文章针对蛋白质二级结构预测这一复杂非线性模式分类问题,提出了基于径向基函数的预测方法。在分析了基于神经网络预测方法的基础上,讨论了蛋白质二级结构预测算法研究中的数据选取、网络结构与参数对网络性能的影响,实验结果表明这一方法的可行性和有效性。
Aiming at solving the complicated non-linear pattern classification problem of protein secondary structure prediction,a new method based on radial basis function is proposed.The paper discusses the influence of data selection, structure design and parameter modification on the performance of the networks by analyzing the prediction methods based on neural networks.The results indicate that this method is feasible and effective.