检索结果-内蒙古大学图书馆

International Conference on Distributed Computing in Sensor Systems (DCOSS)

作者： Dakshanya Maddala Habib M. Ammari Department of Electrical Engineering and Computer Science Frank H. Dotterweich College of Engineering Wireless Sensor and Mobile Autonomous Networks (WiSeMAN) Research Lab Texas A&M University-Kingsville Kingsville Texas USA

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

Sensor deployment, and in particular coverage, is a fundamental component in the design and development of wireless sensor networks. Achieving coverage (or 1-coverage) in three-dimensional (or spatial) wireless sensor networks (WSNs), which requires that every point in a spatial field of interest (FoI), is an open challenging problem. In particular, the problem of k-coverage in spatial WSNs, where every point in a spatial FoI is k-covered (or covered by at least k sensors at the same time), is even more challenging. In this paper, we investigate the problem of connected k-coverage in spatial WSNs, where a spatial FoI is k-covered while all the sensors participating in this k-coverage process are connected to each other. Our study aims at producing an energy-efficient and optimized protocol, which helps achieve connected k-coverage in spatial WSNs with a minimum number of sensors, thus, extending the network lifespan. Precisely, this study is based on convex polyhedral space fillers that help establish an irregular hexagonal prism tessellation referred to as Irregular Honeycomb Network (IHN), which serves as a medium to achieve k-coverage in spatial WSNs. First, we propose a randomly distributed sensor placement strategy, which is designed to guarantee full k-coverage of a spatial FoI. To this end, we tile a spatial FoI with irregular hexagonal prisms, known as space fillers, which are adjacent to each other without any gaps or overlaps. Second, we exploit this tiling strategy to guarantee k-coverage of a spatial FoI. Then, we compute the spatial sensor density (i.e., number of sensors per unit volume) to k-cover a spatial FoI. Third, we determine the necessary relationship between the sensors’ communication and sensing ranges to ensure network connectivity. We corroborate our analysis with various simulation results.

关键词： Wireless communication Wireless sensor networks Sensor placement Protocols Simulation Stochastic processes Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Drive-Charge Dilemma in Electric Mobility: Price of Anarchy and Data Analytics Standpoint 5

Drive-Charge Dilemma in Electric Mobility: Price of Anarchy ...

引用

5th International Conference on Advanced Communication Technologies and Networking, CommNet 2022

作者： Mahrez, Zineb Sabir, Fssaid Saad, Walid Badidi, Elarbi Hassan Ii University of Casablanca Nest Research Group Lri Lab Ensem Morocco University of Quebec at Montreal Departrment of Computer Science MontrealQCH2L 2C4 Canada Wireless VT Department of Computer Science and Software Engineering Virginia Tech VA United States College of Information Technology Uae University Department of Computer Science and Software Engineering United Arab Emirates

ISBN: (数字)9781665450546

ISBN: (纸本)9781665450546

The advent of electric mobility has created new costs that are closely linked to and influenced by the actions and behaviors of electric vehicle (EV) drivers. These include time-, energy-, and risk-related costs that each driver seeks to reduce by adjusting his or her strategy. In this paper, an electric vehicle charging dilemma using a non-cooperative routing game with selfish players is formulated. We assume that an electric vehicle plans a trip from one place to another and, in the process, must choose a specific route, stop at a roadside station, decide on the charging station, and charge its battery by a certain amount. The strategy of EVs to drive or stop depends on factors related to battery level, waiting status at charging stations, availability of charging types, and traffic load both on roads and at stations. The research problem aims to solve the EV driver's dilemma and determine the route that the EV driver must take to optimize his travel cost.' To solve the dilemma, we propose to build a simulation model based on input data obtained from historical records of U.S. government sources, as described in the paper. © 2022 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Parametric Evaluation and Electromagnetic Performance Comparison of Conventional and Double-Stator Wound-Field Flux Switching Machines

