A Multispectral Spectroscopic Based Sensing System for Quality Parameters Measurement in Raw Milk Samples

Lactometer is used to monitor milk quality at various dairy centers but this may lead towards incorrect results because it requires human intervention and exact temperature correction as well as overall process is time-consuming. Presented work proposes the multispectral based spectroscopic approach along with the comparative study of different chemometric and artificial neural network (ANN) based techniques to measure different milk quality parameters. A multispectral spectroscopic sensing module has been designed using off the shelf components and further interfaced with 8-bit microcontroller based embedded system to produce three different spectrums of transmittance and scattering at +90 degree and –90 degree over the wavelength range of 340–1030 nm. Data acquisition process has been performed for 150 milk samples (cow, buffalo, and mix) collected from the bulk milk cooling center (BMC), Jaipur. Different statistical modeling techniques such as principle component regression (PCR), multiple linear regression (MLR) and partial least square regression (PLSR) have been implemented to develop correlation models between extracted features and target milk parameters. Implemented techniques have been compared based on the accuracy of their prediction models and it has been observed that PLSR shows better results compared to other two techniques. ANN-based modeling approach also has been explored to improve the accuracy of results. Five different artificial neural networks (ANN) based modeling techniques (LevenbergMarquardt, Bayesian regulation, scaled conjugate gradient, gradient descent and resilient) have been used to predict targeted milk quality parameters. Out of them, Gradient descent modeling technique performs better to predict fat content of the milk (R2 = 0.96198), Bayesian regulation performs better to predict lactose content (R2 = 0.90594) and others (solid non-fat (SNF), protein) are just satisfactory (R2 = 0.76077 for SNF using scaled conjugate gradient, R2 = 0.41935 for protein using Levenberg Marquardt). Produced results are validated with the MilkoScan FT1 system installed at Rajasthan Corporation of Dairy Federation (RCDF), Jaipur and it has been observed that results presented higher order of coefficient of determination as mentioned above (except protein, S.N.F.). A smartphone-based android application also has been developed to acquire data from the embedded system using Bluetooth protocol and transfer to cloud with the location information for further analysis.