Cold water coral distribution prediction method and system based on sample selection expansion

Abstract

The invention relates to a cold water coral distribution prediction method and system based on sample selection expansion. According to the method, firstly, a training set is generated by adopting a random uniform sampling method, and the problem that ocean coral distribution prediction lacks negative samples is solved; secondly, a radial basis function neural network prediction model is trained through the training set, and unlabeled samples are marked by using the trained model; meanwhile, the steps are cycled for multiple times, and accidental factors of single prediction are eliminated. The concept of priori knowledge is introduced into the method, and the label-free prediction results of the previous cycle are grouped; and then, according to the principle that the higher the probability of the positive sample is, the higher the confidence is, different groups are put into the reconstructed virtual label-free sample set according to different proportions, and the next cycle is entered. Finally, unlabeled samples are classified according to the average positive sample probability to realize prediction of cold water coral distribution.

Description

technical field [0001] The invention relates to a cold-water coral distribution prediction method and system based on sample selection and expansion. Background technique [0002] Cold-water corals are widespread throughout the world, covering most areas of the ocean. Cold-water corals have been found in the adjacent seas of 41 countries around the world, but the survival of cold-water corals is facing unprecedented threats from humans. Human activities that threaten cold-water corals include deep-sea trawling, laying submarine cables, dumping garbage, and industrial pollution. [0003] It is urgent to strengthen the management and protection of cold-water corals, and effective species distribution information is the premise of management and protection. However, the acquisition cost of deep-sea observation data is high, and it is difficult to obtain complete global distribution information of cold-water corals through large-scale deep-sea observation. Therefore, the pred...

AI Technical Summary

Problems solved by technology

Instead, only the locations where cold-water corals are found in actual deep-sea observations can be classified as positive samples for cold-water deletion.

The difference between the prediction of the distribution of cold-water corals and the traditional prediction is that the prediction of cold-water corals has the characteristics of difficulty in obtaining negative samples

Images