检索结果-内蒙古大学图书馆

An interpretable convolutional neural network via generalized time–frequency scattering

Signal Processing 2025年 237卷

作者： Liu, Xiaoping Chen, Gong Shi, Jun Tao, Ran School of Information and Electronics Beijing Institute of Technology and the Beijing Key Laboratory of Fractional Signals and Systems Beijing100081 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Communication Research Center Harbin Institute of Technology Harbin150001 China

Convolutional neural networks (CNNs) have recently demonstrated impressive performance in complex machine learning tasks. However, the CNN requires a large quantity of annotated data to converge to a good solution, and the theoretical understanding of this network is still in its infancy. Towards this end, a variant of the CNN, dubbed the deep scattering network (DSN), has been proposed by employing the linear time–frequency transform. The DSN inherits the hierarchical structure of the CNN, but chooses predefined wavelet/Gabor filters as its convolutional kernels instead of data-driven linear filters. Unfortunately, the DSN suffers from a major drawback that it is suitable for stationary image textures but not for non-stationary image textures, since wavelet/Gabor filters are intrinsically linear translation-invariant filters. The aim of this paper is to overcome this deficiency based upon a generalized linear time–frequency transform–the short-time fractional Fourier transform (STFRFT) which can be interpreted as a bank of linear translation-variant filters and thus may be well suitable for non-stationary texture analysis. We first introduce a generalized time–frequency scattering transform using the STFRFT. By applying the derived result, we propose an interpretable CNN by cascading the STFRFTs and modulus operators. Moreover, several basic properties of the proposed interpretable CNN are derived, and an efficient implementation of this network is also presented. Finally, the applications of the derived results are discussed. © 2025 Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control for Shunt Active Power Filter under Stochastic Solar Photovoltaics Behavior

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Prakash, Surya Alkhatib, Mohamed Sindi, Hatem F. Alghamdi, Sultan Behera, Ranjan Kumar Muduli, Utkal Ranjan Nit Jamshedpur Dept. of Electrical Engg Jharkhand Jamshedpur India Uae University Al Ain Dept. of Electrical and Communication Engg Coe Abu Dhabi15551 United Arab Emirates King Abdulaziz University Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering Jeddah21589 Saudi Arabia Indian Institute of Technology Patna Dept. of Electrical Engineering Bihta801103 India Khalifa University Apec Dept. of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates

The paper discusses the challenges in controlling a two-stage photovoltaic (PV)-based shunt active power filter (SAPF) under distorted grid conditions and stochastic PV system behavior. To address this, the paper proposes an adaptive proportional integral (API) regulator to regulate the DC-link voltage, which adapts its parameters based on the DC-link error voltage to provide low bandwidth for disturbance rejection and high bandwidth for dynamic performance enhancement. The paper also proposes an estimation method for the reference current using the sliding discrete Fourier transform and the instantaneous symmetrical component theory, which is suitable for non-ideal grid or load conditions. The accuracy of the proposed reference current estimation method is analyzed using time- and frequency-domain analysis. The performance of the PV-SAPF system with the proposed control algorithms is illustrated through simulation and real-time hardware validation under various grid conditions. Despite distorted grid conditions, the total harmonic distortion of the grid current is substantially within IEEE Std 519-2014. The proposed API regulator and reference current estimation method show promising results in improving the performance of the PV-SAPF system in the presence of internal and external disturbances. © 2013 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Topic Belief Formation Through Bifurcations Over Signed Social Networks

引用

IEEE Transactions on Automatic Control 2025年

作者： Bizyaeva, Anastasia Franci, Alessio Leonard, Naomi E. University of Washington NSF AI Institute in Dynamic Systems Dept. of Mechanical Engineering SeattleWA98195 United States University of Liège Dept. of Electrical Engineering and Computer Science Belgium WEL Research Institute Wavre Belgium Princeton University Dept. of Mechanical and Aerospace Engineering PrincetonNJ08544 United States

