基于SVM的ACC优化算法在入侵检测中的研究

Research on ACC Optimization Algorithm Based on SVM in Intrusion Detection

针对ACC（蚁群聚类）算法在入侵检测系统数据训练时间较长, 参数选择不佳的情况, 本文提出了将SVM（支持向量机）与蚁群聚类相结合的优化算法.该算法对其中的特定对像聚类, 对关键参数进行选择, 减少了学习训练的时间, 加快了学习训练速度.实验结果表明, 该算法大幅提高了入侵检测的精准率, 降低了入侵检测的误报率和漏报率, 大大提升了入侵检测的性能.

Aiming at ACC （ant colony clustering） algorithm in the intrusion detection system with long training time and poor selection of parameters, this paper proposes a combination of SVM （support vector machine） and ant colony clustering optimization algorithm. The algorithm selects the specific pairs of images and selects the key parameters, reducing the time of learning and training, and speeding up the speed of learning and training. The experimental results show that the algorithm greatly improves the accuracy of intrusion detection, reduces the false alarm rate and false alarm rate of intrusion detection, and greatly improves the performance of intrusion detection.