📄 node41.html
字号:
<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.2//EN"><!--Converted with LaTeX2HTML 96.1-h (September 30, 1996) by Nikos Drakos (nikos@cbl.leeds.ac.uk), CBLU, University of Leeds --><HTML><HEAD><TITLE>Important methods which are (still) missing</TITLE><META NAME="description" CONTENT="Important methods which are (still) missing"><META NAME="keywords" CONTENT="TiseanHTML"><META NAME="resource-type" CONTENT="document"><META NAME="distribution" CONTENT="global"><LINK REL=STYLESHEET HREF="TiseanHTML.css"></HEAD><BODY bgcolor=ffffff LANG="EN" > <A NAME="tex2html487" HREF="node42.html"><IMG WIDTH=37 HEIGHT=24 ALIGN=BOTTOM ALT="next" SRC="icons/next_motif.gif"></A> <A NAME="tex2html485" HREF="node40.html"><IMG WIDTH=26 HEIGHT=24 ALIGN=BOTTOM ALT="up" SRC="icons/up_motif.gif"></A> <A NAME="tex2html481" HREF="node40.html"><IMG WIDTH=63 HEIGHT=24 ALIGN=BOTTOM ALT="previous" SRC="icons/previous_motif.gif"></A> <BR><B> Next:</B> <A NAME="tex2html488" HREF="node42.html">Acknowledgments</A><B>Up:</B> <A NAME="tex2html486" HREF="node40.html">Conclusion and perspectives</A><B> Previous:</B> <A NAME="tex2html482" HREF="node40.html">Conclusion and perspectives</A><BR> <P><H2><A NAME="SECTION000101000000000000000">Important methods which are (still) missing</A></H2><P>Let us finish the discussion by giving some perspectives on future work.So far, the TISEAN project has concentrated on the most common situationof a single time series. While for multiple measurements of similar naturemost programs can be modified with moderate effort, a general frameworkfor heterogeneous multivariate recordings (say, blood pressure and heart beat)has not been established so far in a nonlinear context. Nevertheless, we feelthat concepts like generalized synchrony, coherence, or information floware well worth pursuing and at some point should become available to a widercommunity, including applied research.<P>Initial experience with nonlinear time series methods indicates that some ofthe concepts may prove useful enough in the future to become part of theestablished time series tool box. For this to happen, availability of thealgorithms and reliable information on their use will be essential. Thepublication of a substantial collection of research level programs through theTISEAN project may be seen as one step in that direction. However, thepotential user will still need considerable experience in order to make theright decisions - about the suitability of a particular method for a specifictime series, about the selection of parameters, about the interpretation ofthe results. To some extent, these decisions could be guided by software thatevaluates the data situation and the results automatically. Previousexperience with black box dimension or Lyapunov estimators has not beenencouraging, but for some specific problems, ``optimal'' answers can inprinciple be defined and computed automatically, once the optimality criterionis formulated. For example, the prediction programs could be encapsulated in aframework that automatically evaluates the performance for a range ofembedding parameters etc. Of course, quantitative assessment of the results isnot always easy to implement and depends on the purpose of the study.As another example, it seems realistic to define ``optimal'' Poincarésurfaces of section and to find the optimal solutions numerically.<P>Like in most of the time series literature, the issue of stationarity hasentered the discussion only as something the lack of which has to be detectedin order to avoid spurious results. Taking this point seriously amounts torejecting a substantial fraction of time series problems, including the mostprominent examples, that is, most data from finance, metereology, and biology.It is quite clear that the mere rejection of these challenging problems is notsatisfactory and we will have to develop tools to actually analyse, understand,and predict nonstationary data. Some suggestions have been made for thedetection of fluctuating control parameters [<A HREF="citation.html#Kadtke">89</A>, <A HREF="citation.html#B1">90</A>, <A HREF="citation.html#casEEG">91</A>, <A HREF="citation.html#statio">92</A>].Most of these can be seen as continuous versions of the classification problem,another application which is not properly represented in TISEAN yet.<P>Publishing software, or reviews and textbooks for that matter, in a fieldevolving as rapidly as nonlinear time series analysis will always have thecharacter of a snapshot of the state at a given time. Having the options eitherto wait until the field has saturated sufficiently or to risk that programs, orstatements made, will become obsolete soon, we chose the second option.We hope that we can thus contibute to the further evolution of the field.<P><HR><A NAME="tex2html487" HREF="node42.html"><IMG WIDTH=37 HEIGHT=24 ALIGN=BOTTOM ALT="next" SRC="icons/next_motif.gif"></A> <A NAME="tex2html485" HREF="node40.html"><IMG WIDTH=26 HEIGHT=24 ALIGN=BOTTOM ALT="up" SRC="icons/up_motif.gif"></A> <A NAME="tex2html481" HREF="node40.html"><IMG WIDTH=63 HEIGHT=24 ALIGN=BOTTOM ALT="previous" SRC="icons/previous_motif.gif"></A> <BR><B> Next:</B> <A NAME="tex2html488" HREF="node42.html">Acknowledgments</A><B>Up:</B> <A NAME="tex2html486" HREF="node40.html">Conclusion and perspectives</A><B> Previous:</B> <A NAME="tex2html482" HREF="node40.html">Conclusion and perspectives</A><P><ADDRESS><I>Thomas Schreiber <BR>Wed Jan 6 15:38:27 CET 1999</I></ADDRESS></BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -