SpecEES: DISCOVER: Device Identification for Spectrum-optimization using COnVolutional nEural netwoRks

SpecEES:DISCOVER:使用卷积神经网络进行频谱优化的设备识别

基本信息

  • 批准号:
    1923789
  • 负责人:
  • 金额:
    $ 75万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2019
  • 资助国家:
    美国
  • 起止时间:
    2019-10-01 至 2023-09-30
  • 项目状态:
    已结题

项目摘要

The research objective of this project, called DISCOVER, is to harness the power of deep machine learning (ML) algorithms to communicate wirelessly with high spectral efficiency and low power consumption. The techniques will result in advanced networking protocols that consume minimal resources by securely identifying the devices that are active in the surrounding environment without (or with minimal) control signaling. Apart from learning channel usage and device activity, DISCOVER will allow for rapidly deploying these algorithms in hardware, so that real-time inferences can be made. Thus, DISCOVER is directly aligned with the US President's executive order from February 2019 'Maintaining American Leadership in Artificial Intelligence' that seeks to prioritize research and development of America's artificial intelligence (AI) capabilities. DISCOVER aims to bring together industry, academia and government stakeholders through collaborative workshops towards identifying high priority challenges, limitations of available data sources, and identify a list of candidate machine learning solutions that will shape the next generation of wireless technologies. The open source release of signal datasets and simulation code will foster new interactions of wireless researchers with core machine learning domain experts.DISCOVER has three goals for optimizing spectrum utilization with overlapping interests of either energy saving or resilience to identity spoofing through the use of deep learning architectures: 1. It aims to explore deep convolutional neural network (CNN) architectures that will allow highly accurate device classification and demonstrate how to eliminate identifier-related protocol fields. This approach of reducing packet headers will achieve quantifiable spectrum utilization improvements, especially for large-scale deployment of the Internet of Things (IoT). 2. It aims to demonstrate the first learning-in-the-loop radio frequency (RF) system where spectrum-driven decisions are enabled through real-time deep learning algorithms implemented directly on the device hardware. This will result in significant energy savings for embedded IoT devices. 3. The emulation engine developed in the project will empower users to create custom-signals to train ML algorithms. Furthermore, it will create community RF signal datasets that will ensure means of standardized validation for the larger research community.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
这个名为DISCOVER的项目的研究目标是利用深度机器学习(ML)算法的能力,以高频谱效率和低功耗进行无线通信。这些技术将产生高级网络协议,通过安全地识别在没有(或使用最少)控制信令的情况下在周围环境中活动的设备,从而消耗最少的资源。除了了解通道使用情况和设备活动外,DISCOVER还将允许在硬件中快速部署这些算法,以便进行实时推断。因此,Discovery与美国总统2019年2月发布的行政命令直接一致,该行政命令旨在将美国人工智能(AI)能力的研发放在优先位置。Discovery旨在通过协作研讨会将业界、学术界和政府利益相关者聚集在一起,以确定高优先级挑战、可用数据源的限制,并确定将塑造下一代无线技术的候选机器学习解决方案列表。信号数据集和模拟代码的开源发布将促进无线研究人员与核心机器学习领域专家的新交互。DISCOVER有三个目标,即通过使用深度学习架构来优化频谱利用,同时兼顾节能或对身份欺骗的弹性:1.它旨在探索深度卷积神经网络(CNN)架构,该架构将允许高精度的设备分类,并演示如何消除与标识相关的协议字段。这种减少数据包头的方法将实现可量化的频谱利用率提升,特别是对于大规模部署物联网(IoT)。2.它旨在演示第一个环路学习射频(RF)系统,其中频谱驱动的决策通过直接在设备硬件上实施的实时深度学习算法来实现。这将显著节省嵌入式物联网设备的能源。3.项目中开发的仿真引擎将使用户能够创建自定义信号来训练ML算法。此外,它还将创建社区射频信号数据集,以确保为更大的研究社区提供标准化验证。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。

项目成果

期刊论文数量(22)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Multimodality in mmWave MIMO Beam Selection Using Deep Learning: Datasets and Challenges
使用深度学习的毫米波 MIMO 波束选择中的多模态:数据集和挑战
  • DOI:
    10.1109/mcom.002.2200028
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    11.2
  • 作者:
    Gu, Jerry;Salehi, Batool;Roy, Debashri;Chowdhury, Kaushik R.
  • 通讯作者:
    Chowdhury, Kaushik R.
PRONTO: Preamble Overhead Reduction With Neural Networks for Coarse Synchronization
  • DOI:
    10.1109/twc.2023.3256961
  • 发表时间:
    2021-12
  • 期刊:
  • 影响因子:
    10.4
  • 作者:
    N. Soltani;Debashri Roy;K. Chowdhury
  • 通讯作者:
    N. Soltani;Debashri Roy;K. Chowdhury
DEEP LEARNING AT THE EDGE FOR CHANNEL ESTIMATION IN BEYOND-5G MASSIVE MIMO
  • DOI:
    10.1109/mwc.001.2000322
  • 发表时间:
    2021-04-01
  • 期刊:
  • 影响因子:
    12.9
  • 作者:
    Belgiovine, Mauro;Sankhe, Kunal;Chowdhury, Kaushik R.
  • 通讯作者:
    Chowdhury, Kaushik R.
Automated deep learning-based wide-band receiver
  • DOI:
    10.1016/j.comnet.2022.109367
  • 发表时间:
    2022-10-07
  • 期刊:
  • 影响因子:
    5.6
  • 作者:
    Azari, Bahar;Cheng, Hai;Erdogmus, Deniz
  • 通讯作者:
    Erdogmus, Deniz
NN-key: A Neural Network-Based Secret Key for Demapping OFDM Symbols
NN-key:基于神经网络的 OFDM 符号解映射密钥
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Kaushik Chowdhury其他文献

