Scanning signal feature extraction method based on independent component analysis and recognition method

Abstract

The invention discloses a scanning signal feature extraction method based on independent component analysis. The method comprises the steps that six-lead scanning eye electric signals are collected and subjected to band-pass filtering treatment, an airspace filter set corresponding to different scanning task backgrounds is built through an ICA method for filtered data, linear protection is carried out, and airspace feature parameters of scanning signals are obtained. The invention further discloses a recognition method of the scanning signal feature extraction method based on independent component analysis. An ICA airspace filter set is built for each experiment sample in an eye movement database, feature parameters are extracted, cross validation is carried out through a support vector machine, and the optimal ICA filter set and SVM model parameters are determined; the optimal ICA airspace filter set is used for filtering, and then the result is fed into an SVM classifier to be recognized. The scanning signal feature extraction method based on independent component analysis and the recognition method have the advantages of being higher in recognition accuracy rate, higher in expansibility, good in application prospect and the like.

Description

technical field [0001] The invention relates to a scanning signal feature extraction method and recognition method based on independent component analysis. Background technique [0002] The eye movement patterns triggered by people performing specific activities can reveal their behavioral status to a large extent, such as: reading, writing, resting, etc., and this eye movement pattern can be obtained by tracking eye movements, so The design and implementation of Human Activity Recognition (HAR) algorithm based on eye movement information has become a new research hotspot. [0003] At this stage, the use of video to record eye movement signals has been widely used, but the video-based eye-tracking system, especially the wearable eye-tracking system, is expensive, bulky and heavy, and at the same time, the system power consumption and The real-time analysis of the results is also not satisfactory. Electro-oculogram (Electro-oculogram, EOG) is a low-cost eye movement signal ...

AI Technical Summary

Problems solved by technology

Although the above-mentioned detection methods have achieved some success, they mainly focus on the analysis of eye movement signals of a single lead. The analysis process only considers the changes of the single-lead signal and ignores the correlation information between the leads. Guarantee the correct rate of recognition of saccade signals; in addition, when the types of eye movement signals increase, the above methods are difficult to effectively identify, or even unrecognizable

Images