检索结果-内蒙古大学图书馆

Leaders and Collaborators: Addressing Sparse Reward Challenges in Multi-Agent Reinforcement Learning

IEEE TRANSACTIONS ON EMERGING TOPICS IN computational INTELLIGENCE 2025年第2期9卷 1976-1989页

作者： Sun, Shaoqi Liu, Hui Xu, Kele Ding, Bo Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410003 Peoples R China

Cooperative multi-agent reinforcement learning (MARL) has emerged as an effective tool for addressing complex control tasks. However, sparse team rewards present significant challenges for MARL, leading to low exploration efficiency, slow learning speed, and homogenized behaviors among agents. To address these issues, we propose a novel Leader-Collaborator (LC) MARL framework inspired by human social collaboration. The LC framework introduces parallel online knowledge distillation for policy networks (KDPN). KDPN extracts knowledge from two policy networks with different training objectives: one aims to maximize individual rewards, while the other aims to maximize team rewards. The extracted knowledge is utilized to construct team leaders and collaborators. By effectively balancing individual and team rewards, our approach enhances exploration efficiency and promotes behavioral diversity among agents. This addresses the issue of low learning efficiency caused by the lack of objectives early in the agent's learning process and facilitates the development of more effective and differentiated team interaction policies. Additionally, we present the Self-Repairing Strategy (SRS) and Self-Augmenting Strategy (SAS) to facilitate team policies learning while preserving the initial team goal. We evaluate the effectiveness of the LC framework by conducting extensive experiments on the Multi-Agent Particle Environment (MPE), the Google Research Football (GRF), and StarCraft Multi-Agent Challenge (SMAC) with varying levels of difficulty. Our experimental results demonstrate that LC significantly improves the efficiency of the agent's exploration, achieves state-of-the-art performance, and accelerates the learning of the optimal policy. Specifically, in the SMAC scenarios, our method increases the winning rate by 21.9%, increases the average cumulative reward by 12%, and reduces the training time by 57% to achieve optimal performance.

关键词： computational modeling Training Reinforcement learning Sports Knowledge engineering computational intelligence Teamwork Sun Standards Predictive models Multi-agent reinforcement learning sparse rewards online knowledge distillation exploration efficiency

来源：评论

学校读者我要写书评

暂无评论

MISOCP Model for Reactive Power Optimization With Nonuniform Voltage Regulators in Unbalanced Three-Phase Active Distribution Networks

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 10118-10129页

作者： Mu, Chenggang Ding, Tao Wang, Shunqi Jia, Wenhao Shahidehpour, Mohammad Luo, Zhao Xi An Jiao Tong Univ Sch Elect Engn Xian 710049 Shaanxi Peoples R China IIT Dept Elect & Comp Engn Chicago IL 60616 USA Kunming Univ Sci & Technol Sch Elect Engn Kunming 650500 Yunnan Peoples R China

Reactive power optimization (RPO) is a key task in the operation and control of active distribution networks (ADNs). The nonlinear power flow constraints and the integers introduced by voltage regulator (VR) constraints make the nonconvex RPO model difficult to solve. In this paper, a RPO model is proposed considering the nonuniform tap ratios of VRs. The three phases in VRs are independently controlled and the phase coupling effects are strictly considered. Moreover, to deal with the bilinear relationship among continuous complex voltage phasors and discrete tap ratios, the voltage phasor matrix is decoupled into real and imaginary parts, and a status variable method is proposed to exactly linearize the bilinear terms. Further, the nonlinear power flow constraints are relaxed to a set of second-order cone constraints without neglecting the coupling effect among the three phases and are proved to be equivalent to the semi-definite constraints, which does not require the rank-1 verification and is more efficient and scalable. Thus, the original nonconvex RPO for three-phase unbalanced ADNs is simplified to a mixed-integer second-order cone programming (MISOCP) model. Case studies validate the model's effectiveness, and the computational efficiency meets practical requirements. Note to Practitioners-This paper simplifies the complex problem of reactive power optimization for active distribution networks with unbalanced three-phase power flows. We offer a novel RPO model improving the typically nonconvex and nonlinear optimal power flow problem, and addressing the particular challenges imposed by voltage regulators optimization with nonuniform tap ratios. Independent control of the VR phases and accurate incorporation of phase coupling effects have been realized, greatly simplifying the optimization process. The transformation of nonlinear power flow constraints into a computationally efficient set of second-order cone constraints eliminates the need for cumbersome ran

