18277318. METHOD AND DEVICE(S) FOR SUPPORTING MACHINE LEARNING BASED CREST FACTOR REDUCTION AND DIGITAL PREDISTORTION simplified abstract (Telefonaktiebolaget LM Ericsson (publ))

METHOD AND DEVICE(S) FOR SUPPORTING MACHINE LEARNING BASED CREST FACTOR REDUCTION AND DIGITAL PREDISTORTION

Organization Name

Telefonaktiebolaget LM Ericsson (publ)

Inventor(s)

S M Shahrear Tanzil of Ottawa (CA)

Ashim Biswas of Sollentuna (SE)

METHOD AND DEVICE(S) FOR SUPPORTING MACHINE LEARNING BASED CREST FACTOR REDUCTION AND DIGITAL PREDISTORTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18277318 titled 'METHOD AND DEVICE(S) FOR SUPPORTING MACHINE LEARNING BASED CREST FACTOR REDUCTION AND DIGITAL PREDISTORTION

Simplified Explanation

The patent application describes a method and device for supporting machine learning based signal conditioning on multiple digital input signals related to different frequency bands in a wireless communication network.

• The device obtains multiple digital input signals as complex valued signals.
• The device performs feature construction on the input signals to provide constructed feature signals based on predefined feature types.
• The predefined feature types include the real part, imaginary part, absolute value, and phase of each complex valued sample of the input signals.

Potential Applications

This technology could be applied in wireless communication networks to improve signal quality and efficiency before power amplification and transmission.

Problems Solved

1. Signal distortion and interference in different frequency bands. 2. Inefficient power amplification due to poor signal quality.

Benefits

1. Enhanced signal conditioning for improved transmission quality. 2. Increased efficiency in power amplification processes.

Potential Commercial Applications

Optimizing signal processing in wireless communication networks for better performance and reliability.

Possible Prior Art

There may be prior art related to signal processing and feature extraction in wireless communication systems, but specific examples would need to be researched.

Unanswered Questions

How does this technology compare to traditional signal processing methods in terms of efficiency and accuracy?

This article does not provide a direct comparison between the proposed technology and traditional signal processing methods.

What are the potential limitations or challenges in implementing this technology on a large scale in existing wireless networks?

The article does not address the potential obstacles or scalability issues that may arise when implementing this technology in real-world wireless communication systems.

Original Abstract Submitted

Method and device(s) for supporting performance of machine learning based CFR and DPD on multiple digital input signals relating to different frequency bands, respectively, in order to signal condition said signals before power amplification and subsequent transmission in said frequency bands by a wireless communication network. The device(s) obtain said multiple digital input signals as complex valued signals. The device(s) perform feature construction that takes said multiple digital input signals as input and provides constructed feature signals according to predefined constructed feature types as output. Said predefined constructed feature types relate to at least the following per complex valued sample of the obtained complex valued multiple digital input signals the real part of the sample, the imaginary part of the sample and at least one of the absolute value of the sample and the phase of the sample.