检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Eltaras, Tamer Ahmed Malluhi, Qutaibah Savino, Alessandro Di Carlo, Stefano Qayyum, Adnan Qadir, Junaid Control and Computer Engineering Dept Politecnico di Torino Turin10129 Italy Computer Science and Engineering Dept Qatar University Doha2713 Qatar Computer Science Information Technology University Dept Punjab Pakistan

In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent studies show that private training data can be leaked through many gradient attacks. While previous analytical-based attacks have successfully reconstructed input data from fully connected layers, their effectiveness diminishes when applied to convolutional layers. This paper introduces an advanced data leakage method to efficiently exploit convolutional layers' gradients. We present a surprising finding: even with non-fully invertible activation functions, such as ReLU, we can analytically reconstruct training samples from the gradients. To the best of our knowledge, this is the first analytical approach that successfully reconstructs convolutional layer inputs directly from the gradients, bypassing the need to reconstruct layers' outputs. Prior research has mainly concentrated on the weight constraints of convolution layers, overlooking the significance of gradient constraints. Our findings demonstrate that existing analytical methods used to estimate the risk of gradient attacks lack accuracy. In some layers, attacks can be launched with less than 5 % of the reported constraints. The source code is available for download from: https://***/tamertaras91/***. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Necessity of Past Input/output Information in Reinforcement Learning based Robust control

引用

Transactions of the Korean Institute of Electrical Engineers 2021年第12期70卷 1953-1957页

作者： Shim, Hyungbo Kim, Jeong Woo Park, Jooyoung Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Dept. of Control & Instrumentation Engineering Korea University Korea Republic of

Reinforcement learning yields a feedback controller that achieves specific control goal (which is often translated as a reward function). However, it often suffers from the Sim2Real gap, and domain randomization is known to be a method to overcome this issue. In this paper, we demonstrate necessity of input/outpu history when domain randomization is employed by a formal example and a simulation result. This is equivalent to the necessity of dynamic feedback controller in terms of control theory. © The Korean Institute of Electrical Engineers

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Kernel-based multi-step predictors for data-driven analysis and control of nonlinear systems through the velocity form

arXiv

引用

arXiv 2024年

作者： Verhoek, Chris Tóth, Roland The Control Systems group The Dept. of Electrical Engineering The Eindhoven University of Technology Netherlands The Institute for Computer Science and Control Budapest Hungary

We propose kernel-based approaches for the construction of a single-step and multi-step predictor of the velocity form of nonlinear (NL) systems, which describes the time-difference dynamics of the corresponding NL system and admits a highly structured representation. The predictors in turn allow to formulate completely data-driven representations of the velocity form. The kernel-based formulation that we derive, inherently respects the structured quasi-linear and specific time-dependent relationship of the velocity form. This results in an efficient multi-step predictor for the velocity form and hence for nonlinear systems. Moreover, by using the velocity form, our methods open the door for data-driven behavioral analysis and control of nonlinear systems with global stability and performance guarantees. © 2024, CC BY-NC-SA.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

Transfer and Bayesian Learning Approaches for Land Use and Land Cover Classification

Transfer and Bayesian Learning Approaches for Land Use and L...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Zainab Malik Aisha Sir Elkhatem Gokhan Bilgin Dept. of Computer Engineering Yildiz Technical University Istanbul Turkey Dept. of Control and Automation Engineering Yildiz Technical University Istanbul Turkey

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

Land use and land cover (LULC) classification is essential for understanding the impact of both human activities and natural processes on the Earth’s surface. This classification plays a critical role in deforestation, urban planning, and damage assessment. However, traditional machine learning techniques often face challenges in achieving consistent accuracy in diverse datasets. In this study, we implement transfer learning and Bayesian learning approaches to enhance the accuracy and robustness of LULC classification. Transfer learning leverages knowledge from previous classification problems, while Bayesian learning addresses uncertainties in the classification process. Using the Remote Sensing Image Classification Benchmark (RSI-CB128) dataset, the study evaluates the performance of Bayesian Convolutional Neural Networks (CNN), Mobile Neural Networks (MobileNet), Inception Neural Networks (InceptionNet), Densely Connected Convolutional Networks (DenseNet) and Efficient Neural Networks (EfficientNet). The study also investigates the impact of varying the Bayesian layers on model performance, finding that a medium number of layers optimally captures model uncertainty. The results indicate that the transfer learning models, particularly MobileNet, achieved the highest accuracy of 97. 48% compared to 90. 33% for Bayesian CNN. These findings suggest that transfer learning techniques are highly effective for LULC classification, providing a reliable method for practical applications in remote sensing.

