The Research On The Mine Target Recognition Based On The Support Vector Machines

Support Vector Machine (SVM) algorithm is a kind of pattern classification algorithm which bases on the theory of Statistical Learning Theory (SLT). Because of its features of better computational efficiency, robustness and statistical stability, SVM gets rapid development in these recent years. It's widely used in many fields which belong to the application of pattern classification.This paper describes the algorithm of SVMs based on the status of mine target recognition and gives the specific SVMs algorithm and training process especially for mine target echo database. We improved the SVMs algorithm in two aspects: training speed and predicting acuity applied them in mine target recognition analysis and got delighted results. All of the experiments results and discussing of relative problems are in the end of the paper. There are also some problems that we don't resolve and the work that we will do next in the last part. Since mine target echo data can be analyzed in general statistical analysis process despite of its own features. This paper simply introduced the methods of the feature extraction of mine target and different SVM methods of kernel function. And it also introduced several feasible SVMs software processes for mine target recognition, including the transformation of the database format, the transformation of the database matrix, and the selection of the model's parameters.Through the experiments, comparing with other kernel functions, RBF SVM and higher degree polynomial function SVM are better in mine target recognition than other kernel functions. Our SVM process is very easy to use and we gave some programs to help researcher carry it. We compared it with some generally used SVM algorithm based on the same dataset. And the results showed that the two algorithms have the same predicting acuity and training speed in training.All in all, as a new tool treating mine target recognition, SVMs bases on good theory and has a wonderful perspective. SVMs itself and its improved algorithm will show advantages in much wider mine researching field.