An approach to seafloor classification with GA-based neural network
Chen, Yongqi ... [et al.]
The Learning Vector Quantization (LVQ) Neural Network approach has been widely used in acoustic seafloor classification. However, one of its major weak points is the sensitivity to the initialization, affecting the seafloor classification accuracy. In this paper, Genetic Algorithm (GA) is used to optimize the initial values of LVQ. The GA-based LVQ can rapidly provide the optimum initial reference vectors and accurately identify various types of seafloor sediments. The proposed approach was applied to seafloor classification using Multibeam Echo Sounder (MBES) backscatter strength data in Jiaozhou Bay near Qingdao City of China. Compared with the standard LVQ, the experiment results indicate that the approach of GA-based LVQ can improve the seafloor classification speed and accuracy.
Event: XXIII International FIG Congress : Shaping the change
Only personal, non-commercial use of this document is allowed.