Kaushik Chowdhury的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Kaushik Chowdhury', 18)}}的其他基金

NSF-SNSF: Rapid Beamforming for Massive MIMO using Machine Learning on RF-only and Multi-modal Sensor Data
NSF-SNSF:在纯射频和多模态传感器数据上使用机器学习实现大规模 MIMO 的快速波束成形
  • 批准号:
    2401047
  • 财政年份:
    2024
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
Collaborative Research: SWIFT: MEDUSA: Mid-band Environmental Sensing Capability for Detecting Incumbents during Spectrum Sharing
合作研究:SWIFT:MEDUSA:用于在频谱共享期间检测现有企业的中频环境传感能力
  • 批准号:
    2229444
  • 财政年份:
    2022
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
Collaborative Research: CCRI: New: RFDataFactory: Principled Dataset Generation, Sharing and Maintenance Tools for the Wireless Community
合作研究:CCRI:新:RFDataFactory:无线社区的原则性数据集生成、共享和维护工具
  • 批准号:
    2120447
  • 财政年份:
    2021
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
I-Corps: Smart Mask for Respiratory Monitoring and Prevention of Airborne Diseases
I-Corps:用于呼吸监测和预防空气传播疾病的智能口罩
  • 批准号:
    2042080
  • 财政年份:
    2021
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
PFI:AIR-TT: DeepBeam: Wirelessly chargeable portable batteries through energy beamforming
PFI:AIR-TT:DeepBeam:通过能量波束成形进行无线充电的便携式电池
  • 批准号:
    1701041
  • 财政年份:
    2017
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
WiFiUS: Coordinating US-Finland Collaboration on Wireless Research through WiFiUS PI Meetings
WiFiUS:通过 WiFiUS PI 会议协调美国-芬兰无线研究合作
  • 批准号:
    1644763
  • 财政年份:
    2016
  • 资助金额:
    $ 75万
  • 项目类别:
    Continuing Grant
Student Travel Support for ACM MobiHoc 2016
ACM MobiHoc 2016 学生旅行支持
  • 批准号:
    1631979
  • 财政年份:
    2016
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
I-Corps: Software-Defined Distributed Wireless Charging
I-Corps:软件定义的分布式无线充电
  • 批准号:
    1644598
  • 财政年份:
    2016
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
CAREER: IDEA: Integrated Data and Energy Access for Wireless Sensor Networks
职业:IDEA:无线传感器网络的集成数据和能源访问
  • 批准号:
    1452628
  • 财政年份:
    2015
  • 资助金额:
    $ 75万
  • 项目类别:
    Continuing Grant
EAGER: Network Protocol Stack for Galvanic Coupled Intra-body Sensors
EAGER:电流耦合体内传感器的网络协议栈
  • 批准号:
    1453384
  • 财政年份:
    2014
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant

相似海外基金

ZeDiAx: Using zebrafish to discover how axons grow in diameter
ZeDiAx:利用斑马鱼发现轴突直径如何增长
  • 批准号:
    EP/Y029577/1
  • 财政年份:
    2024
  • 资助金额:
    $ 75万
  • 项目类别:
    Fellowship
Pioneering alpine epigenomics to discover adaptive genetic elements
开拓高山表观基因组学以发现适应性遗传元素
  • 批准号:
    DE240100184
  • 财政年份:
    2024
  • 资助金额:
    $ 75万
  • 项目类别:
    Discovery Early Career Researcher Award
Observations and methods to discover circumbinary planets
发现绕双星行星的观测和方法
  • 批准号:
    2886685
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
    Studentship
NSFDEB-NERC: Machine learning tools to discover balancing selection in genomes from spatial and temporal autocorrelations
NSFDEB-NERC:机器学习工具,用于从空间和时间自相关中发现基因组中的平衡选择
  • 批准号:
    NE/Y003519/1
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
    Research Grant
A High-Throughput Screening Platform to Discover RNA Methylation Inhibitors
发现 RNA 甲基化抑制剂的高通量筛选平台
  • 批准号:
    10705980
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
Whole genome sequence interpretation for lipids to discover new genes and mechanisms for coronary artery disease
脂质的全基因组序列解释,以发现冠状动脉疾病的新基因和机制
  • 批准号:
    10722515
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
EAGER: Understanding How Employees Discover and React to Health and Wellbeing Benefits
EAGER:了解员工如何发现健康和福祉福利并做出反应
  • 批准号:
    2332805
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
    Standard Grant
Using advanced genomic and computational approaches to discover and characterize novel genetic variants in neurodevelopmental disorders.
使用先进的基因组和计算方法来发现和表征神经发育障碍中的新遗传变异。
  • 批准号:
    491213
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
    Fellowship Programs
Using unique methods in flow virometry to discover new proteins on the HIV surface and their impact on HIV infection.
使用流式病毒测定中的独特方法来发现 HIV 表面的新蛋白质及其对 HIV 感染的影响。
  • 批准号:
    483598
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
    Operating Grants
Observations and methods to discover circumbinary planets
发现绕双星行星的观测和方法
  • 批准号:
    2886288
  • 财政年份:
    2023
  • 资助金额:
    $ 75万
  • 项目类别:
    Studentship
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了