检索结果-内蒙古大学图书馆

Smart Grid and Energy engineering (SGEE), International Conference on

作者： Zehua Liu Yanqin Wang Yifan Liu Hongying Miao School of Control and Computer Engineering North China Electric Power University Beijing China State Grid Jibei Electric Power Co. Ltd. Chengde Power Supply Company Chengde China

ISBN: (数字)9798331530686

ISBN: (纸本)9798331530693

In order to realize the accurate classification and feature grasping of power users by the power supply department, this paper proposes a method of power user portrait by fusing heterogeneous data from multiple sources. The method first uses the K-means++ algorithm and combines the elbow rule to determine the optimal number of clusters K, and clusters the user load data and basic information separately; subsequently, the key load features are screened out by the mRMR method, and the radar diagram is used to visually display the features of different categories of users; finally, the refined construction of the user portrait is realized by combining various types of attribute labels, which provides the basis for the enterprise to provide personalized services. In this paper, the effectiveness of the proposed method is verified on two datasets.

关键词： Economics Power supplies Electricity Clustering algorithms Radar Grasping Feature extraction Real-time systems Smart grids Elbow

来源：评论

学校读者我要写书评

暂无评论

pFedBL: Federated Bayesian Learning with Personalized Prior

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Yu, Xinhui Tashakori, Arvin Zou, Liang Wang, Z. Jane University of British Columbia department of Electrical and Computer Engineering Vancouver V6T 1Z4 BC Canada China University of Mining and Technology School of Information and Control Engineering Xuzhou 221116 China

Most existing federated learning (FL) frameworks use deterministic models as the task model, which may suffer from overfitting due to small-scale data at client sides. Since Bayesian learning (BL) can quantify the uncertainty associated with both model parameters and prediction outcomes, there have been efforts to integrate BL with FL and the global objective is transformed into posterior approximation using Bayesian optimization. Variational inference is commonly used in such efforts which utilize the global distribution as the prior for the optimization of local Bayesian neural networks (BNNs) and thus eliminates the need for assigning specific prior distributions for clients. However, due to statistical heterogeneity across clients, the global distribution, representing the collective knowledge of all clients, may not be precise as client prior. To address this concern, we propose a federated Bayesian learning framework with personalized priors (pFedBL) where each client is assigned with a local BNN. Specifically, we first introduce a KL-divergence-based distribution aggregation scheme to ensure the effectiveness of the global distribution. Meanwhile, under the mild assumption that the server has access to a general unlabeled dataset, the server uses predictions as well as predictive uncertainty of these data, derived from local BNNs, to construct feature distributions. These distributions are then provided to clients for fine-tuning the global distribution, resulting in personalized priors. In addition, to ensure optimal integration of local and global data insights, we design an adaptive ζ strategy in the local objective function to balance the log-likelihood estimation term and the KL divergence term. We provide theoretical analysis regarding the upper bound of the averaged generalization error for the proposed pFedBL and experimental results demonstrate its effectiveness on three datasets under different problem settings © 2020 IEEE.

关键词： Bayesian learning federated learning personalized prior predictive uncertainty variational inference

来源：评论

学校读者我要写书评

暂无评论

GBMIA: Gradient-based Membership Inference Attack in Federated Learning

GBMIA: Gradient-based Membership Inference Attack in Federat...

引用

IEEE International Conference on Communications (ICC)

作者： Xiaodong Wang Naiyu Wang Longfei Wu Zhitao Guan Xiaojiang Du Mohsen Guizani School of Control and Computer Engineering North China Electric Power University China Department of Mathematics & Computer Science Fayetteville State University Fayetteville NC USA Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi UAE

Membership inference attack (MIA) has been proved to pose a serious threat to federated learning (FL). However, most of the existing membership inference attacks against FL rely on the specific attack models built from the target model behaviors, which make the attacks costly and complicated. In addition, directly adopting the inference attacks that are originally designed for machine learning models into the federated scenarios can lead to poor performance. We propose GBMIA, an attack model-free membership inference method based on gradient. We take full advantage of the federated learning process by observing the target model's behaviors after gradient ascent tuning. And we combine prediction correctness and the gradient norm-based metric for membership inference. The proposed GBMIA can be conducted by both global and local attackers. We conduct experimental evaluations on three real-world datasets to demonstrate that GBMIA can achieve a high attack accuracy. We further apply the arbitration mechanism to increase the effectiveness of GBMIA which can lead to an attack accuracy close to 1 on all three datasets. We also conduct experiments to substantiate that clients going offline and the overlap of clients' training sets have great effect on the membership leakage in FL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Pedestrians’ Crossing Intentions with a Conv-Transformer Network 8th

Recognition of Pedestrians’ Crossing Intentions with a Conv...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Yang, Biao Yan, Guocheng Wang, Fujun Yang, Changchun Liu, Xiaofeng College of IoT Engineering Hohai University Changzhou213100 China School of Microelectronics and Control Engineering Changzhou University Changzhou213100 China School of Computer Science and Artificial Intelligence Changzhou University Changzhou213100 China Graduate School of Environment and Information Sciences YOKOHAMA National University Yokohama240-8501 Japan

