检索结果-内蒙古大学图书馆

IEEE International Conference on Web Services (ICWS)

作者： Jiamei Liu Chang-ai Sun Tong Wu Marco Aiello School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Department of Service Computing IAAS University of Stuttgart Stuttgart Germany

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

There are long-term concerns about the risk of privacy leakage when data is acquired and transmitted via Internet of Things (IoT) devices, which too often hinders the development of data-driven applications and services. To tackle such obstacle, we present a novel blockchain-based data service provisioning architecture based on federated learning, named BP-DSP. The system enables data owners to contribute to data-driven services without exposing their private data. To enhance the model accuracy and reduce the communication overhead, we build a data preference and data summary model, by which the model selects data providers whose data preferences align with those of the customers, serving as participating nodes in federated learning training. By leveraging lightweight homomorphic encryption algorithms, BP-DSP encrypts the model gradients to prevent the potential privacy leakage of data owners’ sensitive information from the inference attack. We construct a reputation-based incentive mechanism to motivate computational nodes to perform model parameter validation and punish participating nodes that upload false parameters or low-quality models in order to constrain their self-interest. Through a detailed security analysis, we show that parameter and model privacy are well preserved during the whole process. Finally, we conduct extensive experiments on real-world datasets to demonstrate the efficiency and reliability of BP-DSP, that the BP-DSP speeds up operational efficiency by over 40%.

关键词： Training Privacy Data privacy Accuracy Federated learning Computational modeling Data models Inference algorithms Blockchains Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient Protection of IoT Networks using Trust Management on the IEEE 802.15.4 Protocol 11

Energy-efficient Protection of IoT Networks using Trust Mana...

引用

11th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2021

作者： Khan, Zeeshan Ali Herrmann, Peter National University of Computer and Emerging Sciences Department of Computer Science Lahore Pakistan Information Security and Communication Technology Trondheim Norway

ISBN: (纸本)9781665443999

Many devices used in the Internet of Things (IoT) have scarce processing resources and restricted energy budgets. Thus, established security mechanisms to protect IoT nodes against malicious attacks cannot be applied. Trust management is a promising technology to circumvent the processing limitations since it makes the use of lightweight but still powerful security mechanisms possible. In earlier work, we proposed a trust-based routing solution that builds the reputation of IoT devices to detect maliciously behaving ones. It has, however, the disadvantage of additional battery draining since it works only with constant idle listening of the communication channel which is quite energy intensive. In this paper, we present a method to alleviate this problem by aligning the proposed security algorithm with the popular IEEE 802.15.4 protocol that offers functionality to reduce active channel listening. In particular, we suggest an adaption to one of the application modes of IEEE 802.15.4 such that we can use our trust-based algorithm with often only slight losses from idle listening. The results of the protocol adaptations are discussed for two different scenarios. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation Approach for Gait Analysis using Machine Learning

Pose Estimation Approach for Gait Analysis using Machine Lea...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Sharon Jemimah Peace C V. Ebenezer Bijolin Edwin Abinayaa. R Sharan D Roshini Thanka Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Chennai India

The purpose of the paper is to incorporate machine learning in gait analysis by solving the problems associated with the health of aged people by concentrating on the frailty and senility syndromes that affect elderly individuals with the incorporation of machine learning. Deterioration of cognitive and motor abilities is a common result of ageing and has an effect on elderly people’s quality of life. Some studies have connected these changes in gait patterns to the decline in cognitive and motor function. As a result, gait analysis is a useful tool for diagnosing senility and frailty diseases. By transferring the pose estimation data to a correct statistical analysis, gait analysis can be carried out utilizing machine learning and computer vision approaches, allowing physiotherapists to analyze and treat patients accordingly.

关键词： Legged locomotion Renewable energy sources computer vision Machine learning algorithms Statistical analysis Pose estimation Machine learning

来源：评论

学校读者我要写书评

暂无评论

Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learning

arXiv

引用

arXiv 2024年

作者： Wu, Man Zheng, Xin Zhang, Qin Shen, Xiao Luo, Xiong Zhu, Xingquan Pan, Shirui The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Monash University Melbourne Australia The College of Computer Science and Software Engineering Shenzhen University Guangdong China The School of Computer Science and Technology Hainan University Haikou China The Dept. of Electrical Engineering & Computer Science Florida Atlantic University United States Griffith University QLD Australia

