Hi Mike --<br><br> -- Great idea! I think this would be a very interesting topic to discuss from a machine learning perspective. I can't make next Wednesday, unfortunately, but the following one would work.<br><br>
My friend is sending some data from her setup, where the fish are so young they are still inside the egg. The signal will likely not come from a particular color channel, as there is probably not enough blood-cell density in these tiny fish (~2 mm long) to filter the light. I'm wondering if the refractive properties of the moving heart muscles will provide enough signal to extract the heart beat.<br>
<br> cheers --<br><br> -- Todd <br><br><br><div class="gmail_quote">On Thu, Oct 21, 2010 at 9:47 AM, Mike Schachter <span dir="ltr"><<a href="mailto:mike@mindmech.com">mike@mindmech.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><br>Todd, seems like you're going to have to use OpenCV to identify the<br>region of interest in the fish face though (j/k). They speculate that<br>
the heart rate signal is contained mostly in the green channel:<br><br>
"The second component typically, but not always contained the<br>strongest pulse signal. It is unclear why this is the case but one<br>might expect it to be related to the green channel and the fact<br>that hemoglobin absorptivity is highest in green/yellow light."<br>
<br>Do you have your zebrafish fixed while you're trying to take data?<br><br>In general, is anyone interested in this stuff from a machine-learning<br>perspective? We give (almost) weekly talks at the machine learning<br>
group and I'd be happy to go over the paper and a high level overview<br>of ICA. We also have a guy who is familiar with OpenCV for the face<br>recognition. Maybe we could all get together on a Machine Learning<br>Wednesday (7:30pm)?<br>
<font color="#888888">
<br> mike</font><div><div></div><div class="h5"><br><br><br><br><div class="gmail_quote">On Wed, Oct 20, 2010 at 11:51 PM, Todd Anderson <span dir="ltr"><<a href="mailto:tanders@stanford.edu" target="_blank">tanders@stanford.edu</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
Yea, I was hoping to just feed it the fish data. I have experience with ICA, so I think I'll just use the paper as inspiration!<div><div></div><div><br><br><br><div class="gmail_quote">On Wed, Oct 20, 2010 at 7:54 PM, Eric Boyd <span dir="ltr"><<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">The article I linked<div><br>
<br>
<a href="http://www.opticsinfobase.org/abstract.cfm?URI=oe-18-10-10762" target="_blank">http://www.opticsinfobase.org/abstract.cfm?URI=oe-18-10-10762</a><br>
<br></div>
actually has enough technical details that you could probably write code. Of course that's a big project :-).<br>
<br>
Eric<div><br>
<br>
<br>
<br>
<br>
On 10/20/10 10:46 PM, Todd Anderson wrote:<br>
</div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div>
Did anyone ever find a software package or code for this? I'd like to<br>
see if it can track zebrafish heart rates...<br>
<br>
<br>
<br>
On Mon, Oct 11, 2010 at 1:03 PM, Eric Boyd <<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a><br></div><div><div></div><div>
<mailto:<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a>>> wrote:<br>
<br>
My guess would be that they can't really get HRV. It looks to me like<br>
their analysis system requires multiple beats just to get the heart-rate<br>
accurately (they do the equivalent of an FFT to get it). But given that<br>
they can get HR at all, I'm sure getting HRV is just a matter of time.<br>
Might be hard with only 15Hz webcam though - if my calculations are<br>
right that limits intra-beat timings to +/-4BPM, yes? Or could you<br>
calculate HRV over a big data set?!?<br>
<br>
I am looking forward to having my new pulse-choker stuff (using polar<br>
heart rate receiver and a heart-shaped circuit I have designed), I'm<br>
totally gonna hack a logger into one of them and when I do so I'll share<br>
the data here :-).<br>
<br>
Eric<br>
<br>
On 10/9/10 6:03 PM, Tomm wrote:<br>
> A tray app that monitors your heart rate is a great idea. I<br>
wonder if<br>
> the time resolution is good enough to measure heart rate variation<br>
> (HRV)? Variations in heartrate is also pretty interesting:<br>
><br>
> "[...] asked 52 adults to report how often they experienced positive<br>
> emotions like happiness, awe, and gratitude and how socially<br>
connected<br>
> they felt in their social interactions every day for a period of nine<br>
> weeks. The researchers also measured the HRV of each individual<br>