ISBN: (纸本)9783031067662

Recognizing pedestrians’ crossing intentions is critical for self-driving cars to avoid vehicle-pedestrian collisions. However, it is challenging to recognize pedestrians’ crossing intentions based on their appearance or actions under severe conditions, including occlusions, dim illumination, and pedestrians standing far away. In this work, a Conv-transformer network is proposed to recognize pedestrians’ crossing intentions. Pedestrians’ appearance is modeled by a Resnet network, which will output a feature sequence describing pedestrians at different time steps. A Transformer network is then introduced to model the feature sequence to output the recognition result, which is crossing or not crossing. Evaluations on benchmarking databases, including JAAD and PIE, are performed. Results show that the proposed method can recognize pedestrians’ crossing intentions precisely. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

Acoustic Feature Extraction of Wind Turbine Blades Based on Improved MFCC-GFCC

Acoustic Feature Extraction of Wind Turbine Blades Based on ...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Ziyi Wang Yuanye Chen Hua Wang Haichao Wang Fang Fang School of Control and Computer Engineering North China Electric Power University Beijing China Huaneng Clean Energy Research Institute Beijing China Shaanxi Oceanx Technology Co. Ltd Xianyang China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

As a critical component of wind turbines, the structural integrity of the blades is crucial for safe operation. To enhance the performance of health monitoring and fault detection systems, an acoustic feature extraction method is proposed to designed to aid in the development of a digital twin model for wind turbine blades (WTB). Our approach begins with a time index algorithm based on local maxima, which isolates single-blade data from audio recordings of the wind turbine. Then a blade acoustic signal feature extraction technique is developed by combining improved Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC). This technique leverages anomaly contribution and the maximal information coefficient (MIC) as comprehensive indicators to filter out irrelevant and negative features. By multiplying and fusing the features, our method achieves feature complementarity and reduces computational complexity. The proposed method can be seamlessly integrated into digital twins for wind turbines.

关键词： Microwave integrated circuits Blades Computational modeling Feature extraction Wind turbines Digital twins Indexes Mel frequency cepstral coefficient Computational complexity Monitoring

来源：评论

学校读者我要写书评

暂无评论

Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection

arXiv

引用

arXiv 2024年

作者： Adams, Steven Patanè, Andrea Lahijanian, Morteza Laurenti, Luca Delft Center for Systems and Control Technical Universiy of Delft Delft2628 CD Netherlands School of Computer Science and Statistics Trinity College Dublin Dublin 2 Ireland Department of Aerospace Engineering Sciences and Computer Science University of Colorado Boulder BoulderCO80303 United States

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this equivalence is commonly employed to analyze neural networks and has led to various breakthroughs over the years. However, neural networks and Gaussian processes are equivalent only in the limit;in the finite case there are currently no methods available to approximate a trained neural network with a Gaussian model with bounds on the approximation error. In this work, we present an algorithmic framework to approximate a neural network of finite width and depth, and with not necessarily i.i.d. parameters, with a mixture of Gaussian processes with error bounds on the approximation error. In particular, we consider the Wasserstein distance to quantify the closeness between probabilistic models and, by relying on tools from optimal transport and Gaussian processes, we iteratively approximate the output distribution of each layer of the neural network as a mixture of Gaussian processes. Crucially, for any NN and ǫ > 0 our approach is able to return a mixture of Gaussian processes that is ǫ-close to the NN at a finite set of input points. Furthermore, we rely on the differentiability of the resulting error bound to show how our approach can be employed to tune the parameters of a NN to mimic the functional behavior of a given Gaussian process, e.g., for prior selection in the context of Bayesian inference. We empirically investigate the effectiveness of our results on both regression and classification problems with various neural network architectures. Our experiments highlight how our results can represent an important step towards understanding neural network predictions and formally quantifying their uncertainty. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Abnormal Electricity Consumption Behavior Identifying Method with Multiple Types of Users Based on Bo-Gcn

SSRN

引用

SSRN 2024年

作者： Han, Xiaojuan Li, Haoyu Xu, Minglu He, Ziliang Li, Bin School of Control Engineering and Computer Science North China Electric Power University Beijing102206 China State Grid Beijing Electric Power Company Changping Power Supply Company Beijing102200 China