We propose and analyze a nonlinear dynamic model of continuous-time multi-dimensional belief formation over signed social networks. Our model accounts for the effects of a structured belief system, self-appraisal, internal biases, and various sources of cognitive dissonance posited by recent theories in social psychology. We prove that agents become opinionated as a consequence of a bifurcation. We analyze how the balance of social network effects in the model controls the nature of the bifurcation and, therefore, the belief-forming limit-set solutions. Our analysis provides constructive conditions on how multi-stable network belief equilibria and belief oscillations emerging at a belief-forming bifurcation depend on the communication network graph and belief system network graph. Our model and analysis provide new theoretical insights on the dynamics of social systems and a new principled framework for designing decentralized decision-making on engineered networks in the presence of structured relationships among alternatives. © 1963-2012 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Microfluidics with Machine Learning for Biophysical Characterization of Cells

引用

Annual review of analytical chemistry (Palo Alto, Calif.) 2025年第1期18卷 447-472页

作者： Jeon, Hyungkook Han, Jongyoon Department of Manufacturing Systems and Design Engineering (MSDE) Seoul National University of Science and Technology (SEOULTECH) Seoul Republic of Korea email: Departments of Biological Engineering and Electrical Engineering and Computer Science Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts USA email: Critical Analytics for Manufacturing Personalized Medicine (CAMP) Interdisciplinary Research Group Singapore-MIT Alliance for Research and Technology (SMART) Centre Singapore

Understanding the biophysical properties of cells is essential for biological research, diagnostics, and therapeutics. Microfluidics enhances biophysical cell characterization by enabling precise manipulation and real-time measurement at the microscale. However, the high-throughput nature of microfluidic systems generates vast amounts of data, complicating analysis. Integrating artificial intelligence (AI) methods, including machine learning and deep learning, with microfluidic technologies addresses these challenges. AI excels at analyzing large, complex datasets, improving the accuracy and efficiency of microfluidic experiments and facilitating new biological discoveries. This review examines the synergy between microfluidics and machine learning for biophysical cell characterization, categorizing existing methods based on the types of input data used for machine learning analysis, highlighting recent advancements, and discussing challenges and future directions in this interdisciplinary field.

关键词： artificial intelligence biophysical properties of cells cell analysis cell characterization machine learning microfluidic signature microfluidics

来源：评论

学校读者我要写书评

暂无评论

Decision-Focused Learning for Complex System Identification: HVAC Management System Application

arXiv

引用

arXiv 2025年

作者： Favaro, Pietro Toubeau, Jean-François Vallée, François Dvorkin, Yury Power Systems and Markets Research Group University of Mons Mons Belgium Ralph O’Connor Sustainable Energy Institute Department of Electrical and Computer Engineering Department of Civil and System Engineering Johns Hopkins University BaltimoreMD United States

As opposed to conventional training methods tailored to minimize a given statistical metric or task-agnostic loss (e.g., mean squared error), Decision-Focused Learning (DFL) trains machine learning models for optimal performance in downstream decision-making tools. We argue that DFL can be leveraged to learn the parameters of system dynamics, expressed as constraint of the convex optimization control policy, while the system control signal is being optimized, thus creating an end-to-end learning framework. This is particularly relevant for systems in which behavior changes once the control policy is applied, hence rendering historical data less applicable. The proposed approach can perform system identification — i.e., determine appropriate parameters for the system analytical model — and control simultaneously to ensure that the model’s accuracy is focused on areas most relevant to control. Furthermore, because black-box systems are non-differentiable, we design a loss function that requires solely to measure the system response. We propose pre-training on historical data and constraint relaxation to stabilize the DFL and deal with potential infeasibilities in learning. We demonstrate the usefulness of the method on a building Heating, Ventilation, and Air Conditioning day-ahead management system for a realistic 15-zone building located in Denver, US. The results show that the conventional RC building model, with the parameters obtained from historical data using supervised learning, underestimates HVAC electrical power consumption. For our case study, the ex-post cost is on average six times higher than the expected one. Meanwhile, the same RC model with parameters obtained via DFL underestimates the ex-post cost only by 3%. © 2025, CC BY-NC-ND.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

引用

Expert systems with Applications 2025年 282卷

作者： Wang, Dan Xia, Yuze Pedrycz, Witold Li, Zhiwu Yu, Zhenhua College of Computer Science and Technology Xi'an University of Science and Technology Xi'an710054 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Research Center of Performance and Productivity Analysis Istinye University Istanbul Turkey Institute of Systems Engineering Macau University of Science and Technology Macau900000 China School of Electro-Mechanical Engineering Xidian University Xi'an710071 China

