检索结果-内蒙古大学图书馆

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

Journal of computer science & Technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 25000China Institute of Information Technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

来源：评论

学校读者我要写书评

暂无评论

Dynamic Optimal Power Flow Method based on Reinforcement learning for Offshore Wind Farms Considering Multiple Points of Common Coupling

引用

Journal of Modern Power systems and Clean Energy 2024年第6期12卷 1749-1759页

作者： Yang Fu Zixu Ren shurong Wei Lingling Huang Fangxing Li Yang Liu Engineering Research Center of Offshore Wind Technology Ministry of Education(Shanghai University of Electric Power) Shanghai 200090China Department of Electrical Power Engineering Shanghai University of Electric PowerShanghai 200090China Department of Electrical Engineering and Computer Science The University of TennesseeKnoxvilleTN 37996USA

The widespread adoption of renewable energy sources presents significant challenges for power system *** paper proposes a dynamic optimal power flow(DOPF)method based on reinforcement learning(RL)to ad-dress the dispatching *** proposed method consid-ers a scenario where large-scale offshore wind farms are inter-connected and have access to an onshore power grid through multiple points of common coupling(PCCs).First,the opera-tional area model of the offshore power grid at the PCCs is es-tablished by combining the prediction results and the transmis-sion capacity limit of the offshore power *** upon this,a dynamic optimization model of the power system and its RL en-vironment are constructed with the consideration of offshore power dispatching ***,an improved algorithm based on the conditional generative adversarial network(CGAN)and the soft actor-critic(sAC)algorithm is *** analyzing an improved IEEE 118-node system,the proposed method proves to have the advantage of economy over a longer *** resulting strategy satisfies power system opera-tion constraints,effectively addressing the constraint problem of action space of RL,and it has the added benefit of faster so-lution speeds.

关键词： Offshore power grid optimal scheduling dy-namic optimal power flow(DOPF) reinforcement learning(RL) renewable energy

来源：评论

学校读者我要写书评

暂无评论

Improved Manta Ray Foraging Optimizer-based sVM for Feature selection Problems:A Medical Case study

引用

Journal of Bionic Engineering 2024年第1期21卷 409-425页

作者： Adel Got Djaafar Zouache Abdelouahab Moussaoui Laith Abualigah Ahmed Alsayat Faculty of informatics University of Science and Technology Houari BoumedieneAlgiersAlgeria LRIA Laboratory University of Science and Technology Houari BoumedieneAlgiersAlgeria Computer Science Department University of Mohamed El Bachir El IbrahimiBordj Bou ArreridjAlgeria Computer Science Department University of Ferhat AbbasSetifAlgeria Computer Science Department Prince Hussein Bin Abdullah Faculty for Information TechnologyAl al-Bayt UniversityMafraq 25113Jordan Department of Computer Science College of Computer and Information SciencesJouf UniversityJoufSaudi Arabia Department of Electrical and Computer Engineering Lebanese American University13-5053ByblosLebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman 19328Jordan MEU Research Unit Middle East UniversityAmman 11831Jordan Applied science research center Applied science private universityAmman 11931Jordan School of Computer Sciences Universiti Sains Malaysia11800 PenangMalaysia School of Engineering and Technology Sunway University Malaysia27500 Petaling JayaMalaysia

support Vector Machine(sVM)has become one of the traditional machine learning algorithms the most used in prediction and classification ***,its behavior strongly depends on some parameters,making tuning these parameters a sensitive step to maintain a good *** the other hand,and as any other classifier,the performance of sVM is also affected by the input set of features used to build the learning model,which makes the selection of relevant features an important task not only to preserve a good classification accuracy but also to reduce the dimensionality of *** this paper,the MRFO+sVM algorithm is introduced by investigating the recent manta ray foraging optimizer to fine-tune the sVM parameters and identify the optimal feature subset *** proposed approach is validated and compared with four sVM-based algorithms over eight benchmarking ***,it is applied to a disease Covid-19 *** experimental results show the high ability of the proposed algorithm to find the appropriate sVM’s parameters,and its acceptable performance to deal with feature selection problem.

关键词： support vector machine Parameters tuning Feature selection Bioinspired algorithms Manta ray foraging optimizer

来源：评论

学校读者我要写书评

暂无评论

Predicting the success Rate of Reward-based Crowdfunding Campaigns: Evidence from Machine learning

引用

International Journal of Information and Management sciences 2023年第3期34卷 179-191页

作者： Chan, Chia-Ling Lee, Yen-sheng Research Division VI Taiwan Institute of Economic Research Taiwan Davis School of Business Colorado Mesa University United States

