检索结果-内蒙古大学图书馆

Robust Tracking Control of Piezoelectric Actuators Using Super-Twisting Sliding Mode With Bouc-Wen Hysteresis Model-Based Enhanced Jaya Algorithm

引用

IEEE ACCESS 2025年 13卷 15547-15555页

作者： Hang, Nguyen Thi Thu Son, Nguyen Ngoc Ind Univ Ho Chi Minh City Fac Elect Technol Ho Chi Minh City 700000 Vietnam Saigon Univ Fac Elect & Telecommun Ho Chi Minh City 700000 Vietnam

This paper introduces a Super-Twisting Sliding Mode Control (STSMC) strategy integrated with a Bouc-Wen hysteresis model for tracking control of the piezoelectric (PZT) actuator. The Bouc-Wen model, which captures the nonlinear hysteretic behavior of the PZT actuator, is estimated using a modified Jaya algorithm enhanced with L & eacute;vy flight distribution (called LeJaya). This modification improves the update mechanism by using L & eacute;vy flight distribution for better global search capabilities and employing an adaptive population scheme to optimize both exploration and exploitation. The STSMC with Bouc-Wen hysteresis is designed to overcome the chattering phenomenon and guarantee global asymptotic stability. The stability control of the PZT system is verified by Lyapunov's Law. Simulation results demonstrate the robustness and effectiveness of the proposed method in comparison to classical sliding mode control (SMC), neural sliding mode control (RBFSMC), and fuzzy sliding mode control (FuzzySMC), highlighting improved tracking performance and removed chattering phenomena. The proposed method offers a promising solution for precise and stable control of the PZT actuator in the presence of hysteresis.

关键词： Lead zirconate titanate Hysteresis Actuators computational modeling Mathematical models Sliding mode control Heuristic algorithms Optimization Uncertainty Asymptotic stability Bouc-Wen hysteresis piezoelectric actuator super-twisting algorithm high-order sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient STAR-RIS Enhanced UAV-Enabled MEC Networks With Bi-Directional Task Offloading

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第4期24卷 3258-3272页

作者： Xiao, Han Hu, Xiaoyan Zhang, Weile Wang, Wenjie Wong, Kai-Kit Yang, Kun Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China UCL Dept Elect & Elect Engn London WC1E 7JE England Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea Nanjing Univ State Key Lab Novel Software Technol Nanjing 210008 Peoples R China Nanjing Univ Suzhou Campus Sch Intelligent Software & Engn Suzhou 215163 Peoples R China Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ England

This paper introduces a novel multi-user mobile edge computing (MEC) scheme facilitated by a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) and a unmanned aerial vehicle (UAV). Unlike existing MEC approaches, the proposed scheme enables bi-directional offloading, allowing users to concurrently offload tasks to the MEC servers located at ground base station (BS) and UAV with the support of the STAR-RIS. To evaluate the effectiveness of the proposed MEC scheme, we first formulate an optimization problem aiming at maximizing the energy efficiency of the system while ensuring the quality of service (QoS) constraints by jointly optimizing the resource allocation, user scheduling, passive beamforming of the STAR-RIS, and the UAV trajectory. A block coordinate descent (BCD) iterative algorithm designed with the Dinkelbach's algorithm and the successive convex approximation (SCA) technique is proposed to effectively handle the formulated non-convex optimization problem characterized by significant coupling among variables. Simulation results indicate that the proposed STAR-RIS enhanced UAV-enabled MEC scheme possesses significant advantages in enhancing the system energy efficiency over other baseline schemes including the conventional RIS-aided scheme.

关键词： Autonomous aerial vehicles Servers Wireless communication Optimization Vectors Relays computational modeling Bidirectional control Base stations Technological innovation STAR-RIS unmanned aerial vehicle (UAV) mobile edge computing (MEC) energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Rotated Object Detection Model With Feature Redundancy Optimization for Coronary Athero-Sclerotic Plaque Detection

引用

IEEE ACCESS 2025年 13卷 48431-48448页

作者： Hao, Xue Hamed, Haza Nuzly Abdull Su, Qichen Dai, Xin Deng, Linqiang Univ Teknol Malaysia UTM Fac Comp Johor Baharu 81310 Johor Malaysia Shanxi Agr Univ Fac Software Jinzhong 030600 Shanxi Peoples R China