Deep learning models have achieved remarkable success in the field of computer vision. However, it is difficult to understand and explain the complex internal mechanisms of deep learning models. Existing explanation methods often suffer from issues such as random noises and feature redundancy, which may mislead users and obscure the practical decision-making process of the models. To address these issues and improve the interpretation quality, we propose a novel method named Feature Similarity Group-Class Activation Mapping (FSG-CAM), which aims to enhance the clarity and quality of model's interpretation and to improve the computational efficiency by reducing noise and redundancy. FSG-CAM introduces leveraging feature similarity grouping to reduce noise and redundancy, thereby achieving clearer and more efficient explanation that align closely with human vision. We first use the gradient of target class computed to the model's output to guide the initial feature map and calculates the similarity between different feature channels. Then, feature channels with similar activation distributions are grouped together, and the sub-channels in each group are stacked to obtain a new feature channel. Next, the mixture masks are formed using normalization and binarization techniques, and the final saliency map is obtained by a linear weighted combination. We conduct extensive experiments based on ImageNet and MS COCO datasets for a collection of qualitative and quantitative analysis on several metrics such as Average Drop/Increase, Insertion/Deletion Curves, noise assessment, and ablation experiments. The results demonstrate that FSG-CAM indeed improves the interpretation quality and produces more consistent explanations with human vision. © 2025 Elsevier Ltd

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

IntSHU: A Security-Enabled Intelligent Soft Handover Approach for UAV-Aided 5G and Beyond

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Karmakar, Raja Kaddoum, Georges Akhrif, Ouassima Heritage Institute of Technology Department of Computer Science and Engineering IoT and Cyber Security including Blockchain Technology Kolkata700107 India University of Quebec Department of Electrical Engineering ETS Montreal Canada Lebanese American University Cyber Security Systems and Applied AI Research Center Beirut Lebanon

Unmanned aerial vehicles (UAVs) play a significant role in serving as gNodeBs (gNBs), or user devices (UDs). However, considering the high data rates and low latency required by fifth generation (5G) and beyond, it is essential to maintain a reliable connection at UAVs, particularly due to frequent handovers. To minimize handover failures, the hysteresis margin and time-to-trigger (TTT) should be dynamically adjusted. Furthermore, to prevent vulnerabilities to threats, UAV and gNB authentication and secure communication should be addressed during handovers. However, available literature uses a learning-based approach to handover management in UAV-aided 5G networks, thereby neglecting security, or offers a handover authentication mechanism, but lacks a novel handover strategy. To fill this gap in the literature, in this study, we design an Intelligent Soft Handover for UAV-enabled cellular networks (IntSHU), a generative adversarial network (GAN)-based scheme designed for intelligent soft handovers in UAV-enabled 5G and beyond. IntSHU uses adapted hysteresis margins and TTT values, dynamically generated through an -greedy policy. In addition, we implement a lightweight, physically unclonable function (PUF)-based message encryption and authentication scheme via blockchain for streamlined access control during handovers. The results of our simulation indicate that IntSHU significantly enhances network performance by facilitating reliable soft handovers. © 2015 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Editorial: Urban multi-energy system networks with high proportion of renewable energy

引用

Frontiers in Energy research 2025年 13卷

作者： Ding, Xiaoyi Xiang, Yue Morais, Hugo School of Water Resources and Hydroelectric Engineering Xi’an University of Technology Xi’an China Department of Electrical Engineering Sichuan University Chengdu China Institute of Systems and Computer Engineering: Research and Development Higher Technical Institute University of Lisbon Lisbon Lisbon Portugal

