Methods and systems for multi-layer perceptron based non-linear interference management in multi-technology communication devices

Patent metadata

Field	Value
Publication number	US-9484974-B2
Application number	US-201514849528-A
Country	US
Kind code	B2
Filing date	Sep 9, 2015
Priority date	Sep 10, 2014
Publication date	Nov 1, 2016
Grant date	Nov 1, 2016

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.

First claim

What is claimed is:

1. A method for managing interference in a multi-technology communication device, comprising:
receiving an aggressor signal at the multi-technology communication device;
dividing the aggressor signal into a real aggressor signal component and an imaginary aggressor signal component;
augmenting the real aggressor signal component and the imaginary aggressor signal components with weight factors at a hidden layer of a multilayer perceptron neural network;
executing a first linear combination of the real aggressor signal component and the imaginary aggressor signal component at the hidden layer to produce a hidden layer intermediate signal;
executing a nonlinear sigmoid function for the hidden layer intermediate signal at the hidden layer to produce a hidden layer output signal;
augmenting, a plurality of the hidden layer output signals each with the weight factors at an output layer of the multilayer perceptron neural network;
executing a second linear combination of the augmented plurality of hidden layer output signals at the output layer to produce a real output layer output signal and an imaginary output layer output signal; and
executing a linear filter function on the real output layer output signal and the imaginary output layer output signal to produce an estimated real nonlinear interference and an estimated imaginary nonlinear interference.

2. The method of claim 1 , further comprising:
combining the estimated real nonlinear interference and the estimated imaginary nonlinear interference to produce an estimated nonlinear interference;
determining an error of the estimated nonlinear interference;
determining whether the error of the estimated nonlinear interference exceeds an efficiency threshold; and
canceling the estimated nonlinear interference from a victim signal.

3. The method of claim 2 , wherein canceling the estimated nonlinear interference from the victim signal comprises canceling the estimated nonlinear interference from the victim signal in response to determining that the error of the estimated nonlinear interference does not exceed the efficiency threshold,
the method further comprising training the weight factors to reduce the error of the estimated nonlinear interference in response to determining that the error of the estimated nonlinear interference exceeds the efficiency threshold.

4. The method of claim 3 , wherein training the weight factors to reduce the error of the estimated nonlinear interference comprises using a Gauss-Newton algorithm to train the weight factors.

5. The method of claim 2 , further comprising selecting the weight factors to reduce the error of the estimated nonlinear interference.

6. The method of claim 5 , wherein selecting the weight factors to reduce the error of the estimated nonlinear interference comprises selecting the weight factors used for a previous determination of a previous estimated nonlinear interference for a previous victim signal within a predetermined time period.

7. The method of claim 1 , wherein the linear filter function is a finite impulse response filter.

8. The method of claim 1 , wherein the linear filter function has a Hammerstein structure.

9. The method of claim 1 , wherein dividing the aggressor signal into the real aggressor signal component and the imaginary aggressor signal component comprises generating an aggressor kernel such that the real aggressor signal component is a real aggressor kernel component and the imaginary aggressor signal component is an imaginary aggressor kernel component.

10. The method of claim 9 , wherein the aggressor kernel is a set of non-linear inputs derived from the aggressor signal.

11. The method of claim 1 , wherein executing the first linear combination of the real aggressor signal component and the imaginary aggressor signal component at the hidden layer comprises executing a linear combination of the real aggressor signal component, the imaginary aggressor signal component, and a bias factor at the hidden layer.

12. The method of claim 1 , wherein executing the second linear combination of the augmented hidden layer output signals at the output layer to produce the real output layer output signal and the imaginary output layer output signal comprises executing a linear combination of the augmented hidden layer output signals and a bias factor at the output layer.

13. The method of claim 1 , wherein executing the linear filter function on the real output layer output signal and the imaginary output layer output signal to produce the estimated real nonlinear interference and the estimated imaginary nonlinear interference comprises:
augmenting the real output layer output signals and the imaginary output layer output signal each with the weight factors at a plurality of instances corresponding to a number of taps of the a linear filter function to produce augmented real output layer output signals and augmented imaginary output layer output signals;
executing a third linear combination of the augmented real output layer output signals to produce the estimated real nonlinear interference; and
executing a fourth linear combination of the augmented imaginary output layer output signals to produce the estimated imaginary nonlinear interference.

14. A multi-technology communication device, comprising:
an antenna;
a processor communicatively connected to the antenna and configured with processor-executable instructions to perform operations comprising:
dividing an aggressor signal received via the antenna into a real aggressor signal component and an imaginary aggressor signal component;
augmenting the real aggressor signal component and the imaginary aggressor signal component with weight factors at a hidden layer of a multilayer perceptron neural network;
executing a first linear combination of the real aggressor signal component and the imaginary aggressor signal component at the hidden layer to produce a hidden layer intermediate signal;
executing a nonlinear sigmoid function for the hidden layer intermediate signal at the hidden layer to produce a hidden layer output signal;
augmenting a plurality of the hidden layer output signals each with the weight factors at an output layer of the multilayer perceptron neural network;
executing a second linear combination of the augmented plurality of hidden layer output signals at the output layer to produce a real output layer output signal and an imaginary output layer output signal; and
executing a linear filter function on the real output layer output signal and the imaginary output layer output signal to produce an estimated real nonlinear interference and an estimated imaginary nonlinear interference.

15. The multi-technology communication device of claim 14 , wherein the processor is configured with processor-executable instructions to perform operations further comprising:
combining the estimated real nonlinear interference and estimated imaginary nonlinear interference to produce an estimated nonlinear interference;
determining an error of the estimated nonlinear interference;
determining whether the error of the estimated nonlinear interference exceeds an efficiency threshold; and
canceling the estimated nonlinear interference from a victim signal.

16. The multi-technology communication device of claim 15 , wherein the processor is configured with processor-executable instructions to perform operations comprising:
canceling the estimated nonlinear interference from the victim signal in response to determining that the error of the estimated nonlinear interference does not exceed

Assignees

• Qualcomm Inc

Inventors

• Tu Sheng-Yuan
• Abrishamkar Farrokh
• Cheraghi Parisa
• Kang Insung
• Shahidi Reza

Classifications

• H04B1/40 Primary

  Circuits · CPC title

• H04B1/525

  with means for reducing leakage of transmitter signal into the receiver · CPC title

• H04B15/00

  Suppression or limitation of noise or interference (by means associated with receiver H04B1/10) · CPC title

• H04B1/123 Primary

  using adaptive balancing or compensation means (adaptive filter circuits and algorithms H03H) · CPC title