|
Hm, maybe I can convert the rtlsdr source I have to
handle extio files. That might keep me off the street a few days.
OTOH it would be a more fun challenge to skip the extra dll and
include that code into a sourcexxx.dll. Then you'll be able to
Simonize (ouch) work I kludge into something in your style and
more trouble free.
{o.o}
On 20220102 10:29:21, Simon Brown
wrote:
I
see that it would be nice to play with but is not very
practical and requires a lot of effort from me. There’s no
API for the RX888, just raw ADC data and ‘good luck to the
programmer’.
Oh poo.
{o.o}
On 20220102 09:44:53, Simon Brown wrote:
A few hours is a few days. Adding serial
number support is straightforward, I have no plans to add
the 64 MHz bandwidth.
Please somewhere in there squeeze in a
few hours to put together the new RX888 knowledge to make it
more useful within SDRC.
{o.o}
On 20220102 08:37:39, Simon Brown
wrote:
Agreed about the training. I hope to
have the AI included by Easter, then I can dig further.
Still a lot to do to get a nice UI harness working.
Simon Brown, G4ELI
https://www.sdr-radio.com
Tensorflow is an excellent system for
this sort of thing. The author of that article used
random words to train the model, but if he used more
traditional ham conversations it would help a lot, at
least for amatuer use including typical abbreviations
and Q signs so they would be better represented and not
read as errors by the model. The other thing that would
be useful would be to send a bunch of known CW text
from an automated keyer and pick up the audio from a
remote SDR, so the model would include fading and other
non-linear impairments that come from real HF paths that
hams deal with all the time. The cherry on top would be
to have hams send a set of known text with keyer, bug or
straight key and capture that over the HF signal path as
well.
If the ML model is trained well, I
would not be at all surprised if it could decode CW
much better than the best human. I have been
surprised as to how amazing the pattern recognition
capabilities of well trained models are. The key is
all in the training.
On Sat, Jan 1, 2022 at 1:14 PM
Simon Brown <simon@...>
wrote:
Milo,
And excellent article –
something I want to understand this year.
Simon Brown, G4ELI
https://www.sdr-radio.com
There are a huge number of
new tools for using AI today that leverage
modern compute infrastructure. Unfortunately,
many of the public ML tools out there are
optimized for visual image processing, as
opposed to audio or RF SIGINT style uses. But a
number of efforts exist to convert audio or RF
to an image, and then use the image tools to do
the training and generate a model for decoding.
While the training is computationally expensive,
once the model is built, it can be pretty
efficient to run.
There was another one that
used ML, GIMP and RTL-SDR's to do signal
identification using images again, but I can't
seem to find it now.
On Sat, Jan 1, 2022 at 9:55
AM Simon Brown <simon@...>
wrote:
Well,
This actually will be a
step into AI in 2023 – 1988 / 1989 I was
working in AI at SWIFT, sadly the brains
of the operation was on the plane that
crashed at Lockerbie. 30+ years later it’s
time to try and remember the theory and
see how it’s changed.
You will do a great
job. Solving the unsteady CW hand issue
will be interesting. Even some machine
produced CW will be a challenge to
decode. Looking forward to your work on
it in a few months from now. Computers
are amazing but programmers even more
amazing. Ha!
On Jan 1, 2022, at
11:35 AM, Simon Brown <simon@...>
wrote:
Hi,
I’ve often said
that a computer can decode better than
the human brain, now I’m trying to
prove it. ‘I may be some time…’
Happy 2022 to
all. May good SDR things happen this
year. Good luck Simon on the CW
decoder. It’s much needed.
On Jan 1, 2022,
at 9:02 AM, Simon Brown <simon@...>
wrote:
Hi All,
Over here it’s
2022 so a very happy new year to
you all. I’ve updated the current
V3.1 beta and am now spending
January designing a CW Decoder
harness which I hope will help me
develop a good CW Decoder, so for
January and possibly February
you’ll not be hearing much from me
😊 .
