检索结果-内蒙古大学图书馆

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Peng Sun Zhibo Wang Yunhe Feng Liantao Wu Yanjun Li Hairong Qi Zhi Wang State Key Laboratory of Industrial Control Technology Zhejiang University P. R. China School of Cyber Science and Engineering Wuhan University P. R. China Department of Electrical Engineering and Computer Science University of Tennessee Knoxville USA School of Computer Science and Technology Zhejiang University of Technology P. R. China

ISBN: (数字)9781728164120

ISBN: (纸本)9781728164137

Truth discovery is an effective tool to unearth truthful answers in crowdsourced question answering systems. Incentive mechanisms are necessary in such systems to stimulate worker participation. However, most of existing incentive mechanisms only consider compensating workers' resource cost, while the cost incurred by potential privacy leakage has been rarely incorporated. More importantly, to the best of our knowledge, how to provide personalized payments for workers with different privacy demands remains uninvestigated thus far. In this paper, we propose a contract-based personalized privacy-preserving incentive mechanism for truth discovery in crowdsourced question answering systems, named PINTION, which provides personalized payments for workers with different privacy demands as a compensation for privacy cost, while ensuring accurate truth discovery. The basic idea is that each worker chooses to sign a contract with the platform, which specifies a privacy-preserving level (PPL) and a payment, and then submits perturbed answers with that PPL in return for that payment. Specifically, we respectively design a set of optimal contracts under both complete and incomplete information models, which could maximize the truth discovery accuracy, while satisfying the budget feasibility, individual rationality and incentive compatibility properties. Experiments on both synthetic and real-world datasets validate the feasibility and effectiveness of PINTION.

关键词： Privacy Knowledge discovery Crowdsourcing Contracts Task analysis Drugs

来源：评论

学校读者我要写书评

暂无评论

Parameter training methods for convolutional neural networks with adaptive adjustment method based on Caputo fractional-order differences

引用

Chaos, Solitons & Fractals 2025年 199卷

作者： Haiming Zhao Honggang Yang Jiejie Chen Ping Jiang Zhigang Zeng School of Computer and Information Engineering Hubei Normal University Huangshi 435000 China School of Automation Wuhan University of Technology Wuhan 430000 China School of Computer Hubei Polytechnic University Huangshi 435000 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430000 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan 430000 China

As deep learning technologies continue to permeate various sectors, optimization algorithms have become increasingly crucial in neural network training. This paper introduces two adaptive momentum algorithms based on Grünwald–Letnikov and Caputo fractional-order differences—Fractional Order Adagrad (FAdagrad) and Fractional Order Adam (FAdam)—to update parameters more flexibly by adjusting momentum information. Commencing from the definitions of fractional derivatives, we propose integrating fractional-order differences with gradient algorithms in convolutional neural networks (CNNs). These adaptive momentum algorithms, leveraging Grünwald–Letnikov and Caputo fractional-order differences, offer enhanced flexibility, thereby accelerating convergence. Our nonlinear parameter tuning method for CNNs demonstrates superior performance compared to traditional integer-order momentum algorithms and the standard Adam algorithm. Experimental results on the BraTS2021 dataset and CIFAR-100 dataset reveal that the proposed fractional-order optimization algorithms significantly outperform their integer-order counterparts in model optimization. They not only expedite convergence but also improve the accuracy of image recognition and segmentation.

关键词： Adaptive momentum algorithms Convolutional neural networks Deep learning Fractional-order differences

来源：评论

学校读者我要写书评

暂无评论

Varying Balancing Transfer Learning for BN Parameter Estimation

Varying Balancing Transfer Learning for BN Parameter Estimat...

引用

Chinese control and Decision Conference, CCDC

作者： Wenqiang Guo Zhengwei Wen Zhigao Guo Cheng Xu Qinkun Xiao Lingling Mao School of Information Engineering & Artificial Intelligence Shaanxi University of Science & Technology Xi’an China School of Electrical & Control Engineering Shaanxi University of Science & Technology Xi’an China School of Electronic Engineering and Computer Science Queen Mary University of London London UK College of Electronics & Information Xi’an Technological University Xi’an China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

To solve the problem of Bayesian network (BN) parameter estimation accuracy under small dataset conditions, this paper proposes a parameter Varying Balancing Transfer Learning algorithm (VBTL) based on varying weight transfer learning. Firstly, the MAP method and the MLE method are used to learn the initial parameters of the target domain and the parameters of each source domain. Then, the source weight factors of the source domain are obtained according to the different data source contributions. Based on the sample statistic the data size threshold values, the balance coefficients for the target initial parameters and the source domain parameters are calculated to obtain the final target parameters. The experimental results show that under the condition of the small data set, the learning accuracy of VBTL algorithm is better than MLE algorithm, MAP algorithm or classical transfer learning algorithm (LoLP). Under the condition of sufficient data set, the learning accuracy of VBTL algorithm approaches the classical MLE algorithm, and the correctness of the algorithm is verified. Moreover, we demonstrate the successful application to real-world bearing fault diagnosis case studies. Compared with the LoLP algorithm, the VBTL algorithm achieves about 10% enhancement for the average diagnosis precision.

