Method for medical waste classification based on neural network

Abstract

The invention relates to a method for medical waste classification based on a neural network. The method comprises the steps of acquiring a to-be-recognized image; inputting the image into a pre-trained neural network model, and outputting the category of the image; determining a network structure of an initial neural network model and initializing network parameters of the initial neural networkmodel; obtaining a sample set; selecting a sample from the sample set, and executing the following training steps: inputting the selected sample image into an initial neural network model to obtain aprediction category of the sample; comparing the prediction category of the sample with the category in the annotation information; determining whether the initial neural network model reaches a preset standard condition according to a comparison result; and in response to determining that the initial neural network model reaches the standard reaching condition, taking the initial neural network as a trained neural network.

Description

technical field [0001] The invention relates to a method for classifying medical waste, in particular to a neural network-based method for classifying medical waste, and belongs to the field of medical technology. Background technique [0002] The neural network-based intelligent medical waste classification algorithm mainly refers to solving the problems of medical waste identification, classification and recycling in the medical field through data mining, big data technology and artificial intelligence. Medical waste, different from regular waste in daily life, mainly refers to directly or indirectly infectious, toxic and other hazardous waste produced by medical institutions in medical treatment, prevention, health care and other related activities, specifically including infectious, pathological sexual, injurious, pharmaceutical, and chemical wastes. These wastes contain a large number of bacterial viruses, and have certain characteristics of space pollution, acute viru...

AI Technical Summary

Problems solved by technology

At the present stage, medical waste is mainly recycled and processed by the unified purchasing department, so it is necessary to pay the corresponding processing fee to the third party, which will not only increase the cost of hospital waste, but also aggravate the hospital’s neglect of waste facilities and human resources, and further will gradually fall into a vicious circle

Images