Be good in
2022,
Simon Brown,
G4ELI
https://www.sdr-radio.com
--
--
--
--
--
--
--
- + - + -
|
|
|
Simon Brown
I see that it would be nice to play with but is not very practical and requires a lot of effort from me. There’s no API for the RX888, just raw ADC data and ‘good luck to the programmer’.
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of jdow
Sent: 02 January 2022 18:04
To: main@SDR-Radio.groups.io
Subject: Re: [SDR-Radio] Happy New Year Oh poo.
{o.o}
On 20220102 09:44:53, Simon Brown wrote: A few hours is a few days. Adding serial number support is straightforward, I have no plans to add the 64 MHz bandwidth. Please somewhere in there squeeze in a few hours to put together the new RX888 knowledge to make it more useful within SDRC.
{o.o}
On 20220102 08:37:39, Simon Brown wrote: Agreed about the training. I hope to have the AI included by Easter, then I can dig further. Still a lot to do to get a nice UI harness working. Simon Brown, G4ELI https://www.sdr-radio.com Tensorflow is an excellent system for this sort of thing. The author of that article used random words to train the model, but if he used more traditional ham conversations it would help a lot, at least for amatuer use including typical abbreviations and Q signs so they would be better represented and not read as errors by the model. The other thing that would be useful would be to send a bunch of known CW text from an automated keyer and pick up the audio from a remote SDR, so the model would include fading and other non-linear impairments that come from real HF paths that hams deal with all the time. The cherry on top would be to have hams send a set of known text with keyer, bug or straight key and capture that over the HF signal path as well. If the ML model is trained well, I would not be at all surprised if it could decode CW much better than the best human. I have been surprised as to how amazing the pattern recognition capabilities of well trained models are. The key is all in the training. On Sat, Jan 1, 2022 at 1:14 PM Simon Brown <simon@...> wrote: Milo, And excellent article – something I want to understand this year. Simon Brown, G4ELI https://www.sdr-radio.com There are a huge number of new tools for using AI today that leverage modern compute infrastructure. Unfortunately, many of the public ML tools out there are optimized for visual image processing, as opposed to audio or RF SIGINT style uses. But a number of efforts exist to convert audio or RF to an image, and then use the image tools to do the training and generate a model for decoding. While the training is computationally expensive, once the model is built, it can be pretty efficient to run. There was another one that used ML, GIMP and RTL-SDR's to do signal identification using images again, but I can't seem to find it now. On Sat, Jan 1, 2022 at 9:55 AM Simon Brown <simon@...> wrote: Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed. On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
--
--
--
--
-- - + - + -
|
|
|
Oh poo.
{o.o}
On 20220102 09:44:53, Simon Brown
wrote:
A
few hours is a few days. Adding serial number support is
straightforward, I have no plans to add the 64 MHz
bandwidth.
Please somewhere in there squeeze in a few
hours to put together the new RX888 knowledge to make it more
useful within SDRC.
{o.o}
On 20220102 08:37:39, Simon Brown wrote:
Agreed about the training. I hope to have
the AI included by Easter, then I can dig further. Still a
lot to do to get a nice UI harness working.
Simon Brown, G4ELI
https://www.sdr-radio.com
Tensorflow is an excellent system for
this sort of thing. The author of that article used
random words to train the model, but if he used more
traditional ham conversations it would help a lot, at
least for amatuer use including typical abbreviations and
Q signs so they would be better represented and not read
as errors by the model. The other thing that would be
useful would be to send a bunch of known CW text from an
automated keyer and pick up the audio from a remote SDR,
so the model would include fading and other non-linear
impairments that come from real HF paths that hams deal
with all the time. The cherry on top would be to have
hams send a set of known text with keyer, bug or straight
key and capture that over the HF signal path as well.
If the ML model is trained well, I
would not be at all surprised if it could decode CW much
better than the best human. I have been surprised as to
how amazing the pattern recognition capabilities of well
trained models are. The key is all in the training.