Coronary atherosclerotic plaques are a major cause of cardiovascular disease (CVD). Although there have been significant advancements in plaque-assisted diagnosis by deep learning methods utilizing intravascular optical coherence tomography (IVOCT), images still contain redundant features, including residual blood, thrombus, and extensive black backgrounds. Furthermore, the feature fusion process produces redundant information. These redundant features interfere with plaque feature extraction, resulting in decreased performance and increased computational complexity. Current methods for addressing redundant features rely mostly on simple feature selection or reduction methods, overlooking the significance of redundant features in model training. The Redundancy Feature Diminishment Strategy (RFDS) is designed to address this issue by dynamically adjusting the importance of redundant features during the training process. Meanwhile, RFDS is introduced into spatial and channel reconstruction convolution (SCConv) to form the enhancement structure RFDS-SCConv, which refines feature extraction by adaptively regulating redundant features in both spatial and channel dimensions. Based on RFDS-SCConv, a lightweight plaque detection framework, YOLO-Plaque, is proposed. RFDS-SCConv and FasterBlock are integrated into the framework to substantially reduce the interference of redundant features during feature extraction and fusion. This study evaluates the robustness of the YOLO-Plaque model by tenfold cross-validation utilizing 2504 IVOCT images collected from a collaborative project between the School of Software at Shanxi Agricultural University and Shanxi Provincial Coal Centre Hospital. Experimental results demonstrate that YOLO-Plaque performs better than existing plaque detection models while remaining lightweight. The vital metric mAP50 has increased by 3.59% reaching 91.23%, while GFLOPs and parameters decreased to 7.2 and 2.55M, respectively.

关键词： Feature extraction Redundancy Convolution Training Interference computational modeling Termination of employment Atherosclerosis Accuracy Robustness Feature redundancy coronary atherosclerotic plaques detection and intravascular optical coherence tomography (IVOCT)

来源：评论

学校读者我要写书评

暂无评论

Hiba: Hierarchical High-Performance Blockchain Architecture

引用

IEEE TRANSACTIONS ON NETWORKING 2025年第1期33卷 311-326页

作者： Obiri, Isaac Amankona Gao, Jianbin Xia, Qi Xia, Hu Cobblah, Christian Nii Aflah Univ Elect Sci & Technol China UESTC Shenzhen Inst Adv Study Sch Comp Sci & Engn Sch Cyber Secur Chengdu 611731 Peoples R China Univ Elect Sci & Technol China UESTC Blockchain Res Inst Chengdu 611731 Peoples R China Jiaozi Financial Holding Grp Co Ltd Chengdu 610095 Peoples R China

Sharding has the potential to overcome the scalability constraints of monolithic blockchains. However, some challenges are associated with sharding, such as optimizing the placement of transactions into shards to minimize cross-shard transactions, balancing workload as shard capacity increases, and identifying shards that process transactions maliciously. To address these challenges, we propose a hierarchical high-performance blockchain (Hiba) architecture. Hiba leverages inter-shard to facilitate cross-shard consensus, where a pre-selected subset of nodes from both transaction originating and receiving shards collaboratively participate in the validation process. This design ensures the validity of transactions and mitigates double-spending risks across various shards. Simultaneously, it reduces validation costs by eliminating the need for all nodes in both shards to actively participate in the consensus process. Additionally, Hiba implements a novel multi-tiered validation system. Following initial validation at the intra-shard and inter-shard levels, a subset of randomly chosen or suspicion-based transactions undergoes further validation through auxiliary consensus. This auxiliary consensus acts as a secondary validation layer, ensuring the integrity of the intra-shard/inter-shard consensus process. To improve transaction processing efficiency, we implement an optimized workload distribution scheme based on fitness functions to minimize the number of cross-shard transactions. The experimental results demonstrate that Hiba surpasses the existing works regarding throughput and latency.

