检索结果-内蒙古大学图书馆

Task Scheduling Mechanism for Crowdsourcing in Mobile Social Networks

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Jiale Yi, Longhao Gao, Xiaofeng Bhatti, Shahzad Sarwar Yuan, Ting Chen, Guihai Shanghai Jiao Tong University Department of Computer Science and Engineering China Emerson University Faculty of Computing and Emerging Technologies Multan Pakistan Shanghai Jiao Tong University Department of Automation China

With the popularization of smart phones, mobile crowdsourcing emerged and gained growing attention in the recent years. Mobile users are now able to conduct complex tasks with the communication between each other. In this paper, we study the task scheduling problem in the mobile crowdsourcing systems based on the spontaneously formed mobile social networks (MSNs). We introduce two crowdsourcing task scheduling problems under this system model, with one problem aiming to minimize the total cost of some crowdsourcing tasks and the other focusing on minimizing the final completion time of the tasks belonging to the same project. We introduce a unified framework to solve the problems and propose two approximation algorithms for these two problems in the offline versions respectively and prove Their approximation ratios accordingly. Based on the two algorithms, we further design two online algorithms to deal with the workers' dynamism and also analyze their competitive ratios. Finally, we verify the effectiveness and efficiency of the proposed methods through numerical experiments on real and synthetic datasets. © 2002-2012 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Distributed formation control for manipulator end-effectors

arXiv

引用

arXiv 2021年

作者： Wu, Haiwen Jayawardhana, Bayu De Marina, Hector Garcia Xu, Dabo Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen9747 AG Netherlands Department of Computer Architecture and Automatic Control Faculty of Physics Universidad Complutense de Madrid Madrid28040 Spain School of Automation Nanjing University of Science and Technology Nanjing210094 China

We present three classes of distributed formation controllers for achieving and maintaining the 2D/3D formation shape of manipulator end-effectors to cope with different scenarios due to availability of modeling parameters. We firstly present a distributed formation controller for manipulators whose system parameters are perfectly known. The formation control objective is achieved by assigning virtual springs between end-effectors and by adding damping terms at joints, which provides a clear physical interpretation of the proposed solution. Subsequently, we extend it to the case where manipulator kinematic and system parameters are not exactly known. An extra integrator and an adaptive estimator are introduced for gravitational compensation and stabilization, respectively. Simulation results with planar manipulators and with seven degree-of-freedom humanoid manipulator arms are presented to illustrate the effectiveness of the proposed approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Distributed formation control of manipulators' end-effector with internal model-based disturbance rejection

arXiv

引用

arXiv 2021年

作者： Wu, Haiwen Jayawardhana, Bayu de Marina, Hector Garcia Xu, Dabo Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen9747 AG Netherlands Department of Computer Architecture and Automatic Control Faculty of Physics Universidad Complutense de Madrid Madrid28040 Spain The School of Automation Nanjing University of Science and Technology Nanjing210094 China

This paper addresses the problem of end-effector formation control for manipulators that are subjected to external disturbances: input disturbance torques and disturbance forces at each end-effector. The disturbances are assumed to be non-vanishing and are superposition of finite number of sinusoidal and step signals. The formation control objective is achieved by assigning virtual springs between end-effectors, by adding damping terms at joints, and by incorporating internal model-based dynamic compensators to counteract the effect of the disturbances;all of which presents a clear physical interpretation of the proposed approach. Simulation results are presented to illustrate the effectiveness of the proposed approach. © 2021, CC BY.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

An experiential learning approach to learn AI in an online workshop

An experiential learning approach to learn AI in an online w...

引用

IEEE International Conference on Teaching, Assessment and Learning for engineering (TALE)

作者： Yuan Xu Ching Sing Chai Helen Meng Savio Wai Ho Wong King Woon Yau Thomas K. F. Chiu Irwin King Yeung Yam Faculty of Engineering The Chinese University of Hong Kong Hong Kong SAR China Department of Curriculum and Instruction The Chinese University of Hong Kong Hong Kong SAR China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong SAR China Department of Educational Psychology The Chinese University of Hong Kong Hong Kong SAR China Department of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong SAR China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong SAR China

As educating K-12 students about artificial intelligence (AI) gains prominence, the question of which pedagogical approach could promote the learning of AI needs exploration. This study aims to investigate the feasibility and effectiveness of learning fundamental AI concepts through online experiential learning. A total of 673 secondary school students participated in a two-day online workshop. A set of pre-and-post questionnaires was applied to assess students' understanding of fundamental AI concepts and their perceptions to learn AI. The results showed the online workshop was effective in improving students’ knowledge of AI and their motivation to learn about it. These findings suggested that the use of online experiential learning approach to learn AI is not only feasible but also appropriate for secondary school students. Furthermore, this study discussed the practical implications of incorporating experiential learning into online learning experience for K-12 students, providing insights into the potential of online workshops as a means of learning AI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Social Bot Detection via Structural Information Theory

arXiv

引用

arXiv 2024年

作者： Peng, Hao Zhang, Jingyun Huang, Xiang Hao, Zhifeng Li, Angsheng Yu, Zhengtao Yu, Philip S. School of Cyber Science and Technology Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China State Key Laboratory of Public Big Data Guizhou University No. 2708 South Section of Huaxi Avenue Huaxi District Guizhou Province Guiyang City550025 China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China College of Science University of Shantou No. 243 University Road Shantou515063 China School of Computer Science and Engineering Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China Faculty of Information Engineering and Automation Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