关键词： Reactive power Programming Vectors Voltage control Optimization Load flow computational modeling Static VAr compensators Regulators MISO Reactive power optimization active distribution network three-phase unbalance nonuniform voltage regulator mixed-integer second-order cone programming

来源：评论

学校读者我要写书评

暂无评论

Signal Processing-Free Intelligent Model for Power Quality Disturbances Identification

引用

IEEE ACCESS 2025年 13卷 9910-9922页

作者： Al-Mashdali, Mohammed F. Islam, Asif Hassan, Abdulbasit Shafiullah, Md Al-Dhaifallah, Mujahed Al Fuwail, Khalid King Fahd Univ Petr & Minerals Elect Engn Dept Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals Interdisciplinary Res Ctr Sustainable Energy Syst Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals High Voltage Lab Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals Control & Instrumentat Engn Dept Dhahran 31261 Saudi Arabia Air Force Inst Technol Kaduna Nigeria

Integrating different types of renewable energy sources in the power system substantially challenges the power quality (PQ), directly affecting the system's stability and service life span. The rise of power quality disturbances (PQD) generates irregularities in voltage and current waveforms, harming smart grid networks and linked devices. Traditional methods for PQD classification use complicated feature extraction techniques, which can be computationally expensive and lack scalability. This research proposes applying basic convolutional neural network (CNN) models for automated PQD detection and categorization as a prospective solution to these issues. By directly examining PQD images generated from signal data, these models reduce the requirement for human-crafted features. The study analyzes alternative CNN setups, training datasets, and disturbance types to measure model performance. The results demonstrate that these simple CNN models maintain stable accuracy values in normal and noisy environments, even with increasing classes and noise, the models managed to maintain a high-performance level with up to 99.39% accuracy for 17 classes when the Adam optimizer was used instead of RMSprop. The models could deal with noise-related disturbances, still achieving accuracy as high as 96.42% when trained by just 50% of the dataset under 30dB SNR (Signal to Noise Ratio) conditions. Moreover, comparing the two frequencies on 50Hz and 60Hz performance does not show the equivalent models' robustness over different operating levels. This study highlights the potential of CNNs in boosting power quality disturbance categorization and presents paths for further inquiry in model refining and optimization. The study focuses on CNN-based models applied in power quality disturbance detection and classification research.

关键词： Convolutional neural networks Power quality Mathematical models computational modeling Protection Feature extraction Renewable energy sources Accuracy Power system stability Signal processing algorithms Convolutional neural networks (CNN) power quality (PQ) renewable energy machine learning

来源：评论

学校读者我要写书评

暂无评论

KNIGCN: Key Node Identification in UAV Swarm Networks Using a Graph Convolutional Network

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第11期12卷 16227-16242页

作者： Ai, Qixun Hou, Changbo Zhou, Zhichao Wu, Xiangyu Song, Zhen Harbin Engn Univ Coll Informat & Commun Engn Harbin 150001 Peoples R China Harbin Engn Univ Key Lab Adv Marine Commun & Informat Technol Minist Ind & Informat Technol Harbin 150001 Peoples R China

In the field of Internet of Things (IoT), uncrewed aerial vehicle (UAV) swarms are widely used to assist IoT communication due to their simple deployment, high mobility and high cost effectiveness to help improve IoT network coverage and topological flexibility. However, due to the openness of UAV swarm network, UAV nodes are vulnerable to malicious attacks and fail, especially some key nodes, which will seriously degrade the network performance. To solve this problem, a key node identification model based on graph convolutional network (GCN), named KNIGCN, is proposed. Specifically, the topology model of UAV cluster network is first built based on flying ad hoc network (FANET) communication architecture and Dijkstra's algorithm, then node criticality labels in the network are made by means of traffic statistics, and finally KNIGCN model is used to predict the criticality scores of each node and sort them so as to screen out a certain number of key nodes. The experimental results show that the model has good performance of key node identification. Compared with traditional methods, the proposed method makes a more reasonable judgment of node criticality, and the key nodes identified have a more important impact on network performance. Moreover, the proposed scheme can effectively improve the identification speed of key nodes in large-scale, complex or dynamically changing topology of UAV cluster networks. It can provide an effective scheme for maintaining the security and stability of UAV swarm network communication.

