检索结果-内蒙古大学图书馆

Interference Estimation via Model-Based Deep Learning in Grant-Free Networks

IEEE Wireless Communications Letters 2025年

作者： Pereira, Diogo Oliveira, Rodolfo da Costa, Daniel Benevides Kim, Hyong Instituto de Telecomunicações Lisbon1049-001 Portugal Universidade Nova de Lisboa Dep. de Engenharia Electrotécnica e de Computadores Faculdade de Ciências e Tecnologia Caparica2829-516 Portugal Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia Carnegie Mellon University Electrical and Computer Engineering PittsburghPA United States

This paper presents a novel approach for estimating interference distribution parameters in grant-free access networks using a model-based deep learning (DL) framework. Our method integrates the precision of analytical models with the adaptability of deep learning algorithms. Specifically, we employ an analytical model to generate labeled data, which enhances the deep learning model’s ability to estimate interference levels. Through extensive validation, we demonstrate that our approach accurately estimates interference across a broad range of scenarios, including operating regions not covered during the model’s training. Moreover, our method also estimates the spatial density of interfering nodes, making it a valuable tool for interference management in grant-free access networks. This methodology offers a robust solution for improving interference estimation accuracy, aiding decision-making at the Medium Access control (MAC) and physical layers in grant-free access schemes. © 2025 IEEE. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Gait-Based User Identification for Smart Home: When Machine Learning Meets FBG Accelerometers

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Alhussein, Ghada Chi, Hao Ran Alberto, Nelia Antunes, Paulo Hadjileontiadis, Leontios Radwan, Ayman Domingues, M. Fatima Instituto de Telecomunicações-University of Aveiro Aveiro Portugal Instituto de Telecomunicações I3N and Dep. of Physics-University of Aveiro Aveiro Portugal Khalifa University of Science and Technology Department of Biomedical Engineering and Biotechnology Abu Dhabi United Arab Emirates Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece Instituto de Telecomunicações Instituto Superior Tècnico -University of Lisbon Lisbon Portugal

Advancements in fiber optic sensor technology and telecommunications have paved the way for innovative health monitoring systems. However, previous works in this area have often been limited by the lack of comprehensive datasets, hindering the development of accurate and robust solutions. This paper addresses this gap by presenting a novel dataset and approach to gait-based user identification using a set of four optical Fiber Bragg Grating (FBG) sensor-based accelerometers, integrated into smart home environments. By computing features such as entropy, mean, standard deviation, kurtosis, and skewness from raw signals, and employing three unsupervised machine learning models-K-means, DB-scan, and Gaussian Mixture Model (GMM)-we achieve high accuracy in distinguishing individuals. Our dataset results for each sensor are as follows: for Sensor 1, K-means with a Silhouette Score of 0.3038 and Davies-Bouldin Index of 1.1238;for Sensor 2, K-means with a Silhouette Score of 0.3543 and Davies-Bouldin Index of 0.9659;for Sensor 3, DB-scan with a Silhouette Score of 0.2650 and Davies-Bouldin Index of 0.6855;and for Sensor 4, K-means with a Silhouette Score of 0.3949 and Davies-Bouldin Index of 1.0438. This approach not only enhances user identification but also facilitates personalized healthcare applications and unobtrusive monitoring. © 1975-2011 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Poynting's Vector Modelling for Cyclostationary Electromagnetic Emissions from PCB

Poynting's Vector Modelling for Cyclostationary Electromagne...

引用

2020 Baltic URSI Symposium, URSI 2020

作者： Kuznetsov, Yury Baev, Andrey Konovalyuk, Maxim Gorbunova, Anastasia Russer, Johannes A. Moscow Aviation Institute Theoretical Radio Engineering Dep. Moscow Russia Technical University of Munich Department of Electrical and Computer Engineering Munich Germany

ISBN: (纸本)9788394942199

Estimation of statistical characteristics for radiated electromagnetic emissions caused by a PCB can be implemented by statistical signal processing of time domain signals measured by a near-field scanning system. The relation between the source signal and the signals measured by the nearfield probe at each scanning point can be modelled by linear transformation of the source signal. In this paper a modeling procedure for a near-field to far-field propagator based on Jefimenko's equations is presented. The radial component of instantaneous power density represented by Poyting's vector was derived from the modelled electric and magnetic far fields components. The synchronized impulse responses can be used for computer aided prediction of the spatial-time evolution of the cyclostationary characteristics in the environment surrounding the PCB. The 2D periodic ACF of the far-field shows the cyclostationary properties similar to the properties of the initial random bit sequence. © 2020 Warsaw University of Technology.