关键词： Maximum likelihood estimation Bayes methods Data models Learning systems Parameter estimation Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Empirical evaluation of continuous test-driven development in industrial settings

Empirical evaluation of continuous test-driven development i...

引用

作者： Madeyski, Lech Kawalerowicz, Marcin Faculty of Computer Science and Management Wroclaw University of Science and Technology Wyb. Wyspianskiego 27 Wroclaw50-370 Poland Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland

BACKGROUND: Continuous Test-Driven Development (CTDD) is, proposed by the authors, enhancement of the well-established Test-Driven Development (TDD) agile software development and design practice. CTDD combines TDD with continuous testing (CT) that essentially perform background testing. The idea is to eliminate the need to execute tests manually by a TDD-inspired developer. OBJECTIVE: The objective is to compare the efficiency of CTDD vs TDD measured by the red-to-green time (RTG time), i.e., time from the moment when the project is rendered not compiling or any of the tests is failing, up until the moment when the project compiles and all the tests are passing. We consider the RTG time to be a possible measurement of efficiency because the shorter the RTG time, the quicker the developer is advancing to the next phase of the TDD cycle. METHOD: We perform single case and small-n experiments in industrial settings presenting how our idea of Agile Experimentation materialise in practice. We analyse professional developers in a real-world software development project employing ***. We extend the contribution presented in our earlier paper by: 1) performing additional experimental evaluation of CTDD and thus collecting additional empirical evidence, 2) giving an extended, detailed example how to use and analyse both a single case and small-n experimental designs to evaluate a new practice (CTDD) in industrial settings taking into account natural constraints one may observe (e.g., a limited number of developers available for research purposes) and presenting how to reach more reliable conclusions using effect size measures, especially PEM and PAND which are more appropriate when data are not normally distributed or there is a large variation between or within phases. RESULTS: We observed reduced variance and trimmed means of the RTG time in CTDD in comparison to TDD. Various effect size measures (including ES, d-index, PEM, and PAND) indicate small, albeit non-

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Network Analysis Identifies Circulating miR-155 as Predictive Biomarker of Type 2 Diabetes Mellitus Development in Obese Patients: A Pilot Study

Journal of Liquid Biopsy, The

引用

Journal of Liquid Biopsy, The 2023年 1卷 100070-100070页

作者： Catanzaro, G. Conte, F. Trocchianesi, S. Splendiani, E. Bimonte, V. D'Antonio, F. Paci, P. Morano, S. Migliaccio, S. Ferretti, E. Department of Experimental Medicine Sapienza University of Rome Rome Italy Institute for Systems Analysis and Computer Science "A. Ruberti" (IASI) National Research Council (CNR) Rome Italy Department of Movement Human and Health Sciences University of Foro Italico Rome Italy Department of Computer Control and Management Engineering Sapienza University Rome Italy

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction of Volterra Kernels by Tensor Decomposition using Higher-Order SVD

Dimensionality Reduction of Volterra Kernels by Tensor Decom...

引用

IEEE Conference on Decision and control

作者： Urszula Libal John S. Baras Karl H. Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Wroclaw University of Science and Technology Wroclaw Poland University of Maryland College Park MD USA

ISBN: (数字)9781728174471

ISBN: (纸本)9781728174488

The paper proposes a practical method for a significant dimensionality reduction of Volterra kernels, defining a discrete nonlinear model of a signal by Volterra series of higher order. In system identification of Volterra series, the Volterra kernels and nonlinear inputs of the system can be described by super-symmetrical tensors. The reduction of their dimensionality is obtained by a tensor decomposition technique called Higher Order Singular Value Decomposition (HOSVD). The main contribution of the paper is a cascade learning algorithm for the system identification based on residuals of least squares minimization. Numerical examples for Volterra system of order four are used to illustrate the approach.