Prior research argues that the characteristics of crowdfunding campaigns affect their success rate. We examine this further to understand whether success in funding projects can be predicted by associated project characteristics. We apply machine learning to classify reward-based projects in the *** market. specifically, we construct three classification tree-based models and provide evidence that the proposed machine learning models have a strong out-of-sample predictive power over the probability of fundraising success. In addition, the robustness check through both logistic regression and propensity score matching approaches confirms that project characteristics, except for those linked to venture capital, are among the factors behind crowdfunding campaign success. This study can assist entrepreneurs in understanding the impact of project characteristics on the crowdfunding success rate. © 2023, Tamkang University. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

PBRL-TChain: A performance-enhanced permissioned blockchain for time-critical applications based on reinforcement learning

引用

Future Generation computer systems 2024年 154卷 301-313页

作者： Zhang, Yiguang Lin, Junxiong Lu, Zhihui Duan, Qiang Huang, shih-Chia School of Computer Science Fudan University Shanghai200433 China Information Sciences & Technology Department Pennsylvania State University AbingtonPA United States Shanghai Blockchain Engineering Research Center Shanghai China Department of Electronic Engineering National Taipei University of Technology Taiwan

Permissioned blockchains can provide high security and reliability for various Internet of Things (IoT) systems, such as smart healthcare and vehicular networks. However, the performance issues of permissioned blockchains have been a constraint for fully supporting time-critical tasks with tight requirements of low latency and high throughput. This paper proposes PBRL-TChain, a performance-enhanced permissioned blockchain for time-critical applications based on deep reinforcement learning (DRL). First, we propose a priority ordering mechanism to minimize latency and maximize reliability. Then, we design a fast retransmission mechanism to alleviate the impact of transaction conflicts on the latency performance. Finally, we propose a DRL-based dynamic adjustment method in PBRL-TChain to achieve better performance and reliability. Experiments show that our method outperforms existing methods. Compared with Fabric++ and Athena, it can reduce the latency of time-critical transactions by 10 times, achieving a level of 10 ms, significantly improving the system's performance and reliability. © 2023 Elsevier B.V.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

WPD-ResNest:substation station Level Network Anomaly Traffic Detection based on Deep Transfer learning

引用

CsEE Journal of Power and Energy systems 2024年第6期10卷 2610-2620页

作者： Ting Yang Yucheng Hou Yachuang Liu Feng Zhai Rongze Niu Key Laboratory of Smart Grid of Ministry of Education Tianjin UniversityTianjin 300072China China Electric Power Research Institute Beijing 100192China Henan Electric Power Research Institute Zhengzhou 450052China

With the advancement of new infrastructures,the digitalization of the substation communication network has rapidly increased,and its information security risks have become increasingly *** and reliable substation communication network flow models and flow anomaly detection methods have become an important means to prevent network security problems and identify network *** existing substation network analyzers and flow anomaly detection algorithms are usually based on threshold determination,which cannot reflect the inherent characteristics of substation automation flow based on IEC 61850 and have low detection *** effectively detect abnormal traffic,this paper fully explores the substation network traffic rules,extracts the frequency domain features of the station level network,and designs an abnormal traffic identification model based on the ResNest convolutional neural *** learning is used to solve the problem of insufficient abnormal traffic labeled samples in the ***,a new method of abnormal traffic detection in smart substation station level communication networks based on deep transfer learning is *** T1-1 substation communication network is constructed on OPNET for abnormal simulations,and the actual network traffic in a 110kV substation is fused with CIC DDos2019 and KDD99 data sets for the algorithm performance test,*** accuracy reached is 98.73%and 98.95%,indicating that the detection model proposed in this paper has higher detection accuracy than existing algorithms.

关键词： Anomaly traffic detection deep learning substation station level communication network traffic model

来源：评论

学校读者我要写书评

暂无评论

Decoupled knowledge distillation method based on meta-learning

引用

High-Confidence Computing 2024年第1期4卷 1-6页

作者： Wenqing Du Liting Geng Jianxiong Liu Zhigang Zhao Chunxiao Wang Jidong Huo Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250014China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250014China Aerospace Science&Industry Network Information Development Co. LTDBeijing 100854China

With the advancement of deep learning techniques,the number of model parameters has been increasing,leading to significant memory consumption and limits in the deployment of such models in real-time *** reduce the number of model parameters and enhance the generalization capability of neural networks,we propose a method called Decoupled MetaDistil,which involves decoupled *** method utilizes meta-learning to guide the teacher model and dynamically adjusts the knowledge transfer strategy based on feedback from the student model,thereby improving the generalization ***,we introduce a decoupled loss method to explicitly transfer positive sample knowledge and explore the potential of negative samples *** experiments demonstrate the effectiveness of our method.