On Sat, Jan 1, 2022 at 1:14 PM Simon
Brown <simon@...>
wrote:
Milo,
And excellent article – something
I want to understand this year.
Simon Brown, G4ELI
https://www.sdr-radio.com
There are a huge number of new
tools for using AI today that leverage modern
compute infrastructure. Unfortunately, many of
the public ML tools out there are optimized for
visual image processing, as opposed to audio or RF
SIGINT style uses. But a number of efforts exist
to convert audio or RF to an image, and then use
the image tools to do the training and generate a
model for decoding. While the training is
computationally expensive, once the model is
built, it can be pretty efficient to run.
There was another one that
used ML, GIMP and RTL-SDR's to do signal
identification using images again, but I can't
seem to find it now.
On Sat, Jan 1, 2022 at 9:55
AM Simon Brown <simon@...>
wrote:
Well,
This actually will be a
step into AI in 2023 – 1988 / 1989 I was
working in AI at SWIFT, sadly the brains of
the operation was on the plane that crashed
at Lockerbie. 30+ years later it’s time to
try and remember the theory and see how it’s
changed.
You will do a great
job. Solving the unsteady CW hand issue
will be interesting. Even some machine
produced CW will be a challenge to decode.
Looking forward to your work on it in a
few months from now. Computers are amazing
but programmers even more amazing. Ha!
On Jan 1, 2022, at
11:35 AM, Simon Brown <simon@...>
wrote:
Hi,
I’ve often said that
a computer can decode better than the
human brain, now I’m trying to prove it.
‘I may be some time…’
Happy 2022 to all.
May good SDR things happen this year.
Good luck Simon on the CW decoder.
It’s much needed.
On Jan 1, 2022,
at 9:02 AM, Simon Brown <simon@...>
wrote:
Hi All,
Over here it’s
2022 so a very happy new year to you
all. I’ve updated the current V3.1
beta and am now spending January
designing a CW Decoder harness which
I hope will help me develop a good
CW Decoder, so for January and
possibly February you’ll not be
hearing much from me 😊
.
Be good in 2022,
Simon Brown,
G4ELI
https://www.sdr-radio.com
--
--
--
--
--
--
- + - + -
|
|
|
Simon Brown
A few hours is a few days. Adding serial number support is straightforward, I have no plans to add the 64 MHz bandwidth.
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of jdow
Sent: 02 January 2022 17:08
To: main@SDR-Radio.groups.io
Subject: Re: [SDR-Radio] Happy New Year Please somewhere in there squeeze in a few hours to put together the new RX888 knowledge to make it more useful within SDRC.
{o.o}
On 20220102 08:37:39, Simon Brown wrote: Agreed about the training. I hope to have the AI included by Easter, then I can dig further. Still a lot to do to get a nice UI harness working. Simon Brown, G4ELI https://www.sdr-radio.com Tensorflow is an excellent system for this sort of thing. The author of that article used random words to train the model, but if he used more traditional ham conversations it would help a lot, at least for amatuer use including typical abbreviations and Q signs so they would be better represented and not read as errors by the model. The other thing that would be useful would be to send a bunch of known CW text from an automated keyer and pick up the audio from a remote SDR, so the model would include fading and other non-linear impairments that come from real HF paths that hams deal with all the time. The cherry on top would be to have hams send a set of known text with keyer, bug or straight key and capture that over the HF signal path as well. If the ML model is trained well, I would not be at all surprised if it could decode CW much better than the best human. I have been surprised as to how amazing the pattern recognition capabilities of well trained models are. The key is all in the training. On Sat, Jan 1, 2022 at 1:14 PM Simon Brown <simon@...> wrote: Milo, And excellent article – something I want to understand this year. Simon Brown, G4ELI https://www.sdr-radio.com There are a huge number of new tools for using AI today that leverage modern compute infrastructure. Unfortunately, many of the public ML tools out there are optimized for visual image processing, as opposed to audio or RF SIGINT style uses. But a number of efforts exist to convert audio or RF to an image, and then use the image tools to do the training and generate a model for decoding. While the training is computationally expensive, once the model is built, it can be pretty efficient to run. There was another one that used ML, GIMP and RTL-SDR's to do signal identification using images again, but I can't seem to find it now. On Sat, Jan 1, 2022 at 9:55 AM Simon Brown <simon@...> wrote: Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed. On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
--
--
--
-- - + - + -
|
|
|
Humans have an advantage. We understand context and
current AI implementations don't come close to understanding
context. That is subject to change.