Graph learning plays a pivotal role and has gained significant attention in various application scenarios, from social network analysis to recommendation systems, for its effectiveness in modeling complex data relations represented by graph structural data. In reality, the real-world graph data typically show dynamics over time, with changing node attributes and edge structure, leading to the severe graph data distribution shift issue. This issue is compounded by the diverse and complex nature of distribution shifts, which can significantly impact the performance of graph learning methods in degraded generalization and adaptation capabilities, posing a substantial challenge to their effectiveness. In this survey, we provide a comprehensive review and summary of the latest approaches, strategies, and insights that address distribution shifts within the context of graph learning. Concretely, according to the observability of distributions in the inference stage and the availability of sufficient supervision information in the training stage, we categorize existing graph learning methods into several essential scenarios, including graph domain adaptation learning, graph out-of-distribution learning, and graph continual learning. For each scenario, a detailed taxonomy is proposed, with specific descriptions and discussions of existing progress made in distribution-shifted graph learning. Additionally, we discuss the potential applications and future directions for graph learning under distribution shifts with a systematic analysis of the current state in this field. The survey is positioned to provide general guidance for the development of effective graph learning algorithms in handling graph distribution shifts, and to stimulate future research and advancements in this area. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

computer Vision-Based Detection and Recognition Model of Objects for any Autonomous Systems in Low Illumination Condition 2

Computer Vision-Based Detection and Recognition Model of Obj...

引用

2nd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2022

作者： Ashok, P. Kavinilavu, A. Ananthi, S. Suganthi, P. Iniyan, E.U. Sri Sai Ram Institute of Technology Department of Computer Science and Engineering Chennai India 5Prathyusha Engineering College Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9781665437899

The theories and methods it studies have received extensive attention in many disciplines and fields, promoting the development of artificial intelligence systems and expanding the possibilities of computer applications. Image processing is an important field of pattern recognition methods. The widely used character recognition (OCR) is a typicalapplication of pattern recognition in image processing. The pattern recognition process can be seen as a mapping process from the sample space to the category space. If you divide an n-dimensional feature space with n features asparameters into different regions, each region corresponds to a class of pattern classes. Among them, feature selection and extraction is an important part of pattern recognition. Ifthe selected features can fully reflect the essential features of the class, the classifier is easier to design. According to the presence or absence of standard samples, pattern recognition can be divided into surveillance identification methods and non-supervisory identification methods. The supervisory identification method is to design a classifierunder the condition that the class to which the training sample belongs is known, and the method for recognizing the sample is performed by the classifier. © 2022 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Weighted Salp Swarm Algorithm to Minimize Congestion in Smart City Environment 4

Weighted Salp Swarm Algorithm to Minimize Congestion in Smar...

引用

4th International Conference on Electronics and Sustainable communication Systems, ICESC 2023

作者： Sathish Kumar, G. Sivasankar, C. Rathinam, Anantha Raman Latha, P. Gojan School of Business and Technology Department of Information Technology Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Kl University Department of Computer Science and Engineering -Honors Andhra Pradesh Vijayawada India St.Joseph's College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350300093

Rapid urban population growth increases various issues, including lengthy traffic congestion and pollution which makes city living unsafe and uninhabitable. Applications for smart cities go beyond just using technology to make cities better and the lives of their inhabitants better. However, it can develop complete solutions for the growth of sustainable communities. This article introduces a Weighted Salp Swarm algorithm to minimize Congestion (WSSC) in vehicular ad-hoc networks. The Slap Swarm algorithm is employed in this article to improve the network performance by switching from one vehicle to nearby vehicles to send data packets efficiently. The minimal use of vehicle's energy guarantees the network's maximum lifespan. The main objective is to reduce congestion and prevent packet loss while minimizing data transmission delays under competing conditions. The performance comparison of WSSC with other existing approaches shows that the efficiency of WSSC in terms of throughput and lifetime is improved than others. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Modeling of Drugs using Virtual Screening and in Silico Approach

Machine Learning based Modeling of Drugs using Virtual Scree...

引用

Smart Electronics and communication (ICOSEC), International Conference on

作者： K S Balamurugan K Appathurai P J Sathish Kumar D Kumutha R Surendran Department of Electronics and Communication Engineering Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of Computer Technology KG College of Arts and Science Coimbatore India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Electronics and Communication Engineering Jeppiaar Institute of Technology Sriperumudur Tamilnadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

The process and implementation of drug development is a complex structure which is a time-consuming process with higher accuracy. A transformative approach to optimize drug discovery is achieved through the integration of drug discovery with a virtual screening process. This is implemented through the in silico machine learning process. The traditional methods involve extracting and testing numerous chemical compounds in vitro and in vivo in the identification of potential drug contenders. These methods lead to various drawbacks that include higher costs with timelines. To overcome the drawbacks of the existing system, the integration of paradigm modeling is initiated. The behavior of molecules with biological targets is determined through In-silico machine learning algorithms. The effective analysis of millions of chemical compounds is done using a virtual screening process through computational simulations and desired pharmacological effects. The machine learning algorithms help in the extraction of intricate patterns from the molecular dataset. Certain properties such as molecule binding affinity, bioavailability, and toxicity are predicted using these algorithms. They help to optimize the molecular structure in silico to improve the interaction with the target proteins. The reliability is achieved through the quality of the training data with the robustness of the algorithm. They help to generalize newer chemical combinations that provide the solution for various diseases with personalized recommendations through the aid of artificial intelligence.