关键词： Model compression Knowledge distillation Meta-learning Decoupled loss

来源：评论

学校读者我要写书评

暂无评论

Recent advancements in driver’s attention prediction

引用

Multimedia Tools and Applications 2025年第12期84卷 10969-11000页

作者： Moradi, Morteza Palazzo, simone Rundo, Francesco spampinato, Concetto Department of Electrical Electronics and Computer Engineering University of Catania Catania95124 Italy STMicroelectronics ADG Research and Development Power and Discretes Catania95121 Italy

Ensuring the precise anticipation of a driver’s attention is crucial for upholding safety in diverse human-centric transportation scenarios. This capability proves invaluable for discerning and evaluating accident risks in driver assistance systems, as well as in autonomous driving scenarios. Beyond traditional approaches that consider contextual variables and non-visual cues, such as the driver’s mental state and brain activity patterns, recent groundbreaking advancements in deep learning-based computer vision have propelled the momentum of visual attention prediction. The fundamental concept behind these techniques is to replicate the human visual system’s ability to identify critical objects or regions capturing a driver’s attention. Notably, the integration of salient object detection and attention mechanisms has gained popularity across various application domains. This paper provides a comprehensive overview of the current state of the art in this field. The primary focus of the study is to explore the architectures and workflows of deep learning-based models dedicated to the attention prediction process. To achieve this, we examine recent works in the field, specifically selecting those that have leveraged (simulated) attention mechanisms to estimate the driver’s attention area. Our analysis delves into the contributions of each model, elucidating their architectural design and underlying organization. Additionally, we scrutinize the effectiveness of each model by explaining the reported experimental results. © The Author(s), under exclusive licence to springer science+Business Media, LLC, part of springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Graphene-based dual-function acoustic transducers for machine learning-assisted human-robot interfaces

引用

InfoMat 2023年第2期5卷 66-79页

作者： Hao sun Xin Gao Liang-Yan Guo Lu-Qi Tao Zi Hao Guo Yangshi shao Tianrui Cui Yi Yang Xiong Pu Tian-Ling Ren Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijingPeople's Republic of China CAS Center for Excellence in Nanoscience Beijing Key Laboratory of Micro-nano Energy and SensorBeijing Institute of Nanoenergy and NanosystemsChinese Academy of SciencesBeijingPeople's Republic of China State Key Laboratory of Power Transmission Equipment and System Security and New Technology School of Electrical EngineeringChongqing UniversityChongqingPeople's Republic of China School of Computer Science&Technology Beijing Institute of TechnologyBeijingPeople's Republic of China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijingPeople's Republic of China

Human–robot interface(HRI)electronics are critical for realizing robotic ***,we report graphene-based dual-function acoustic transducers for machine learning-assisted human–robot interfaces(GHRI).The GHRI functions both an artificial ear through the triboelectric acoustic sensing mechanism and an artificial mouth through the thermoacoustic sound emission *** success of the integrated device is also attributed to the multifunctional laser-induced graphene,as either triboelectric materials,electrodes,or thermoacoustic *** systematically optimizing the structure parameters,the GHRI achieves high sensitivity(4500 mV Pa^(–1))and operating durability(1000000 cycles and 60 days),capable of recognizing speech identities,emotions,content,and other information in the human *** the assistance of machine learning,30 speech categories are trained by a convolutional neural network,and the accuracy reaches 99.66%and 96.63%in training datasets and test ***,GHRI is used for artificial intelligence communication based on recognized speech *** work shows broad prospects for the development of robotic intelligence.

关键词： human-robot interface laser-induced graphene machine learning thermoacoustic triboelectric nanogenerator

来源：评论

学校读者我要写书评

暂无评论

Improving adherence to medication in an intelligent environment using reinforcement learning

引用

Journal of Reliable Intelligent Environments 2025年第1期11卷 1-10页

作者： Ismail, Ahsan Naeem, Muddasar Khalid, Umamah Bint Abbas, Musarat Department of Electronics Quaid-i-Azam University Islamabad Pakistan Research Center on ICT Technologies for Healthcare and Wellbeing Università Telematica Giustino Fortunato Benevento Italy

Correct and timely medication plays an important role in the treatment and recovery of a patient. Poor health outcomes are associated with the nonadherence to medication which also increases health care costs for patients and society. The medication process can be difficult for many patients such as dementia patients who face the challenge of forgetfulness in medication intake. Therefore, an intelligent and efficient patient engagement environment ensures enduring health and positive clinical outcomes. such an intelligent system can be realized employing reinforcement learning (RL) which brought significant impacts in many areas, and has useful applications in healthcare as well. This work introduces an RL-based intelligent environment that can engage the patient to improve adherence, through proper engagement alerts based on user adherence reports, and suggest him/her to improve the adherence by sending the engagement message to the user. The intelligent RL agent decides the optimal decision to send the engagement message to the user based on a patient’s behavior. The proposed system could be useful to improve adherence to medication and assist the patient in accurately following his/her medication schedule. However, the proposed system would require integration with actual patient data and electronic health records before real-world deployment. © The Author(s), under exclusive licence to springer Nature switzerland AG 2024.

关键词： Intelligent environment Medical treatment Medication adherence optimization Medication error Reinforcement 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：