{o.o}
On 20220102 09:19:43, Siegfried
Jackstien wrote:
In noisy conditions a human can decode better, cause when a
human hears something like "c o . . w a l l", the human knows
the missing r and n.
The brain is the best noisefilter ever. A computer can come
close. But when the conditions are at the noise border, the
brain can fill in missing signs.
Decoding BELOW the noiseborder?? yes thats a thing a computer
can do (but not with a hand keyed cw signal) ... see WSPR or ft4
/ft8 modes
The other station is "smearing signs" a bit?!? No way to decode
by pc, but a brain still can read that.
I guess a really good cw decoder is not that easy ;-)
HNY Simon
Greetings Sigi dg9bfc
Am 01.01.2022 um 17:35 schrieb Simon
Brown:
Hi,
I’ve often said that a computer can
decode better than the human brain, now I’m trying to prove
it. ‘I may be some time…’
Happy 2022 to all. May good SDR things
happen this year. Good luck Simon on the CW decoder. It’s
much needed.
On
Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...>
wrote:
Hi All,
Over here it’s 2022 so a very happy
new year to you all. I’ve updated the current V3.1 beta
and am now spending January designing a CW Decoder
harness which I hope will help me develop a good CW
Decoder, so for January and possibly February you’ll not
be hearing much from me 😊 .
Be good in 2022,
Simon Brown, G4ELI
https://www.sdr-radio.com
--
--
- + - + -
|
|
|
In noisy conditions a human can decode better, cause when a human
hears something like "c o . . w a l l", the human knows the
missing r and n.
The brain is the best noisefilter ever. A computer can come
close. But when the conditions are at the noise border, the brain
can fill in missing signs.
Decoding BELOW the noiseborder?? yes thats a thing a computer can
do (but not with a hand keyed cw signal) ... see WSPR or ft4 /ft8
modes
The other station is "smearing signs" a bit?!? No way to decode
by pc, but a brain still can read that.
I guess a really good cw decoder is not that easy ;-)
HNY Simon
Greetings Sigi dg9bfc
Am 01.01.2022 um 17:35 schrieb Simon
Brown:
toggle quoted message
Show quoted text
Hi,
I’ve often said that a computer can decode
better than the human brain, now I’m trying to prove it. ‘I
may be some time…’
Happy 2022 to all. May good SDR things
happen this year. Good luck Simon on the CW decoder. It’s
much needed.
On Jan 1,
2022, at 9:02 AM, Simon Brown <simon@...>
wrote:
Hi All,
Over here it’s 2022 so a very happy new
year to you all. I’ve updated the current V3.1 beta and am
now spending January designing a CW Decoder harness which
I hope will help me develop a good CW Decoder, so for
January and possibly February you’ll not be hearing much
from me 😊 .
Be good in 2022,
Simon Brown, G4ELI
https://www.sdr-radio.com
--
--
- + - + -
|
|
|
Please somewhere in there squeeze in a few hours to
put together the new RX888 knowledge to make it more useful within
SDRC.
{o.o}
On 20220102 08:37:39, Simon Brown
wrote:
Agreed
about the training. I hope to have the AI included by
Easter, then I can dig further. Still a lot to do to get a
nice UI harness working.
