Study on roadbed disease recognition algorithm based on support vector machine

Abstract

Based on the principle of support vector machines as well as the analysis to the characteristics of roadbed diseases, a new GPR echo signal recognition algorithm is brought up. By using the proposed method to identify the ground-penetrating radar measured data, the test results show that this algorithm is better than the neural network recognition algorithm and overcomes the shortcomings of the local minimum value and over-learning. The algorithm is suitable for ground-penetrating radar signal recognition and is an efficient algorithm.