From: pippo@pluto.it   
      
   Hi all,   
   I'm develop a communicatino protocol, useful to wireless sensor networks,   
   which uses SVM.   
   In this work I use SVM in order to predict data in such a way to reduce the   
   energy cost of each sensor in the network.   
   So, I execute before a training phase on each sensor, while after I execute   
   a prediction phase on each sensor. The predicted value is compared with the   
   real value (about temperature, light, voltage, ecc...)   
   However, I have seen that SVM Regression doesn't work very well.   
   In fact, I my training set is about values taken from,  e.g., the period   
   08:00 AM to 12:00 AM and I would predict a value for 09:00 AM (i.e a time   
   between 8 and 12 AM), regression works well.   
   Instead, if I would like predict a value for 1:00PM (outside the previous   
   interval of time) prediction doesn't work well.   
   Is this normal?   
   Does anybody have experience with this topic?   
   Thanks in advance   
      
   Roberto   
      
   [ comp.ai is moderated ... your article may take a while to appear. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)