公开(公告)号：US09924522B2

公开(公告)日：2018-03-20

申请号：US14867801

申请日：2015-09-28

Applicant: Drexel University

Inventor： Nikhil Gulati ,  David Gonzalez ,  Kapil R. Dandekar

IPC: H04B1/44 ,  H04W72/08 ,  H01Q1/00 ,  H01Q13/20 ,  H04W24/02 ,  H04B7/0417 ,  H04B7/06

CPC classification number: H04W72/082 ,  H01Q1/007 ,  H01Q13/20 ,  H04B1/44 ,  H04B7/0417 ,  H04B7/0626 ,  H04W24/02 ,  H04W72/085

Abstract: A method for selecting the state of a reconfigurable antenna installed at either the receiver or transmitter of a communication system is provided. The proposed method uses online learning algorithm based on the theory of multi-armed bandit to perform antenna state selection. The selection technique utilizes the Post-Processing Signal-to-Noise Ratio (PPSNR) as a reward metric and maximizes the long-term average reward over time. The performance of the learning based selection technique is empirically evaluated using wireless channel data. The data is collected in an indoor environment using a 2×2 MIMO OFDM system employing highly directional metamaterial Reconfigurable Leaky Wave Antennas. The learning based selection technique shows performance improvements in terms of average PPSNR and regret over conventional heuristic policies.

公开(公告)号：US20160021671A1

公开(公告)日：2016-01-21

申请号：US14867801

申请日：2015-09-28

Applicant: Drexel University

Inventor： Nikhil Gulati ,  David Gonzalez ,  Kapil R. Dandekar

IPC: H04W72/08 ,  H04B7/06 ,  H04B7/04

CPC classification number: H04W72/082 ,  H01Q1/007 ,  H01Q13/20 ,  H04B1/44 ,  H04B7/0417 ,  H04B7/0626 ,  H04W24/02 ,  H04W72/085

Abstract: A method for selecting the state of a reconfigurable antenna installed at either the receiver or transmitter of a communication system is provided. The proposed method uses online learning algorithm based on the theory of multi-armed bandit to perform antenna state selection. The selection technique utilizes the Post-Processing Signal-to-Noise Ratio (PPSNR) as a reward metric and maximizes the long-term average reward over time. The performance of the learning based selection technique is empirically evaluated using wireless channel data. The data is collected in an indoor environment using a 2×2 MIMO OFDM system employing highly directional metamaterial Reconfigurable Leaky Wave Antennas. The learning based selection technique shows performance improvements in terms of average PPSNR and regret over conventional heuristic policies.

Abstract translation: 提供了一种用于选择安装在通信系统的接收机或发射机处的可重新配置天线的状态的方法。 提出的方法使用基于多武装强盗理论的在线学习算法进行天线状态选择。 选择技术利用后处理信噪比（PPSNR）作为奖励度量，并使长期平均奖励随时间推移最大化。 使用无线信道数据对基于学习的选择技术的性能进行经验性评估。 使用采用高度定向的超材料可重构泄漏波天线的2×2 MIMO OFDM系统在室内环境中收集数据。 基于学习的选择技术显示了平均PPSNR的性能改进，并对传统启发式策略感到遗憾。

公开(公告)号：US20150140938A1

公开(公告)日：2015-05-21

申请号：US14565665

申请日：2014-12-10

Applicant: Drexel University

Inventor： Nikhil Gulati ,  David Gonzalez ,  Kapil Dandekar

IPC: H04W72/08 ,  H04W24/02 ,  H01Q13/20

CPC classification number: H04W72/082 ,  H01Q1/007 ,  H01Q13/20 ,  H04B1/44 ,  H04B7/0417 ,  H04B7/0626 ,  H04W24/02 ,  H04W72/085

Abstract: A method for selecting the state of a reconfigurable antenna installed at either the receiver or transmitter of a communication system is provided. The proposed method uses online learning algorithm based on the theory of multi-armed bandit to perform antenna state selection. The selection technique utilizes the Post-Processing Signal-to-Noise Ratio (PPSNR) as a reward metric and maximizes the long-term average reward over time. The performance of the learning based selection technique is empirically evaluated using wireless channel data. The data is collected in an indoor environment using a 2×2 MIMO OFDM system employing highly directional metamaterial Reconfigurable Leaky Wave Antennas. The learning based selection technique shows performance improvements in terms of average PPSNR and regret over conventional heuristic policies.

Abstract translation: 提供了一种用于选择安装在通信系统的接收机或发射机处的可重新配置天线的状态的方法。 提出的方法使用基于多武装强盗理论的在线学习算法进行天线状态选择。 选择技术利用后处理信噪比（PPSNR）作为奖励度量，并使长期平均奖励随时间推移最大化。 使用无线信道数据对基于学习的选择技术的性能进行经验性评估。 使用采用高度定向的超材料可重构泄漏波天线的2×2 MIMO OFDM系统在室内环境中收集数据。 基于学习的选择技术显示了平均PPSNR的性能改进，并对传统启发式策略感到遗憾。