Sequence Classification Prediction Based on SVM-KNN

Deoxyribonucleic acid (DNA) is the carrier of all genetic information in organisms, and studying DNA sequence classification is to predict the classification of DNA. To solve the problem that a single machine learning algorithm is difficult to achieve effective classification, a classification model based on support vector machine (SVM) and K-nearest neighbor (KNN) fusion algorithm (SVM-KNN) is established in this study. DNA sequence files CP021707 and CP085300 were downloaded from the website of National Center for Biotechnology Information (NCBI), and feature extraction was carried out using base-based frequency feature extraction method to construct 84-dimensional feature vector. Then the classification prediction is based on KNN, SVM and SVM-KNN algorithm respectively. The experimental results show that the classification accuracy based on SVM-KNN algorithm model is effectively improved compared with that based on KNN and SVM algorithm model, so that DNA sequence classification is more effective.