基于改进模糊神经网络的细胞活性预测  

Cell Viability Prediction Based on Improved Fuzzy Neural Network

作　　者：李向广 孙金金 吴云昭 陈世闯 LI Xiangguang;SUN Jinjin;WU Yunzhao;CHEN Shichuang(Analytical Instruments Division,Autobio Labtec Instruments Co.,Ltd.,Zhengzhou,Henan 450000,China)

机构地区：[1]安图实验仪器(郑州)有限公司分析仪器事业部,河南郑州450000

出　　处：《自动化应用》2024年第17期20-23,共4页Automation Application

摘　　要：针对细胞活性的预测问题,提出了一种利用自适应差分进化算法优化的模糊神经网络(ADE-FNN)预测模型。首先,通过模糊化处理细胞培养过程中的多种影响因素(如培养基成分、温度、pH值等),将这些因素作为模糊神经网络的输入。然后,利用已有的细胞活性数据对模型进行训练,优化网络参数。经过多次迭代和调整,模型逐渐学习到输入与输出之间的复杂映射关系。最后,利用细胞活性仿真实验验证所提ADE-FNN算法的性能。结果表明,基于模糊神经网络的细胞活性预测模型具有较高的预测精度和泛化能力。与传统的统计方法相比,该模型能够更好地处理数据中的不确定性和噪声,从而提供更准确的预测结果。此外,该模型还具有较好的可解释性,有助于深入理解细胞活性的影响因素及其作用机制。Aiming at the prediction of cell viability,a fuzzy neural network based on adaptive differential evolution(ADEFNN)prediction model is proposed,which is optimized by adaptive differential evolution algorithm.Firstly,a variety of influencing factors in the process of cell culture,such as medium composition,temperature,pH value and so on,are fuzzified,and these factors are used as the input of fuzzy neural network.Then,the existing cell activity data are used to train the model and optimize the network parameters.After many iterations and adjustments,the model gradually learned the complex mapping relationship between input and output.Finally,the performance of the proposed ADE-FNN algorithm is verified by cell viability simulation experiments.The results show that the cell activity prediction model based on fuzzy neural network has high prediction accuracy and generalization ability.Compared with the traditional statistical methods,this model can better deal with the uncertainty and noise in the data,so as to provide more accurate prediction results.In addition,the model also has good interpretability,which is helpful to understand the influencing factors of cell activity and its mechanism.

关 键 词：模糊神经网络 差分进化 新颖变异策略 自适应变异因子 细胞活性预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]