Multi-core SVM training and alarm method, device and system for intrusion signal recognition

Abstract

The invention provides a multi-core SVM training and alarming method, device and system for intrusion signal recognition, and relates to the technical field of intelligent security and protection, andthe method comprises the steps: obtaining an intrusion signal data set, and carrying out the normalization processing; selecting a plurality of basic kernel functions, determining the similarity between kernel matrixes corresponding to the plurality of basic kernel functions according to the plurality of basic kernel functions and the intrusion signal data set, and determining the kernel weight of each basic kernel function according to the similarity; determining a multi-kernel function according to the kernel weight; and determining a sample membership degree according to a fuzzy rough setmethod, performing multi-kernel SVM training and optimization according to the sample membership degree and the multi-kernel function, determining an optimized kernel weight and a Lagrange multiplierof an optimal solution, and completing training of the multi-kernel SVM. According to the method, the kernel weight is determined through alignment to construct the multi-kernel function, and multi-kernel SVM training and optimization are carried out in combination with calculation of the sample membership degree, so that the classification interval reaches the maximum, and recognition of different types of intrusion signals is more accurate.

Description

technical field [0001] The invention relates to the field of intelligent security technology, in particular to a multi-core SVM training and alarm method, device and system for intrusion signal identification. Background technique [0002] With the continuous development of economy and science and technology, the places requiring high-quality security work are also increasing. In order to better protect the safety of the country and personal property, it is necessary to make the security system cover as comprehensively as possible and the alarm is accurate. In recent years, a series of high-tech technologies such as the Internet of Things and cloud processing have developed rapidly, enabling information resources to be shared online. At the same time, in order to meet the security requirements of places with large areas and many places, such as various large shopping malls and financial centers, the security alarm system must have remote monitoring and control, alarm inform...

AI Technical Summary

Problems solved by technology

However, since the pulse echo signal received by the system is a non-stationary signal, and the noise interference of various factors is large, it increases the difficulty of identifying the characteristic information of the intrusion signal and reduces the accuracy of the alarm.

Images