SPATIAL INFERENCE USING CENSORED MULTIPLE TESTING WITH FDR CONTROL

A wireless sensor network performs spatial inference on a physical phenomenon of interest. The areas in which this phenomenon ex- hibits interesting or anomalous behavior are identified whilst con- trolling false positives. We expand our previous work based on multiple hypothesis testing (MHT) and local false discovery rates to save energy and reduce spectrum use. The number of transmis- sions from sensors producing uninformative statistics are reduced by introducing censoring for MHT that imposes a communication rate constraint while maintaining the desired performance. Two novel methods are proposed. As our numerical experiments demonstrate, both approaches reduce the number of transmissions while maintain- ing false discovery rate control. In addition, one method allows to either define a fixed number of total transmissions or to trade the number of transmissions off against the achieved detection power.