关键词： Autonomous aerial vehicles Network topology Accuracy Internet of Things Topology Computer architecture computational modeling Adaptation models Predictive models Training Dijkstra's algorithm flying ad hoc network (FANET) graph convolutional network (GCN) key node identification uncrewed aerial vehicle (UAV) swarm network

来源：评论

学校读者我要写书评

暂无评论

On Analytical Estimation of Inductances in Equivalent Ladder Network Model of a Homogeneous Transformer Winding Using FRA Data

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2025年第1期40卷 472-483页

作者： Rao, Tirlingi Madhava Pramanik, Saurav Mitra, Sourav Indian Inst Technol Dept Elect Engn Kharagpur 721302 India

The determination of ladder-network model parameters for transformer winding holds paramount significance in validating the design constraints of the transformer winding, with a particular emphasis on facilitating thorough analysis of its impulse behaviour. As these parameters cannot be measured directly, the majority of studies documented in the literature rely on iterative optimization techniques for estimation, and as of now, no analytical solution has been reported and implemented. To address this concern, this paper introduces an analytical approach for estimating unknown self and mutual inductances in equivalent ladder-network model of a homogeneous transformer winding, employing frequency response measurement. For this purpose, the method derived necessary linear and non-linear equations of unknown inductances pertaining to the coupled ladder-network model of the winding. The solution is directly obtained utilizing essential peak and trough frequencies extracted from three measured admittance magnitude responses along with series and ground capacitances determined separately. The practicality of the method has been verified using experimental results on three different transformer windings including one with iron-core. For improved precision, the estimated inductance values were fine-tuned further using conventional optimization technique. Results indeed demonstrate the practicality as well as efficacy of the method.

关键词： Windings Mathematical models Analytical models Frequency measurement Capacitance Frequency response computational modeling Transient analysis Inductance Capacitance measurement Transformer winding self and mutual inductances driving-point admittance frequency response analysis natural frequencies

来源：评论

学校读者我要写书评

暂无评论

Syntactic-Aware Text Classification Method Embedding the Weight Vectors of Feature Words

引用

IEEE ACCESS 2025年 13卷 37572-37590页

作者： Wang, Meng Kim, Jisu Yan, Yuting Chinese Acad Sci Natl Sci Lib Beijing 100190 Peoples R China Renmin Univ China Sch Appl Econ Beijing 100872 Peoples R China Yunnan Univ Finance & Econ Kunming 650399 Peoples R China

Text classification is the process of categorizing sentences into predefined classes on the basis of their meanings or functions. In this context, feature words play a crucial role in representing the core meaning and key information of sentences, reflecting the main content and deep semantics of scientific literature. Optimizing text classification models using feature words is an important task in the information mining of scientific literature. To address text classification considering feature words, this study constructs a set of feature words from a linguistic perspective and quantitatively expresses the weight differences of various feature words on the basis of syntactic structure features. By embedding the weight information, absolute position, relative position, and contextual information of feature words into pre-trained models, the universal text classification models considering feature word vector weights is established. The analysis of hyperparameter space relationships reveals that the hyperparameter settings are not simple linear relationships and that their interactions are often nonlinear and complex. Employing the Bayesian optimization algorithm facilitates the model in finding the optimal hyperparameters while reducing computational costs. Based on the public dataset RCMR 280K, the experimental results demonstrate that considering feature words enables the model to capture sentence structure and features in text classification task, improving the recognition accuracy of the model. Compared with base models (BERT, SciBERT, RoBERTa and ModernBERT) and their regularized models which consider feature words, the improved ModernBERT, which is based on weighted feature word vectors, achieves an average F1 of 95.8% in the recognition tasks of research objective, method, result and conclusion sentences, an improvement of 1.2%, 0.8%, 1.1%, and 0.9%, respectively. In addition, the results show that large language models (LLMs) exhibit robust performance in