at the<br>
> beginning and end of the study by measuring heart rate during a<br>
> two-minute session of normal breathing. HRV at the beginning of the<br>
> study predicted how quickly people developed positive feelings and<br>
> experiences of social connectedness throughout the nine-week<br>
period. In<br>
> addition, experiences of social connectedness predicted increases<br>
in HRV<br>
> at the end of the study, demonstrating a reciprocal relationship<br>
between<br>
> heart rate and having satisfying social experiences."<br>
><br>
<a href="http://www.scientificamerican.com/article.cfm?id=the-neuroscience-of-heart" target="_blank">http://www.scientificamerican.com/article.cfm?id=the-neuroscience-of-heart</a><br>
><br>
> Tom<br>
><br>
> On Sat, Oct 9, 2010 at 8:21 AM, Eric Boyd <<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a><br>
<mailto:<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a>><br></div></div><div><div></div><div>
> <mailto:<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a> <mailto:<a href="mailto:mrericboyd@yahoo.com" target="_blank">mrericboyd@yahoo.com</a>>>> wrote:<br>
><br>
><br>
<a href="http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded" target="_blank">http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded</a><br>
<<a href="http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded" target="_blank">http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded</a>><br>
><br>
<<a href="http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded" target="_blank">http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded</a><br>
<<a href="http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded" target="_blank">http://www.youtube.com/watch?v=LyWnvAWEbWE&feature=player_embedded</a>>><br>
><br>
> Basically, using nothing other than a webcam (1.3MP, 15 Hz!),<br>
they can<br>
> read your heart rate. Then they built that into a "medical<br>
mirror", so<br>
> you can see your heart beat in the morning when you brush<br>
your teeth :-)<br>
><br>
> I found one of his papers about it online, full text:<br>
><br>
> Non-contact, automated cardiac pulse measurements using video<br>
imaging<br>
> and blind source separation<br>
> <a href="http://www.opticsinfobase.org/abstract.cfm?URI=oe-18-10-10762" target="_blank">http://www.opticsinfobase.org/abstract.cfm?URI=oe-18-10-10762</a><br>
><br>
> Looks to me like the big breakthrough here is the motion<br>
independence,<br>
> which they got through a combination of face recognition and<br>
cropping<br>
> and separating the video into it's three component colors.<br>
They claim<br>
> an average error from the reference pulseox reading of less<br>
than 1 BPM<br>
> even with movement, that's pretty impressive.<br>
><br>
> Anyone want to write a laptop app which would just keep the<br>
webcam on<br>
> all the time and log your heartbeat?<br>
><br>
> Eric<br>
> _______________________________________________<br>
> Cyborg mailing list<br>
> <a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a><br>
<mailto:<a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a>><br>
<mailto:<a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a><br>
<mailto:<a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a>>><br>
> <a href="https://www.noisebridge.net/mailman/listinfo/cyborg" target="_blank">https://www.noisebridge.net/mailman/listinfo/cyborg</a><br>
><br>
><br>
_______________________________________________<br>
Cyborg mailing list<br>
<a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a> <mailto:<a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a>><br>
<a href="https://www.noisebridge.net/mailman/listinfo/cyborg" target="_blank">https://www.noisebridge.net/mailman/listinfo/cyborg</a><br>
<br>
<br>
<br>
<br></div></div>
--<br>
<a href="http://www.octotod.net" target="_blank">http://www.octotod.net</a><br>
</blockquote>
</blockquote></div><br><br clear="all"><br></div></div><font color="#888888">-- <br><a href="http://www.octotod.net" target="_blank">http://www.octotod.net</a><br>
</font><br>_______________________________________________<br>
Cyborg mailing list<br>
<a href="mailto:Cyborg@lists.noisebridge.net" target="_blank">Cyborg@lists.noisebridge.net</a><br>
<a href="https://www.noisebridge.net/mailman/listinfo/cyborg" target="_blank">https://www.noisebridge.net/mailman/listinfo/cyborg</a><br>
<br></blockquote></div><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br><a href="http://www.octotod.net" target="_blank">http://www.octotod.net</a><br>