Faced with environment pollution and climate change, it is essential to develop advanced low-carbon energy system based on renewable sources. Micro-energy networks with a high proportion of renewable energy are one of the most important methods to achieve the complementary use of renewable energy and fossil energy with high efficiency of energy utilization. research on urban-level energy networks would be an important step for applying and integrating renewable sources. Faced with high penetration rate of renewable energy, the robust ability and safety operation are challenging from both sides of energy generation and the electrical grid. Meanwhile, the increasing number of electrical and fuel cell powered vehicles put additional difficulties for optimization and scheduling. Therefore, research on urban energy systems with a high proportion of renewable energy is extremely *** topic (“Urban Multi-energy System Networks with High Proportion of Renewable Energy”) aims to look into the key problems existing in the integrated multi-energy network system for the urban level and provide a detailed theoretical basis and experimental data for the design and operation of integrated micro-energy networks at the international academic level. The topic received several submissions within the field of renewable energy systems, including modeling and optimization, grid supply, the interaction between grid and EV/fuel cell cars, and advanced controlling strategy of off-grid/grid-connected microgrid systems, ***-carbon development of energyFeng et al. [1] modeled the natural gas system, power system, and their coupling components, and proposed a low-carbon economic control framework based on MASAC. The objective was to minimize both operational costs and carbon emissions. Simulation results using a nodal system demonstrated that this method significantly reduces costs and emissions compared to traditional approaches. Hu et al. [2] developed a low-carbon scheduling mod

关键词： dynamic control electric vehicle (EV) multi-energy system renewable energy synthetic fuel

来源：评论

学校读者我要写书评

暂无评论

Data-Filtered Prediction with Decomposition and Amplitude-Aware Permutation Entropy for Workload and Resource Utilization in Cloud Data Centers

引用

IEEE Internet of Things Journal 2025年

作者： Yuan, Haitao Hu, Qinglong Wang, Meijia Wang, Shen Bi, Jing Buyya, Rajkumar Shi, Shuyuan Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Hong Kong999077 Hong Kong Beijing University of Technology School of Software Engineering The Faculty of Information Technology Beijing100124 China Lab School of Computing and Information Systems MelbourneVIC3010 Australia Beihang University School of Integrated Circuit Science and Engineering Beijing China CSSC Systems Engineering Research Institute Beijing China Southern Methodist University Department of Computer Science The Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

In recent years, cloud computing has witnessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and interdependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVAPI for achieving high-accuracy workload prediction in cloud computing systems. SVAPI employs the Savitzky-Golay filter, Variational mode decomposition, and the mode selection based on Amplitude-aware Permutation entropy for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVAPI improves the prediction accuracy by 37.7% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVAPI enhances the prediction accuracy of workload, CPU, and memory by 65.6%, 66.9%, and 70.8%, respectively, demonstrating that SVAPI owns strong abilities in noise filtering, feature processing, and multivariate joint analysis for achieving higher prediction accuracy. © 2014 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Data-Driven Granular Model for Battery Remaining Useful Life Prediction

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Jing, TaiLong Du, Sheng Wang, Cong Wu, Chao Pedrycz, Witold Sharaf, Mohamed Li, ZhiWu Luoyang Institute of Science and Technology School of Electrical Engineering and Automation Luoyang471023 China China University of Geosciences School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Xi’an710072 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland King Saud University College of Engineering Department of Industrial Engineering Riyadh11421 Saudi Arabia Institute of Systems Engineering Macau University of Science and Technology Macau China

Accurate and meaningful prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) provides a significant guide for the maintenance and management of these LIBs. A singular numerical predictive result by numerous conventional models is insufficient to furnish decision-makers with comprehensive or nuanced insights. To address this issue, predictive RUL results in the form of information granules are essential. In this study, a hybrid data-driven granular model is established for battery RUL prediction with granular (interval-based) quantification for LIBs. This granular model is designed and formulated in a way that it produces comprehensive prediction outcomes realized as information granules, which are expressed in a more descriptive and comprehensive manner. Thus, the resulting information granules can effectively reflect and communicate the confidence associated with the predictions. The granular model is realized in two steps: 1) probabilistic prediction results are produced by a hybrid numeric predictive model and 2) a comprehensive granulation of the probabilistic results is achieved under the principle of information granularity. The granular predictive results are holistically evaluated and optimized by the two associated criteria of granularity (coverage and specificity). This transformation of information granules provides an intuitive and interpretable display for battery maintenance and safe work. The proposed granular model is verified by using an open-access LIBs dataset, and the experimental results demonstrate that the proposed granular model outperforms other comparative methods. © 2025 IEEE. All rights reserved.

关键词： Prediction models

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：