公开(公告)号：US09484974B2

公开(公告)日：2016-11-01

申请号：US14849528

申请日：2015-09-09

Applicant: QUALCOMM Incorporated

Inventor： Sheng-Yuan Tu ,  Farrokh Abrishamkar ,  Parisa Cheraghi ,  Insung Kang ,  Reza Shahidi

IPC: H04B15/00 ,  H04B1/40 ,  H04B1/525

CPC classification number: H04B1/40 ,  H04B1/123 ,  H04B1/525 ,  H04B15/00

Abstract: The various embodiments include methods and apparatuses for canceling nonlinear interference during concurrent communication of multi-technology wireless communication devices. Nonlinear interference may be estimated using a multilayer perceptron neural network with Hammerstein structure by dividing an aggressor signal into real and imaginary components, augmenting the components by weight factors, executing a linear combination of the augmented components, and executing a nonlinear sigmoid function for the combined components at a hidden layer of multilayer perceptron neural network to produce a hidden layer output signal. At an output layer, hidden layer output signals may be augmented by weight factors, and the augmented hidden layer output signals may be linearly combined to produce real and imaginary components of an estimated jammer signal. A linear filter function may be executed for the components of the jammer signal, and to produce a nonlinear interference estimate used to cancel the nonlinear interference of a victim signal.

Abstract translation: 各种实施例包括用于在多技术无线通信设备的并发通信期间消除非线性干扰的方法和装置。 可以使用具有Hammerstein结构的多层感知器神经网络来估计非线性干扰，通过将侵略者信号除以实部和虚部，通过权重因子增加分量，执行增强分量的线性组合，以及执行组合的非线性S形函数 组件在隐藏层的多层感知器神经网络中产生隐层输出信号。 在输出层，可以通过加权因子来增加隐层输出信号，并且增强的隐层输出信号可以被线性组合以产生估计的干扰信号的实部和虚部。 可以对干扰信号的分量执行线性滤波器功能，并且产生用于消除受害信号的非线性干扰的非线性干扰估计。

公开(公告)号：US20160072649A1

公开(公告)日：2016-03-10

申请号：US14849563

申请日：2015-09-09

Applicant: QUALCOMM Incorporated

Inventor： Sheng-Yuan TU ,  Farrokh Abrishamkar ,  Brian Clarke Banister ,  Roberto Rimini ,  lnsung Kang ,  Taesang Yoo

IPC: H04L25/03 ,  H04B1/7107

CPC classification number: G06N3/04 ,  G05B13/027 ,  G06N3/08 ,  H04B1/1036 ,  H04B1/1081 ,  H04B1/123 ,  H04B1/406 ,  H04B1/525 ,  H04B1/7107 ,  H04L25/03159 ,  H04W88/06

Abstract: The various embodiments include methods and apparatuses for cancelling nonlinear interference during concurrent communication of multi-technology wireless communication devices. Nonlinear interference may be estimated using a minimum mean squares interference filter by generating aggressor kernels from the aggressor signals, augmenting the aggressor kernels by weight factors and executing a linear combination of the augmented output, at an intermediate layer to produce intermediate layer outputs. At an output layer, a linear filter function may be executed on the intermediate layer outputs to produce an estimated nonlinear interference used to cancel the nonlinear interference of a victim signal.

Abstract translation: 各种实施例包括用于在多技术无线通信设备的并发通信期间消除非线性干扰的方法和装置。 可以使用最小均方干扰滤波器通过从侵略者信号产生攻击者内核来估计非线性干扰，通过权重因子增加侵略者内核并在中间层处执行增强输出的线性组合以产生中间层输出。 在输出层，可以对中间层输出执行线性滤波函数，以产生用于消除受害信号的非线性干扰的估计的非线性干扰。

