检索结果-内蒙古大学图书馆

A Fuzzy Identification Method Based on the Likelihood Function and Noise clustering Algorithm

International Journal of Fuzzy Systems 2023年第1期25卷 136-144页

作者： Tsai, Shun-Hung Chen, Yi-Ting Department of Electrical Engineering National Sun Yat-sen University Lien-hai Rd. Kaohsiung804 Taiwan Graduate Institute of Automation Technology National Taipei University of Technology Zhongxiao E. Rd. Taipei106 Taiwan

In this paper, based on the modified fuzzy c-regression model and noise clustering algorithm, a fuzzy identification method is proposed. Firstly, by considering the relations for the real model, the established model, and the outliers, a modified objective function with noise is proposed to alleviate the affection of noise. Additionally, the consequent parameters of the fuzzy model can be obtained by the iterative formula which obtained by the Lagrangian formula. Furthermore, a modified membership function, which is involved the likelihood function, is propounded to get a more suitable multivariate normal distribution for the data points. Lastly, two examples are illustrated to show the validity and effectiveness of the proposed results. © 2022, The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Complicated Imbalanced and Overlapped Data Oversampling Approach via Hypersphere Coverage and Adaptive Differential Evolution for Anomaly Detection of Industrial Internet of Things

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第10期12卷 14002-14015页

作者： Shang, Wenli Ding, Lei Yang, Xueying Gu, Zhaojun Sui, He Guangzhou Univ Sch Elect & Commun Engn Guangzhou 510006 Peoples R China Guangzhou Univ Sch Cyber Sci & Technol Guangzhou 510006 Peoples R China Civil Aviat Univ China Informat Secur Evaluat Ctr Civil Aviat Tianjin 300300 Peoples R China Civil Aviat Univ China Sch Aeronaut Engn Tianjin 300300 Peoples R China

Anomaly detection is a unique type of classification challenge. The coupling of imbalance, overlap, and other complexity of the data, such as noise in industrial Internet of Things (IIoT) scenarios affect the detection accuracy seriously. To address this issue, this article proposes a novel oversampling approach based on synthetic minority oversampling technology via hypersphere coverage and adaptive differential evolution (HCADE-SMOTE). However, overlap intensification caused by generated samples and over-loss of valid information have always been crucial problems for traditional SMOTE-based approaches. In HCADE-SMOTE, we identify error-prone samples, including minority noise and boundary samples based on the hypersphere coverage algorithm first. Then, we fine tune the distribution of these error-prone samples before generation with an adaptive differential evolution algorithm. Instead of deletion mechanism, it avoids transitional information loss. With error-prone samples far away from the boundary, HCADE-SMOTE improves the boundary distribution and simplifies the judge the decision boundary for the detection models. Furthermore, minority samples are oversampled based on local hypersphere density and compactness with a weighted SMOTE mechanism to address the imbalance problem. The superiority of this HCADE-SMOTE is verified by experiments from optimization of sample distribution, effect of anomaly detection, and statistical tests, compared with seven well-known SMOTE-based methods. The experimental results show that HCADE-SMOTE is the most prominent to alleviate overlap with Fisher's discriminant ratio metric. After HCADE-SMOTE, the detection results reached the best with classification metrics, for the four detection models support vector machines (SVM), logistic regression (LR), naive Bayes, and decision tree (DT). The statistical tests also prove HCADE-SMOTE has significant difference from other SMOTE-based methods, superior to them.

关键词： Noise Industrial Internet of Things Anomaly detection Couplings Complexity theory clustering algorithms Adaptation models Noise measurement Interpolation Deep learning Adaptive differential evolution hypersphere coverage industrial anomaly detection oversampling

来源：评论

学校读者我要写书评

暂无评论

Improved K-Means Algorithm for Nearby Target Localization

引用

IEEE ACCESS 2025年 13卷 14872-14880页

作者： Yuan, Zongwen Wang, Xingdi Chen, Fuyang Ma, Xicheng Chaohu Univ Sch Elect Engn Hefei 238024 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 210016 Peoples R China Beijing Measurement & Control Technol Co Ltd Beijing 471000 Peoples R China

In a multi-source localization system, direction of arrival (DOA) estimation of angles always suffers from errors due to noise interference, sensor position inaccuracies, and other factors. When the distance between target sources is much smaller than the distance between sensors and target sources, the accuracy of traditional localization algorithms based on direction finding and cross-fixing deteriorates. In this paper, we propose a localization algorithm based on K-means clustering. To tackle the problem of unknown initial positions of target sources, we employ a grid density peak clustering(DPC) method for initial localization. In the K-means algorithm, we integrate a quartile range anomaly detection algorithm to address interference signal issues. Finally, we propose an invalid compensation algorithm to filter out invalid signals, thereby compensating for the estimation errors in angles. Through the collection of real-world data, we compare the performance of the traditional direction finding and cross-fixing algorithms with the proposed algorithm in the localization of nearby target points. Experimental results demonstrate that the proposed algorithm significantly improves localization accuracy.

