检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Big Data, BigData 2024

作者： Kaddoura, Laila Miles Fernandez, Alexis Brown, Erin Ananthavaram, Neha Wang, Taehyung Department of Computer Science University of California Berkeley Department of Computer Science California State University Northridge

ISBN: (纸本)9798350362480

This study investigates the impact of automobile air conditioning systems on fuel consumption and gas emissions in hybrid and internal combustion engine vehicles using machine learning algorithms. Dynamic and static data were collected via an OBDII sensor from the vehicles examined, complemented by weather data sourced from the OpenWeatherMap API to capture external factors such as temperature and humidity during each trip. Machine learning models, including Linear Regression, XGBoost, and a Stacking ensemble model, were trained to predict fuel consumption rates over time, supplemented by an XGBoost Classifier to ascertain whether the air conditioning was in use during trips. The regressor models achieved low error scores after training and modifications, while the classifier achieved an accuracy of 99%. The findings from this research may inform future studies aimed at optimizing vehicle performance under varying road, driving, and weather conditions while minimizing energy consumption and harmful emissions. © 2024 IEEE.

关键词： Fuel consumption

来源：评论

学校读者我要写书评

暂无评论

Optimizing User-Centric Clustering and Pilot Assignment in Cell-Free Networks for Enhanced Spectral Efficiency

引用

IEEE Internet of Things Journal 2025年第13期12卷 23139-23153页

作者： Aboulfotouh, Ahmed Fadlullah, Zubair Md Fouda, Mostafa M. Ismail, Muhammad Niyato, Dusit Lakehead University Department of Computer Science Thunder BayON Canada Western University Department of Computer Science Ontario LondonN6G 2V4 Canada Idaho State University College of Science and Engineering Department of Electrical and Computer Engineering PocatelloID83209 United States Tennessee Tech University Faculty of Engineering Department of Computer Science CookevilleTN United States Nanyang Technological University School of Computer Science and Engineering Singapore

Cell-free networks have emerged as a new paradigm for beyond-5G networks, offering uniform coverage and improved control over interference. However, scalability poses a challenge in full cell-free networks, where all access points (APs) serve all users. This challenge is addressed by user-centric clustering, where each user is served by a subset of APs, reducing complexity while maintaining coverage. In this paper, we provide an analysis of the relation between the user-centric clustering and pilot assignment problems in cell-free networks, and introduce a formulation which decouples both problems enabling each to be solved independently. We present a general problem formulation for the user-centric clustering problem, allowing the use of diverse per-user and network-wide performance metrics. Specifically, we focus on one instance of this framework, utilizing per-user spectral efficiency and network-wide sum spectral efficiency (SE) as metrics. Additionally, we formulate the pilot assignment problem to minimize overall channel estimation error while considering the user-centric clusters in evaluating the desirability of pilot assignments, which leads to better performing solutions. Both problems are classified as binary nonlinear programs that are at least NP-hard. To solve these optimization problems, our proposed methodology employs sample average approximation coupled with surrogate optimization for the user-centric clustering problem and utilizes the genetic algorithm for the pilot assignment problem. Numerical experiments demonstrate that the optimized solutions surpass baseline solutions, leading to significant improvements in spectral efficiency. © 2014 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing 5G Enabled Solar Power Plant Performance through Reinforcement Learning 22

Enhancing 5G Enabled Solar Power Plant Performance through R...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Kaur, Kanwalinderjit Ramos, Jarl Christian California State University Department of Computer & Electrical Engineering & Computer Science BakersfieldCA United States

ISBN: (纸本)9798331508050

The utilization of fifth-generation wireless technology (5G) and artificial intelligence (AI) has opened many paths toward making solar power utility systems run more efficiently. 5G and AI have emerged within the last couple of years as competent technologies that can be used in various settings, including within the field of utility delivery. The main concern about this is how these technologies should be used in renewable energy systems and to what extent they improve operations. This research work is about 5G-enabled solar power systems. One of the models used AI-based implementation, while the other does not. Data for both models pertained to parameters such as power, state of charge, harmonic distortion, and voltage are collected. The results are then compared to determine the effectiveness of using AI with the system. Analysis has shown that implementing AI technology with 5G in a solar power system greatly improves power efficiency by stabilizing the voltage of the model. Furthermore, integrating AI with this model has proven to show unparalleled accuracy compared to a version of the model that does not use AI. It can therefore be inferred that usage of 5G with AI technologies will generally be an improvement over solar power implementations that do not use them. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient resource allocation in blockchain-based Cybertwin-driven 6G

