检索结果-内蒙古大学图书馆

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Zhaowen Chen Mingze Zhang Caleb Mostyn Honglu Jiang Xianglong Feng Department of Computer Science and Software Engineering Miami University Oxford

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

Federated Learning (FL) offers significant advancements in user/data privacy, learning quality, model efficiency, scalability, and network communication latency. However, it faces notable security challenges, particularly with the emergence of backdoor attacks. The distributed nature of FL complicates the development of backdoor-resistant systems compared to traditional machine learning environments. In this paper, we propose a novel approach to turn the perceived curse of model inversion (MI) attacks into a blessing, using them as a tool for detecting backdoor attacks in FL environments. Leveraging MI outputs, we propose a K-means-based feature extraction and Isolation-Forest-based anomaly detection algorithm to analyze behavior and detect abnormal learning performance, thereby identifying backdoor attacks. Experimental results demonstrate the effectiveness and superior performance of our method in detecting backdoor attacks within FL systems.

关键词： Privacy Machine learning algorithms Federated learning Databases Scalability Forestry Feature extraction Security Faces Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

From Data to Diagnosis: Investigating Approaches in Mental Illness Detection 2

From Data to Diagnosis: Investigating Approaches in Mental I...

引用

2nd International Conference of Intelligent Methods, Systems and Applications, IMSA 2024

作者： Montasser, Reem Kadry Mazen, Sherif A. Helal, Iman M. A. October University for Modern Sciences and Arts Faculty of Computer Science Software Engineering Department Giza Egypt Cairo University Faculty of Computers and Artificial Intelligence Information Systems Department Giza Egypt

ISBN: (纸本)9798350362633

Mental illness is a considerable global public health problem, impacting both individual well-being and society's health. The growing popularity of social media and the increase of other data sources led to more research interest in detecting mental illness with a particular focus on utilizing and fusing emotional information. Artificial intelligence techniques like natural language processing and others, have shown encouraging improvements in recognizing complex relationships in a wide range of textual data, including clinical notes, social media posts, and interviews. In this paper, we assess the different branches of artificial intelligence based on previous research in mental illness detection, discussing methods, trends, challenges, and future research directions. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Fitts' Law in 3D Extended Reality 25

A Systematic Review of Fitts' Law in 3D Extended Reality

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Amini, Mohammadreza Stuerzlinger, Wolfgang Teather, Robert J Batmaz, Anil Ufuk Department of Computer Science & Software Engineering Concordia University MontrealQC Canada Simon Fraser University VancouverBC Canada School of Information Technology Carleton University OttawaON Canada

ISBN: (纸本)9798400713941

Fitts' law is widely used as an evaluation tool for pointing or selection tasks, evolving into diverse applications, including 3D extended reality (XR) environments like virtual, augmented, and mixed reality. Despite standards like ISO 9241:411, the application of Fitts' law varies significantly across studies, complicating comparisons and undermining the reliability of findings in 3D XR research. To address this, we conducted a systematic review of 119 publications, focusing on 122 studies that used Fitts' law in 3D XR user experiments. Our analysis shows that over half of these studies referenced Fitts' law without thoroughly investigating throughput, movement time, or error rate. We performed an in-depth meta-analysis to examine how Fitts' law is incorporated into research. By highlighting trends and inconsistencies, and making recommendations this review aims to guide researchers in designing and performing more effective and consistent Fitts-based studies in 3D XR, enhancing the quality and impact of future research. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Time-Division Online Speculative Inference for Cost-Effective Intelligent Internet of Things 10

Time-Division Online Speculative Inference for Cost-Effectiv...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Du, Yao Wang, Zehua Leung, Cyril Leung, Victor C.M. The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9798350373011