关键词： cyclostationary electromagnetic fields impulse response Jefimenko's equations linear-time invariant system near-field measurements Poynting's vector stochastic processes time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Joint Resource Allocation and User Fairness Optimization in mmWave-NOMA HetNets

Reinforcement Learning Based Joint Resource Allocation and U...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Sima Sobhi-Givi Mahdi Nouri Mahrokh G. Shayesteh Hashem Kalbkhani Zhiguo Ding Electrical and Computer Engineering Department Urmia University Urmia Iran Elect. Eng. Dep. Sharif university of technology Mobile Telecommunication Company of Iran (MCI) International Telecommunication Union (ITU) Tehran Iran ACRI Elec. Eng. Dep. Wireless Research Lab Sharif University of Technology Tehran Iran Faculty of Elec. Eng. Urmia University of technology Urmia Iran School of Electrical and Electronic Engineering The University of Manchester Manchester UK

In this paper, we propose heterogeneous network (HetNet) with mmWave and hybrid non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) transmission, where uplink (UL) of macrocell users (MCUs) and downlink (DL) of small cell users (SCUs) share the same resource block (RB) to increase the network capacity. Also, an imperfect successive interference cancelation (I-SIC) decoding is considered due to hardware impairment of the real-world NOMA systems. We formulate the problem of joint power and resource block (RB) allocation to maximize rate-fairness and sum-rate by considering minimum quality of service (QoS) requirements. Reinforcement learning (RL) named Q-learning (QL) and deep Q-learning network (DQN) algorithms are employed to solve these problems. The results indicate that the proposed QL and DQN algorithms increase the fairness and sum-rate while low number of iterations is required.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Based Model Predictive control for Quadcopters with Dual Gaussian Process

arXiv

引用

arXiv 2021年

作者： Liu, Yuhan Tóth, Roland The Harbin Institute of Technology Department of Control Science and Engineering Harbin China The Eindhoven University of Tech. Dep. of Electrical Eng. Control Systems Group Eindhoven Netherlands The Institute for Computer Science and Control Budapest Hungary

An important issue in quadcopter control is that an accurate dynamic model of the system is nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. Gaussian process (GP) based estimation is an effective tool to learn unknown dynamics from input/output data. However, conventional GP-based control methods often ignore the computational cost associated with accumulating data during the operation of the system and how to handle forgetting in continuous adaption. In this paper, we present a novel Dual Gaussian Process (DGP) based model predictive control strategy that improves the performance of a quadcopter during trajectory tracking. The bio-inspired DGP structure is a combination of a long-term GP and a short-term GP, where the long-term GP is used to keep the learned knowledge in memory and the short-term GP is employed to rapidly compensate unknown dynamics during online operation. Furthermore, a novel recursive online update strategy for the short-term GP is proposed to successively improve the learnt model during online operation in an efficient way. Numerical simulations are used to demonstrate the effectiveness of the proposed strategy. © 2021, CC BY-NC-SA.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Next Generation Image Watermarking via Combined DWT-SVD Technique

Next Generation Image Watermarking via Combined DWT-SVD Tech...