公开(公告)号：US20160072543A1

公开(公告)日：2016-03-10

申请号：US14849532

申请日：2015-09-09

Applicant: QUALCOMM Incorporated

Inventor： Farrokh Abrishamkar ,  Sheng-Yuan Tu ,  Parisa Cheraghi ,  lnsung Kang ,  Jeremy Stein

IPC: H04B1/40 ,  H04B15/00

CPC classification number: H04B1/40 ,  H04B1/123 ,  H04B1/525 ,  H04B15/00

Abstract: The various embodiments include methods and apparatuses for canceling nonlinear interference during concurrent communication of multi-technology wireless communication devices. Nonlinear interference may be estimated using a multi-layer perceptron neural network with Hammerstein structure by dividing an aggressor signal into real and imaginary components, augmenting the components by weight factors, executing a linear combination of the augmented components, and executing a nonlinear sigmoid function for the combined components at a hidden layer of multi-layer perceptron neural network to produce a hidden layer output signal. At an output layer, hidden layer output signals may be augmented by weight factors, and the augmented hidden layer output signals may be linearly combined to produce real and imaginary components of an estimated jammer signal. A linear filter function may be executed for the components of the jammer signal, and to produce a nonlinear interference estimate used to cancel the nonlinear interference of a victim signal.

Abstract translation: 各种实施例包括用于在多技术无线通信设备的并发通信期间消除非线性干扰的方法和装置。 可以使用具有Hammerstein结构的多层感知器神经网络来估计非线性干扰，通过将侵略者信号划分成实部和虚部，通过权重因子增加分量，执行增强分量的线性组合，以及执行非线性Sigmoid函数 组合成分在隐层多层感知神经网络中产生隐层输出信号。 在输出层，可以通过加权因子来增加隐层输出信号，并且增强的隐层输出信号可以被线性组合以产生估计的干扰信号的实部和虚部。 可以对干扰信号的分量执行线性滤波器功能，并且产生用于消除受害信号的非线性干扰的非线性干扰估计。

公开(公告)号：US20160071003A1

公开(公告)日：2016-03-10

申请号：US14510907

申请日：2014-10-09

Applicant: QUALCOMM Incorporated

Inventor： Farrokh Abrishamkar ,  Sheng-Yuan Tu ,  Yin Huang ,  Ori Shental ,  Insung Kang

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G05B13/027 ,  G06N3/08 ,  H04B1/1036 ,  H04B1/1081 ,  H04B1/123 ,  H04B1/406 ,  H04B1/525 ,  H04B1/7107 ,  H04L25/03159 ,  H04W88/06

Abstract: The various embodiments include methods and apparatuses for cancelling nonlinear interference during concurrent communication of dual-technology wireless communication devices. Nonlinear interference may be estimated using a multilayer perceptron neural network by augmenting aggressor signal(s) by weight factors, executing a linear combination of the augmented aggressor signals, and executing a nonlinear sigmoid function for the combined aggressor signals at a hidden layer of multilayer perceptron neural network to produce a hidden layer output signal. Multiple hidden layers may repeat the process for the hidden layer output signals. At an output layer, hidden layer output signals may be augmented by weight factors, and the augmented hidden layer output signals may be linearly combined to produce an estimated nonlinear interference used to cancel the nonlinear interference of a victim signal. The weight factors may be trained based on a determination of an error of the estimated nonlinear interference.

Abstract translation: 各种实施例包括用于在双技术无线通信设备的并发通信期间消除非线性干扰的方法和装置。 可以使用多层感知器神经网络来估计非线性干扰，通过用权重因子增强攻击者信号，执行增强的侵略者信号的线性组合，以及在多层感知器的隐藏层处执行组合的攻击者信号的非线性S形函数 神经网络产生隐层输出信号。 多个隐藏层可能会重复隐藏层输出信号的过程。 在输出层，可以通过加权因子来增加隐层输出信号，并且增强隐层输出信号可以被线性组合以产生用于消除受害信号的非线性干扰的估计的非线性干扰。 可以基于估计的非线性干扰的误差的确定来训练加权因子。