[Objective]To rapidly predict and explore the relationship between yeast cell activity and impedance using neural networks.[Methods]The impedance values of dead yeast cells were obtained by testing yeast cells with different concentrations using impedance technology.A prediction model based on BP neural networks optimized by grey wolf algorithm was employed to explore the relationship between yeast cell activity and impedance at different frequencies.[Results]There existed a complex non-linear relationship between yeast cell activity and impedance,where the impedance of yeast cell suspension increased with the increase of yeast cell concentration at certain frequencies.It was observed that the impedance of active cells was higher than that of dead cells at relative frequencies.The error of the BP neural network prediction model optimized by the grey wolf algorithm was significantly smaller than that of the BP neural network,and the fitted values were closer to the actual values.[Conclusions]The methods proposed in this study effectively address the non-linear relationship between impedance and yeast cell activity,providing valuable insights for the application of impedance technology in the field of cell detection.
关键词
酵母菌/细胞检测/电化学阻抗谱/BP神经网络/灰狼优化算法
Key words
yeast/cell detection/electrochemical impedance spectroscopy/BP neural network/grey wolf optimization algorithm
维普
万方数据