检索结果-内蒙古大学图书馆

Multi-agent policy transfer via task relationship modeling

Science China(Information sciences) 2024年第8期67卷 102-114页

作者： Rongjun QIN Feng CHEN Tonghan WANG Lei YUAN Xiaoran WU Yipeng KANG Zongzhang ZHANG Chongjie ZHANG Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir Technologies School of Engineering and Applied Sciences Harvard University Department of Computer Science and Technology Tsinghua University Institute for Interdisciplinary Information Sciences Tsinghua University

Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous studies on multi-agent transfer learning have accommodated teams of different sizes but heavily relied on the generalization ability of neural networks for adapting to unseen tasks. We posit that the relationship among tasks provides key information for policy *** utilize this relationship for efficient transfer by attempting to discover and exploit the knowledge among tasks from different teams, proposing to learn an effect-based task representation as a common latent space among tasks, and using it to build an alternatively fixed training scheme. Herein, we demonstrate that task representation can capture the relationship among teams and generalize to unseen tasks. Thus, the proposed method helps transfer the learned cooperation knowledge to new tasks after training on a few source ***, the learned transferred policies help solve tasks that are difficult to learn from scratch.

关键词： multi-agent reinforcement learning cooperative transfer learning task relationship modeling multi-agent policy reuse multi-agent multi-task learning

来源：评论

学校读者我要写书评

暂无评论

BLOCK-SECURE: AI-Based Blockchain Enabled Secure Framework for IoMT Applications

BLOCK-SECURE: AI-Based Blockchain Enabled Secure Framework f...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Panchal, Barkha Bhatia, Jitendra Kumhar, Malaram Tanwar, Sudeep Dutta, Ashit Kumar Rodrigues, Joel J.P.C. Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad India Dept. of Comp. Science and Information Systems College of Applied Sciences AlMaarefa University Saudi Arabia Amazonas State University AM Manaus Brazil

ISBN: (纸本)9798350350548

The Internet of Medical Things (IoMT) revolutionizes healthcare by integrating medical devices and systems with the internet. However, the vast amounts of sensitive medical data in IoMT networks pose significant security and privacy concerns. Traditional security measures often fall short in identifying the malicious data attacks within the IoMT ecosystems. This paper introduces an AI-based non-malicious data classification scheme based on blockchain. We applied and evaluated the machine learning (ML) classifiers, such as support vector machine (SVM), random forest (RF), and K-Nearest neighbor (KNN). We evaluated the proposed framework based on various performance metrics that includes accuracy, precision, recall, and F1 score. The accuracy using SVM obtained 75.3%, RF is 75.9%, and KNN is 84.3%. The results shows that KNN performs better than other models by the factor of 9%. © 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

AG- Learn: Adaptive Gamification Approach for Interactive Learning Systems

引用

SN computer Science 2025年第2期6卷 1-32页

作者： Bennani, Souha Maalel, Ahmed Ghezala, Henda Ben Daouahi, Achref RIADI Laboratory National School of Computer Sciences University of Manouba Manouba 2010 Tunisia Higher Institute of Applied Science and Technology University of Sousse Sousse 4003 Tunisia Envast Technopôle de Sousse Cité Hammam Maarouf Route Ceinture de Sahloul Sousse 4000 Tunisia

The learner and the learning content are the key factors that contribute to the success of any learning system. In this regard, scientific research is focused on these two factors to improve learner engagement with the learning environment. Each learner seeks an environment appropriate to their needs, which provides personalized and adaptive content to ensure a more successful and useful learning experience for them. To deliver this content, we identify the learner’s intentions, needs and preferences. Existing research is emerging towards the adaptation of learning systems and shows that modeling the learner profile is an important process for achieving this adaptation. We have found that it is necessary to focus on the learner and focus on their dynamic profile to improve their engagement with the learning environment. In this work, we integrate the concept of adaptation into the learning systems, but also to integrate the concept of gamification, based on the dynamic learner profile, to offer an environment not only adequate for academic needs but also a fun and entertaining environment. It is therefore this context that we propose an adaptive gamification approach called “AG-Learn” (Adaptive Gamification in Learning) by focusing on several learner characteristics, using machine learning techniques and recommender systems. We have combined the two concepts “adaptive learning” and “gamification” to provide gamified learning adapted to the learner profile with the objective of motivating and engaging them more and improving the quality of education and learning outcomes. We tested the effectiveness of our contributions in a gamified learning environment called “Class Quiz”. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adaptive gamification Adaptive learning Artificial intelligence E-learning Learner profile Recommendation system