引用

IEEE Transactions on Industry Applications 2025年

作者： Idoko, Hillary C. Akuru, Udochukwu B. Popoola, Olawale Ullah, Wasiq Khan, Faisal Masisi, Lesedi Tshwane University of Technology Department of Electrical Engineering Pretoria0183 South Africa University of Nigeria Department of Electrical Engineering Nsukka410001 Nigeria Tshwane University of Technology Pretoria Campus Department of Electrical Engineering 0183 South Africa Kabul Polytechnic University Vice Chancellor of Research and Journals Department of Electrical Engineering Faculty of Electromechanics Kabul1005 Afghanistan COMSATS University Islamabad Abbottabad Campus Electric Machine Design Research Lab Department of Electrical and Computer Engineering Khyber Pakhtunkhwa Abbottabad22060 Pakistan The University of the Witwatersrand School of Electrical and Information Engineering Braamfontein West 2000 South Africa

In this paper, a comprehensive electromagnetic performance comparison of the conventional wound field flux switching machine (WFFSM) and the double stator WFFSM (DSWFFSM) is undertaken for high torque density applications, based on finite element analysis (FEA). The initial design study reveals superior specific density and torque density of the DSWFFSM over WFFSM. Parametric analysis is then used to systematically vary key structural variables to study their influence on average torque, torque ripple, efficiency and power factor, while a multi-objective optimisation based on normalised weighted objectives is used to select the optimal designs upon which a comparative evaluation is performed to reiterate the intrinsic advantages of DSWFFSM in achieving elevated torque performance. The results show that specific torque and torque density of the DSWFFSM finally increased by 43.5% and 30.4% over the WFFSM, respectively. The torque ripple of the DSWFFSM is also finally reduced by 75.9%. To validate the FEA results, an experimental analysis is provided based on a pre-existing DSWFFSM prototype. © 1972-2012 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Structured Waveguide Grating for Controlled Resonant Reflection 6

Structured Waveguide Grating for Controlled Resonant Reflect...

引用

6th Annual IEEE research and Applications of Photonics in Defense Conference, RAPID 2023

作者： Avrutsky, Ivan Klein, Matthew Vangala, Shivashankar Walker, Dennis E. Smith, Evan Hendrickson, Joshua R. Wayne State University Department of Electrical and Computer Engineering DetroitMI48202 United States Wayne State University Department of Physics and Astronomy DetroitMI48202 United States Sensors Air Force Research Lab Wright Patterson AFBOH45433 United States KBR Inc. BeavercreekOH45431 United States

ISBN: (纸本)9781665423526

Waveguide gratings with structured period provide controllable ratio between coupling coefficients in different diffraction orders and allow for control of resonant reflection spectra. We report conceptual model, numerical studies, and fabrication of GaN structured period waveguide gratings designed for the mid-IR spectral range. © 2023 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing in Healthcare: A Bird's Eye View 7

Natural Language Processing in Healthcare: A Bird's Eye View

引用

7th Workshop on Natural Language for Artificial Intelligence, NL4AI 2023

作者： Bacco, Luca Dell'Orletta, Felice Merone, Mario Department of Engineering Unit of Computer Systems and Bioinformatics Campus Bio-Medico University of Rome Via Alvaro del Portillo 21 Rome00128 Italy ItaliaNLP Lab National Research Council Istituto di Linguistica Computazionale "antonio Zampolli" Via Giuseppe Moruzzi 1 Pisa56124 Italy

The healthcare industry is experiencing an unprecedented era of transformation, driven by the proliferation of Electronic Health Records (EHRs) and the emergence of vast amounts of natural language data from sources like social media. This dynamic landscape presents novel opportunities for companies, healthcare practitioners, and researchers, underpinned by the transformative potential of Natural Language Processing (NLP) technologies. This paper offers a brief overview of the rationale for studying NLP in healthcare, highlighting its foundational importance. It explores the current trends and invaluable resources available in the field, while also delving into the multifaceted challenges that must be addressed to harness the full potential of NLP in healthcare. By consolidating essential insights and bridging the gap between opportunities and challenges, this manuscript serves as a valuable resource for both established researchers and newcomers seeking to navigate the complex terrain of NLP in healthcare, ultimately contributing to the advancement of this critical domain. © 2023 Copyright for this paper by its authors.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Acoustic BPE in Decoder-Only TTS

arXiv

引用

arXiv 2024年

作者： Li, Bohan Shen, Feiyu Guo, Yiwei Wang, Shuai Chen, Xie Yu, Kai MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University China Shenzhen Research Institute of Big Data CUHK-Shenzhen China

Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM). To shorten the sequence length of speech tokens, acoustic byte-pair encoding (BPE) has emerged in SLM that treats speech tokens from self-supervised semantic representations as characters to further compress the token sequence. But the gain in TTS has not been fully investigated, and the proper choice of acoustic BPE remains unclear. In this work, we conduct a comprehensive study on various settings of acoustic BPE to explore its effectiveness in decoder-only TTS models with semantic speech tokens. Experiments on LibriTTS verify that acoustic BPE uniformly increases the intelligibility and diversity of synthesized speech, while showing different features across BPE settings. Hence, acoustic BPE is a favorable tool for decoder-only TTS. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optimizing emissions for machine learning training

Optimizing emissions for machine learning training

引用

Conference on Technologies for Sustainability (Sustech)

作者： Sachini Piyoni Ekanayake Tapan Shah Scott Evans Department of Electrical and Computer Engineering University at Albany Albany NY USA Machine Learning Lab GE Research San Ramon CA USA Machine Learning Lab GE Research Niskayuna NY USA

来源：评论

学校读者我要写书评

暂无评论

RFFCE: Residual Feature Fusion and Confidence Evaluation Network for 6DoF Pose Estimation

RFFCE: Residual Feature Fusion and Confidence Evaluation Net...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Qiwei Meng Shanshan Ji Shiqiang Zhu Tianlei Jin Te Li Jason Gu Wei Song Research Center for Intelligent Robotics Zhejiang Lab Research Institute of Interdisciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

In this paper, we propose a novel RGBD-based object 6DoF pose estimation network - RFFCE. It is a two-stage method that firstly leverages deep neural networks for feature extraction and object points matching, and then the geometric principles are utilized for final pose computation. Our approach consists of three primary innovations: residual feature fusion for representative RGBD feature extraction; confidence evaluation and confidence-based paired points offsets regression for self-evaluation and self-optimization respectively. Their effectiveness is verified through an ablation study, and our RFFCE achieves the SOTA performance on LineMOD, Occlusion-LineMOD and YCB-Video datasets. Additionally, we also conduct a real-world object grasping experiment for visualization and qualitative evaluation of the RFFCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified p Attacks

arXiv

引用

arXiv 2023年

作者： Wang, Ren Li, Yuxuan Liu, Sijia The Department of Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States The Trustworthy and Intelligent Machine Learning Research Lab the Department of Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States The Department of Computer Science and Engineering Michigan State University East LansingMI48824 United States

Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase. Recent studies have shown that despite the success of improving adversarial robustness against a single type of attack using robust training techniques, models are still vulnerable to diversified p attacks. To achieve diversified p robustness, we propose a novel robust mode connectivity (RMC)-oriented adversarial defense that contains two population-based learning phases. The first phase, RMC, is able to search the model parameter space between two pre-trained models and find a path containing points with high robustness against diversified p attacks. In light of the effectiveness of RMC, we develop a second phase, RMC-based optimization, with RMC serving as the basic unit for further enhancement of neural network diversified p robustness. To increase computational efficiency, we incorporate learning with a self-robust mode connectivity (SRMC) module that enables the fast proliferation of the population used for endpoints of RMC. Furthermore, we draw parallels between SRMC and the human immune system. Experimental results on various datasets and model architectures demonstrate that the proposed defense methods can achieve high diversified p robustness against ∞, 2, 1, and hybrid attacks. Codes are available at https://***/wangren09/MCGR. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Adaptive Beamforming Based on Interference-Plus-Noise Covariance Matrix Reconstruction for Speech Separation

Adaptive Beamforming Based on Interference-Plus-Noise Covari...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Yongxiong Xiao Shiqiang Zhu Te Li Minhong Wan Wei Song Jason Gu Qiang Fu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Lab Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

Estimating the interference-plus-noise covariance matrix (INCM) is critical for the robustness of the minimum variance distortionless response (MVDR) beamformer. Existing INCM reconstruction methods are computationally intensive and not suitable for real-time speech separation. We propose a singular value decomposition (SVD) based INCM reconstruction method for speech separation. The spatial covariance matrix (SCM) for each source is obtained by rank-1 approximation using the nominal steering vector (SV) or the pre-measured relative transfer function (RTF). The INCM used to separate each source is reconstructed as the sum of the covariance matrices of interference and spherical isotropic noise. The proposed method is evaluated using the mixed signal received by a circular array with six microphones placed in a simulated reverberation chamber. The results show that the proposed method has comparable sound quality performance to the reference method, but requires much less computation.

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：