wind speed,alongside global horizontal irradiation and extra-terrestrial horizontal irradiance,were obtained for the two cities of Tamanrasset-and-Adrar for two *** computational algorithms were considered and analyzed for the suitability of *** two new algorithms,namely Average Ensemble and Ensemble using support vector regression were developed using the hybridization *** accuracy of the developed models was analyzed in terms of five statistical error metrics,as well as theWilcoxon rank-sum and ANOVA *** the previously selected algorithms,K Neighbors Regressor and support vector regression exhibited good ***,the newly proposed ensemble algorithms exhibited even better *** proposed model showed relative root mean square errors lower than 1.448%and correlation coefficients higher than *** was further verified by benchmarking the new ensemble against several popular swarm intelligence *** is concluded that the proposed algorithms are far superior to the commonly adopted ones.

关键词： Renewable energy resources hybrid modeling tilted solar irradiation arid region

来源：评论

学校读者我要写书评

暂无评论

A Novel Early Warning Model for Hand, Foot and Mouth Disease Prediction Based on a Graph Convolutional Network

引用

Biomedical and Environmental Sciences 2022年第6期35卷 494-503页

作者： JI Tian Jiao CHENG Qiang ZHANG Yong ZENG Han Ri WANG Jian Xing YANG Guan Yu XU Wen Bo LIU Hong Tu NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and PreventionChinese Center for Disease Control and PreventionBeijing 100026China Academy of Cyber Science and Engineering Southeast UniversityNanjing 211189JiangsuChina Center for Biosafety Mega Science Chinese Academy of SciencesWuhan 430071HubeiChina Guangdong Center for Disease Control and Prevention Guangzhou 511430GuangdongChina Shandong Center for Disease Control and Prevention Jinan 250014ShandongChina LIST Key Laboratory of Computer Network and Information Integration(Southeast University)Ministry of EducationSoutheast UniversityNanjing 211189JiangsuChina

Objectives Hand,foot and mouth disease(HFMD)is a widespread infectious disease that causes a significant disease burden on *** achieve early intervention and to prevent outbreaks of disease,we propose a novel warning model that can accurately predict the incidence of *** We propose a spatial-temporal graph convolutional network(STGCN)that combines spatial factors for surrounding cities with historical incidence over a certain time period to predict the future occurrence of HFMD in Guangdong and Shandong between 2011 and *** 2011-2018 data served as the training and verification set,while data from 2019 served as the prediction *** important parameters were selected and verified in this model and the deviation was displayed by the root mean square error and the mean absolute *** As the first application using a STGCN for disease forecasting,we succeeded in accurately predicting the incidence of HFMD over a 12-week period at the prefecture level,especially for cities of significant *** This model provides a novel approach for infectious disease prediction and may help health administrative departments implement effective control measures up to 3 months in advance,which may significantly reduce the morbidity associated with HFMD in the future.

关键词： HFMD Early warning model STGCN Disease prediction

来源：评论

学校读者我要写书评

暂无评论

Forecasting-Aided Graphical Learning for Robust State Estimation of Distribution System 1

引用

8th Purple Mountain Forum on Smart Grid Protection and control, PMF 2023

作者： Di, Cao Zhao, Junbo Hu, Jiaxiang Huang, Yuehui Huang, Qi Chen, Zhe Hu, Weihao University of Electronic Science and Technology of China Chengdu China Department of Electrical and Computer Engineering University of Connecticut StorrsCT06269 United States State Key Laboratory of Operation and Control of Renewable Energy and Storage Systems China Electric Power Research Institute Beijing China Department of Energy Technology Aalborg University Pontoppidanstraede 111 Aalborg Denmark

ISBN: (数字)9789819992515

ISBN: (纸本)9789819992508

The forecasting of of pseudo-measurements play an important role in distribution system state estimation (DSSE). This paper proposes robust DSSE method based on forecasting-aided graphical learning method. The nodal power consumption models are first built to produce pseudo-measurements based on deep neural network. Then, the pseudo-measurements and real-time measurements are represented as a graph according to the topology of the distribution network, which are further processed by a graph attention network to capture the mapping relationship between the graphical measurements and the state variables based on the error modeling of pseudo-measurements. The robustness against anomalous measurements is achieved through the embedding of structural information of DN. The modeling of pseudo-measurements further enhance its robustness by guiding the formulation of edge weights of the graph neural network. Comparative tests are carried out on a IEEE 119-node system to demonstrate the effectiveness and robustness of the proposed method. © 2024, State Grid Electric Power.

关键词： Electric power distribution

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：