Intelligent Internet of Things (IIoT), a network paradigm, is an interconnection of intelligent edge devices, empowered by machine learning models. The recent emergence of large language models (LLMs) opens a new path towards IIoT. Although device models are generally lightweight and suitable for edge devices with limited processing power, their performance is less impressive compared to LLMs running on large servers. Server models offer superior performance with the cost of significant computational resources for model inference. To realize cost-effective IIoT, we introduce a novel collaborative inference framework: the online speculative inference enabled by device collaboration and time divisions. We aim to find the minimum number of servers required for the immediate processing of arrived inference requests. To solve the problem, we propose an evolving directed acyclic graph along with a Proof-of-Deletion mechanism for cost reduction and privacy protection. Based on computer simulations using heterogeneous LLMs, it is found that time-division online speculative inference is a promising approach towards cost-effective IIoT. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Building Construction Control System Based on Nonlinear Image Enhancement

引用

computer-Aided Design and Applications 2023年 20卷 213-224页

作者： Liu, Congru Lin, Mingsen Ghafoor, Kayhan Zrar Al-Dabagh, Mustafa Zuhaer Nayef Karras, Dimitrios A. School of Urban Construction Wuhan University of Science and Technology Wuhan China Changjiang Polytechnic Wuhan China Department of Computer Science Knowledge University Erbil44001 Iraq Department of Software & Informatics Engineering Salahaddin University-Erbil Erbil44001 Iraq School of Science Dept. General Athens Greece

To reflect the nonlinear characteristics of the building structural adjustment system, an active vibration control strategy based on the nonlinear is proposed. In this method, the size of the structural control force is determined by comparing the allowable energy with the actual energy, and its direction is determined by taking the derivative of the energy. Because there is no need to solve the linear matrix inequality, the calculation is simple and the operation is convenient. Moreover, when multiple actuators with the same capacity limit are used, the control output force is consistent, thus avoiding the design of multiple control systems and simplifying the controller design. The simulation results show that the maximum controlled displacements of floor 6 to floor 8 are 1.16cm, 1.12cm, and 0.97cm, respectively. The proposed nonlinear energy control method has the advantages of simple control process and avoiding actuator saturation. © 2023 CAD Solutions, LLC.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Maximizing IoT Security: An Examination of Cryptographic Algorithms

Maximizing IoT Security: An Examination of Cryptographic Alg...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Arya, Leena Sharma, Yogesh Kumar Kumar, Ramakrishna Padmanaban, Harish Devi, Suman Tyagi, Lalit Kumar Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering AP Guntur India College of Engineering National University of Science and Technology Department of Ece Muscat Oman Site Reliability and Software Engineering Professional Investment Banking HoustonTX United States Chaudhary Devi Lal University Department of Computer Science and Engineering Haryana Sirsa India G L Bajaj Institute of Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350357769

The proliferation of Internet of Things (IoT) devices has created a ubiquitous network of interconnected sensors and devices that generate and exchange vast amounts of data. With this increased connectivity comes a pressing need for robust security measures to safeguard IoT communications' integrity, confidentiality, and authenticity. This paper categorizes cryptographic algorithms commonly employed in IoT security, including symmetric and asymmetric encryption methods, digital signatures, and key exchange protocols. By examining the attributes of these algorithms, their strengths, and potential vulnerabilities, this paper assesses their effectiveness within the unique context of IoT. Furthermore, the paper highlights the significance of cryptographic algorithm optimization in IoT security. Strategies for enhancing algorithm efficiency, such as algorithm selection, key management, and hardware acceleration are thoroughly explored. Through these case studies, this paper underscores the practical implications of cryptographic algorithm selection and optimization, illustrating how they can prevent security breaches and enhance IoT security. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEiF: Efficient Isolated Forest with e Branches for Anomaly Detection 24

EEiF: Efficient Isolated Forest with e Branches for Anomaly ...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhang, Yifan Xiang, Haolong Zhang, Xuyun Xu, Xiaolong Fan, Wei Zhang, Qin Qi, Lianyong School of Software Nanjing University of Information Science and Technology China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services China School of Computing Macquarie University Australia University of Oxford Uffield Department of Women's & Reproductive Health United Kingdom College of Computer Science and Software Engineering Shenzhen University China Faculty of Science and Engineering China

ISBN: (纸本)9798331506681

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods. © 2024 IEEE.