关键词： clustering algorithms Interference Location awareness Autonomous aerial vehicles Accuracy Prediction algorithms Direction-of-arrival estimation Target tracking Trajectory Direction of arrival passive location K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Toward a BMS2 Design Framework: Adaptive Data-Driven State-of-Health Estimation for Second-Life Batteries With BIBO Stability Guarantees

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第3期11卷 7684-7696页

作者： Cui, Xiaofan Aadil Khan, Muhammad Singh, Surinder Sharma, Ratnesh Onori, Simona Stanford Univ Dept Energy Sci & Engn Stanford CA 94305 USA Univ Calif Los Angeles Dept Elect & Comp Engn Los Angeles CA 90095 USA Relyion Energy Inc Fremont CA 94538 USA

A key challenge that is currently hindering the widespread use of retired electric vehicle (EV) batteries for second-life (SL) applications is the ability to accurately estimate and monitor their state of health (SOH). SL battery systems can be sourced from different battery packs with a lack of knowledge of their historical usage. Accurate SOH estimation is critical because it enables reliable performance, safety, and optimal utilization of SL batteries, ensuring they meet the requirements of various applications including grid energy storage and backup power. In this work, for in-the-field use of SL batteries, we introduce an online adaptive health estimation approach with the guarantees of bounded-input, bounded-output (BIBO) stability. This method relies exclusively on operational data that can be accessed in real-time from SL batteries. The effectiveness of the proposed approach is shown on a laboratory-aged experimental dataset of retired EV batteries.

关键词： Batteries Estimation Adaptation models Computational modeling Data models Battery charge measurement Temperature measurement Aging Voltage measurement Degradation Adaptive estimation batteries battery management systems (BMS) clustering algorithms data-driven modeling machine learning prognostics and health management second-life (SL) batteries sensitivity analysis state of health (SOH)

来源：评论

学校读者我要写书评

暂无评论

Multi-AAV Energy-Efficient Detection Coverage Under Jamming Environment: A Hierarchical Collaborative Learning Approach

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第5期74卷 7351-7363页

作者： Fang, Chao Feng, Yanxiang Li, Xiaoling Yang, Yikang Xi An Jiao Tong Univ Sch Automat Sci & Engn Xian 710049 Peoples R China Chang An Univ Sch Elect & Control Engn Xian 710064 Peoples R China

Autonomous aerial vehicles (AAVs) can provide detection coverage service in many scenarios. The fair coverage is achieved by designing carefully AAVs' trajectories, which are established at each step by choosing the moving action and channel access for transmitting data. However, under the jamming environment, the problematic trajectories could lead to mutual interference and malicious jamming, such that the coverage service fails. The selections of moving action and channel access are usually coupled, and so far no work has addressed them jointly for planning trajectory. As such, this paper investigates the multi-AAV joint optimization of moving action and channel access for the energy-efficient detection coverage. To decouple the strongly-coupled moving action and channel access, we model the studied optimization problem as a hierarchical game, where the stochastic game (resp. potential game) is applied for selecting moving action (resp. channel access). Then, we propose a multi-agent hierarchical cooperative learning (MAHCL) algorithm to attain near-optimal solution for the joint optimization. It is proved that the proposed MAHCL algorithm can asymptotically converge to the near-optimal joint strategy with lower computational complexity. Finally, the simulation results show the higher energy efficiency of MAHCL algorithm compared with the benchmarks.

