检索结果-内蒙古大学图书馆

A Survey on Scalable LoRaWAN for Massive IoT: Recent Advances, Potentials, and Challenges

IEEE Communications Surveys and Tutorials 2023年第3期25卷 1841-1876页

作者： Jouhari, Mohammed Saeed, Nasir Alouini, Mohamed-Slim Amhoud, El Mehdi Mohammed Vi Polytechnic University School of Computer Science Ben Guerir43150 Morocco United Arab Emirates University Department of Electrical and Communication Engineering Al Ain United Arab Emirates King Abdullah University of Science and Technology Computer Electrical and Mathematical Sciences and Engineering Division Thuwal23955-6900 Saudi Arabia

Long-range (LoRa) technology is most widely used for enabling low-power wide area networks (WANs) on unlicensed frequency bands. Despite its modest data rates, it provides extensive coverage for low-power devices, making it an ideal communication system for many Internet of Things (IoT) applications. In general, LoRa is considered as the physical layer, whereas LoRaWAN is the medium access control (MAC) layer of the LoRa stack that adopts a star topology to enable communication between multiple end devices (EDs) and the network gateway. The chirp spread spectrum modulation deals with LoRa signal interference and ensures long-range communication. At the same time, the adaptive data rate mechanism allows EDs to dynamically alter some LoRa features, such as the spreading factor (SF), code rate, and carrier frequency to address the time variance of communication conditions in dense networks. Despite the high LoRa connectivity demand, LoRa signals interference and concurrent transmission collisions are major limitations. Therefore, to enhance LoRaWAN capacity, the LoRa Alliance released many LoRaWAN versions, and the research community has provided numerous solutions to develop scalable LoRaWAN technology. Hence, we thoroughly examine LoRaWAN scalability challenges and state-of-the-art solutions in both the physical and MAC layers. These solutions primarily rely on SF, logical, and frequency channel assignment, whereas others propose new network topologies or implement signal processing schemes to cancel the interference and allow LoRaWAN to connect more EDs efficiently. A summary of the existing solutions in the literature is provided at the end of the paper, describing the advantages and disadvantages of each solution and suggesting possible enhancements as future research directions. © 1998-2012 IEEE.

关键词： Wide area networks

来源：评论

学校读者我要写书评

暂无评论

Stochastic Physics-Informed Deep Generative Network Scenario Generation: Application on Responsive Residential Load Management

Stochastic Physics-Informed Deep Generative Network Scenario...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Afrasiabi, Mousa Afrasiabi, Shahabodin Allahmoradi, Sarah Aghaei, Jamshid Chung, C.Y. University of Saskatchewan Department of Electrical and Computer Engineering Saskatoon Canada Lappeenranta University of Technology School of Energy Systems Department of Electrical Engineering Lappeenranta Finland Central Queensland University School of Engineering and Technology Department of Electrical Engineering Rockhampton Australia The Hing Kong Polytechnic University Department of Electrical Engineering Hong Kong

ISBN: (纸本)9781665471640

This paper introduces a stochastic model for the optimal residential responsive loads power scheduling considering participants' satisfaction. In this context, firstly, a physical-informed based generative adversarial network (PI-GAN) network is designed for scenario generation with a high correlation with the actual data. In this network, conventional GANs are improved to learn spatial-temporal features of the residential loads and physics-informed concepts. To realize the spatial feature of the complex and highly nonlinear time series like residential loads, a residual convolutional neural network (Res-CNN) is considered to learn the spatial features, while the fully temporal features are realized by gated recurrent neural networks (GNN). Then, generated scenarios are used to cover the uncertainty associated with residential loads and provide the optimal results for responsive loads, including shiftable and curtailable loads. The numerical results on actual data in London, England, verify the effectiveness of the proposed stochastic framework and superiority by comparison with conditional GAN and improved version of GAN in scenario generations impact of stochastic demand response program. © 2023 IEEE.

关键词： Demand response gated recurrent neural network physics-informed based generative adversarial network residual convolutional neural network scenario-generation

来源：评论

学校读者我要写书评

暂无评论

Online Retail Customer Segmentation using RFM Quantiles and Clustering Technique 4

Online Retail Customer Segmentation using RFM Quantiles and ...