来源：评论

学校读者我要写书评

暂无评论

Metric Basis of Four-Dimensional Klein Bottle

引用

computer Modeling in Engineering & sciences 2023年第9期136卷 3011-3024页

作者： Ali N.A.Koam Ali Ahmad Maryam Salem Alatawi Muhammad Azeem Muhammad Faisal Nadeem Department of Mathematics College of SciencesNew CampusJazan UniversityJazanSaudi Arabia College of Computer Science&Information Technology Jazan UniversityJazanSaudi Arabia Department of Mathematics Faculty of SciencesUniversity of TabukTabukSaudi Arabia Department of Mathematics Riphah Institute of Computing and Applied SciencesRiphah International UniversityLahorePakistan Department of Mathematics COMSATS University IslamabadLahore CampusLahorePakistan

The Metric of a graph plays an essential role in the arrangement of different dimensional structures and finding their basis in various *** metric dimension of a graph is the selection of the minimum possible number of vertices so that each vertex of the graph is distinctively defined by its vector of distances to the set of selected *** set of selected vertices is known as the metric basis of a *** applied mathematics or computer science,the topic of metric basis is considered as locating number or locating set,and it has applications in robot navigation and finding a beacon set of a computer *** to the vast applications of this concept in computer science,optimization problems,and also in chemistry enormous research has been *** extend this research to a four-dimensional structure,we studied the metric basis of the Klein bottle and proved that the Klein bottle has a constant metric dimension for the variation of all its *** the metric basis is variying in 3 and 4 values when the values of its parameter change,it remains constant and unchanged concerning its order or number of *** methodology of determining the metric basis or locating set is based on the distances of a ***,we proved the main theorems in distance forms.

关键词： Klein bottle metric basis resolving set metric dimension

来源：评论

学校读者我要写书评

暂无评论

Entropy generation optimisation for unsteady stagnation Casson nanofluid flow over a stretching sheet with binary chemical reaction and Arrhenius activation energy using the bivariate spectral quasi-linearisation method

引用

International Journal of Ambient Energy 2022年第1期43卷 6489-6501页

作者： Oyelakin, I.S. Mthethwa, H. Sithole Kameswaran, Peri K. Shaw, S. Sibanda, P. School of Computer Science and Applied Mathematics University of the Witwatersrand Johannesburg Braamfontein South Africa School of Mathematics Statistics and Computer Science University of KwaZulu-Natal Scottsville Pietermaritzburg South Africa Department of Mathematics School of Advanced Sciences Vellore Institute of Technology Vellore India Department of Mathematics and Statistical Sciences Botswana International University of Science and Technology Palapye Botswana

The heat and mass transport with Arrhenius activation energy has countless uses such as in nuclear reactors, the synthesis of chemical compounds, geothermal artificial lakes, and retrieval of thermal lubricants. The focus of this work is the analysis of Arrhenius activation energy and binary chemical reaction in a stagnation point Casson nanofluid flow over a stretching sheet. The system is subjected to a nonlinear radiation and a magnetic field. The transport equations are simplified using the Williams and Rhyne non-similar transformation. The solution to the transformed coupled system of nonlinear partial differential equations is obtained using the bivariate spectral quasi-linearisation method. Entropy generation that measures the degenerate useful energy and deprivation of the performance of engineering systems is analysed. Numerical results describing changes in the fluid velocity, temperature, concentration, entropy generation and Bejan number are presented and discussed for different fluid parameters. Activation energy parameter boosts up the solute concentration at the surface while an opposite is observed far away from the surface. The entropy generation decreases with an increase in the unsteady parameter and Casson number, while the opposite response was observed for a higher Reynolds number. Brinkman number gears up the entropy generation while it shows an opposite phenomenon for Bejan number. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