Research on social bot detection plays a crucial role in maintaining the order and reliability of information dissemination while increasing trust in social interactions. The current mainstream social bot detection models rely on black-box neural network technology, e.g., Graph Neural Network, Transformer, etc., which lacks interpretability. In this work, we present UnDBot, a novel unsupervised, interpretable, yet effective and practical framework for detecting social bots. This framework is built upon structural information theory. We begin by designing three social relationship metrics that capture various aspects of social bot behaviors: Posting Type Distribution, Posting Influence, and Follow-to-follower Ratio. Three new relationships are utilized to construct a new, unified, and weighted social multi-relational graph, aiming to model the relevance of social user behaviors and discover long-distance correlations between users. Second, we introduce a novel method for optimizing heterogeneous structural entropy. This method involves the personalized aggregation of edge information from the social multi-relational graph to generate a two-dimensional encoding tree. The heterogeneous structural entropy facilitates decoding of the substantial structure of the social bots network and enables hierarchical clustering of social bots. Thirdly, a new community labeling method is presented to distinguish social bot communities by computing the user's stationary distribution, measuring user contributions to network structure, and counting the intensity of user aggregation within the community. Compared with ten representative social bot detection approaches, comprehensive experiments demonstrate the advantages of effectiveness and interpretability of UnDBot on four real social network datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Analysis of the EMF Parameters of the Stator Winding in the Run-Down Mode for Diagnosing Faults in an Induction Motor

Analysis of the EMF Parameters of the Stator Winding in the ...

引用

Smart Information Systems and Technologies (SIST), IEEE International Conference on

作者： Assel Yussupova Alexandra Potapenko Alexandr Neftissov Dariya Urazalimova Oleh Serbin Department of Electrical Engineering and Automation Toraighyrov University Pavlodar Kazakhstan Faculty of Computer Science Toraighyrov University Pavlodar Kazakhstan Research and innovation center “Industry 4.0” Astana IT University Astana Kazakhstan Dr. Habil. (Social sciences Communication) Chief Executive Officer CEO & Executive Director Yaroslav Mudryi National Library of Ukraine Professor of Kyiv National University of Culture and Arts Ukraine

In industry, as well as in power plants and substations of developed countries, induction motor (IM) are the most common electrical machine. They consume a large amount of the generated electricity. At the same time, they account for a sufficient number of failures of all electrical equipment. In this case, the proportion of failures due to a break in a squirrel-cage rotor, according to various authors, can reach about 5-10%. However, experimental studies at a number of plants and power plants in the Pavlodar region have shown that the damage factor of the squirrel-cage IM rotor is much higher. As a rule, the breakage of the squirrel-cage rotor rods does not lead to an immediate failure of the IM, but is accompanied by a deterioration in its electromechanical characteristics. Basically, the harm from the operation of such IM is expressed in increased energy consumption. Moreover, a year of its operation leads to an excessive consumption of electricity, comparable to the cost of the IM itself. The article shows that today there are a large number of proposals for a method for diagnosing damage to the short-circuited rotor winding of an induction motor (IM) during operation. However, their sensitivity is limited by the need for detuning from fluctuations in the parameters of the electrical network, vibrations of the IM and the uneven moment of resistance of its load. Most of these effects can be eliminated if IM diagnostics are carried out based on the analysis of the EMF parameters in the stator winding in the rundown mode. The authors have analyzed the parameters of the EMF of the stator winding at all stages of the rundown mode and substantiated the use of the presented method for diagnosing faults in an induction motor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Classification of Benign and Malignant Breast Lesions Based on Contrast Manipulation and Gradient Map

Improved Classification of Benign and Malignant Breast Lesio...

引用

E-Health and Bioengineering Conference (EHB)

作者： Iulia–Nela Anghelache Nastase Simona Moldovanu Luminita Moraru The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati UGAL Galati Romania Department of Chemistry Physics and Environment Faculty of Sciences and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (数字)9781665485579

ISBN: (纸本)9781665485586

This study proposes an approach to enhance the contrast breast ultrasound (BUS) images with the preservation of the finer details. The main idea is to use the relevant and most important features in the classification of BUS images as benign or malignant. Among the contrast manipulation techniques, both linear under- and overexposure methods, contrast limiting adaptive histogram equalization (CLAHE) method and homomorphic filtering are used. The gradient maps of original images are generated for further analysis. Also, the gradient maps of original images are improved by the local mean subtraction and divisive normalization. Eight structural features are extracted from each gradient map image type. The extracted features feed a Random Forest (RF) classifier to determine their relevance for BUS images classification. An accuracy of 97.12% has been obtained for improved gradient map images and 93.03% for gradient map images.