关键词： Jamming Autonomous aerial vehicles Trajectory Interference Games Heuristic algorithms Optimization Energy efficiency Dynamic scheduling clustering algorithms Anti-jamming detection coverage multi-agent reinforcement learning potential game AAV networks

来源：评论

学校读者我要写书评

暂无评论

FCER: A Federated Cloud-Edge Recommendation Framework With Cluster-Based Edge Selection

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 1731-1743页

作者： Wu, Jiang Yang, Yunchao Hu, Miao Zhou, Yipeng Wu, Di Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Macquarie Univ Fac Sci & Engn Dept Comp Sydney NSW 2112 Australia

The traditional recommendation system provides web services by modeling user behavior characteristics, which also faces the risk of leaking user privacy. To mitigate the rising concern on privacy leakage in recommender systems, federated learning (FL) based recommendation has received tremendous attention, which can preserve data privacy by conducting local model training on clients. However, devices (e.g., mobile phones) used by clients in a recommender system may have limited capacity for computation and communication, which can severely deteriorate FL training efficiency. Besides, offloading local training tasks to the cloud can lead to privacy leakage and excessive pressure to the cloud. To overcome this deficiency, we propose a novel federated cloud-edge recommendation framework, which is called FCER, by offloading local training tasks to powerful and trusted edge servers. The challenge of FCER lies in the heterogeneity of edge servers, which makes the parameter server (PS) deployed in the cloud face difficulty in judiciously selecting edge servers for model training. To address this challenge, we divide the FCER framework into two stages. In the first pre-training stage, edge servers expose their data statistical features protected by local differential privacy (LDP) to the PS so that edge servers can be grouped into clusters. In the second training stage, FCER activates a single cluster in each communication round, ensuring that edge servers with statistical homogenization are not repeatedly involved in FL. The PS only selects a certain number of edge servers with the highest data quality in each cluster for FL. Effective metrics are proposed to dynamically evaluate the data quality of each edge server. Convergence rate analysis is conducted to show the convergence of recommendation algorithms in FCER. We also perform extensive experiments to demonstrate that FCER remarkably out performs competitive baselines by 3.85%-9.14%on HR@10 and1.46%-11.77%on NDCG@10

关键词： Servers Training Privacy Recommender systems Data models Federated learning clustering algorithms Convergence Computational modeling Differential privacy recommender system privacy protections

来源：评论

学校读者我要写书评

暂无评论

WSNetDefender: Securing Wireless Sensor Networks Using BBIDNet and Fuzzy-DQN Threat Mitigation System (FD-TMS)

引用

IEEE ACCESS 2025年 13卷 93439-93452页

作者： Aleisa, Mohammed A. Majmaah Univ Coll Comp & Informat Sci Dept Comp Sci Al Majmaah 11952 Saudi Arabia

In the Wireless Sensor Network (WSN), there has been a significant increase in intruders, owing towards rapid expansion in the cyber-space that encloses multi-layered cybersecurity. The aim of this work is to tackle the increasing cybersecurity issues in Wireless Sensor Networks (WSNs) by proposing an innovative framework named WSNetDefender. It encompasses a Boosted BiLSTM Intrusion Detector Network (BBIDNet) to identify intrusions with precise accuracy and a Fuzzy-DQN Threat Mitigation System (FD-TMS) to respond to threats dynamically. The framework aims to enhance the accuracy of detection of intrusion while reducing false positives and resource *** first step involves gathering data from two distinct wireless sensor network datasets. Subsequently, preprocessing is done using the new Integrated Preprocessing Engine (IPE), wherein the Gaussian filtering for denoising, Kalman filtering for data fusion (2 databases), and Min-Max normalization for standardization are available. Then, features are extracted using the new NetFlow Profiling Network (NPN), which encloses the CAN Bus Analysis, Behavior Profiling, and Netflow Analysis. The newly introduced Jackal-Wolf Hybrid Optimizer (JWHO) assisted in selecting the optimal features from NPN, thereby assisting the model in lowering computing difficulty in terms of both memory and time. The proposed JWHO is the conceptual synergy of Golden Jackal Optimization and Grey Wolf Optimizer (GJO-GWO), respectively. The extracted JWHO-based features are utilized to train the new BBIDNet, which makes the accurate detection of intruders in WSN. This BBIDNet is the combination of the Bidirectional Long Short-Term Memory (BiLSTM) network with AdaBoost. Once, an attacker is found to be available, then for the concern attacker is mitigated via the new FD-TMS. In FD-TMS, the threat scoring and prioritization are undergone with respect to fuzzy rules, and based on the critical level identified, the mitigation is done using the Dee

关键词： Wireless sensor networks Accuracy Feature extraction Databases Prevention and mitigation Intrusion detection Optimization clustering algorithms Computational modeling Bidirectional long short term memory WSN cybersecurity intrusion detection threat mitigation system hybrid optimization algorithm deep learning reinforced learning

来源：评论

学校读者我要写书评

暂无评论

New energy efficient access timing control based on reduction and weighted optimal hierarchical clustering 5

New energy efficient access timing control based on reductio...