EEG and fMRI Artifact Detection Techniques: A Survey of Recent Developments

引用

SN computer Science 2023年第5期4卷 528页

作者： Mili, Rahma Bouaziz, Bassem Maalel, Ahmed Gargouri, Faiez Multimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL) Faculty of Economics and Management of Sfax University of Sfax Sfax 3021 Tunisia Multimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL) Higher Institute of Computer and Multimedia of Sfax Sfax 3021 Tunisia RIADI Laboratory National School of Computer Sciences University of Manouba Manouba 2010 Tunisia Higher Institute of Applied Sciences and Technology University of Sousse Sousse 4003 Tunisia

The evolution of different techniques for exploring cerebral activity and the development of signal processing and analysis methods have enabled a better understanding of the dynamic cerebral mechanisms in favor of fine diagnosis and characterization of certain diseases such as dementia and epilepsy. Integration of functional magnetic resonance imaging (fMRI) with electroencephalography (EEG) has offered the possibility of understanding new insights into neuroscientific studies because of the higher temporal and spatial measurements of brain activity when compared with the use of each technique separately. However, the experimental limitations of fMRI/EEG are mainly the numerous artifacts, mainly due to switching of magnetic field gradients and cardiac activity. To provide a comprehensive overview of this research area, a systematic mapping study has been conducted. This mapping study aims to identify the topics studied within the artifacts’ detection in EEG and fMRI data, as well as examine the adopted research methodologies, identify the gaps in the current research and point to directions for future research. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Artifacts Deep learning EEG fMRI Systematic mapping study

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Approaches for Data Security in Cloud Environments 2

Hybrid Deep Learning Approaches for Data Security in Cloud E...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Rekha, S. Sharma, Manish Kannan, Sathish Upadhye, Vijay Jagdish Patil, Harshal Rajkumar, S. PSG College of Arts and Science Department of Computer Science Tamil Nadu Coimbatore641 014 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of VLSI Microelectronics Tamil Nadu Chennai602105 India Parul Institute of Applied Sciences Parul University Research and Development Cell Department of Microbiology Gujarat Waghodia India Computer Science and Engineering Maharashtra Pune412115 India Institute of Technology Hawassa University Faculty of Manufacturing Department of Mechanical Engineering Ethiopia

ISBN: (纸本)9798350327533

More recent studies have concentrated on methods to improve the security and privacy of cloud operations for the benefit of user data. For example, in order to safeguard sensitive data kept by a cloud-deployed procedure, it is important to guarantee secure transmission of sensitive data across multiple stakeholders. Researchers have investigated deeply into the subject of cloud security concerns, which include data breaches, denial of service, data loss, service rejection, and threats from malicious users. These issues typically stem from problems like multi-tenancy, lack of control over data, and trust issues. Cloud providers are primarily responsible for ensuring the security of the cloud platform. This study proposes a CNN-BiLSTM-AM hybrid model that combines Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), and Attention Mechanism (AM). In order to determine how well our proposed hybrid model worked, this study tested it extensively against the traditional CNN and Long Short-Term Memory (LSTM) techniques. An established standard for evaluating intrusion detection systems, the CICIDS 2017 dataset was used in the study. The experimental results demonstrated that the proposed hybrid model outperformed the competition. The proposed hybrid model delivers the highest performance measure of accuracy (99.2%), detection rate (98.807%), and precision (99.59%). © 2024 IEEE.

关键词： Cardiovascular Disease Deep Learning Electrocardiogram Heartbeat Normalization

来源：评论

学校读者我要写书评

暂无评论

Simulation of thermoelectric coolers for optical electronic devices by means of optimal control methods 16

Simulation of thermoelectric coolers for optical electronic ...

引用

16th International Conference on Correlation Optics, COR 2023

作者： Kotsur, M. Vikhor, L. Institute of Applied-Physics and Computer Sciences Yuriy Fedkovych Chernivtsi National University Chernivtsi58012 Ukraine Inst. of Thermoelectricity of the Natl. Acad. of Sci. and Min. of Education and Science of Ukraine Chernivtsi58029 Ukraine

