Pilot working state recognition model establishing method

Abstract

The invention provides a pilot working state recognition model establishing method. The method comprises the following steps of: S1, preprocessing flight data; S2, extracting features of the preprocessed flight data; S3, carrying out data dimensionality reduction on the extracted features by utilizing a Trelets algorithm; and S4, carrying out training and modeling on the dimensionality reduced data by utilizing a Gaussian process classifier optimized on the basis of cuckoo algorithm. The method has favorable time domain localization ability and is immune to noise interference so that the feature values are more cautious. According to the method, original data is reduced to lower dimensionality, so that the complexity of the dimensionality reduced data is reduced and basis is laid for further more correct classification; the parameter optimization is relatively easy and easier to converge; and global or approximate global optimization results are searched for functions as far as possible, so that the local optimization of models is avoided.

Description

technical field [0001] The invention relates to the technical field of pilot fatigue detection and supervision and early warning, in particular to a modeling method for identifying a pilot's working state. The method obtains a model that can evaluate the pilot's workload state by using algorithms such as machine learning according to flight parameters when the aircraft is working. Background technique [0002] For the pilot state detection model in traditional aviation missions, the process is similar to the classic pattern recognition process, which is mainly divided into: data preprocessing, feature extraction, data dimensionality reduction processing, and machine learning algorithm classification processing. [0003] In terms of feature extraction technology, the time-domain signal feature mean, variance and root mean square are often used to characterize the amplitude characteristics of the signal and the difference of the original flight parameters. However, these time-...

AI Technical Summary

Problems solved by technology

The Si process can be obtained by minimizing the negative logarithmic marginal probability with respect to the hyperparameters. Generally, the hyperparameters are determined by the gradient descent method and the Newton method. However, as the number of dimensions of the initial variable increases, the algorithm tends to fall into a local extremum. , the selection of the initial value has a great influence on the algorithm

Images