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 103-114页

作者： Salim, Mikail Mohammed Pan, Yi Park, Jong Hyuk Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of Department of Computer Science Georgia State University Atlanta United States

Inefficient task scheduling schemes compromise network performance and increase latency for delay intolerant tasks. Cybertwin based 6G services support data logging of operational queries for appropriate resource allocation in Multi-Access Edge and Cloud Computing. In this paper, a Cybertwin assisted task scheduling scheme is proposed for energy-efficient job allocation to Edge-Cloud based on delay tolerance. Cybertwins using the Logger Function and the Digital Asset Function exchange Digital Assets with cloud operators using Smart Contracts to ensure maximum computational resources. The novelty of this study resides in using Communication Assistant Cybertwins to build profiles for all network entities and assign tasks based on their delay tolerance and the available resources of each Edge Datacenter and Cloud service provider. Compared with the Full Offloading scheme, experimental results demonstrate the higher energy efficiency of the task scheduling scheme. Offloading tasks to multiple data centers and smart contract-based selection of cloud operators result in reduced computation time. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

DisCovHAR: Contrastive Attention for Human Activity Recognition under Distribution Shifts

引用

IEEE Internet of Things Journal 2025年第12期12卷 21973-21983页

作者： Chen, Luke Odema, Mohanad Faruque, Mohammad Abdullah Al University of California at Irvine Department of Electrical Engineering and Computer Science IrvineCA92697 United States

Advances in Internet of Things (IoT) wearable sensors and edge-artificial intelligence (Edge-AI) have enabled practical realizations of machine learning (ML)-enabled mobile sensing applications like human activity recognition (HAR). The effective deployment of these data-driven models necessitates learning robust representations capable of handling prevalent distribution shifts (DS), including new users, device positions, rotations, and more. In that respect, contrastive learning (CL) has shown promise in learning transformation-invariant features, outperforming traditional HAR methods. However, recent findings reveal that the contrastive loss induces shrinkage and expansion of the feature space which may limit the generalization capacity of the model. To address this, we propose DisCovHAR, a contrastive attention method to selectively apply the contrastive loss to a subset of the feature space through the transformer encoder attention mechanism. Extensive experiments on three HAR datasets (DSADS, PAMAP2, and USCHAD) demonstrate its superiority over state-of-the-art methods. Specifically, our approach yields up to 4.47% and 7.82% average accuracy improvements in subject-wise and position-wise generalization settings. Furthermore, DisCovHAR demonstrates up to 5.07% increased robustness compared to prior methods under multivariate distribution shift scenarios. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

All-optical image denoising using a diffractive visual processor

引用

Light(science & Applications) 2024年第3期13卷 429-445页

作者： Çağatay Işıl Tianyi Gan Fazil Onuralp Ardic Koray Mentesoglu Jagrit Digani Huseyin Karaca Hanlong Chen Jingxi Li Deniz Mengu Mona Jarrahi Kaan Akşit Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCA 90095USA Bioengineering Department University of CaliforniaLos AngelesCA 90095USA California NanoSystems Institute(CNSI) University of CaliforniaLos AngelesCA 90095USA University College London Department of Computer ScienceLondonUnited Kingdom

