DEVELOPING A PROTOTYPE OF A LOW COST AND RAPIDLY DEPLOYABLE MICRO-SENSOR NODE TO DETECT AND CLASSIFY UNDERWATER TARGETS AND THERMAL ANALYSIS OF THE SYSTEM

Keywords : Underwater wireless sensor networks, Target detection, Target classification, Decision tree, Thermal 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.

One of the important sensor network applications is target classification in battlefields. Cheap and 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.

In this thesis we present development of the prototype of a low cost, rapidly deployable micro-sensor node to detect and classify underwater targerts.

Being a member of wireless sensor networks for tactical surveillance, our node is capable of detecting and classifying submarines, SDV (small delivery vehicles), underwater mines and divers in open, shallow and very shallow water. Our nodes are made up of a surface buoy and a micro sensor cluster, i.e., magnetic, thermal, acoustic, which can be lowered at a given depth. The magnetic, acoustic and thermal data from low cost microsensors (only a couple of dollars) are processed to classify a detected target by a micro controller collocated at the sensor cluster, and the result is transferred to the surface buoy via the cable that connects the buoy and the cluster.

Decision tree algorithm is used as a classification technique for dynamic diver, mine, submarine, small delivery vehicle detection. 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. The sensed proximity, magnetic and acoustic data are used for collaborative classification.