Pig cough sound recognition method based on improved DS evidence theory multi-classifier fusion

The invention discloses a pig cough sound recognition method based on improved DS evidence theory multi-classifier fusion, and the method comprises the steps: collecting sound segments of live pigs in a pig house, and obtaining a corpus; based on the corpus, obtaining a training set and a test set, and extracting a plurality of acoustic features in the training set and the test set; inputting the plurality of acoustic features in the training set into a plurality of base classifiers, and outputting to obtain a plurality of base classifier performance evaluation indexes; screening the base classifiers according to the performance evaluation indexes of the base classifiers to obtain an optimized base classifier; training an optimal base classifier by using the training set to complete a target training model; and inputting the test set into the target training model, and fusing output results of the optimized base classifier by adopting an improved DS evidence theory to complete pig cough sound recognition. Acc