关键词： Semantics Text categorization Feature extraction Vectors Encoding Accuracy Context modeling Bidirectional control computational modeling Biological system modeling Text classification feature word weight pre-trained model LLM position embedding Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Sparse Linear Discriminant Analysis With Constant Between-Class Distance for Feature Selection

引用

IEEE ACCESS 2025年 13卷 618-632页

作者： Guo, Shuangle Li, Yongxia Zhang, Jianguang Liu, Yue Tian, Tian Guo, Mengchen Shandong Univ Aeronaut Sch Informat Engn Binzhou 256600 Shandong Peoples R China Hengshui Univ Off Acad Affairs Hengshui 053000 Peoples R China Hengshui Univ Dept Math & Comp Sci Hengshui 053000 Peoples R China Hengshui Univ Off Human Resources Hengshui 053000 Peoples R China Univ Calif Davis Dept Appl Math Davis CA 95616 USA Xiamen Univ Malaysia Dept Elect & Elect Engn Sepang 43900 Malaysia

Feature selection is an important preprocessing step in machine learning to remove irrelevant and redundant features. Due to its ability to effectively maintain the discriminability of extracted features, Trace Ratio Linear Discriminant Analysis (TR-LDA) has become the foundation for many feature selection algorithms. As is known, TR-LDA is a challenging problem to solve because of its trace-ratio form, and it also faces the scale invariance problem. These two drawbacks of TR-LDA significantly reduce the performance of feature selection algorithms based on it. To overcome these drawbacks, this paper proposes the sparse LDA with constant between-class distance (SLDA-CBD) model to select relavant features. This model first transforms TR-LDA into a non-trace ratio problem with a constant between-class distance constraint, and then imposes row constraints on the projection matrix to implement feature selection. Since the SLDA-CBD model is rooted in TR-LDA, it ensures the discriminative performance of the selected features. The constant between-class distance constraint successfully avoids the scale invariance problem. Additionally, due to the non-trace ratio form of the SLDA-CBD model, it is easily solvable. The experimental results show that the proposed method has better performance compared to the baseline and six state-of-the-art relative methods, with improvements of over 1% on image datasets and over 2% on video datasets in most cases, while also demonstrating high stability, proving its effectiveness and advantage in practical applications.

关键词： Feature extraction Classification algorithms Training Filtering algorithms computational modeling Machine learning algorithms Sparse matrices Mathematical models Vectors Predictive models Feature selection TR-LDA sparse regression

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity-Aware Clustering and Intra-Cluster Uniform Data Sampling for Federated Learning

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN computational INTELLIGENCE 2025年第3期9卷 2545-2556页

作者： Chen, Jian Zhang, Peifeng Chen, Jiahui Lau, Terry Shue Chien Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China Multimedia Univ Fac Comp & Informat Cyberjaya 63100 Malaysia

Federated learning (FL) is an innovative privacy-preserving machine learning paradigm that enables clients to train a global model without sharing their local data. However, the coexistence of category distribution heterogeneity and quantity imbalance frequently occurs in real-world FL scenarios. On the one side, due to the category distribution heterogeneity, local models are optimized based on distinct local objectives, resulting in divergent optimization directions. On the other side, quantity imbalance in widely used uniform client sampling of FL may hinder the active participation of clients with larger datasets in model training, and potentially make the model get suboptimal performance. To tackle this, we propose a framework that incorporates heterogeneity-aware clustering and intra-cluster uniform data sampling. More precisely, we firstly do heterogeneity-aware clustering that performs clustering on clients based on category distribution vectors. Then, we implement intra-cluster uniform data sampling, where local data from each client within a cluster is randomly selected based on a predetermined probability. Furthermore, to address privacy concerns, we incorporate homomorphic encryption to protect clients' category distribution vectors and sample sizes. Finally, the experimental results on multiple benchmark datasets demonstrate that the proposed framework validate the superiority of our approach.