The analysis of user electricity consumption behavior is crucial for assisting power grid operation decision-making and optimizing power grid operation efficiency. In response to the differences in electricity consumption behavior among different types of users and the spatiotemporal correlation of electricity consumption behavior of the same user, this paper proposes a method for identifying abnormal electricity consumption behavior of multiple users based on Bayesian Optimization-graph Convolutional Neural Network (BO-GCN). By conducting statistical analysis on the actual data of user electricity consumption in a certain substation area, feature indicators that characterize user electricity consumption behavior are extracted. The eXtreme Gradient Boosting (XGBoost) tree is used to reduce the above feature indicators, forming the optimal feature set. The optimal feature indicators are regarded as the inputs of the GCN, a model for identifying abnormal electricity consumption behavior of users based on the GCN is established, in which the parameters of the GCN are optimized by Bayesian optimization algorithm to identify abnormal electricity consumption behavior quickly and *** numerical analysis results show that the method proposed in this paper fully utilizes the spatiotemporal correlation of user electricity consumption behavior within the substation area, reducing the impact of differences users on recognition accuracy. © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Derivative-free Constrained Optimization with a Mixed Penalty-Logarithmic Barrier Approach and Direct Search

arXiv

引用

arXiv 2024年

作者： Brilli, Andrea Custódio, Ana L. Liuzzi, Giampaolo Silva, Everton J. "Sapienza" University of Rome Department of Computer Control and Management Engineering "A. Ruberti" Rome Italy Campus de Caparica Caparica2829-516 Portugal Campus de Caparica Caparica2829-516 Portugal

In this work, we propose the joint use of a mixed penalty-logarithmic barrier approach and generating set search, for addressing nonlinearly constrained derivative-free optimization problems. A merit function is considered, wherein the set of inequality constraints is divided into two groups: one treated with a logarithmic barrier approach, and another, along with the equality constraints, addressed using a penalization term. This strategy, initially proposed in the framework of LOG-DFL [12], is adapted and incorporated into SID-PSM [14, 15] algorithm, a generalized pattern search method, allowing to effectively handle general nonlinear constraints. Under reasonable assumptions regarding the smoothness of the functions, convergence is established, without any convexity assumptions. Using CUTEst test problems, numerical experiments demonstrate the robustness, efficiency, and overall effectiveness of the proposed method, when compared with state-of-art solvers and with the original SID-PSM and LOG-DFL *** Codes 65K05, 90C30, 90C56 © 2024, CC BY.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wastewater Treatment Sensor Fault Detection through Deep Learning

Enhancing Wastewater Treatment Sensor Fault Detection throug...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Liliana-Maria Ghinea Mihaela Miron Marian Barbu Department of Automatic Control and Electrical Engineering University "Dunărea de Jos" Galați Romania Department of Computer Science and Information Technology University "Dunărea de Jos" Galați Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

Efficient operation and maintenance of wastewater treatment plants (WWTPs) are essential for safeguarding public health and the environment. The emergence of mechanical faults within complex systems can lead to disruptions, increased operational costs, and environmental risks. As the world moves towards a digitally connected and sustainable future, the development of Deep Learning (DL) tools for fault detection and isolation (FDI) in wastewater treatment processes is expected to become paramount. Therefore, in this study, we developed two neural models, a Feedforward Neural Network (FFNN) and a Long Short-Term Memory (LSTM), to address the detection of mechanical faults such as bias, stuck, spikes, and precision degradation of the Dissolved Oxygen (DO) sensor. The classification results showed remarkable accuracy performances during testing: for Dataset 1, FFNN achieved 96.56%, while LSTM reached 99.36%; and for Dataset 2, FFNN achieved 99.36%, and LSTM reached 99.57%.

关键词： Deep learning Degradation Accuracy Fault detection Plants (biology) Biological system modeling Data models Wastewater treatment Long short term memory Testing

来源：评论

学校读者我要写书评

暂无评论

Industrial Semantic Communications for Tool Wear Monitoring in Industrial IoT Networks

Industrial Semantic Communications for Tool Wear Monitoring ...

引用

IEEE International Conference on Communications in China Workshops (ICCC)

作者： Mingqiang Zhang Yajuan Yang Baokun Song Zexin Chen Xiaocong Ma Dongyang Li Na Li Feng Cao Yanping Zhang Haixia Zhang School of Cyber Science and Engineering Qufu Normal University Qufu China College of Oceanography and Space Informatics China University of Petroleum (East China) Huangdao China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Control Science and Engineering Shandong University Jinan China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong University Jinan China

ISBN: (数字)9798350377675

ISBN: (纸本)9798350377682

In this paper, we propose an Industrial Semantic Communications (ISC) framework to ensure efficient and in-telligent communication in Industrial Internet-of-Things (IIoT) networks, and further apply the proposed framework to the task of tool wear monitoring. A semantic-aware tool wear monitoring network (TWM-Net) is designed to accurately identify the idling state from tool wear data, thus assisting the semantic data transmission process of the ISC framework. Then, a demo software system is implemented to verify the delay performance of the proposed ISC framework. Experimental results demonstrated that the proposed ISC framework can facilitate the semantic information exchange between edge industrial system and cloud platform together with the deep compressed sensing method, and significantly reduce the amount of data transmissions in IIoT networks. The source code and dataset is available through https://***/pnixsoft/TWM-Net.

关键词： Vibrations Source coding Software systems Multitasking Delays Data communication Monitoring Information exchange Industrial Internet of Things Testing

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：