Forest fire identification method based on multi-view robust bilateral twin vector machine

Abstract

The invention discloses a forest fire identification method based on a multi-view robust bilateral twin support vector machine. The method comprises the following steps: developing a new optimizationmodel: adopting a robust multi-view learning algorithm of a bilateral twin support vector machine: applying an MvRDTSVM to forest fire identification, and performing an experiment on a forest fire data comparing four single-view and multi-view methods by utilizing real image data, and testing robustness and generalization performance of the forest fire database; expressing the MvGSVM as an SVM type problem again, meanwhile, introducing bilateral constraints, taking an L1 norm as a distance measurement mode in a target function, and improving the robustness of the model. Because the targetfunction is non-convex and non-smooth, the invention designs a new effective iterative algorithm and theoretically proves the convergence of the algorithm, and because a series of QPP problems need to be solved in the iterative process, the calculation cost is increased, and the rapid version of the MvRDTSVM, namely the MvFRDTSVM, is further developed. By solving a series of linear equations rather than the QPP problems, the calculation speed is greatly increased, and the calculation cost is saved.

Description

technical field [0001] The invention relates to the field of algorithm improvement, in particular to a forest fire recognition method based on a multi-view robust bilateral twin vector machine. Background technique [0002] Support vector machines (SVM) have made outstanding contributions to pattern recognition and data mining in the past few decades. It has been used in a wide range of applications such as text classification, facial recognition and bioinformatics. Although it has obvious advantages in classification tasks, conventional SVM still requires high computational complexity and cannot solve the "exclusive or" (XOR) problem. In this regard, Mangasarian and Wild proposed a simple and effective classifier, It is called generalized eigenvalue proximal SVM (GEPSVM). The purpose of GEPSVM is to find two non-parallel hyperplanes. By solving a pair of generalized eigenvalue problems, GEPSVM can achieve faster calculation speed and can classify complex data sets better ...

AI Technical Summary

Problems solved by technology

However, MvGSVM is a multi-view extension of GEPSVM, which is not compatible with standard SVM and cannot guarantee to minimize structural risk

Furthermore, due to the use of the squared L2-norm distance metric, models in MvGSVM may be susceptible to outliers or noise present in real datasets, and deviations from hyperplane normal vectors can affect classification results

Images