关键词： Anomaly Detection Efficient FR clustering Parallel Algorithm

来源：评论

学校读者我要写书评

暂无评论

Crafting Tomorrow's Trends with Automated Precision, Efficiency, and Faultless Excellence in Apparel Industry for Medium Scale Businesses 6

Crafting Tomorrow's Trends with Automated Precision, Efficie...

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Hiruni Herath, H.M. Jayaweera, J.M.M.G. Jayasinghe, J.M.Y. Randeni, K.M.T.D. Amarasena, Nelum Chathuranga Rathnayake, Samadhi Chandanathilaka, S.N. Sri Lankan Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lankan Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798331517878

In the evolving landscape of Sri Lanka's apparel industry, the predominance of manual methods in the pre-production phase necessitates innovative technological interventions to enhance efficiency. This research explores the complexities of garment production, addressing critical challenges such as machine breakdowns, maintenance, and workforce management. By employing advanced technologies such as image recognition, loT devices, and machine learning, this study aims to transform pre-production decision-making, optimize sewing machine performance, implement predictive maintenance strategies, and refine workforce optimization. These initiatives, driven by domain expertise and cutting-edge methodologies, not only aim to bridge existing gaps in the industry but also pave the way for significant advancements, ensuring a future characterized by precision, efficiency, and operational excellence. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis In Uzbek Texts In The Restaurant Field 3

Sentiment Analysis In Uzbek Texts In The Restaurant Field

引用

3rd IEEE International Conference on Problems of Informatics, Electronics and Radio engineering, PIERE 2024

作者： Kumushoy, Niyazmetova Farogat, Yusupova Ogabek, Sobirov Urgench Branch of Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi Department of Software Engineering Urgench Uzbekistan Urgench State University Department of Computer Science Urgench Uzbekistan

ISBN: (纸本)9798331516321

Sentiment analysis plays a crucial role in natural language processing, particularly in evaluating user comments and extracting valuable insights for classification tasks. This analysis can significantly impact customer satisfaction and influence a company's future development. In our study, we focused on feedback from restaurants in Tashkent, collected via Google Maps. We constructed a dataset that reflects user sentiments and applied logistic regression models for analysis. Through our evaluation, we found that proper preprocessing steps, such as stemming-especially important for agglutinative languages like Uzbek-greatly enhance model performance. These steps help in reducing words to their root forms, allowing the model to better understand the underlying sentiments. Our best-performing model achieved an impressive accuracy of 91%, demonstrating the effectiveness of our approach. The results highlight the importance of sentiment analysis in the restaurant industry, providing actionable insights that can help businesses improve their services and customer experiences. By leveraging user feedback, companies can make informed decisions that foster growth and enhance customer loyalty. Overall, our research underscores the potential of sentiment analysis in driving business success through careful data handling and analysis techniques. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Online Container Scheduling for Data-intensive Applications in Serverless Edge Computing 42

Online Container Scheduling for Data-intensive Applications ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shang, Xiaojun Mao, Yingling Liu, Yu Huang, Yaodong Liu, Zhenhua Yang, Yuanyuan Stony Brook University Department of Electrical and Computer Engineering United States Shenzhen University College of Computer Science and Software Engineering Shenzhen China Stony Brook University Department of Applied Mathematics and Statistics United States

ISBN: (纸本)9798350334142

Introducing the emerging serverless paradigm into edge computing could avoid over- and under-provisioning of limited edge resources and make complex edge resource management transparent to application developers, which largely facilitates the cost-effectiveness, portability, and short time-to-market of edge applications. However, the computation/data dispersion and device/network heterogeneity of edge environments prevent current serverless computing platforms from acclimating to the network edge. In this paper, we address such challenges by formulating a container placement and data flow routing problem, which fully considers the heterogeneity of edge networks and the overhead of operating serverless platforms on resource-limited edge servers. We design an online algorithm to solve the problem. We further show its local optimum for each arriving container and prove its theoretical guarantee to the optimal offline solution. We also conduct extensive simulations based on practical experiment results to show the advantages of the proposed algorithm over existing baselines. © 2023 IEEE.

关键词： Edge computing

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：