检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Srivastava, Gautam Yun, Unil Department of Computer Science and Information Engineering National Taiwan University Taiwan Department of Distributed Systems and Informatic Devices Silesian University of Technology Poland Department of Math and Computer Science Brandon University Brandon Canada Department of Computer Science and Engineering Sejong University Korea Republic of

Time-series prediction is increasingly popular in a variety of applications, such as smart factories and smart transportation. Researchers have used various techniques to predict power consumption, but existing models lack discussion of collaborative learning and privacy issues among multiple clients. To address these issues, we propose Multi-Head Heterogeneous Federated Learning (MHHFL) systems that consist of multiple head networks, which independently act as carriers for federated learning. In the federated period, each head network is embedded into 2-dimensional vectors and shared with the centralized source pool. MHHFL then selects appropriate source networks and blends the head networks as knowledge transfer in federated learning. The experimental results show that the proposed MHHFL systems significantly outperform the benchmark and state-of-the-art systems and reduce the prediction error by 24.9% to 94.1%. The ablation studies demonstrate the effectiveness of the proposed mechanisms in the MHHFL (head network embedding and selection mechanisms), which significantly outperforms traditional federated average and random transfer. © 2025, CC BY-NC-SA.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

The Role of Soft Skills in Engineering Education 53

The Role of Soft Skills in Engineering Education

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Fojcik, Marcin Fojcik, Martyna Katarzyna Ziebinski, Adam Pollen, Bjarte Kampen, Anne-Lena Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Førde Norway Volda University Collage Department of Humanities and Education Volda Norway Silesian University of Technology Department of Distributed Systems and Informatics Devices Gliwice Poland Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Bergen Norway

ISBN: (纸本)9798350336429

The rapid but uneven education development worldwide is creating many challenges. Changing conditions and rules in engineering fields such as programming, automation, and electronics are not always followed by changes in education. Employers expect potential candidates to be current with the latest domain competencies and soft skills. The idea is to hire candidates with both knowledge (theoretical and practical) and experience in reflection and collaboration skills. Universities can not always keep up with the development of technology and the adaptation of curricula because change happens so quickly. Therefore, upgrades are needed in engineering education. Focusing education solely on measurable knowledge and results is a simple but often insufficient approach to presenting the entire curriculum within the time frame of a course. Our study of about 150 engineering students in Poland and Norway included the role of students' experiences in hands-on activities, especially labs. The research aimed to determine what students expect, what influences their results, and what complications may arise. The study results show that students often struggle with time management, prioritizing, and understanding practical tasks. In addition, there is a difference between students with and without practical work experience. Our research showed that both groups of students did not achieve all their intended educational goals for various reasons. Therefore, adapting the current teaching system to the student's needs and requirements is important. © 2023 IEEE.

关键词： Bolognia process culture model engineering education laboratory teaching soft skills

来源：评论

学校读者我要写书评

暂无评论

PpNNT: Multiparty Privacy-Preserving Neural Network Training System

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 370-383页

作者： Feng, Qi He, Debiao Shen, Jian Luo, Min Choo, Kim-Kwang Raymond Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China School of Information Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai201204 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

By leveraging smart devices [e.g., industrial Internet of Things (IIoT)] and real-time data analytics, organizations, such as production plants can benefit from increased productivity, reduced costs, enhanced self-monitoring, and autonomous decision-making. In such a setting, machine learning plays an important role in data analytics, but the use of conventional centralized machine learning solutions may raise uncomfortable concerns about data privacy. Hence, one can explore the use of federated learning. In this article, we propose privacy-preserving deep neural network training (PpNNT), which is designed to support federated learning in the multiparty setting. To minimize the overall costs, we further design a hybrid architecture to fully maximize resource utilization. Our proposed design allows the PpNNT system to provide high security, efficiency, and scalability for IIoT data analytics, as evidenced by our theoretical security proof and experimental results on the CIFAR10 dataset. © 2020 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Data Poisoning: Issues, Challenges, and Needs 7

Data Poisoning: Issues, Challenges, and Needs

引用

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of Engineering & Technology 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots

