Adaptive digital filters - page 16
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
I have heard about Kalman filter, but never dealt with it in detail. It seems to be statistically optimal, which of course inspires some optimism, but on the other hand, how many great technologies from other fields of science, which do not work in the market, already existed? It is necessary to look.
NorthernWind if interested I can offer Kalman for a nominal fee, http://www.myfolder.nm.ru/kalman.htm
Garfish, I can also tell you who is interested in Kalman. They are Prival, Neutron, grasn, lna01. I'm sure I haven't named them all, but these guys are definitely in the top ten. I'm not there, as I'm happy with the JMA for now, which is apparently better than the Kalman you drew. I wonder if I'll wait for the venerable Kalman to outdo the not so venerable Juric after all.
Here's a comparison with the real Jurik. And here's a comparison with SkA_JMA - a homemade Jurik, no relation, even close, to the real Jurik.
Garfish, I can also tell you who is interested in Kalman. They are Prival, Neutron, grasn, lna01. I'm sure I haven't named them all, but these guys are definitely in the top ten. I'm not there, as I'm happy with the JMA for now, which is apparently better than the Kalman you drew. I wonder if I'll wait for the venerable Kalman to outdo the not so venerable Juric after all.
Mathemat for the clients thank you.
LeoV thanks again for the buy, you have a zero-order sliding window forecast on your chart, if you put the forecast from a higher order recursive filter the result will be much better than KFRP(KFRF()) :)
You're welcome. But they are unlikely to buy...
The result will be much better than KFRP(KFRF()) :)
Show me the result, eh?
Here. But I don't mean that in a bad way. Just as a result. Need to know how to use it......
Mathemat for the customers thank you.
LeoV thanks again for the buy, you have a zero order sliding window forecast on your chart, if you put a forecast from a higher order filtering recursively the result will be much better than KFRP(KFRF()) :)
Not at all. Better with a sliding window, in my opinion......
You're welcome. But they're unlikely to buy...
Show the result, eh?
about that, red line in my opinion is closer to the data, although the total size of the averaging window in Kalman is the same 4+11, and in zhm 15, in fact it is not the averaging window, in Kalman it is the memory size, the meaning is different, you can get no filtering at high orders with memory depth of 100.
Although, who is looking for what, someone needs the filter to be smoother, someone needs to approximate the data more accurately.
at higher orders in the filter there are harmonic components on reversals in the form of overflows and smooth fading.
Garfish, I can also tell you who is interested in Kalman. They are Prival, Neutron, grasn, lna01. I'm sure I haven't named them all, but these guys are definitely in the top ten. I'm not there, as I'm happy with the JMA for now, which is apparently better than the Kalman you drew. I wonder if I'll wait for the venerable Kalman to outdo the not so venerable Juric after all.
If any of the programmers are free, I'm ready to share my experience with Kalman (ichmo the soft sign in the name is redundant). It works in Matcadet.
Garfish for the offer thanks, but I'm more interested in doing it myself, very encouraged by some of the results.