Motion Pattern Classification on Online/Active Data-Machine Learning

Abstract

Abstract: Ship behaviour recognition and prediction is very important for the early warning of risky behaviour, identifying potential ship collision, improving maritime traffic efficiency etc., and thus is a very active topic in the intelligent maritime navigation community. The high flow of vessel traffic affects the difficulty of monitoring vessel in the middle of the sea because of limited human visibility, occurrence of vessel accidents at the sea and other illegal activities that illustrate abnormal vessel behaviour such as oil bunkering, piracy, illegal fishing and other crimes that will continue and will certainly have an impact on losses in several aspects. An existing system involves, Automatic Identification System (AIS) for short-range operation, Long-Range Identification and Tracking (LRIT), Vessel Monitoring System (VMS) are widely used automatic reporting systems for the ship/vessels. Further few classification algorithms like Bayesian, CNN and many other methods which does not permit to draw definite conclusions about the overall effectiveness of the identification procedure because of noise level. Automatic identification system (AIS) trajectory will collect data from multiple sensors that record dynamic and static ship information. AIS sequences (and records) are affected by subjective ship-officer behavior such as collision-avoidance decisionmaking and good seamanship