关键词： Blockchains Sharding Scalability Security Throughput Bitcoin Costs Optimization Delays computational modeling Hierarchical blockchain sharding scalability intra-consensus inter-consensus cross-shard transactions

来源：评论

学校读者我要写书评

暂无评论

Online Scheduling for Multi-Access in Space-Air-Ground Integrated Networks Using iGNNSeq-Enhanced Reinforcement Learning

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第3期74卷 4774-4787页

作者： Xie, Yuejiao Wu, Qianqian Niu, Guanchong Pun, Man-On Han, Zhu Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Peoples R China Xidian Univ Guangzhou Inst Technol Guangzhou 510555 Peoples R China Univ Houston Dept Elect & Comp Engn Houston TX 77004 USA Kyung Hee Univ Dept Comp Sci & Engn Seoul 446701 South Korea

Space-air-ground integrated networks (SAGINs) have become a key area of research, representing a cutting-edge architectural concept for sixth-generation (6G) networks aimed at achieving ubiquitous connectivity. This paper focuses on the challenge of online access scheduling across multiple platforms. Specifically, when multiple users randomly enter the network and request access through high-altitude platform (HAP) relays, the system must make real-time decisions on whether to grant or deny access, while considering the connections between HAPs and low-Earth orbit (LEO) satellites. By explicitly modelingthe data collection process and the workload associated with transmission tasks, we formulate the multi-access scheduling challenge as a mixed-integer programming (MIP) problem, which presents high computational complexity. Given the practical system's lack of prior knowledge about user attributes, such as arrival times and channel conditions, we propose a deep reinforcement learning (DRL)-based model for real-time decision-making. To enhance feature extraction within the DRL architecture, we introduce a graph neural network (GNN)-based encoder, and employ a sequence-to-sequence (Seq2Seq) module to manage the exponential increase in action space resulting from simultaneous decisions on multiple access requests. Extensive simulations demonstrate that the integrated GNN and Seq2Seq (iGNNSeq)-enhanced RL achieves performance comparable to offline solutions while significantly reducing computational complexity.

关键词： Satellites Low earth orbit satellites Costs computational modeling Satellite broadcasting Resource management Relays Heuristic algorithms Computer architecture Vehicle dynamics Deep reinforcement learning (DRL) graph neural networks (GNNs) online access scheduling sequence to sequence (Seq2Seq) space-air-ground integrated networks (SAGINs)

来源：评论

学校读者我要写书评

暂无评论

Sparsified Random Partial Model Update for Personalized Federated Learning

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第4期24卷 3076-3091页

作者： Hu, Xinyi Chen, Zihan Feng, Chenyuan Min, Geyong Quek, Tony Q. S. Yang, Howard H. Zhejiang Univ JU UIUC Inst Haining 314400 Peoples R China Singapore Univ Technol & Design Informat Syst Technol & Design Pillar Singapore City 487372 Singapore Eurecom F-06410 Sophia Antipolis France Univ Exeter Dept Comp Sci Exeter EX4 4QF England

Federated Learning (FL) stands as a privacy-preserving machine learning paradigm that enables collaborative training of a global model across multiple clients. However, the practical implementation of FL models often confronts challenges arising from data heterogeneity and limited communication resources. To address the aforementioned issues simultaneously, we develop a Sparsified Random Partial Update framework for personalized Federated Learning (SRP-pFed), which builds upon the foundation of dynamic partial model updates. Specifically, we decouple the local model into personal and shared parts to achieve personalization. For each client, the ratio of its personal part associated with the local model, referred to as the update rate, is regularly renewed over the training procedure via a random walk process endowed with reinforced memory. In each global iteration, clients are clustered into different groups where the ones in the same group share a common update rate. Benefiting from such design, SRP-pFed realizes model personalization while substantially reducing communication costs in the uplink transmissions. We conduct extensive experiments on various training tasks with diverse heterogeneous data settings. The results demonstrate that the SRP-pFed consistently outperforms the state-of-the-art methods in test accuracy and communication efficiency.