关键词： Deforestation Accuracy Uncertainty Computational modeling Transfer learning Neural networks Urban planning Land surface Bayes methods Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The All Wheel Speed Balance control Concept 27

The All Wheel Speed Balance Control Concept

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Atheupe, Gael P. Martinez, Didier Monsuez, Bruno Renault Technical Centre Renault Group & Ensta Paris Paris France Renault Technical Centre Renault Group Dept. Chassis Control & Adas Systems Guyancourt France Ensta Paris Dept. Computer Science & Systems Engineering Paris France

ISBN: (纸本)9798331505929

The transition to vehicle electrification introduces new demands on chassis dynamics, paving the way for advances in driving dynamics, safety, and efficiency. A key consideration arises: how are driving torque impulses converted in electric vehicles with multiple power sources? This study introduces a novel approach to address these demands through the integration of state-of-the-art yaw control, using concurrent front/rear axle and front right/front left torque distribution based on the wheel speed balance control concept. Our aim is not necessarily to demonstrate the supremacy of our approach, but rather to present a fresh philosophical perspective on the problem of yaw control in electric vehicles. Our method embodies dynamic load transfer and axle dynamics into the yaw control problem formulation, setting it apart from current methodologies. Through experimental results, we illustrate the effectiveness of our proposed approach regardless of road surface conditions. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation of Thermal Faults in Batteries for Enhanced Safety

Modeling and Simulation of Thermal Faults in Batteries for E...

引用

IEEE Design and Diagnostics of Electronic Circuits and Systems (DDECS)

作者： Francesco Tosoni Sara Vinco Franco Fummi Department of Engineering IM University of Verona Verona Italy Dept. of Control and Computer Engineering Politecnico di Torino Turin Italy

ISBN: (数字)9798331528010

ISBN: (纸本)9798331528027

Batteries are a central component of many complex systems, including mobile devices, sensors, electric vehicles, etc. Keeping the battery working in normal conditions avoids dangerous hazards for the user or the system itself and helps extend the device’s life. The battery temperature is one of the most delicate aspects of these devices since some dangerous scenarios, like thermal runaway, could occur due to variable conditions. This paper uses a battery model of an electric vehicle from the automotive area as a case study to simulate the thermal response to normal usage. Then, thermal fault scenarios are modeled within equivalent circuital device descriptions and analyzed regarding state-of-charge, temperature, and voltage output. The findings presented offer a valuable starting point for improving the design phase of the batteries in multiple fields by testing fault scenarios already during simulation.

关键词： Temperature sensors Voltage Electric vehicles Sensor systems Batteries Thermal analysis Sensors Circuit faults Integrated circuit modeling Testing

来源：评论

学校读者我要写书评

暂无评论

Reference Tracking for Constrained Uncertain Linear Systems by Stochastic MPC

引用

IFAC-PapersOnLine 2023年第2期56卷 10421-10427页

作者： Jannik Hahn Olaf Stursberg Control and System Theory Dept. of Electrical Engineering and Computer Science University of Kassel 34121 Kassel Germany

This paper addresses model predictive control of a class of linear systems subject to additive stochastic disturbances and constraints. The underlying stochastic optimal control problem combines inverse cumulative distribution functions with ellipsoid-in-polyhedron formulations to reduce the conservatism induced by constraint satisfaction. By use of terminal constraints and time-varying weights within the cost functional, the presented control scheme satisfies criteria for mean-square stability and can be adapted to reference-tracking problems for arbitrary reference signals.