Image denoising,one of the essential inverse problems,targets to remove noise/artifacts from input *** general,digital image denoising algorithms,executed on computers,present latency due to several iterations implemented in,e.g.,graphics processing units(GPUs).While deep learning-enabled methods can operate non-iteratively,they also introduce latency and impose a significant computational burden,leading to increased power ***,we introduce an analog diffractive image denoiser to all-optically and non-iteratively clean various forms of noise and artifacts from input images–implemented at the speed of light propagation within a thin diffractive visual processor that axially spans<250×λ,whereλis the wavelength of *** all-optical image denoiser comprises passive transmissive layers optimized using deep learning to physically scatter the optical modes that represent various noise features,causing them to miss the output image Field-of-View(FoV)while retaining the object features of *** results show that these diffractive denoisers can efficiently remove salt and pepper noise and image rendering-related spatial artifacts from input phase or intensity images while achieving an output power efficiency of~30–40%.We experimentally demonstrated the effectiveness of this analog denoiser architecture using a 3D-printed diffractive visual processor operating at the terahertz *** to their speed,power-efficiency,and minimal computational overhead,all-optical diffractive denoisers can be transformative for various image display and projection systems,including,e.g.,holographic displays.

关键词： remove rendering holographic

来源：评论

学校读者我要写书评

暂无评论

A machining center selection study using neural networks

引用

Neural Computing and Applications 2025年 1-38页

作者： Ic, Yusuf Tansel Yıldız, Burak Kececi, Barış Sert, Mustafa Department of Industrial Engineering Baskent University Ankara06970 Turkey Department of Computer Engineering Baskent University Ankara06970 Turkey Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States

Machining centers (MCs) are crucial high-technology machine tools that are widely used in the manufacturing industry. Since their high investment necessities, the selection of the appropriate MC for a company is an important task so that the company’s competitive advantages can be continued in the future. In the literature, there are many studies for MC selection using multi-criteria decision-making (MCDM) models and their fuzzy versions. This type of selection model must use selection criteria weighting procedures that are mainly based on subjective preferences. On the other hand, some attempts are provided in the literature to set objective decision-making models, such as the design of an experiment (DoE)-based Technique for Order Preferences by Similarity to the Ideal Solution (TOPSIS) model. In this study, we improved the DoE-based TOPSIS approach using neural network-based solutions and compared their capability of the MC selection studies against the classical MCDM and DoE-TOPSIS models. The proposed model can handle the newly generated scenarios using the Neural Networks. The feedforward neural network (FFNN)-based model utilizes machine learning techniques to overcome some of the challenges by modeling the complex relationships among various decision criteria without relying on human judgment for weighting. As a form of artificial neural network, FFNNs learned from large datasets and captured non-linear patterns, making them well-suited for the MC selection problem. Their capability to process high-dimensional inputs with numerous variables and interactions aligns effectively with the complexities of the MC selection problem. Therefore, the proposed FFNN model is very competitive against the DoE-TOPSIS and classical TOPSIS models. © The Author(s) 2025.

关键词： Cutting

来源：评论

学校读者我要写书评

暂无评论

Recent advances in tip-enhanced Raman spectroscopy probe designs

引用

Nano Research 2023年第4期16卷 5555-5571页

作者： Da Xu Boqun Liang Yaodong Xu Ming Liu Department of Electrical and Computer Engineering University of California-RiversideRiversideCalifornia 92521USA Materials Science and Engineering program University of California-RiversideRiversideCalifornia 92521USA

Tip-enhanced Raman spectroscopy(TERS)imaging is a super-resolution imaging technique that features the merits of both surface-enhanced Raman spectroscopy(SERS)and scanning probe microscopy(SPM),such as the high chemical sensitivity from the former and the nanoscale spatial resolution from the *** advantages make TERS an essential nanospectroscopic characterization technique for chemical analysis,materials science,bio-sensing,*** probes,the most critical factor determining the TERS imaging quality,are expected to provide a highly confined electromagnetic hotspot with a minimized scattering background for the generation of Raman signals with high spatial *** two decades of development,numerous probe design concepts have been proposed and *** review provides a comprehensive overview of the state-of-the-art TERS probe designs,from the working mechanism to the practical *** start with reviewing the recent development of TERS configurations and the corresponding working mechanisms,including the SPM platforms,optical excitation/collection techniques,and probe preparation *** then review the emerging novel TERS probe designs,including the remote-excitation probes,the waveguide-based nanofocusing probes,the metal-coated nanofocusing probes,the nanowire-assisted selective-coupling probes,and the tapered metal-insulator-metal *** discussion focuses on a few critical aspects,including the surface-plasmon-polariton(SPP)hotspot excitation technique,conversion efficiency,working frequency,and *** the end,we review the latest TERS applications and give a perspective on the future of TERS.