引用

Cyber Resilience (ICCR), International Conference on

作者： Qais Al-Na'amneh Ammar Almomani Ahmad Nasayreh Khalid M.O. Nahar Hasan Gharaibeh Rabia Emhamed Al Mamlook Mohammad Alauthman Department of Cyber Security Applied Science Private University Amman Jordan School of Computing Skyline University College Sharjah United Arab Emirates I. T. department AlHuson University College AlBalqa Applied University Irbid Jordan Department of Computer Sciences Yarmouk University Irbid Jordan Faculty of Information Technology Computer Sciences Yarmouk University Irbid Jordan Dep. of Business Administration Trine University Indiana USA Dep.of Mechanical and Industrial Engineering University of Zawia Tripoli Libya Department of Information Security Faculty of Information Technology University of Petra Amman Jordan

ISBN: (数字)9798350394962

ISBN: (纸本)9798350394979

Personal computers and the Internet are used in different areas and are easier to use. Most data is easy to transmit and duplicate in digital format, and being tampered with and stolen easily leads to issues for content owners and service providers. The Paper describes a secure (tampering-resistant) method for watermarking images for protection and authentication and digital media like audio, video, and multimedia data, and a combination of singular value decomposition (SVD) and Discrete wavelet transform (DWT) for insertion watermark by MATLAB to increase accuracy, simplicity, and flexibility Readability, secure robustness, and imperceptibility the visibility of the image. The proposed algorithm consists of three main steps: Firstly, we decomposed the original image into four sub-bands and the original watermark. Secondly, embed the watermark in the LL sub-band by replacing the singular value for the watermark. Finally, embed a watermark in the other three sub-bands by adding LL values for a watermark in each sub-band in the original image.

关键词： Resistance PSNR Watermarking Transforms Streaming media Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Foetus Brain MRI Based on K-nn Algorithm, A Case Study 12th

Segmentation of Foetus Brain MRI Based on K-nn Algorithm, A ...

引用

12th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2020 and 16th International Conference on Information Assurance and Security, IAS 2020

作者： Salgado, Paulo Azevedo Perdicoúlis, Teresa-Paula CITAB-Dep. de Engenharias ECT UTAD Quinta de Prados Vila Real5000-801 Portugal Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Rua Silvio Lima-Polo II Coimbra3030-290 Portugal

ISBN: (纸本)9783030736880

The segmentation of magnetic resonance images of the fetal brain has been emerging as a clinical tool to detect abnormalities during the development of the foetus. Since the brain is still in development, a mixture of regions of white matter, grey matter and transition structures that are related to brain growth are still associated with it. In this work, two versions of the K-nearest neighbour algorithm are proposed as the core method for the recognition of different regions of an image;the first one is a refinement of the standard algorithm since some statistics are associated with the pixel, and the second a reinforcing iterative version of the same method. Both versions are used to identify 3 apriori selected regions—the brain, the intracranial region and the remaining part of the foetus. The effectiveness of the method has been demonstrated in a magnetic resonance image segmentation that was first pre-processed with digital filters for feature extraction. The present study illustrates the capabilities of this type of method to support obstetricians and general practitioners to assess the foetus and, in particular, its brain. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

The Realization Factors of Taiwan's Low Altitude Airspace Economy and UAM: Analysis and Evaluation

The Realization Factors of Taiwan's Low Altitude Airspace Ec...

引用

IEEE International Conference on e-Business engineering (ICEBE)

作者： Tung-Ling Wu Chih-Ming Kung Guan-Ting Lin Kuen-Yu Tsai Guang-Yun Meng Yu-Che Huang Wan-Shu Cheng Institute of Transportation at Ministry of Transportation and Communications Taiwan R.O.C. Dep. Of Information Technology&Communication Shin Chin Univeristy Kaohsiung Campus Taiwan R.O.C. Dep. of Computer Science and Information Management Providence University Taichung Taiwan R.O.C. Department of Electrical Engineering National Taiwan Univeristy Taipei Taiwan R.O.C. Executive Officer Center for Research on High-Performance Remote Sensing and Urban Informatics NTU Taiwan R.O.C.