Simon Brown, G4ELI
https://www.sdr-radio.com
Tensorflow is an excellent system for
this sort of thing. The author of that article used random
words to train the model, but if he used more traditional
ham conversations it would help a lot, at least for amatuer
use including typical abbreviations and Q signs so they
would be better represented and not read as errors by the
model. The other thing that would be useful would be to
send a bunch of known CW text from an automated keyer and
pick up the audio from a remote SDR, so the model would
include fading and other non-linear impairments that come
from real HF paths that hams deal with all the time. The
cherry on top would be to have hams send a set of known text
with keyer, bug or straight key and capture that over the HF
signal path as well.
If the ML model is trained well, I
would not be at all surprised if it could decode CW much
better than the best human. I have been surprised as to
how amazing the pattern recognition capabilities of well
trained models are. The key is all in the training.
On Sat, Jan 1, 2022 at 1:14 PM Simon
Brown <simon@...>
wrote:
Milo,
And excellent article –
something I want to understand this year.
Simon Brown, G4ELI
https://www.sdr-radio.com
There are a huge number
of new tools for using AI today that leverage modern
compute infrastructure. Unfortunately, many of the
public ML tools out there are optimized for visual
image processing, as opposed to audio or RF SIGINT
style uses. But a number of efforts exist to
convert audio or RF to an image, and then use the
image tools to do the training and generate a model
for decoding. While the training is
computationally expensive, once the model is built,
it can be pretty efficient to run.
There was another one
that used ML, GIMP and RTL-SDR's to do signal
identification using images again, but I can't
seem to find it now.
On Sat, Jan 1, 2022
at 9:55 AM Simon Brown <simon@...>
wrote:
Well,
This actually
will be a step into AI in 2023 – 1988 / 1989 I
was working in AI at SWIFT, sadly the brains
of the operation was on the plane that crashed
at Lockerbie. 30+ years later it’s time to try
and remember the theory and see how it’s
changed.
You will do a
great job. Solving the unsteady CW hand
issue will be interesting. Even some machine
produced CW will be a challenge to decode.
Looking forward to your work on it in a few
months from now. Computers are amazing but
programmers even more amazing. Ha!
On Jan 1, 2022, at
11:35 AM, Simon Brown <simon@...>
wrote:
Hi,
I’ve often
said that a computer can decode better
than the human brain, now I’m trying to
prove it. ‘I may be some time…’
Happy 2022
to all. May good SDR things happen this
year. Good luck Simon on the CW decoder.
It’s much needed.
On Jan 1,
2022, at 9:02 AM, Simon Brown <simon@...>
wrote:
Hi All,
Over here
it’s 2022 so a very happy new year to
you all. I’ve updated the current V3.1
beta and am now spending January
designing a CW Decoder harness which I
hope will help me develop a good CW
Decoder, so for January and possibly
February you’ll not be hearing much
from me 😊 .
Be good
in 2022,
Simon
Brown, G4ELI
https://www.sdr-radio.com
--
--
--
--
--
- + - + -
|
|
|
Simon Brown
Agreed about the training. I hope to have the AI included by Easter, then I can dig further. Still a lot to do to get a nice UI harness working. Simon Brown, G4ELI https://www.sdr-radio.com
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Milo Medin (K6CZ)
Sent: 02 January 2022 16:31
To: main@sdr-radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New Year Tensorflow is an excellent system for this sort of thing. The author of that article used random words to train the model, but if he used more traditional ham conversations it would help a lot, at least for amatuer use including typical abbreviations and Q signs so they would be better represented and not read as errors by the model. The other thing that would be useful would be to send a bunch of known CW text from an automated keyer and pick up the audio from a remote SDR, so the model would include fading and other non-linear impairments that come from real HF paths that hams deal with all the time. The cherry on top would be to have hams send a set of known text with keyer, bug or straight key and capture that over the HF signal path as well. If the ML model is trained well, I would not be at all surprised if it could decode CW much better than the best human. I have been surprised as to how amazing the pattern recognition capabilities of well trained models are. The key is all in the training. On Sat, Jan 1, 2022 at 1:14 PM Simon Brown <simon@...> wrote: Milo, And excellent article – something I want to understand this year. Simon Brown, G4ELI https://www.sdr-radio.com There are a huge number of new tools for using AI today that leverage modern compute infrastructure. Unfortunately, many of the public ML tools out there are optimized for visual image processing, as opposed to audio or RF SIGINT style uses. But a number of efforts exist to convert audio or RF to an image, and then use the image tools to do the training and generate a model for decoding. While the training is computationally expensive, once the model is built, it can be pretty efficient to run. There was another one that used ML, GIMP and RTL-SDR's to do signal identification using images again, but I can't seem to find it now. On Sat, Jan 1, 2022 at 9:55 AM Simon Brown <simon@...> wrote: Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed. On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
--
--
-- - + - + -
|
|
|
Tensorflow is an excellent system for this sort of thing. The author of that article used random words to train the model, but if he used more traditional ham conversations it would help a lot, at least for amatuer use including typical abbreviations and Q signs so they would be better represented and not read as errors by the model. The other thing that would be useful would be to send a bunch of known CW text from an automated keyer and pick up the audio from a remote SDR, so the model would include fading and other non-linear impairments that come from real HF paths that hams deal with all the time. The cherry on top would be to have hams send a set of known text with keyer, bug or straight key and capture that over the HF signal path as well.