关键词： tip-enhanced Raman spectroscopy plasmonics scanning probe microscopy nanoscale imaging nanophotonics nanofocusing

来源：评论

学校读者我要写书评

暂无评论

A Local Differential Privacy Trajectory Protection Method Based on Temporal and Spatial Restrictions for Staying Detection

引用

Tsinghua science and Technology 2024年第2期29卷 617-633页

作者： Weiqi Zhang Zhenzhen Xie Akshita Maradapu Vera Venkata Sai Qasim Zia Zaobo He Guisheng Yin College of Computer Science and Technology Harbin Engineering UniversityHarbin 150001China School of Computer Science and Technology Shandong UniversityQingdao 266237China Department of Computer Science Georgia State UniversityAtlantaGA 30303USA College of Information Science and Technology Jinan UniversityGuangzhou 510632China

The widespread availability of GPS has opened up a whole new market that provides a plethora of location-based ***-based social networks have become very popular as they provide end users like us with several such services utilizing GPS through our ***,when users utilize these services,they inevitably expose personal information such as their ID and sensitive location to the *** to untrustworthy servers and malicious attackers with colossal background knowledge,users'personal information is at risk on these ***,many privacy-preserving solutions for protecting trajectories have significantly decreased utility after *** have come up with a new trajectory privacy protection solution that contraposes the area of interest for ***,Staying Points Detection Method based on Temporal-Spatial Restrictions(SPDM-TSR)is an interest area mining method based on temporal-spatial restrictions,which can clearly distinguish between staying and moving ***,our privacy protection mechanism focuses on the user's areas of interest rather than the entire ***,our proposed mechanism does not rely on third-party service providers and the attackers'background knowledge *** test our models on real datasets,and the results indicate that our proposed algorithm can provide a high standard privacy guarantee as well as data availability.

关键词： local-differential privacy stay points detection trajectory data areas of interest temporal-spatial clustering

来源：评论

学校读者我要写书评

暂无评论

Leakage Thresholds and Security Trade-offs in Finite Blocklength Wiretap Channels

Leakage Thresholds and Security Trade-offs in Finite Blockle...

引用

2025 International Conference on Computing, Networking and Communications, ICNC 2025

作者： Sodagari, Shabnam California State University Department of Computer Engineering Computer Science Long BeachCA90840 United States

ISBN: (数字)9798331520960

ISBN: (纸本)9798331520960

This work discusses the bounds for the wiretap channel (WTC) in the finite blocklength regime, characterizing the behavior of the performance trade-off between information delivery to the legitimate receiver and information leakage to the eavesdropper as a function of blocklength. Since the error probability at the legitimate receiver is the same as that of a conventional point-to-point channel, the characterization of the former builds on the finite blocklength analysis for that case. The information leakage bound relies on the analysis of the corresponding leakage density. This paper extends these concepts by incorporating the use of the Berry-Esseen theorem in assessing the convergence rates of leakage and secrecy metrics to their asymptotic values, which provides a refined analytical tool to evaluate the performance of secrecy systems under finite blocklength constraints. Furthermore, this approach facilitates a quantification of the trade-offs involved, integrating concepts such as the aggregate leakage rate and empirical average leakage, thus enabling a more comprehensive understanding of how system parameters affect the overall secrecy performance. This allows for a more detailed exploration of the dependencies between blocklength, secrecy, and reliability trade-offs required to balance effective communication against security imperatives. These analyses also highlight the critical balance necessary between ensuring low probability of error for the legitimate receiver while maintaining stringent secrecy requirements against an eavesdropper. Furthermore, the study introduces metrics such as aggregate leakage rate and empirical average leakage, providing new insights into how these factors interplay to influence the overall performance of secure communication systems. © 2025 IEEE.

关键词： Leak detection

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：