A Machine-Learning Based Connectivity Model for ...
We evaluate the accuracy of a multivariate, non-parametric path loss model derived from 42,157,324 RSSI samples collected over one year from an environmental wireless sensor network. The 2218 links in the network span a 2000 km2 basin and are deployed in a complex environment, with large variations of terrain attributes and vegetation coverage. The model is based on an ensemble regression tree machine learning algorithm (Random Forest). We compare the accuracy of this model to several well-known canonical (Free Space, plane earth) and empirical propagation models (Weissberger, ITU-R, COST235). We show how this model achieves a 37% reduction in the average prediction error compared to the canonical/empirical model with the best performance. The article presents a in-depth discussion on the strengths and limitations of the proposed approach.
There are no views created for this resource yet.
|Last updated||August 23, 2017|
|Created||August 23, 2017|
|License||Creative Commons Attribution Share-Alike|
|created||over 1 year ago|
|last modified||over 1 year ago|
|on same domain||1|