关键词： Histograms Ultrasonic imaging Limiting Breast Feature extraction Lesions Standards

来源：评论

学校读者我要写书评

暂无评论

Melanoma Detection using a Random Forest Algorithm

Melanoma Detection using a Random Forest Algorithm

引用

E-Health and Bioengineering Conference (EHB)

作者： Felicia-Anisoara Damian Simona Moldovanu Luminita Moraru The Modelling & Simulation Laboratory University Dunarea de Jos of Galati UGAL Galati Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics University Dunarea de Jos of Galati UGAL Galati Romania Department of Chemistry Physics and Environment Faculty of Sciences and Environment University Dunarea de Jos of Galati UGAL Galati Romania

ISBN: (数字)9781665485579

ISBN: (纸本)9781665485586

In recent years, statistical evidence has identified melanoma as a major cause of skin cancer deaths. In this study, we propose a skin analysis lesions based on colour features (C) and Hu (H) moments to differentiate benign (nevi) and malignant (melanoma) lesions and, a classification based on Random Forest algorithm. Colour features are found as follows. Pre-processing for hair removing using the Dull-razor method; image segmentation based on the optimal colour threshold set on each RGB colour channel (red, green, blue); 23 colour features extraction using the minimum and maximum RGB intensity and Hu moments; Random Forest (RF) algorithm to accurately differentiate benign and malignant skin lesions. This study used three datasets: 7-Point, Med-Node, PH2. RF classifier performance in terms of accuracy was: 94% for the 7-point dataset with H5, H7, H6, H2, C08 selected as relevant features; 98.1% for the Med-Node dataset and H7, H5, H6, H2, H1 ACC the relevant features; and, 96.5% for the PH2 dataset and H5, H6, H7, C03, H1 selected as relevant features, respectively. Shape features based on Hu moments are found to improve the classification performance of the skin lesions compared to the colour features.

关键词： Visualization Image segmentation Image color analysis Shape Melanoma Skin Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

ReSSL: relational self-supervised learning with weak augmentation 21

ReSSL: relational self-supervised learning with weak augment...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Mingkai Zheng Shan You Fei Wang Chen Qian Changshui Zhang Xiaogang Wang Chang Xu School of Computer Science Faculty of Engineering The University of Sydney and SenseTime Research SenseTime Research and Department of Automation Tsinghua University Institute for Artificial Intelligence Tsinghua University (THUAI) Beijing National Research Center for Information Science and Technology (BNRist) University of Science and Technology of China SenseTime Research Department of Automation Tsinghua University Institute for Artificial Intelligence Tsinghua University (THUAI) Beijing National Research Center for Information Science and Technology (BNRist) SenseTime Research and The Chinese University of Hong Kong School of Computer Science Faculty of Engineering The University of Sydney

ISBN: (纸本)9781713845393

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information (i.e., the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduced a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as relation metric, which is thus utilized to match the feature embeddings of different augmentations. Moreover, to boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. Experimental results show that our proposed ReSSL significantly outperforms the previous state-of-the-art algorithms in terms of both performance and training efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy sets complement-based Gated Recurrent Unit 13

Fuzzy sets complement-based Gated Recurrent Unit

引用

13th International Workshop on Fuzzy Logic and Applications, WILF 2021

作者： Ferrero-Jaurrieta, Mikel Dimuro, Graçaliz Pereira Takáč, Zdenko Santiago, Regivan H.N. Fernández, Javier Bustince, Humberto Department of Statistics Computer Science and Mathematics Public University of Navarre Campus Arrosadía s/n Pamplona31006 Spain Centro de Ciências Computacionais Universidade Federal do Rio Grande Rio Grande 96044540 Brazil Institute of Information Engineering Automation and Mathematics Faculty of Chemical and Food Technology Slovak University of Technology in Bratislava Radlinského 9 Bratislava812 37 Slovakia Department of Computer Science and Applied Mathematics Universidade Federal do Rio Grande do Norte Natal1524 Brazil

Gated Recurrent Units (GRU) are neural network gated architectures that simplify other ones (such as, LSTM) by joining gates mainly. For this, instead of using two gates, if x is the first gate, standard operation 1 − x is used to generate the second one, optimizing the number of parameters. In this work, we interpret this information as a fuzzy set, and we generalize the standard operation using fuzzy negations, and improving the accuracy obtained with the standard one. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Fuzzy sets

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：