ISBN: (数字)9798350365856

ISBN: (纸本)9798350365863

Low altitude airspace economy applications will be of highly effective in a wide range of civil activities and will be a critical element in the smart cities of the future. In view of the main features of unmanned aerial vehicle (UAV), such as automatic piloting system, access to uninhabited areas, low cost compared to road and manned aircraft, shorter delivery time, and the ability to carry heavy payloads, it is important to recognize that UAVs can be used for a wide range of civil activities. With the development of these applications in full swing around the world, in addition to advanced communications technology and other related infrastructure, business demand and a favorable investment climate, clarity, definiteness and feasible regulations in the Taiwanese environment are also essential. Based on the premise of local economic strength, the technical level of the telecommunication industry, and commercial demands, Taiwan should establish a rational standard for the UAV regulatory system as soon as possible, so as to facilitate the development of UAM and to ensure the international competitiveness of the related technologies for market development,

关键词： Industries Technological innovation Transportation Autonomous aerial vehicles Regulation Communications technology Aircraft Standards Drones Investment

来源：评论

学校读者我要写书评

暂无评论

Preventing unauthorized use of proprietary data: Poisoning for secure dataset release

arXiv

引用

arXiv 2021年

作者： Fowl, Liam Chiang, Ping-Yeh Goldblum, Micah Geping, Jonas Bansal, Arpit Czaja, Wojtek Goldstein, Tom Department of Mathematics University of Maryland United States Department of Computer Science University of Maryland United States Dep. of Electrical Engineering and Computer Science University of Siegen Germany

Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of released data to train proprietary models that give them an edge over their competitors. These two behaviors can be in conflict as an organization wants to prevent competitors from using their own data to replicate the performance of their proprietary models. We solve this problem by developing a data poisoning method by which publicly released data can be minimally modified to prevent others from training models on it. Moreover, our method can be used in an online fashion so that companies can protect their data in real time as they release it. We demonstrate the success of our approach on ImageNet classification and on facial recognition. © 2021, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing value creation in Energy Communities through flexibility management and network ancillary services provision

Enhancing value creation in Energy Communities through flexi...

引用

2022 ECEEE Summer Study on Energy Efficiency: Agents of Change

作者： Patrão, Carlos Matos, Luisa Landeck, Jorge Klein, Lurian Mendes, Gonçalo da Silva, Nuno Pinho Fulgêncio, Nuno O'Callaghan, Tim Stevens, Peter Institute of Systems and Robotics and Cleanwatts Dep. of Electrical and Computer Engineering University of Coimbra Portugal Cleanwatts Coimbra Portugal University of Coimbra and Cleanwatts LIBPhys Department of Physics University of Coimbra Portugal Lappeenranta-Lahti University of Technology LUT Finland R&D Nester Centro de Investigação em Energia REN Sacavém Portugal Electric Corby Corby Enterprise Centre England United Kingdom

ISBN: (纸本)9789198827002

The Clean Energy for all Europeans policy package has opened the way for a major transition of the European energy landscape towards customer empowerment and local energy markets development. The European Green Deal, the Fit for 55 % package and the European Directives revision are pushing forward Renewable Energy Communities, which will disrupt the energy sector and overcome limitations of existing rigid energy markets. The rise of distributed energy technologies is fostering the development of customer-centered services such as peer-to-peer energy trading. However, adequate tools and business models to interface and engage with energy markets are still lacking. The H2020 FleXunity project is addressing the emerging market needs by developing a technological platform, that combines advanced artificial intelligence algorithms, blockchain technology and demand response services, to exploit new business models that could value the aggregation of small-scale energy assets. Although the concept of these platforms is relatively well known, their real-world implementation and validation is still at an early stage. This paper presents the FleXunity project's main objectives, details of the Virtual Power Plant managing Platform under development and the characteristics of two distinct real world pilot Energy Communities already dep.oyed in the UK and Iberia. It also presents an analysis of the role that Demand Response activities and indep.ndent aggregation could play in Energy Communities, and specifically explores the role of Demand Response in the balancing markets of Finland, UK, Spain, and Portugal. Focusing on the pilot markets, the project also identifies the most promising balancing services to be provided by Energy Communities, by surveying and framing the existing regulatory qualification requirements. © 2022 European Council for an Energy Efficient Economy. All rights reserved.

关键词： Smart power grids

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：