引用

5th International Conference on Energy, Power and Advanced Thermodynamic Systems, EPATS 2025

作者： Zhang, Fajun Zhao, Yuanyuan Han, Aoyang Yin, Zhi Wei, Zhen State Grid Qingdao Power Supply Company Qingdao266002 China

During the development and utilization of new energy, the transient abnormal characteristics of power grid control mode switching are multi-terminal. In order to realize efficient access to new energy, the time sequence control method of efficient access of new energy is studied by combining reduction and weighted optimal hierarchical clustering algorithm with convergence effect as the starting point. Under the coupling structure of reduction and weighted optimal hierarchical clustering, the objective function of new energy efficient access timing control is constructed, the constraint conditions are set, and the timing current of new energy efficient access is calculated. According to the calculation results, the timing control interval of new energy efficient access is divided, and the objective function is solved, thus realizing the timing control of new energy efficient access. The experimental results show that this method has a stable and efficient access timing control effect, good convergence effect, and fast speed. © Published under licence by IOP Publishing Ltd.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning From Crowds by Class-Specific Instance Weighting

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年

作者： Ji, Qiang Jiang, Liangxiao Zhang, Wenjun Li, Chaoqun China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China China Univ Geosci Sch Math & Phys Wuhan 430074 Peoples R China

In crowdsourcing scenarios, we can acquire each instance's multiple noisy label set from crowd workers and then infer its integrated label via label integration. To further enhance the quality of integrated labels, some noise correction algorithms have been proposed in recent years. Most of them aim to partition the dataset into a clean set and a noise set, followed by training one or multiple classifiers on the clean set to rectify the instances in the noise set. However, they overlook the fact that the class distribution of the clean set is often inconsistent with that of the noise set, resulting in the subpar correction performance of trained classifiers. To mitigate this inconsistency, this paper proposes a class-specific instance weighting-based noise correction (CIWNC) algorithm. In CIWNC, each class's weight is computed based on the class distribution of the clean set firstly. Subsequently, a class-specific weight is computed for each instance using the weight of the class that its integrated label belongs to, as well as its multiple noisy label set. Finally, a classifier is trained on the instance weighted clean set to rectify the instances in the noise set. Experimental results on 34 simulated and two real-world datasets demonstrate that CIWNC outperforms existing state-of-the-art noise correction algorithms significantly.

关键词： Noise Classification algorithms Noise measurement Crowdsourcing Prediction algorithms clustering algorithms Supervised learning Training Inference algorithms Partitioning algorithms Crowdsourcing learning noise correction instance weighting class-specific instance weighting

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Programmable LFA Defense Using Temporal Graph Learning in AIoT

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第3期12卷 2514-2529页

作者： Li, Yikun Liu, Ying Xia, Yu Zhang, Weiting Quan, Wei Kang, Jiawen Zhang, Hongke Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Peng Cheng Lab Dept New Networks Shenzhen 518000 Guangdong Peoples R China Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Guangdong Univ Technol Guangdong Key Lab IoT Informat Technol Guangzhou 510006 Peoples R China

In the current era of rapid advancements in Artificial Intelligence of Things (AIoT), with the increase in cloud data center operations and the limited security computing capabilities of AIoT terminal devices, link flooding attack (LFA) has emerged as a complex and stealthy new threat. However, the existing defense methods based on programmable networks usually have issues of slow offline inference and delayed defense activation. To address these issues, we propose a collaborative programmable defense framework (CPDTG) to predict, detect, and mitigate LFA. First, an early attack intention prediction model based on temporal graph learning (TGL) is proposed to accurately locate attacks and promptly activate defenses to save resource consumption during idle time. Second, a switch-native clustering algorithm independent of the global perspective is introduced for line-speed detection of LFA. The unsupervised algorithm does not rely on labeled datasets for training, which enhances its robustness against differentiated attack scenarios. Third, we propose a distributed defense mechanism that achieves the pushback deployment of adaptive rate-limiting strategies. Compressing the potential attack vector space effectively increases the difficulty of launching rolling attacks. Extensive experimental validation demonstrates the effectiveness of the proposed CPDTG in predicting and defending against LFA.

关键词： Switches Servers Cloud computing Internet of Things Prevention and mitigation Predictive models Denial-of-service attack Computer crime Collaboration clustering algorithms Attack intention prediction link flooding attack (LFA) programmable data plane (PDP) temporal graph learning (TGL)

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

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

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：