关键词： Training Servers computational modeling Data models Mobile computing Federated learning Context modeling Optimization Adaptation models Convergence Client clustering convergence rate personalized federated learning sparsification

来源：评论

学校读者我要写书评

暂无评论

TinyAP: An Intelligent Access Point to Combat Wi-Fi Attacks Using TinyML

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第2期12卷 2135-2145页

作者： Agrawal, Anand Maiti, Rajib Ranjan Birla Inst Technol & Sci Pilani Dept CSIS Hyderabad Campus Secunderabad 500078 India

In the recent past, there has been a significant surge in MAC layer Wi-Fi attacks, leaving wireless local area networks (WLANs) vulnerable to different types of network intrusions. The current routers cum access point (AP) lack the necessary intelligence to prevent or combat these attacks, thereby making it imperative to rely on various network intrusion detection systems. To address this issue, we have developed an intelligent AP that can identify different MAC layer attacks and generate alerts as required. This has been achieved using lightweight machine learning (ML) models on a microcontroller, leveraging the TensorFlow-lite-micro (TFLite Micro) libraries. A framework called TinyAP has been developed, which uses the efficient neural architecture search (NAS) and the lightweight to classify Wi-FI attack at the AP level. The system consists of a Raspberry Pi 3 B+, functioning as an AP and an Arduino Nano 33 BLE Sense acting as a plugin. The Nano module executes pretrained Tiny ML (TinyML) models, where the models are prepared (i.e., searched, trained and converted) on a Desktop PC (DESKTOP-47M82UC). We employed NAS for multilevel perceptrons (MLPNAS) to generate the five best neural architecture models to deploy on the system. To test the efficacy of this innovative approach, an online data set containing 13 different Wi-Fi-labeled attacks has been used. TinyAP has achieved an average accuracy of 96.45% for all the Wi-Fi attacks and a maximum accuracy of 100% in the 2 Class (2C) classification for some of the Wi-Fi attacks like key reinstallation attack and Kr00k. Additionally, TinyAP has also shown a maximum accuracy of 95.19% in multiclass classification. The average accuracy of TinyAP shows a marginal reduction of 0.76% in 2C classification and 0.04% in multiclass classification when compared with multilayer perceptron (MLP) models. The promising result of the TinyAP is that it provides a much-needed layer of protection for networks and offers a proactive secur

关键词： Wireless fidelity Accuracy Monitoring Internet of Things computational modeling Wireless communication Neural architecture search for multilevel perceptrons (MLPNAS) Tiny machine learning (TinyML) Wi-Fi Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Simulation Optimization of Spatiotemporal Dynamics in 3D Geometries

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 10442-10456页

作者： Yao, Bing Leonelli, Fabio Yang, Hui Univ Tennessee Knoxville Dept Ind & Syst Engn Knoxville TN 37996 USA James A Haley Vet Hosp Cardiac Electrophysiol Lab Tampa FL 33620 USA Penn State Univ Harold & Inge Marcus Dept Ind & Mfg Engn University Pk PA 16802 USA

Many engineering and healthcare systems are featured with spatiotemporal dynamic processes. The optimal control of such systems often involves sequential decision making. However, traditional sequential decision-making methods are not applicable to optimize dynamic systems that involves complex 3D geometries. Simulation modeling offers an unprecedented opportunity to evaluate alternative decision options and search for the optimal plan. In this paper, we develop a novel simulation optimization framework for sequential optimization of 3D dynamic systems. We first propose to measure the similarity between functional simulation outputs using coherence to assess the effectiveness of decision actions. Second, we develop a novel Gaussian Process (GP) model by constructing a valid kernel based on Hausdorff distance to estimate the coherence for different decision paths. Finally, we devise a new Monte Carlo Tree Search (MCTS) algorithm, i.e., Normal-Gamma GP MCTS (NG-GP-MCTS), to sequentially optimize the spatiotemporal dynamics. We implement the NG-GP-MCTS algorithm to design an optimal ablation path for restoring normal sinus rhythm (NSR) from atrial fibrillation (AF). We evaluate the performance of NG-GP-MCTS with spatiotemporal cardiac simulation in a 3D atrial geometry. Computer experiments show that our algorithm is highly promising for designing effective sequential procedures to optimize spatiotemporal dynamics in complex geometries. Note to Practitioners-This article proposes a novel simulation optimization framework for sequential decision making to optimize spatiotemporal dynamics in complex geometries. This framework incorporates the advantage of Bayesian modeling and Gaussian Process inference into Monte-Carlo tree search to effectively solve the sequential optimization problem. It has significant potential to contribute to the emerging discipline of computational engineering and medicine, and further realize precision control/treatment planning in various manu

