RECURRENCE PLOTS

For the next symposium in 2019, we offer a scholarship for PhD students! More info: http://symposium.recurrence-plot.tk/?a=scholarship

This is completely right. For the measures based on vertical structures, I suggest to include the LOI and not to apply the Theiler window. This should also be noted in the explanation of the method when a publication is prepared.

This is really a good point. When the LOI is not excluded, the denominator is N × N . There are some special cases where this definition of RR is helpful. In other applications, it can be required to exclude the LOI, then the denominator is N ( N –1). Further, a Theiler window can be required, which...

As far as I know, there is no public software for it. I myself have developed a C++ code but it is only for a pilot study and I need to check again whether it is maturated enough to be used for general purpose or other data. Moreover, the code is more than 10 years old …

The eigth international recurrence plot symposium will be organized by the Jiangsu University in Nanjing, China, in August 21-23, 2019. The venue will be in Zhenjiang.

More information:
http://symposium.recurrence-plot.tk/

Hi Pier,

the empty region means that the states in this epoch do not occur at any other times. These state are unique. Perhaps you could also show us the time series?

Best
Norbert

No, it is not possible. The base of the CRP is the distance between two points (on two different phase space trajectories).

Yes, sure. As long as you don't delete the install.m file, you can use it several times, also at other machines.

Look at this answer:
http://www.recurrence-plot.tk/forum/vie ... 4224#p5623

Hi, I think nargoutchk was introduced before MATLAB R2006a. But it seems that your MATLAB is too old and does not have this function. I suggest to write simple function called nargoutchk.m and put it into the CRPtool folder: function out = nargoutchk(in1,in2) % do nothing By doing this you only lose...

Hi Mircea, you are right, when using the fixed number of neighbours (which is the original definition of an RP by Eckmann 1987) the RP is not symmetric. This should be clear because for recurrence pair i and j the k nearest neighbours of the state at time point i are not necessarily the k nearest ne...

Hi,

it depends on the data. I assume that you somehow normalized the data beforehand.

Then, only look at the RR. RR is the probability of recurrence with respect to some lag. Therefore, in your case, I would chose lag +15.

Best
Norbert

sounds more like feature extraction or support vector machines. I'm not an expert in this.

It is better to send me an email with all information I would need to figure out the problem. (MATLAB version, operation system etc)
Thanks!
NM

Hello Fan.Mi, thanks for your kind words. Regarding your question: it is something different when you calculate the RQA for each of the N channels separately or when you combine all N channels to one phase space trajectory (of then dimension N ), because then you get only one RQA result. It depends ...