引用

Internet of Things and Cyber-Physical systems 2024年第1期4卷 19-23页

作者： Gill, Sukhpal Singh Xu, Minxian Patros, Panos Wu, Huaming Kaur, Rupinder Kaur, Kamalpreet Fuller, Stephanie Singh, Manmeet Arora, Priyansh Parlikad, Ajith Kumar Stankovski, Vlado Abraham, Ajith Ghosh, Soumya K. Lutfiyya, Hanan Kanhere, Salil S. Bahsoon, Rami Rana, Omer Dustdar, Schahram Sakellariou, Rizos Uhlig, Steve Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Raygun Performance Monitoring Wellington New Zealand Center for Applied Mathematics Tianjin University Tianjin China Department of Science Kings Education London United Kingdom Cymax Group Technologies BC Canada QM Academy Queen Mary University of London London United Kingdom Jackson School of Geosciences University of Texas at Austin AustinTX United States Centre for Climate Change Research Indian Institute of Tropical Meteorology Pune India Microsoft Hyderabad India Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Machine Intelligence Research Labs AuburnWA United States Faculty of Computing and Data Science FLAME University Maharashtra Pune India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Computer Science University of Western Ontario London Canada Sydney Australia School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

ChatGPT, an AI-based chatbot, offers coherent and useful replies based on analysis of large volumes of data. In this article, leading academics, scientists, distinguish researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research discusses ChatGPT capabilities and its use in the education sector, identifies potential concerns and challenges. Our preliminary evaluation shows that ChatGPT perform differently in different subject areas including finance, coding, maths, and general public queries. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions, transforming education through smartphones and IoT gadgets, and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported "hallucinations" within GenerativeAI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial. © 2023 The Authors

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Toward a reference architecture based science gateway framework with embedded e-learning support

Toward a reference architecture based science gateway framew...

引用

作者： Pierantoni, Gabriele Kiss, Tamas Bolotov, Alexander Kagialis, Dimitrios DesLauriers, James Ullah, Amjad Chen, Huankai Fee, David Chan You Dang, Hai-Van Kovacs, Jozsef Belehaki, Anna Herekakis, Themistocles Tsagouri, Ioanna Gesing, Sandra School of Computer Science and Engineering University of Westminster London United Kingdom Parallel and Distributed Systems Laboratory SZTAKI Budapest Hungary Institute of Astronomy Astrophysics Space Applications and Remote Sensing National Observatory of Athens Athens Greece Department of Computer Science and Engineering University of Notre Dame Notre DameIN United States

science gateways have been widely utilized by a large number of user communities to simplify access to complex distributed computing infrastructures. While science gateways are still becoming increasingly popular and the number of user communities is growing, the fast and efficient creation of new science gateways and the flexibility to deploy these gateways on-demand on heterogeneous computational resources, remain a challenge. Additionally, the increase in the number of users, especially with very different backgrounds, requires intuitive embedded e-learning tools that support all stakeholders to find related learning material and to guide the learning process. This paper introduces a novel science gateway framework that addresses these challenges. The framework supports the creation, publication, selection, and deployment of cloud-based reference architectures that can be automatically instantiated and executed even by nontechnical users. The framework also incorporates a knowledge repository exchange and learning module that provides embedded e-learning support. To demonstrate the feasibility of the proposed solution, two scientific case studies are presented based on the requirements of the plasmasphere, ionosphere, and thermosphere research communities. © 2022 The Authors. Concurrency and Computation: Practice and Experience published by John Wiley & Sons Ltd.

关键词： Ionosphere

来源：评论

学校读者我要写书评

暂无评论

Estimating the AGV load and a battery lifetime based on the current measurement and random forest application

Estimating the AGV load and a battery lifetime based on the ...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Hanzel, Krzysztof Grzechca, Damian Ziebinski, Adam Chruszczyk, Lukas Janus, Artur Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Telecommunications and Teleinformatics Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Electronics Electrical Engineering and Microelectronics Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice Poland Silesian University of Technology Student of Electrical EngineeringFaculty of Electrical Engineering Gliwice Poland

ISBN: (纸本)9798350324457

The paper describes the energy consumption from the battery based on the current measurements for various cases, i.e., speed (PWL adjustment) and loads. The main purpose of the research is to have additional and reliable information about power consumption and battery life estimation for autonomous guided vehicles (AGV). The authors propose a two-step algorithm. In the first step, a linear classifier was proposed. Then, the KNN classifier was tested;however, it did not give satisfactory results, so it was finally decided to use the random forest to estimate the load and PWL. The time domain current measurement is evaluated, and the beforementioned algorithms process the selected statistical measures. It has been proven that a two-step algorithm allows for achieving high accuracy. Based on the current observation, the paper is a good starting point for further investigation of the AGV because it is usually implemented in the AGV - so it does not require additional hardware. Moreover, it can lead to better energy management and increase battery lifetime. © 2023 IEEE.

关键词： AGV load estimation machine learning Prediction of energy consumption random forest

来源：评论

学校读者我要写书评

暂无评论

Database Deadlock Diagnosis for Large-Scale ORM-Based Web Applications

Database Deadlock Diagnosis for Large-Scale ORM-Based Web Ap...