关键词： Probabilistic Constraints Mean-Square Stability Predictive control Stochastic control Uncertain Systems

来源：评论

学校读者我要写书评

暂无评论

SB-AGT: A stochastic beam search-enhanced attention-based Gumbel tree framework for drug-drug interaction extraction from biomedical literature

引用

computers in Biology and Medicine 2025年 189卷 110011-110011页

作者： Saad, Eman Kishk, Sherif Ali-Eldin, Amr Saleh, Ahmed I. Communication and Information Technology Center Mansoura University Egypt Electronics and Communication Engineering Dept. Mansoura University Egypt Computer Engineering & Control Systems Dept. Mansoura University Egypt

Drug-Drug Interactions (DDI) and Chemical-Protein Interactions (CPI) detection are crucial for patient safety, as unidentified interactions may lead to severe Adverse Drug Reactions (ADRs). While extensive DDI and CPI information exists within biomedical literature, manual extraction by experts proves time-intensive and resource-demanding. This study presents SB-AGT: Stochastic Beam Search-enhanced Attention-based Gumbel Tree an innovative approach to automated DDI and CPI extraction through an attention-based architecture incorporating a modified Gumbel-Tree method with stochastic beam search optimization. SB-AGT leverages multi-head attention mechanisms and enhanced latent tree structures to effectively capture complex syntactic features and drug relationship patterns. Also, the methodology includes comprehensive preprocessing protocols and addresses dataset imbalance through hybrid sampling techniques. Experimental validation on the DDIExtraction 2013 and CHEMPROT datasets demonstrates the model's effectiveness, achieving precision, surpassing traditional approaches and showing competitive performance compared to contemporary pre-trained models. Through parametric analysis, we establish optimal beam search configurations that maximize the model's extraction accuracy. © 2025 Elsevier Ltd

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

DISTANCE BETWEEN SPECIES BY CONFUSION OPERATORS OF MULTI-CLASS CLASSIFIERS

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2025年第1期2025卷 171-182页

作者： Tarbă, Nicolae Irimescu, Ionela N. Pleavă, Ana M. Scarlat, Eugen N. Mihăilescu, Mona Doctoral School Computer Science and Engineering Department Faculty of Automatic Control and Computers National University of Science and Technology POLITEHNICA Bucharest Romania Applied Sciences Doctoral School National University of Science and Technology POLITEHNICA Bucharest Romania CAMPUS Research Center National University of Science and Technology POLITEHNICA Bucharest Romania Physics Dept National University of Science and Technology POLITEHNICA Bucharest Romania Physics Dept Research Center for Applied Sciences in Engineering National University of Science and Technology POLITEHNICA Bucharest Romania

We introduce a method to evaluate the similarities between classes of objects based on the confusion matrices coming from the multi-class machine learning (ML) predictors that operate in the vector space generated by the classes. Operation in the confusion domain allows us to use the distance as evaluation metric of the closeness of the relevant properties carried by the classes. We applied the method to semiquantitatively evaluate the effects of X-ray and carbon ion radiation on cultured SW1353 chondrosarcoma cells with respect to the non-irradiated reference. We prove that it is possible to draw useful information on the strength of cells nuclei changes. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Radiation effects

来源：评论

学校读者我要写书评

暂无评论

Exploring the Feasibility of Sleep Quality Evaluation with a Reduced Parameter Set

Exploring the Feasibility of Sleep Quality Evaluation with a...

引用

Smart World Congress (SWC), IEEE

作者： Michele Guagnano Sara Groppo Luigi Pugliese Massimo Violante Dept. of Control and Computer Engineering Politecnico di Torino Turin Italy

Sleep covers approximately one-third of life, providing the necessary recovery to fundamental body functions. Sleep deprivation and poor sleep quality cause several side effects in everyday life; among others, the efficiency of the immune system progressively decreases, enhancing the arise of pathologies. Therefore, the evaluation of sleep quality is crucial for providing information about personal health status. However, a uniform and robust method for the assessment of sleep quality is still missing. In this preliminary study, Obstructive Sleep Apneas (OSAs), sleep macro pattern and sleep micro pattern are identified and then combined to provide a comprehensive sleep evaluation. For this purpose, a subset of physiological variables (HR, HRV, SpO 2 , body movements) is derived from Polysomnography (PSG) and exploited for the development of rule-based algorithms. This reduced parameter set is selected considering further implementations on wearable off-the-shelf commercial devices.

关键词：

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：