关键词： Spatiotemporal phenomena Optimization Three-dimensional printing Geometry Heuristic algorithms Decision making computational modeling Solid modeling Planning Numerical models Simulation optimization Monte-Carlo tree search Gaussian process Bayesian analysis sequential decision making spatiotemporal dynamic systems

来源：评论

学校读者我要写书评

暂无评论

Semantic-DARTS: Elevating Semantic Learning for Mobile Differentiable Architecture Search

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第2期12卷 1673-1687页

作者： Guo, Bicheng He, Shibo Shi, Miaojing Yu, Kaicheng Chen, Jiming Shen, Xuemin Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Zhejiang Peoples R China Univ Waterloo Dept Elect & Comp Engn Waterloo ON N2L 3G1 Canada Tongji Univ Coll Elect & Informat Engn Shanghai 200092 Peoples R China Westlake Univ Sch Engn Hangzhou 310031 Zhejiang Peoples R China

Differentiable architecture search (DARTS) is a prevailing direction in automatic machine learning, but it may suffer from performance collapse and generalization issues. Recent efforts mitigate them by integrating regularization into architectural parameters or rule-based operations selection. These efforts primarily emphasize learning the global class-specific features through the image classification task, while overlooking the fine-grained local information during the search process. In this article, we take the first trial to observe that three semantic challenges arise from the classification-based DARTS: 1) inaccurate class-specific features;2) partial target attention;and 3) blurred semantic regions. To tackle them in one shot, we propose Semantic-DARTS, combining the masked image modeling (MIM) paradigm with the classification task to incorporate local semantic information into the architecture search. Specifically, we design a lightweight reconstruction head that recovers the corrupted image based on the condensed latent feature, which learns both the local semantics and their relationship patch-wisely. Simultaneously, the concurrent classification head strengthens the connection between the global category of the target and the local semantics of their parts. As evidenced by our experiments, the proposed approach achieves state-of-the-art results on CIFAR-10, CIFAR-100, and ImageNet. Furthermore, the searched model is not only able to improve global class-specific features but also to capture fine-grained local representations, improving both the classification performance and the generalization ability.

关键词： Semantics Computer architecture Internet of Things Training computational modeling Self-supervised learning Search problems Masked image modeling (MIM) neural architecture search (NAS) self-supervised learning semantic learning

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Enhanced Object Detection for Sustainable Agriculture

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 728-740页

作者： Djenouri, Youcef Belbachir, Ahmed Nabil Michalak, Tomasz Belhadi, Asma Srivastava, Gautam Univ South Eastern Norway Norwegian Res Ctr N-3199 Oslo Norway IDEAS NCBR PL-00801 Warsaw Poland Norwegian Res Ctr N-5008 Grimstad Norway Warsaw Univ PL-00927 Warsaw Poland OsloMet Univ N-0167 Oslo Norway Brandon Univ Dept Math & Comp Sci Brandon MB R7A 6A9 Canada China Med Univ Res Ctr Interneural Comp Taichung 40402 Taiwan Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 India Chitkara Univ Rajpura 140401 India

The integration of autonomous aerial vehicles (AAVs) in agriculture has advanced precision farming by enhancing the ability to monitor and optimize agricultural plots. Object detection-critical for identifying crops, pests, and diseases-presents challenges due to data availability and varying environmental conditions. To address these challenges, we propose a Deep Learning framework tailored to agricultural contexts, utilizing domain-specific knowledge from AAV imagery. Our framework uses a knowledge base of visual features and loss values from multiple deep-learning models during the training phase to choose the most effective model for the testing phase. This approach improves model adaptability and accuracy across diverse agricultural scenarios. Evaluated on a comprehensive dataset of AAV-captured images covering various crop types and conditions, our model shows superior performance compared to state-of-the-art techniques. This demonstrates the value of integrating domain knowledge into deep learning for enhancing object detection, ultimately advancing agricultural efficiency, supporting sustainable resource management, and reducing environmental impact.

关键词： Deep learning Crops Autonomous aerial vehicles YOLO Feature extraction Accuracy computational modeling Data models Adaptation models Resource management Agriculture knowledge guided deep learning object detection remote sensing sustainability

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：