关键词： Training Data models Vectors Federated learning Servers computational modeling Privacy computational intelligence Speech recognition Optimization quantity imbalance category distribution heterogeneity

来源：评论

学校读者我要写书评

暂无评论

A Fast-Efficient Anomaly Detection Framework for State Estimation in Traffic Flow Measurement

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第2期26卷 2309-2320页

作者： Zhang, Zhixun Lu, Jianquan Hu, Jianqiang Luo, Yiping Cao, Jinde Yu, Wenwu Southeast Univ Sch Cyber Sci & Engn Nanjing 210096 Peoples R China Southeast Univ Jiangsu Prov Key Lab Networked Collect Intelligenc Nanjing 211189 Peoples R China Southeast Univ Sch Math Nanjing 211189 Peoples R China Hunan Inst Engn Sch Elect & Informat Engn Xiangtan 411104 Peoples R China Southeast Univ Sch Math Nanjing 210096 Jiangsu Peoples R China Purple Mt Labs Nanjing 211102 Peoples R China

In intelligent transportation systems (ITS), machine learning is highly effective in anomaly detection for state estimation (SE) in traffic flow measurement, but it requires resource-intensive collection of anomaly samples and overlooks spatial characteristics. Additionally, the original SE in traffic flow measurement exhibits low-frequency characteristics due to computational complexity. Considering these limitations, this paper proposes a fast and efficient anomaly detection framework for SE in traffic flow measurement. Initially, an attention-based spatiotemporal graph convolutional network (ASTGCN) model is utilized to extract both temporal and spatial features of SE. The ASTGCN model is trained using quantile regression, relying solely on normal samples during training. This approach eliminates the need for collecting anomalous samples and reduces computational demands. The model establishes a safe interval for SE that significantly improves anomaly detection capabilities. Furthermore, a teacher-student network is implemented, where the teacher network, trained offline, distills its ability to convert low-frequency SE data into high-frequency representations into a simpler student network. The student network executes real-time reconstruction of high-frequency SE, thus enhancing the precision of anomaly detection without substantial resource expenditure. Finally, the analysis conducted on the California's 7th district highway measurement system demonstrates the proposed method's ability to accurately detect anomalous SE in traffic flow measurement.

关键词： Anomaly detection Spatiotemporal phenomena Feature extraction Security computational modeling Accuracy Data models Correlation Attention mechanisms Training ASTGCN model teacher-student network anomaly detection intelligent transportation systems traffic flow measurement

来源：评论

学校读者我要写书评

暂无评论

Covert Communications for Active STAR-RIS-Aided RSMA Systems With Hardware Impairments

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年

作者： Liang, Yuting Huang, Kewen Yang, Liang Li, Xingwang Liu, Hongwu Bian, Yougang Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Jishou Univ Sch Commun & Elect Engn Jishou 416000 Peoples R China Henan Polytech Univ Sch Phys & Elect Informat Engn Jiaozuo 454000 Peoples R China Shandong Jiaotong Univ Sch Informat Sci & Elect Engn Jinan 250357 Peoples R China Hunan Univ Coll Mech & Vehicle Engn State Key Lab Adv Design & Mfg Vehicle Body Changsha 410082 Peoples R China

An active simultaneously transmitting and reflecting reconfigurable intelligent surface (ASTAR-RIS)-aided rate-splitting multiple access (RSMA) system is investigated in this paper. Specifically, a multi-antenna base station (BS) employs the RSMA protocol to communicate with a covert user and a public user with the help of an ASTAR-RIS in the presence of hardware impairments. For this setup, the outage probability (OP) and the detection error probability (DEP) of the warden are derived to characterize the covert communication performance. The covert transmission rate (C-R) in high signal-to-noise ratio (SNR) regions is also taken into consideration, for which an accurate approximate expression is presented. Based on the analytical results, the influences of the number of ASTAR-RIS elements, the RSMA factors, and the reflection coefficient of the ASTAR-RIS elements are analyzed. Finally, numeric simulations validate the correctness of the theoretical results presented in this paper.

关键词： Reconfigurable intelligent surfaces Wireless communication Hardware Receivers NOMA Protocols Signal to noise ratio Power system reliability Numerical models computational modeling Active simultaneously transmitting and reflecting reconfigurable intelligent surface (ASTAR-RIS) covert communication hardware impairments rate-splitting multiple access (RSMA)

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：