AITF: Learning and Adapting Sparse Recovery Algorithms for RF Spectrum Sensing

AITF：学习和适应射频频谱传感的稀疏恢复算法

• 批准号: 1733857
• 负责人: John Wright
• 金额: $ 65万
• 依托单位: Columbia University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1733857&HistoricalAwards=false
• 关键词: AITF; Learning; Adapting; Sparse; Recovery

Wireless communications technology plays a critical role in society, supporting personal communication, business, defense and security, family connectivity, and entertainment. As new applications emerge, the demand for connectivity is increasing at a rapid pace. This development has put a strain on the available resources for communications: the spectrum is a finite natural resource; the most useful portions for mobile applications lie roughly from 700 MHz to 6 GHz. Large portions of it have been allocated to primary users, many of whom play socially critical roles. To accommodate the growing demand for wireless connectivity, there is a need for devices that can sense and utilize available spectrum in an opportunistic manner, while not interfering with primary users. The challenge is to do this in a time- and energy-efficient manner, on mobile devices. A general approach, which promises order-of-magnitude improvements in energy efficiency for rapidly detecting large interfering signals, uses a combination of new hardware to take a small number of measurements of the spectrum as a whole, and nontrivial algorithms to interpret those measurements. This project develops from machine learning to learn algorithms that are adapted to the specific characteristics of the hardware sensor, improving handling of non-linearities, yielding lower power sensors with improved sensitivity. The researchers are mentoring graduate and undergraduate students, whose work crosses disciplinary boundaries, and disseminating the results through new course development and a new textbook. The project studies methodologies for learning and adapting algorithms for sparse recovery for RF spectrum sensing, leveraging a known connection to artificial neural networks, in which the structure of the algorithm dictates the topology and weights of the network. These weights can then be adapted and optimized to fit the characteristics of a physical sensor. A major promise of this approach is the ability to adapt to modeling errors, while simultaneously producing recovery methods that are more sensitive, more robust, and implementable in a simple and efficient manner. The project is developing a principled and transparent methodology, including theoretical characterizations of when and why it is possible to learn reconstruction and support recovery procedures that are effective in both typical and worst-case senses. The project studies these problems both for linear inverse problems and for nonlinear problems, both for sensing the spectrum at a single time, and for integrating information over time. The project experimentally evaluates the impact of these methodologies on the efficiency and sensitivity of hardware sensors, realized as integrated circuits.

无线通信技术在社会中发挥着至关重要的作用，支持个人通信、商业、国防和安全、家庭连接和娱乐。随着新应用的出现，对连接的需求正在快速增长。这一发展给通信的可用资源带来了压力：频谱是有限的自然资源;对移动的应用最有用的部分大约在700 MHz到6 GHz之间。其中很大一部分分配给了主要用户，其中许多人发挥着社会关键作用。为了适应对无线连接的日益增长的需求，需要能够以机会主义方式感测和利用可用频谱而不干扰主用户的设备。挑战在于如何在移动的设备上以节省时间和能源的方式实现这一点。一种通用的方法，它承诺在能源效率的数量级的改进，快速检测大的干扰信号，使用新的硬件的组合，采取少量的测量频谱作为一个整体，和非平凡的算法来解释这些测量。该项目从机器学习发展到学习适应硬件传感器特定特性的算法，改善非线性处理，产生具有更高灵敏度的低功耗传感器。研究人员正在指导研究生和本科生，他们的工作跨越学科界限，并通过新课程开发和新教科书传播结果。该项目研究用于学习和调整RF频谱感知稀疏恢复算法的方法，利用与人工神经网络的已知连接，其中算法的结构决定网络的拓扑结构和权重。然后，可以调整和优化这些权重以适应物理传感器的特性。这种方法的一个主要承诺是能够适应建模错误，同时产生更敏感，更强大，并以简单有效的方式实现的恢复方法。该项目正在制定一个原则性和透明的方法，包括从理论上说明何时以及为什么可以学习在典型和最坏情况下都有效的重建和支持恢复程序。该项目研究这些问题的线性逆问题和非线性问题，无论是在一个单一的时间感测频谱，并随着时间的推移整合信息。该项目实验评估这些方法对硬件传感器的效率和灵敏度的影响，实现为集成电路。

项目成果

Efficient Dictionary Learning with Gradient Descent

• 发表时间: 2018-09
• 期刊: International Journal of Circuit Theory and Applications
• 影响因子: 2.3
• 作者: D. Gilboa;Sam Buchanan;John Wright

A Flexible Phased-Array Architecture for Reception and Rapid Direction-of-Arrival Finding Utilizing Pseudo-Random Antenna Weight Modulation and Compressive Sampling

• DOI: 10.1109/jssc.2019.2900200
• 发表时间: 2019-03
• 期刊: IEEE Journal of Solid-State Circuits
• 影响因子: 5.4
• 作者: Matthew Bajor;Tanbir Haque;Guoxiang Han;Ciyuan Zhang;John Wright;P. Kinget

Deep Networks and the Multiple Manifold Problem

• 发表时间: 2020-08
• 期刊: ArXiv
• 作者: Sam Buchanan;D. Gilboa;John Wright

Complete Dictionary Learning via L4-Norm Maximization over the Orthogonal Group

通过正交群上的 L4 范数最大化完成字典学习

• 发表时间: 2020
• 期刊: Journal of machine learning research
• 影响因子: 6
• 作者: Zhai, Yuexiang;Yang, Zitong;Liao, Zhenyu;Wright, John;Ma, Yi
• 通讯作者: Ma, Yi

An 8-Element, 1-3GHz Direct Space-to-Information Converter for Rapid, Compressive-Sampling Direction-of-Arrival Finding Utilizing Pseudo-Random Antenna-Weight Modulation

8 元件、1-3GHz 直接空间信息转换器，利用伪随机天线权重调制进行快速压缩采样到达方向查找

• DOI: 10.1109/rfic.2018.8428971
• 发表时间: 2018
• 期刊: 2018 IEEE Radio Frequency Integrated Circuits Symposium (RFIC
• 作者: Bajor, Matthew;Haque, Tanbir;Han, Guoxiang;Zhang, Ciyuan;Wright, John;Kinget, Peter R.
• 通讯作者: Kinget, Peter R.