关键词： Tensors Kernel Indexes Singular value decomposition Nonlinear systems Taylor series Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

A biologically inspired feature enhancement framework for zero-shot learning

arXiv

引用

arXiv 2020年

作者： Xie, Zhongwu Cao, Weipeng Wang, Xizhao Ming, Zhong Zhang, Jingjing Zhang, Jiyong College of Computer Science and Software Engineering Shenzhen University Shenzhen China College of Command and Control Engineering Army Engineering University of People’s Liberation Army of China Nanjing China School of Automation Hangzhou Dianzi University Hangzhou China

Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on the ImageNet data set by using deep neural networks. The richness of the feature information embedded in the pre-trained models can help the ZSL model extract more useful features from its limited training samples. However, sometimes the difference between the training data set of the current ZSL task and the ImageNet data set is too large, which may lead to the use of pre-trained models has no obvious help or even negative impact on the performance of the ZSL model. To solve this problem, this paper proposes a biologically inspired feature enhancement framework for ZSL. Specifically, we design a dual-channel learning framework that uses auxiliary data sets to enhance the feature extractor of the ZSL model and propose a novel method to guide the selection of the auxiliary data sets based on the knowledge of biological taxonomy. Extensive experimental results show that our proposed method can effectively improve the generalization ability of the ZSL model and achieve state-of-the-art results on three benchmark ZSL tasks. We also explained the experimental phenomena through the way of feature visualization. Copyright © 2020, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

control design and Lyapunov Functions via Bernstein Approximations: Exact Results ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 6459-6464页

作者： Tareq Hamadneh Nikolaos Athanasopoulos Rafael Wisniewski Al Zaytoonah University of Jordan Department of Mathematics Amman Jordan School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Northern Ireland Section of Automation and Control Aalborg University 9220 Aalborg East Denmark

We study the control problem for polynomial continuous-time dynamical systems. We consider polynomial Lyapunov functions and controllers, both parameterised in Bernstein form. Specifically, we present necessary and sufficient conditions for existence of polynomial controllers and Lyapunov functions of some maximum degree, providing at the same time explicit upper bounds on the degree of the involved Bernstein polynomials. The formulated conditions are a set of algebraic inequalities, in the space of Bernstein coefficients.

关键词： Bernstein polynomials control design certificates of positivity Lyapunov stability control Lyapunov Functions polynomial systems

来源：评论

学校读者我要写书评

暂无评论

A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning

A Biologically Inspired Feature Enhancement Framework for Ze...

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Zhongwu Xie Weipeng Cao Xizhao Wang Zhong Ming Jingjing Zhang Jiyong Zhang College of Computer Science and Software Engineering Shenzhen University Shenzhen China College of Command and Control Engineering Army Engineering University of People’s Liberation Army of China Nanjing China School of Automation Hangzhou Dianzi University Hangzhou China

ISBN: (数字)9781728165509

ISBN: (纸本)9781728165516

Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on ImageNet by using deep neural networks. The richness of the feature information embedded in the pre-trained models can help the ZSL model extract more useful features from its limited training data. However, sometimes the difference between the training data of the current ZSL task and the ImageNet is too large, which may cause the use of pre-trained models has no obvious help or even negative impact on the model performance. To solve this problem, this paper proposes a biologically inspired feature enhancement framework for ZSL. Specifically, we design a dual-channel learning framework that uses auxiliary data sets to enhance the feature extractor of the ZSL model and propose a novel method to guide the selection of the auxiliary data sets based on the knowledge of biological taxonomy. Extensive experimental results show that our proposed method can effectively improve the generalization ability of the ZSL model and achieve state-of-the-art results on three benchmark ZSL tasks. We also explained the experimental phenomena through the way of feature visualization.

关键词： Zero-shot learning feature enhancement feature transfer biological taxonomy ancillary data Respiratory Inspiration extraction device Learning Frameworks Training data Refractive surgery enhancement

来源：评论

学校读者我要写书评

暂无评论

MSR: Multi-scale shape regression for scene text detection

arXiv

引用

arXiv 2019年

作者： Xue, Chuhui Lu, Shijian Zhang, Wei School of Computer Science and Engineering Nanyang Technological University School of Control Science and Engineering Shandong University

State-of-the-art scene text detection techniques predict quadrilateral boxes that are prone to localization errors while dealing with straight or curved text lines of different orientations and lengths in scenes. This paper presents a novel multi-scale shape regression network (MSR) that is capable of locating text lines of different lengths, shapes and curvatures in scenes. The proposed MSR detects scene texts by predicting dense text boundary points that inherently capture the location and shape of text lines accurately and are also more tolerant to the variation of text line length as compared with the state of the arts using proposals or segmentation. Additionally, the multi-scale network extracts and fuses features at different scales which demonstrates superb tolerance to the text scale variation. Extensive experiments over several public datasets show that the proposed MSR obtains superior detection performance for both curved and straight text lines of different lengths and orientations. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

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：