引用

International Conference on Data Engineering

作者： Zhiyuan Dong Zhaoguo Wang Chuanwei Yi Xian Xu Jinyuan Zhang Jinyang Li Haibo Chen Institute of Parallel and Distributed Systems Shanghai Jiao Tong University Department of Computer Science New York University

Today, most database-backed web applications depend on the database to handle deadlocks. At runtime, the database monitors the progress of transaction execution to detect deadlocks and abort affected transactions. However, this common detect-and-recover strategy is costly to performance as aborted transactions waste CPU *** avoid deadlock-induced performance degradation, developers aim to reorganize the application code to remove deadlocks. Unfortunately, doing so is difficult for web applications. Not only do their implementations include hundreds of thousands of LoCs, but they also use third-party object-relational mapping (ORM) frameworks which hide database access details. Consequently, it is hard for developers to accurately diagnose *** propose WeSEER, a deadlock diagnosis tool for web applications. To overcome the opacity of ORMs, WeSEER performs concolic execution on unit tests to extract a web application’s transactions as a sequence of template statements with symbolic inputs as well as path conditions that enable the sequence. WeSEER then analyzes the extracted transactions based on fine-grained lock modeling to identify potential deadlocks and report the code locations that cause them. We implement WeSEER for Java-based (OpenJDK) web applications, and use it to analyze two popular open-source e-commerce applications, Broadleaf and Shopizer. WeSEER has successfully identified 18 potential deadlocks in Broadleaf and Shopizer. Eliminating these identified deadlocks can result in up to 39.5× and 4.5× throughput improvement for Broadleaf and Shopizer, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization

Efficiently Assemble Normalization Layers and Regularization...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Khiem Le Long Ho Cuong Do Danh Le-Phuoc Kok-Seng Wong Department of Computer Science and Engineering University of Notre Dame IN USA College of Engineering and Computer Science Vin University Hanoi Vietnam Open Distributed Systems Technical University Berlin Berlin Germany

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Domain shift is a formidable issue in Machine Learning that causes a model to suffer from performance degradation when tested on unseen domains. Federated Domain Gener-alization (FedDG) attempts to train a global model using collaborative clients in a privacy-preserving manner that can generalize well to unseen clients possibly with domain shift. However, most existing FedDG methods either cause additional privacy risks of data leakage or induce signifi-cant costs in client communication and computation, which are major concerns in the Federated Learning paradigm. To circumvent these challenges, here we introduce a novel architectural method for FedDG, namely gPerXAN 1 1 https://***/lhkhiem28/gPerXAN, which relies on a normalization scheme working with a guiding regularizer: In particular, we carefully design Personalized eXplicitly Assembled Normalization to enforce client mod-els selectively filtering domain-specific features that are bi-ased towards local data while retaining discrimination of those features. Then, we incorporate a simple yet effec-tive regularizer to guide these models in directly capturing domain-invariant representations that the global model's classifier can leverage. Extensive experimental results on two benchmark datasets, i.e., PACS and Office-Home, and a real-world medical dataset, Camelyon17, indicate that our proposed method outperforms other existing methods in ad-dressing this particular problem.

关键词： Degradation Data privacy computer vision Costs Filtering Federated learning Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Int-BEB: Enhanced Binary Exponential Backoff using Q-learning

Int-BEB: Enhanced Binary Exponential Backoff using Q-learnin...

引用

International Conference on Pattern Analysis and Intelligent systems (PAIS)

作者： N. Zerguine Department of Computer Science Networks and Distributed Systems Laboratory Ferhat Abbas Setif 1 University Setif Algeria

Because of their development and success, MANETs are now preferred alternatives in many fields of study and application. The IEEE 802.11 standard is the basis of most wireless technologies. To treat collisions in wireless networks, IEEE 802.11 distributed Coordination Function (DCF) MAC layer employs Binary Exponential Backoff (BEB) algorithm, that is helpful in decreasing the potential of collision, but comes at the expense of several network performance metrics, such as medium access delay, bandwidth management, power use, and fairness. A Deep Learning technique called Deep Reinforcement Learning (DRL) allows an agent to communicate with the environment in order to accomplish a goal. In the present paper, we suggest Q-learning (QL), one of the DRL approaches to improve the Binary Exponential Backoff (BEB) in MANETs. The intelligently designed Int-BEB aims for better CW selection; this selection strikes to reduce collisions as much as possible and to give more chances to nodes that make collisions to access the channel by taking into consideration their residual energy. In-depth simulations are performed to evaluate the performance of the proposed mechanism. The performance of Int-BEB is evaluated in diverse networks with several criteria such as packet successful transmission, packet loss and energy.

关键词：

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：