If the ML model is trained well, I would not be at all surprised if it could decode CW much better than the best human. I have been surprised as to how amazing the pattern recognition capabilities of well trained models are. The key is all in the training.
Good luck, Milo (K6CZ)
On Sat, Jan 1, 2022 at 1:14 PM Simon Brown < simon@...> wrote: Milo, And excellent article – something I want to understand this year. Simon Brown, G4ELI https://www.sdr-radio.com There are a huge number of new tools for using AI today that leverage modern compute infrastructure. Unfortunately, many of the public ML tools out there are optimized for visual image processing, as opposed to audio or RF SIGINT style uses. But a number of efforts exist to convert audio or RF to an image, and then use the image tools to do the training and generate a model for decoding. While the training is computationally expensive, once the model is built, it can be pretty efficient to run. There was another one that used ML, GIMP and RTL-SDR's to do signal identification using images again, but I can't seem to find it now. On Sat, Jan 1, 2022 at 9:55 AM Simon Brown <simon@...> wrote: Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
--
-- - + - + -
|
|
|
Allan Isaacs
Hi Simon
If you are
writing the program will it not precisely reflect the ability of your own brain….
Nowt to do
with the computer.
It will definitely
be a jolly good program.
Allan G3PIY
From:
main@SDR-Radio.groups.io [mailto:main@SDR-Radio.groups.io] On Behalf Of Simon Brown
toggle quoted message
Show quoted text
Sent: 01 January 2022 16:36
To: main@SDR-Radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New
Year
Hi,
I’ve
often said that a computer can decode better than the human brain, now I’m
trying to prove it. ‘I may be some time…’
|
|
|
Simon Brown
toggle quoted message
Show quoted text
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Milo Medin (K6CZ)
Sent: 01 January 2022 20:22
To: main@sdr-radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New Year There are a huge number of new tools for using AI today that leverage modern compute infrastructure. Unfortunately, many of the public ML tools out there are optimized for visual image processing, as opposed to audio or RF SIGINT style uses. But a number of efforts exist to convert audio or RF to an image, and then use the image tools to do the training and generate a model for decoding. While the training is computationally expensive, once the model is built, it can be pretty efficient to run. There was another one that used ML, GIMP and RTL-SDR's to do signal identification using images again, but I can't seem to find it now. On Sat, Jan 1, 2022 at 9:55 AM Simon Brown <simon@...> wrote: Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
--
-- - + - + -
|
|
|
There are a huge number of new tools for using AI today that leverage modern compute infrastructure. Unfortunately, many of the public ML tools out there are optimized for visual image processing, as opposed to audio or RF SIGINT style uses. But a number of efforts exist to convert audio or RF to an image, and then use the image tools to do the training and generate a model for decoding. While the training is computationally expensive, once the model is built, it can be pretty efficient to run.
