Re: [Discuss-gnuradio] GSOC 2017 - Introduction and Ideas for Project

[Martin Braun]

Usman,

On 03/04/2017 07:59 AM, Usman Mahmood wrote:
> [...]
> As a part of GSOC 2017, I want to mainly extend /gr-radar /and develop
> various signal processing modules of impact to users. I will be writing
> a detailed proposal in a few days but for now I have the following ideas: 
> 
> - Computing cross-ambiguity function and providing 3D visualisation
> - Adaptive filter implementation to remove the direct transmitted signal
> in case of passive radar systems which have reference and surveillance
> antennas
> - Batched cross correlation implementation in real time with overlaps
> between batches to ensure continuity
> - Angle of arrival estimation (although I recently found out
> about https://github.com/kit-cel/gr-specest which does something similar)

This all sounds good! I would encourage you to focus on some parts, and
then expand on how you'd like to develop those.

> I am also very interested in extending the machine learning capabilities
> of GNU Radio and create OOT modules that allow users to import models
> from /scikit-learn /(such as decision trees and KNNs)
> and /tensorflow /(such as CNN and LSTM). 
> 
> Ideally, I want to implement these signal processing and machine
> learning techniques together in a single module as I believe they go
> hand-in-hand. I am also open to any other ideas. Please let me know if
> there is any feedback as I write the first proposal draft!

You'll have higher chances if you focus on something, and make sure you
have a plan that moves all the way from writing some code to spending
time on getting it merged. Are you suggesting to do gr-radar with
machine learning concepts? That could be a very interesting project, but
make sure not to overload your proposal. Also, mentors have to believe
this is a reasonable project load for the 3-ish months of GSoC.

In general, this is going in a good direction. Post a first proposal
draft here, and we'll make sure you get some useful feedback.

Cheers,
Martin