ISBN: (纸本)9781510671829

Thermoelectric coolers (TECs) are widely used to ensure a stable operating temperature of IR detectors, which are the main component of most optical electronic devices. Cooling improves such parameters of IR detectors as sensitivity, detectability, speed, range of spectral sensitivity, reliability, etc. TECs provide cooling on a temperature level of up to 190 K. Modern research is carried out in the directions of expanding the temperature range of the TEC and of increasing its coefficient of performance. The paper considers the use of optimal control theory in the simulation of TEC, matched with the parameters of the photodetector. The methods make it possible to determine the most suitable thermoelectric materials, optimal structure and optimal operation mode of TEC. Examples of TEC simulation for IR detectors by means of optimal control methods are given. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Thermoelectric equipment

来源：评论

学校读者我要写书评

暂无评论

Breakthroughs in Resource Management for Mobile, Wireless, and Ad-Hoc Network Architectures

Breakthroughs in Resource Management for Mobile, Wireless, a...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Devi, V.S. Anusuya Patro, E. Krishna Rao Nagpal, Amandeep Singh, Dev Vikram Lakshmi, B. Jabbar, Ahmed Sabah Abed AL-Zahra New Horizon College Of Engineering Departmento Of Applied Sciences Bangalore India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India Lovely Professional University Phagwara India Dxc Technologies India Mlr Institute Of Technology Department Of Computer Science And Engineering Telangana Hyderabad India College Of Medical Technology The Islamic University Medical Laboratory Technology Department Najaf Iraq

ISBN: (纸本)9798350366846

This research introduces a comprehensive suite of resource management algorithms tailored for mobile, wireless, and ad-hoc networks. The suite comprises the Dynamic Resource Allocation (DRA), Intelligent Energy-Aware Routing (IEAR), Predictive Spectrum Access (PSA), Secure Resource Allocation (SRA), and Quality of Service Enhancement (QoSE) algorithms, each addressing specific aspects crucial to network optimization. The DRA algorithm dynamically allocates resources by considering real-time demand, spectrum availability, and interference. Through an ablation study, it was revealed that each component, from real-time measurements to dynamic adjustments and iterative learning, significantly contributes to the algorithm's robustness and efficiency. The DRA algorithm excels in spectrum utilization, making it instrumental in enhancing the performance of wireless networks. A comparative evaluation against existing methods, although illustrated with dummy values for illustrative purposes, highlighted the superiority of the proposed suite. The proposed method consistently outperformed existing techniques across critical parameters such as throughput, energy efficiency, latency, scalability, QoS satisfaction, and various system attributes. Graphical representations further reinforced the promising nature of the proposed algorithms. Figures depicting throughput, latency, QoS satisfaction, and system attribute trends visually demonstrated the dominant performance of the proposed method in diverse network scenarios. In conclusion, this research presents a promising suite of resource management algorithms, offering advancements in spectrum utilization, energy efficiency, low latency, and overall network reliability. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Improving Quality of Service Using a Innovative Energy Effective Reinforcement Based Path Finding in Mobile Ad Hoc Network 2

Improving Quality of Service Using a Innovative Energy Effec...

引用

2nd International Conference on Computing and Data Analytics, ICCDA 2024

作者： Singaravelan, M. Saleem Raja, A. Thangam, S. School of Computing Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Avadi Chennai India College of Computing and information Sciences University of Technology and Applied Sciences Shinas Oman Amrita school of computing Department of computer science and engineering Bengaluru India

ISBN: (数字)9798331542573

ISBN: (纸本)9798331542573

RL stands for reinforcement learning, is a component of the broader field of machine learning. It provides a framework its features help to select an efficient action using previously learned information of interaction and its environment. Mobile nodes are grouped to form a network for communicating themselves termed autonomous network with mobile nodes (MANET). This is a dynamic and independent network requiring no administrative control. The mobile nodes in the network are to be part or apart at any time that causes the topology changes. The frequent topology changes make it hard to determine the destination route. The route discovery in the dynamic topology that consumes more node energy and, minimize the network lifetime. The energy usage and network lifetime are a vital part of the MANET. This paper proposes a new global routing protocol using a reinforcement learning algorithm called modified energy and signal strength Q-learning ad hoc on-demand distance vector algorithm (ESQAODV). This process conducts a result comparison to a local routing algorithm known as AODVSARSA. The proposed algorithm proved a better result with reference to average distribution ratio compared to the other, and complete delay metrics © 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

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：