A Novel System for Seafloor Classification Using Artificial Neural Network (ANN) Hybrid Layout with the Use of Unprocessed Multi-Beam Backscatter Data.

A system for on-line (i.e. real-time) seafloor classification uses multi-beam acoustic device mounted beneath a ship's hull  attached to an r.m.s. estimator module through a beam former module.The multi-beam backscatter r.m.s. data comprises a back

The novel system for seafloor classification uses artificial neural network (ANN) hybrid layout with the use of unprocessed multi-beam backscatter data. Its a real-time seafloor roughness classifier using backscatter data after training the self-organized mapping (SOM) network and learning vector quantization (LVQ) network wherein, the system has the unique capability for the combined use of unsupervised SOM followed by supervised LVQ to achieve a highly improved performance in the roughness classification.

• Combined use of the two variants of the learning vector quantization (LVQ) network to achieve the best classification of the   seafloor characteristics, which is a capability that is hitherto non-existent
• Self-organization of multi-beam input data vectors into coarse clusters in the output space without any a priori information
• Raw dataset can be used as input vectors to the classification network             
• Reduces computational time overhead