关键词： Drugs Analytical models Machine learning algorithms Toxicology Biological system modeling Computational modeling Machine learning Prediction algorithms Drug discovery Chemical compounds

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction based Medical Data Classification using Hybrid Linear Discriminant Analysis 3

Dimensionality Reduction based Medical Data Classification u...

引用

3rd International Conference on Electronics and Sustainable communication Systems, ICESC 2022

作者： Hariharan, B. Prakash, P.N. Senthil Anupama, C.G. Siva, R. Kaliraj, S. Wilfred Blessing, N.R. Intelligence Srm Institute of Science and Technology Department of Computational Tamil Nadu India Rmk College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu India Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India Manipal Institute of Technology Department of Information and Communication Technology Manipal India University of Technology and Applied Sciences-Ibri It Oman

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

Artificial Intelligence and its applications are evolving in all domains especially in the field of medical science. Voluminous amount of clinical data is available and most of the data remains unused. If it is used in effective way then it will be useful in diagnosing the human lives in earlier stages. An effective classification system will help the medical practitioners to provide appropriate diagnosis in earlier stage. Usually, medical data will have lot of features and if all the features are included in decision making it may lead to over fitting of the classification model and in turn accuracy will be affected. Also, if all the features are included in decision making then it will take more resource in building the classification model. Hence there is a need for an effective dimensionality reduction method which not only reduces the number of structures but also improves the classification accuracy. This article recommends a novel ensemble technique named Hybrid Linear Discriminant Analysis (HLDA) for reducing the dimensionality of the medical data. And Random Forest classifier algorithm has been used for building the classification system. For proving the effectiveness of the proposed method, it is compared with LDA, PLS, PCA dimensionality reduction algorithms. Three UCI benchmark datasets namely Breast cancer Wisconsin dataset, Cervical cancer dataset & Heart failure clinical records dataset have been used for the evaluation of the work. The new result proves that this proposed method outclasses the other methods in accuracy, specificity, and sensitivity. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Minimize the routing overhead through 3D cone shaped location-aided routing protocol for FANETs

引用

International Journal of Information technology (Singapore) 2021年第1期13卷 89-95页

作者： Kumar, Sudesh Raw, Ram Shringar Bansal, Abhishek Department of Computer Science Indira Gandhi National Tribal University Amarkantak MP India Department of Computer Science and Engineering Ambedkar Institute of Advanced Communication Technology and Research Delhi India

Recently, designing an effective routing protocol is challenging for flying ad-hoc networks (FANETs) due to the versatile nature of unmanned aerial vehicles (UAVs). Position-based routing schemes are seen to be a remarkable preference for routing in FANETs due to the fact that the geographical information of UAVs is readily available. In this paper, we are interested in the modification of the location-aided routing (LAR) that we call 3D cone shaped location-aided routing (3DC-LAR) a position-based routing (PBR) protocol. In the existing LAR scheme, a route discovery process done through the concept of request zone, in which only nodes presents in the request zone will forward the route request for transmitting the data. The proposed 3DC-LAR scheme modified the definition of request zone using 3D cone shape by intermediate UAVs in FANETs environment. The simulation results reveal that the proposed 3DC-LAR scheme has contributed to lead to an improvement in the terms of routing overhead. © 2020, Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： FANETs LAR MLAR PBR UAVs

来源：评论

学校读者我要写书评

暂无评论

Protecting Terrestrial Networks in Cognitive Satellite-Terrestrial Networks: A NOMA-Based Protocol

Protecting Terrestrial Networks in Cognitive Satellite-Terre...

引用

International Conference on Information and communication technology Convergence (ICTC)

作者： Hyunwoo Jung Jung-Bin Kim Satellite Communication Research Division Electronics and Telecommunications Research Institute (ETRI) Daejeon South Korea Department of Computer Information and Communication Engineering University of Science and Technology (UST) Daejeon South Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

Fifth-generation (5G) standards have spurred the integration of satellite networks to enhance communication capabilities, yet harmonizing spectrum sharing between ter-restrial and satellite domains remains challenging. cognitive satellite-terrestrial networks (CSTNs) address these challenges by leveraging collaboration between terrestrial base stations (tBSs) and satellite base stations (sBSs). This paper explores a novel non-orthogonal multiple access (NOMA)-based CSTN paradigm where the tBS serves as the primary network (PN) and the sBS as the secondary network (SN). The proposed NOMA-based protocol aims to enhance PN protection and overall network capacity. Through Monte-Carlo simulations, this study derives the ergodic capacity and ergodic sum capacity of the protocol. Results indicate effective protection of PN ergodic capacity by NOMA-CSTN, albeit at the expense of compromised SN ergodic capacity compared to orthogonal multiple access (OMA)-based CSTN protocols.

关键词： Base stations NOMA Protocols Satellites Monte Carlo methods Simulation Satellite broadcasting Space-air-ground integrated networks Protection Standards

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：