Convolutional neural network optimization method for underwater target recognition

Abstract

The invention discloses a convolutional neural network optimization method for underwater target recognition, and belongings to the technical field of underwater target recognition. The original sounddata is converted into gray-scale sound spectrum images through short-time Fourier transform and the like, and then the single-layer SAE discriminant classification method and the multi-layer SAE reconstruction classification method are added to the Alexnet model respectively. The gray-scale sound spectrum images are tagged and trained, 70% of the gray-scale sound spectrum images are used as thetraining set and the remaining 30% are used as the test set. The training set and the test set are applied to the Alexnet model before improvement and the improved Alexnet model for the contrast experiment of accuracy and training time and the test results are analyzed. The target classification layer in the convolutional neural network is optimized, the problem that the classification accuracy ofthe current convolutional neural network in the field of underwater target recognition field is low can be solved, the method is more suitable for the field of underwater target recognition than thatbefore improvement and thus the better classification effect in the underwater target field can be obtained.

Description

technical field [0001] The invention belongs to the technical field of underwater target recognition, and in particular relates to a convolutional neural network optimization method for underwater target recognition that solves the problem of low classification accuracy of the current convolutional neural network in the field of underwater target recognition. Background technique [0002] At present, countries are paying more and more attention to the economic and military status of the ocean, and are vigorously conducting related research. Our country is still in a relatively backward stage. Therefore, with the advancement of my country's military automation construction, the research on underwater target recognition needs to be solved urgently. [0003] In underwater target recognition, target classification is the key to the whole process of underwater target recognition. In the original underwater target recognition, the type of the target is mainly determined based on...

AI Technical Summary

Problems solved by technology

Since the data collected in the underwater field has more abstract and complex feature representations than traditional image data, the convolutional neural network related models applied to the traditional image field have certain limitations.

Images