| abstract |
Disclosed are a system and method of multi-modality sensor data classification and fusion comprising partitioning data stored in a read only memory unit on a sensor node using a low query complexity boundary-decision classifier, applying an iterative two-dimensional nearest neighbor classifier to the partitioned data, forming a low query complexity classifier from a combination of the low query complexity boundary-decision classifier and the iterative two-dimensional nearest neighbor classifier, using the low query complexity classifier to identify classification parameters of the sensor node, and monitoring a network of spatially distributed sensor nodes based on the classification parameters of the sensor node. The boundary-decision classifier comprises a single low neuron count hidden layer and a single binary-decision output sensor node, or alternatively, the boundary-decision classifier comprises a linear classifier. Moreover, the network is a wireless unattended ground sensor network, and the data comprises signals transmitted by the sensor node. |