引用

4th International Conference on computer, Communication, Control and Information Technology, C3IT 2024

作者： Majilya, Mouli Maji, Giridhar Ghosh, Partha Sen, Soumya A.K.Choudhury School of Information Technology University of Calcutta Kolkata India Asansol Polytechnic Department of Electrical Engineering Asansol India Academy of Technology Department of Computer Science and Engineering Adisaptagram India

ISBN: (纸本)9798350389128

In the fiercely competitive landscape of modern business, making effective decisions is imperative for generating substantial revenue. With organizations employing diverse strategies to stay ahead, leveraging data for informed decision-making is crucial. Understanding individual preferences and purchasing behaviors can be challenging, but machine learning techniques offer a solution by organizing and analyzing vast datasets. Customer segmentation, particularly through K-means clustering, is instrumental in identifying target groups with similar attributes and interests. The present study focuses on customer clustering method-ologies to give businesses a competitive edge. By collecting, analyzing, and visualizing customer data, we aim to develop a data science model that utilizes K-means clustering and the RFM model (Recency, Frequency, Monetary) for existing customers. Utilizing the UK's e-commerce dataset, which delves into customer purchasing behaviors, we aim to group customers into clusters such as high-value customers, mid-range, and those at risk of churn based on RFM scores. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network

Power System Transient Security Assessment using Unsupervise...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Afrasiabi, Shahabodin Allahmoradi, Sarah Liang, Xiaodong Afrasiabi, Mousa Aghaei, Jamshid Chung, C.Y. University of Saskatchewan Department of Electrical and Computer Engineering Saskatoon Canada Lappeenranta University of Technology School of Energy Systems Department of Electrical Engineering Lappeenranta Finland Central Queensland University School of Engineering and Technology Department of Electrical Engineering Rockhampton Australia The Hing Kong Polytechnic University Department of Electrical Engineering Hong Kong

ISBN: (纸本)9781665471640

This paper introduces an unsupervised deep Bayesian network, built upon normalizing flow and deep Bayesian network principles, to precisely evaluate the transient security condition of a power system. The proposed approach can capture locational and temporal features using an imbalanced dataset, is noise-model-free, and can handle unlabeled data. It can learn interdependencies between different signals and understand high-dimensional signals in power systems. To validate its effectiveness, the proposed method is studied using the New England power system and shows accuracy and reliability in comparison with state-of-the-art deep networks (convolutional neural network (CNN) and long short-term memory (LSTM)) and shallow networks (support vector machine (SVM) and artificial neural network (ANN)). © 2023 IEEE.

关键词： Bayesian network imbalanced dataset noise-model free normalizing flow transient security assessment unsupervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning

引用

ACM Transactions on Management Information Systems 2025年第2期16卷 1-24页

作者： Liu, Xiao-Yang Zhu, Rongyi Zha, Daochen Gao, Jiechao Zhong, Shan White, Matt Qiu, Meikang Department of Computer Science Rensselaer Polytechnic Institute Columbia University New York United States Department of Electrical Engineering Columbia University New York United States Department of Computer Science University of Rochester Rochester United States Department of Computer Science Rice University Houston United States Department of Computer Science University of Virginia Charlottesville United States Executive Director PyTorch Foundation Gm of AI Linux Foundation CA United States School of Computer and Cyber Sciences Augusta University Augusta United States

The surge in interest and application of large language models (LLMs) has sparked a drive to fine-tune these models to suit specific applications, such as finance and medical science. However, concerns regarding data privacy have emerged, especially when multiple stakeholders aim to collaboratively enhance LLMs using sensitive data. In this scenario, federated learning becomes a natural choice, allowing decentralized fine-tuning without exposing raw data to central servers. Motivated by this, we investigate how data privacy can be ensured in LLM fine-tuning through practical federated learning approaches, enabling secure contributions from multiple parties to enhance LLMs. Yet, challenges arise: (1) despite avoiding raw data exposure, there is a risk of inferring sensitive information from model outputs, and (2) federated learning for LLMs incurs notable communication overhead. To address these challenges, this article introduces DP-LoRA, a novel federated learning algorithm tailored for LLMs. DP-LoRA preserves data privacy by employing a Gaussian mechanism that adds noise in weight updates, maintaining individual data privacy while facilitating collaborative model training. Moreover, DP-LoRA optimizes communication efficiency via low-rank adaptation, minimizing the transmission of updated weights during distributed training. The experimental results across medical, financial, and general datasets using various LLMs demonstrate that DP-LoRA effectively ensures strict privacy constraints while minimizing communication overhead. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

