The Mobile Agent Framework for Collaborative Processing in Sensor Networks∗

interval estimate s1 s2 s3 s4 s5 s6 A B C D (a) Uniform 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 −3 −2 −1 0 1 2 3 4 O ve rla p fu nc tio n Abstract interval estimate s1 s2 s3 s4 s5 s6interval estimate s1 s2 s3 s4 s5 s6 (b) Gaussian Figure 10: The overlap function for a set of 6 sensors using two distribution models (resolution is 0.05). The integrated information lies within regions over which the maximal peaks of the overlap function occur with the largest spread. The original proposal for generating and analyzing the overlap function is centralized and can only take place at the processing center. A distributed integration of the overlap function is proposed in [29] for the mobileagent-based computing such that at each stop of the itinerary, a partially integrated result can be generated from previously migrated sensor node outputs and the accuracy of the information derived from this result can be used to justify if the mobile agent needs to continue with its migration. The distributed method would generate the same output as the centralized method if the mobile agents finishes its itinerary.