I'm looking for some algorithm able to better recognize the geometry place only exploiting wi-fi antennas. I read about place recognition is divided in two classes: geometry and fingerprint. I'm interested to use fingerprinting one and I'd like to develop an intelligent system able to learn more and more which is the correct set of right values (e.g. rssi, mac, response rate...) identify the place. I'm not interested to geo-referentiate the place but only to recognize the place. What kind of technique should I consider? Statistical learning (MLE, bayesian models...) or I can think to use classification algorithms like support vector machine or others? can I think to explore fuzzy system for my purpose?
Tell me more
×
Geographic Information Systems Stack Exchange is a question and answer site for
cartographers, geographers and GIS professionals. It's 100% free, no registration required.
|
closed as not a real question by whuber♦ Sep 2 '11 at 12:50
It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, see the FAQ.