On a Sparse Shortcut Topology of Artificial Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第4期3卷 595-608页

作者： Fan, Feng-Lei Wang, Dayang Guo, Hengtao Zhu, Qikui Yan, Pingkun Wang, Ge Yu, Hengyong Rensselaer Polytechnic Institute Department of Biomedical Engineering TroyNY12180 United States University of Massachusetts Department of Electrical and Computer Engineering LowellMA01854 United States

In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs to later layers. Despite the extraordinary effectiveness of shortcuts, there remain open questions on the mechanism and characteristics. For example, why are shortcuts powerful? Why do shortcuts generalize well? In this article, we investigate the expressivity and generalizability of a novel sparse shortcut topology. First, we demonstrate that this topology can empower a one-neuron-wide deep network to approximate any univariate continuous function. Then, we present a novel width-bounded universal approximator in contrast to depth-bounded universal approximators and extend the approximation result to a family of equally competent networks. Furthermore, with generalization bound theory, we show that the proposed shortcut topology enjoys excellent generalizability. Finally, we corroborate our theoretical analyses by comparing the proposed topology with popular architectures, including ResNet and DenseNet, on well-known benchmarks and perform a saliency map analysis to interpret the proposed topology. Our work helps understand the role of shortcuts and suggests further opportunities to innovate neural architectures. © 2020 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A machine learning-guided design and manufacturing of wearable nanofibrous acoustic energy harvesters

引用

Nano Research 2024年第10期17卷 9181-9192页

作者： Negar Hosseinzadeh Kouchehbaghi Maryam Yousefzadeh Aliakbar Gharehaghaji Safoora Khosravi Danial Khorsandi Reihaneh Haghniaz Ke Cao Mehmet R.Dokmeci Mohammad Rostami Ali Khademhosseini Yangzhi Zhu Terasaki Institute for Biomedical Innovation Los AngelesCA 91367USA Department of Textile Engineering Amirkabir University of Technology(Tehran Polytechnic)Hafez Avenue*** TehranIran Department of Electrical and Computer Engineering University of British ColumbiaVancouverBC V6T1Z4Canada Chemical Sciences Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Department of Computer Science University of Southern CaliforniaLos AngelesCA 90007USA

Nanofibrous acoustic energy harvesters(NAEHs)have emerged as promising wearable platforms for efficient noise-to-electricity conversion in distributed power energy systems and wearable sound amplifiers for assistive listening ***,their reallife efficacy is hampered by low power output,particularly in the low-frequency range(<1 kHz).This study introduces a novel approach to enhance the performance of NAEHs by applying machine learning(ML)techniques to guide the synthesis of electrospun polyvinylidene fluoride(PVDF)/polyurethane(PU)nanofibers,optimizing their application in wearable *** use a feed-forward neural network along with solving an optimization problem to find the optimal input values of the electrospinning(applied voltage,nozzle-collector distance,electrospinning time,and drum rotation speed)to generate maximum output performance(acoustic-to-electricity conversion efficiency).We first prepared a dataset to train the network to predict the output power given the input variables with high *** introducing the neural network,we fix the network and then solve an optimization problem using a genetic algorithm to search for the input values that lead to the maximum energy harvesting *** ML-guided wearable PVDF/PU NAEH platform can deliver a maximal acoustoelectric power density output of 829μW/cm^(3) within the surrounding noise *** addition,our system can function stably in a broad frequency(0.1-2 kHz)with a high energy conversion efficiency of 66%.Sound recognition analysis reveals a robust correlation exceeding 0.85 among lexically akin terms with varying sound intensities,contrasting with a diminished correlation below 0.27 for words with disparate semantic ***,this work provides a previously unexplored route to utilize ML in advancing wearable NAEHs with excellent practicability.

关键词： wearable electronics acoustic energy harvester machine learning piezoelectric nanogenerator electrospun nanofiber

来源：评论

学校读者我要写书评

暂无评论

A Survey on Model Predictive Control of DFIGs in Wind Energy Conversion Systems

引用

CSEE Journal of Power and Energy Systems 2024年第3期10卷 1085-1104页

作者： Shuo Yan Junyu Chen Minghao Wang Yongheng Yang Jose M.Rodriguez STEM College RMIT UniversityMelbourneAustralia Hong Kong Polytechnic University Hong KongChina State Key Laboratory of Internet of Things for Smart City(UM) Department of Electrical and Computer EngineeringUniversity of MacaoMacaoChina College of Electrical Engineering Zhejiang UniversityHangzhou 310027China Universidad San Sebastin Campus BellavistaSantiago de ChileCLSantiago de Chile 000000Chile IEEE

This paper presents a comprehensive study on the model predictive control(MPC)of doubly fed induction generators(DFIG)in wind energy conversion systems(WECS);in particular the MPC of the rotor side *** general principle of prevalent MPC strategies is discussed to introduce the theoretical framework in the first ***,mainstream and high-performance MPC methods of DFIGs have been identified as model predictive current control(MPCC),model predictive torque control(MPTC),and model predictive power control(MPPC).Starting from analyzing dynamic models,these MPC strategies are investigated in terms of operating principles and technical *** paper further investigates implementation of MPC strategies in unbalanced *** on the quantitative and qualitative analysis of several case studies,performance of various MPC schemes is compared and their special features are *** for designing MPC strategies of DFIGs in WECS are provided.

关键词： Doubly fed induction generator(DFIG) model predictive control(MPC) wind energy

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Drone Simulator 10

A Lightweight Drone Simulator

引用

10th International Conference on Software Defined Systems, SDS 2023

作者： Blake Putnam, Evan Nihal Senarath, Dylan Ramirez Urquijo, Giselle Tunc, Cihan Bryce, Renee California State Polytechnic University Humboldt Department of Computer Science ArcataCA United States California State Polytechnic University Pomona Department of Electrical and Computer Engineering PomonaCA United States University of North Texas Department of Computer Science and Engineering DentonTX United States

ISBN: (纸本)9798350382235

Drones are valuable assets across industries for a variety of purposes, including but not limited to surveillance, transportation, delivery, smart agriculture, etc. However, drone-related studies may require significant costs to purchase, configure, and deploy to study algorithms and how drones interact with each other. Alternatively, drone simulators can provide a lower-cost option to investigate drones and related algorithms. Nevertheless, drone simulators on the market today tend to be computationally heavy, have a steep learning curve, and may be overwhelming for abstract problem-solving studies. There is a need for an inexpensive and easy testing alternative for researchers and for high-level algorithm development. In this paper, we present a lightweight and easy-to-use drone simulator that allows the definition of multiple drones with their sensors, actuators, speed, and battery limit as well as their communication among themselves. The simulator also allows the definition of the simulation world using small blocks that can be defined using different parameters. We presented two scenarios, such as package delivery and survey area coverage, to show the capabilities of the simulator. The simulator information can be achieved from our group website. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

GA-based Charger Deployment Algorithm in Indoor Wireless Rechargeable Sensor Networks

引用

Journal of Internet Technology 2023年第2期24卷 487-494页

作者： Fang, Zekun Chien, Wei-Che Zhang, Cong Hang, Nghiem Thuy Chen, Wei-Ming Department of Information Management National Dong Hwa University Taiwan Department of Computer Science and Information Engineering National Dong Hwa University Taiwan School of Electrical and Electronic Engineering Wuhan Polytechnic University China Department of Chinese Studies Vietnam National University Viet Nam

The advancement of Internet of Things technology has made continuous environmental monitoring a crucial requirement for various applications. To address the issue of the network life cycle, Wireless Rechargeable Sensor Networks (WRSNs) have emerged as a promising solution. This research is focused on WRSN applications in indoor settings such as the Industrial Internet of Things and indoor greenhouses. In such scenarios, rechargeable wireless sensing devices can gather the required information, reducing equipment costs and eliminating the inconvenience of wired sensors. This study proposes the utilization of a genetic algorithm to optimize the deployment of chargers in indoor environments. Compared to greedy algorithms, this approach can determine the best solution for charger deployment and minimize deployment expenses. © 2023 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Wireless sensor networks

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：