基于近红外光谱技术结合改进的CS-BPNN樱桃番茄SSC和Vc含量检测

Soluble Solids Content and Vitamin C Detection in Cherry Tomatoes Based on Near Infrared Spectroscopy Combined with Improved CS-BPNN

为实现精确预测樱桃番茄中SSC和Vc含量,该研究提出一种改进杜鹃鸟搜索算法优化的BP神经网络(Back Propagation Neural Network Optimized by Improved Cuckoo Search Algorithm,ICS-BPNN)模型。采集样品在1350~1800 nm的近红外光谱数据,首先采用不同方法进行预处理;然后利用稳定性竞争性自适应重加权算法(Stability Competitive Adaptive Reweighting Algorithm,SCARS)、遗传算法(Genetic Algorithm,GA)和自动有序预测因子选择算法(Automatic Ordinal Predictor Selection Algorithm,Auto OPS)3种方法进行特征波长提取;最后结合机器学习方法建立了BP神经网络(Back Propagation Neural Network,BPNN)和基于杜鹃鸟搜索的BP神经网络模型(Back Propagation Neural Network Optimized by Cuckoo Search Algorithm,CS-BPNN)。为进一步提高模型精度与收敛性,引入自适应算法对杜鹃鸟蛋被淘汰的概率进行改进并对越界鸟窝进行新处理-基于改进杜鹃鸟搜索算法优化的BP神经网络。结果表明:优化后模型效果最好,SSC含量使用该模型决定系数R_(c)^(2)和R_(p)^(2)是0.83和0.85,RMSEC和RMSEP为0.85和0.79;Vc含量使用此模型R_(c)^(2)和R_(p)^(2)为0.91和0.91,RMSEC和RMSEP分别是0.48和0.45。因此,采用近红外光谱技术与改进的机器学习方法结合可实现对樱桃番茄内部品质的快速无损预测分析。

To accurately predict soluble solids and vitamin C content in cherry tomatoes,a backpropagation neural network model optimized using the improved cuckoo search algorithm(ICS-BPNN)is proposed.The near-infrared spectra of the samples at 1350~1800 nm were collected and pre-processed using different methods.The stability competitive adaptive reweighted sampling(SCARS),genetic(GA),and automatic ordinal predictor selection(Auto OPS)algorithms were then employed to extract the characteristic wavelength.BPNN and CS-BPNN models were established using machine learning methods.To further enhance accuracy and convergence of the models,an adaptive algorithm was introduced to improve the probability of cuckoo egg elimination,and the cross-border nests were newly processed via ICS-BPNN.The optimized models demonstrated ideal results.The results showed that the coefficients of determination,R_(c)^(2) and R_(p)^(2) of the soluble solid content were 0.83 and 0.85,respectively;the root mean square error of calibration(RMSEC)and prediction(RMSEP)sets were 0.85 and 0.79,respectively.The vitamin C content obtained using the optimized model had R_(c)^(2) and R_(p)^(2) of 0.91 and 0.91,respectively.The RMSEC and RMSEP values were 0.48 and 0.45,respectively.Thus,a combination of near-infrared spectroscopy and improved machine learning methods can achieve the rapid and non-destructive predictive analysis of the internal quality of cherry tomatoes.