Hi Christopher,
On Tue, Mar 8, 2016 at 3:14 PM, Richardson, Christopher (richarc2) <
c.richard...@lancaster.ac.uk> wrote:
> Hi everyone,
>
> I'm very interested in working on the Signal Intelligence (gr-sigint)
> project for the Google Summer of Code.
>
> I'm currently a PhD student at Lancaster University, UK, studying attack
> detection
> in a privacy preserving manner.
>
> I achieved an MSc in Bristol, UK, making use of machine learning
> techniques to detect viruses -
> http://www.lancaster.ac.uk/pg/richarc2/dissertation.pdf.
> As mentioned in the idea suggested by Mr Rajendran "Another approach is to
> use available waterfall images and run some image comparison algorithms",
> I am curious if I could make use of such machine learning techniques to
> achieve this.
>
You could refer this new paper [1] to get an idea about the usage of CNN
for modulation classification. The technique mentioned in the paper works
on quadrature data in time.
It would be interesting to see how much accuracy we can get from
spectrogram information. For simple prototyping and analysis you could use
tensorflow [2] along with GNURadio
>
> I am also especially interested in how the performance of such classifiers
> could be measured through conducting real-world experiments,
> with 2 SDRs (one for transmission and one for reception) at a range of
> increasing distances, potentially making use of
> techniques such as Receiver Operating Characteristic (ROC) curves and the
> Area Under Curve (AUC) as a metric for quantifying
> the performance of a classifier.
>
> I'm currently reading more about algorithms to detect cyclostationary
> features along with a survey on Automatic Modulation Recognition.
> I'm also looking at existing GNU Radio modules such as gr-specest.
>
> If anyone could point me at further reading material or suggestions for
> the proposal, that would be great!
>
The first step for GSoC is to come up with a nice project proposal. Martin
already shared a lot of info on this in the mailinglist. You could look
into past GNURadio GSoC projects [3] and some student info [4]. These are
old links, but will give you an idea how to proceed. For ramping up on
cyclostationarity you could find a lot of sources online, e.g. [5-6].
Good luck.
Best regards,
Sreeraj
[1] http://arxiv.org/abs/1602.04105
[2] https://oshearesearch.com/2016/02/02/gnu-radio-tensorflow-blocks/
[3] https://gnuradio.org/redmine/projects/gnuradio/wiki/GSoCPastProjects
[4] https://gnuradio.org/redmine/projects/gnuradio/wiki/GSoCStudentInfo
[5] http://vtechworks.lib.vt.edu/handle/10919/29981
[6]
http://archives.njit.edu/vol01/etd/2000s/2006/njit-etd2006-115/njit-etd2006-115.pdf
> Kind Regards
>
> Christopher Richardson
>
> ___
> Discuss-gnuradio mailing list
> Discuss-gnuradio@gnu.org
> https://lists.gnu.org/mailman/listinfo/discuss-gnuradio
>
___
Discuss-gnuradio mailing list
Discuss-gnuradio@gnu.org
https://lists.gnu.org/mailman/listinfo/discuss-gnuradio
