Method for classifying single elements in sequence based on bidirectional gating recurrent neural network

Abstract

The invention discloses a method for classifying single elements in a sequence based on a bidirectional gating recurrent neural network. The method comprises the steps of 1) performing manual classification on acquired time sequence signals or data; 2) converting an input data set and a label set to be in a matrix form; 3) randomly dividing the input data set and the corresponding label set into atraining set and a test set, wherein the training set data accounts for 70% of total samples, and the test set data accounts for 30% of the total samples; 4) building a bidirectional gating recurrentneural network model; 5) training the built bidirectional gating recurrent neural network model; 6) performing over-fitting judgment; and 7) classifying the single elements in the sequence by using the trained bidirectional gating recurrent neural network model, and obtaining a final judgment result from an output layer by using an Argmax function, so that correct classification of the single elements in the sequence is achieved. The method disclosed by the invention has the advantages that the recognition accuracy of the sequence data is more than 99%.

Description

Technical field [0001] The invention belongs to the technical field of signal control, and relates to a single element classification method in a sequence based on a bidirectional gated recurrent neural network. Background technique [0002] The classification of a single element in the sequence of waveforms or data with time series characteristics is widely used in practical engineering, such as monitoring the operating status of the power grid, monitoring equipment operating parameters, identifying the types of power quality disturbances, and identifying vibration signals , The recognition of ECG signals, the recognition of audio signals, the attribute judgment of seismic wave patterns, etc. [0003] The current solution to the classification of time series signals is usually to monitor the data within a period of time before determining the corresponding category of the data. It is difficult to classify the time series signals or single element information in the data, so real-t...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a single element classification method in a sequence based on a bidirectional gated cyclic neural network, which solves the problem in the prior art that cannot efficiently and accurately classify and identify a single element in sequence data

Images