6. A DATA MINING BASED TARGET CLASSIFICATION FOR TACTICAL UNDERWATER SENSOR NETWORKS Yaşar DOĞAN, 2004

Keywords : Underwater sensor networks, Classification mining, Decision tree, Target detection, Proximity microsensor, Radiation microsensor, Magnetic microsensor, Acoustic microsensor.

Advances in MEMS, wireless communications, and digital electronics have made it possible to produce large amount of small-size, low-cost sensors which integrate sensing, processing, and communication capabilities together. Also, the low cost makes it possible to have a network of hundreds or thousands of these sensors, thereby enhancing the reliability and accuracy of data and the area coverage. Large amount of these sensors can be quickly deployed in the field, where each sensor independently senses the environment but collaboratively achieves complex information gathering and dissemination tasks like intrusion detection, target tracking, environmental monitoring, remote sensing, global surveillance, etc.

Inexpensive, smart devices with multiple sensors provide opportunities for instrumenting, monitoring and controlling targeting systems. Sensor nodes have capability for acquiring and embedded processing of variety of data forms. Collaborative signal processing and fusion algorithms are needed to aggregate the distributed data from among the nodes in the network, including possibly multiple modalities of data within a sensor node, to make decisions in a reliable and efficient manner. One of the important sensor network applications is target classification in battlefields.

In this thesis we proposed a classification mining based detection algorithm for underwater sensor networks is introduced. Microsensors, which cost only a couple of dollars, are used to tackle the challenge of detecting and classifying submarines, SDV (small delivery vehicles), underwater mines and divers in open, shallow and very shallow water. The algorithm is designed for wireless tactical underwater sensor network architectures where sensors attached to a surface buoy can be lowered to an adjustable depth. Decision tree algorithms are used as a classification mining technique for dynamic diver, mine, submarine, small delivery vehicle detection. The sensed proximity, magnetic and acoustic data are used for collaborative classification.