There was another one that used ML, GIMP and RTL-SDR's to do signal identification using images again, but I can't seem to find it now.
Good luck, milo (K6CZ)
On Sat, Jan 1, 2022 at 9:55 AM Simon Brown < simon@...> wrote: Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha!
On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
-- - + - + -
|
|
|
A working cw tx would be nice.. Now most sdr users use a software like morse keyer connected to console and transmitting in ssb A direct keying in console would be needed Dg9bfc sigi Ps HNY SIMON
Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed. From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Larry Dodd
Sent: 01 January 2022 17:33
To: main@sdr-radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New Year You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha!
On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
-- - + - + -
|
|
|
Simon Brown
Well, This actually will be a step into AI in 2023 – 1988 / 1989 I was working in AI at SWIFT, sadly the brains of the operation was on the plane that crashed at Lockerbie. 30+ years later it’s time to try and remember the theory and see how it’s changed.
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Larry Dodd
Sent: 01 January 2022 17:33
To: main@sdr-radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New Year You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha!
On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
--
-- - + - + -
|
|
|
John
Happy New Year to Simon and everybody else, hope everybody has a great new year. No doubt we'll all get some new SDR's and probably some new antennes and some more of everything else that goes with this great hobby of Amateur Radio, Short Wave Listening and anything else that we might do with our radios. Hope everybody has a great new year, Very Best Wishes and Very Best Regards to All on the list or off the list.
Happy New Year and I hope 2022 is going to be great for everyone. John. Good luck with the CW decoder Simon, Sorry you don't need luck Simon with all of the fantastic software you write. Just a wee bit of time to think and you will have it done in no time. Very Best Wishes and Very Best Regards to all and I hope everybody has a brilliant 2022. Happy New Year to Everybody John.
Simon You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! Larry K4LED On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
-- - + - + -
|
|
|
Larry Dodd
Simon You will do a great job. Solving the unsteady CW hand issue will be interesting. Even some machine produced CW will be a challenge to decode. Looking forward to your work on it in a few months from now. Computers are amazing but programmers even more amazing. Ha! Larry K4LED
On Jan 1, 2022, at 11:35 AM, Simon Brown <simon@...> wrote:
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’ From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Larry Dodd
Sent: 01 January 2022 15:13
To: main@sdr-radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New Year Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
-- - + - + -
|
|
|
Simon Brown
toggle quoted message
Show quoted text
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Roger Need via groups.io
Sent: 01 January 2022 17:23
To: main@SDR-Radio.groups.io
Subject: Re: [SDR-Radio] Happy New Year Simon,
Take a look at CW Skimmer. The algorithm is one of the best for decoding hand sent CW...
Roger -- - + - + -
|
|
|
Roger Need
Simon,
Take a look at CW Skimmer. The algorithm is one of the best for decoding hand sent CW...
Roger
|
|
|
Simon Brown
Hi, I’ve often said that a computer can decode better than the human brain, now I’m trying to prove it. ‘I may be some time…’
From: main@SDR-Radio.groups.io <main@SDR-Radio.groups.io> On Behalf Of Larry Dodd
Sent: 01 January 2022 15:13
To: main@sdr-radio.groups.io
Cc: SDR-Radio@groups.io
Subject: Re: [SDR-Radio] Happy New Year Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed.
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com
--
-- - + - + -
|
|
|
Larry Dodd
Simon. All, Happy 2022 to all. May good SDR things happen this year. Good luck Simon on the CW decoder. It’s much needed. Larry K4LED
On Jan 1, 2022, at 9:02 AM, Simon Brown <simon@...> wrote:
Hi All, Over here it’s 2022 so a very happy new year to you all. I’ve updated the current V3.1 beta and am now spending January designing a CW Decoder harness which I hope will help me develop a good CW Decoder, so for January and possibly February you’ll not be hearing much from me 😊 . Be good in 2022, Simon Brown, G4ELI https://www.sdr-radio.com -- - + - + -
|
|
|
