Classification of Automatic Radar Plotting Aid targets based on improved Fuzzy C-Means

• We proposed an improved FCM based A.I. to classify the marine radar ARPA targets.
• An improved FCM is proposed based on optimization in Euclidean space and Entropy.
• We built the radar and software platform to capture and analyzed 300 hundred targets.

Maritime ARPA, Automatic Radar Plotting Aid, systems often complicate navigation by mistaking channel structures and land objects for vessels in inland rivers and harbors. By using Fuzzy C-Means (FCM), it is possible to construct an artificial intelligence to classify and identify ARPA target types and calculate the possibility of a target being a real vessel based on the target’s speed over ground, vector over ground, and location. The membership functions of each attribute are constructed using statics, expert knowledge, and electronic chart information. The main difficulty in developing a successful FCM framework to achieve the previously stated goals is the determination of a proper method of calculating the classification number C and fuzzy coefficient m. Because the value of C for the case of ARPA targets classification is finite, the best C would be determined by assessing the Euclidean distance. The value of m is related to the discreteness of the evidence and results, which is evaluated using the Shannon entropy and the gain. A number of methods exist to properly evaluate the contributions from different forms of evidence so that the best m can be found using the tendentiousness of the evidence. In field testing, the improved FCM was able to accurately classify the ARPA targets, decrease the workload on the ship’s officer, and increase safety.