Physiological signal fusion identity recognition method based on improved canonical correlation analysis

Abstract

The invention discloses a physiological signal fusion identity recognition method based on improved canonical correlation analysis, which mainly solves the problem of low recognition rate of the existing method. Its implementation steps: 1) Obtain pulse wave and respiration signal and preprocess its training data; 2) Intercept training data waveform, obtain pulse wave training set and respiration training set; 3) Find the intra-class, Inter-class neighborhood; 4) According to the intra-class and inter-class neighborhood, calculate the intra-class and inter-class correlation matrices of the above two sets and construct the regularized canonical correlation analysis objective function; 5) Solve the pulse rate based on regularized canonical correlation analysis 6) Use the transformation matrix to obtain the training fusion feature vector; 7) Obtain the pulse wave and respiratory signal test data to obtain the test fusion vector; 8) Discriminate the category of the test fusion vector to obtain the identification result. The invention improves the identity recognition rate and can be applied to e-commerce and telemedicine identity authentication.

Description

technical field [0001] The invention belongs to the technical field of identification, and in particular relates to an identification method, which can be used in the fields of e-commerce, remote medical identification and the like. Background technique [0002] With the development and application of computer technology and wireless network, Internet-based e-commerce, telemedicine and other applications have developed rapidly, and have become an indispensable part of modern people's life. Because these applications involve personal property accounts, personal physiological information and other important private information, it is particularly important to ensure the safe use of these applications. Compared with single-modal biometric systems, the security of multi-modal biometric systems relies on multiple biometric features, which are difficult to be stolen or copied at the same time, so they have higher security and reliability. The canonical correlation analysis algori...

AI Technical Summary

Problems solved by technology

Finally, the effectiveness of the method is verified by carrying out experimental simulations on multiple databases. However, because the method does not take into account the influence of noise on signal feature extraction, it cannot fully obtain effective feature information, and its identification rate has room for further improvement.

Images