Determination of Fat, SNF and Protein Content in Cow Milk from the Voltage Output of ‘MilkTester’

In this work, we report estimation of fat, protein and solid not fat (SNF) of cow milk using the output voltage obtained from the ‘MilkTester’, developed by the authors at Indian Institute of Technology Kharagpur (IIT Kharagpur). The estimation is carried out in three phases named as “Training”, “Interrelation”, and “Validation”. In the “Training Phase”, output voltage from the “MilkTester” is expressed as multivariate equation of fat, SNF and protein. The data sets of fat, SNF and protein are collected using the commercial instrument, “MilkoScreen”(from FOSS, Denmark). This instrument is installed in National Dairy Research Institute Kalyani, India to measure the constituents of milk. Interrelations between “protein & SNF” and “SNF & fat” are estimated by linear regression analysis using the software, OriginPro 8.5, which return the value of the coefficients of the equations. Finally, relation between output voltage and fat is obtained. Once the value of fat percentage is known, the other two parameters can be found out by using the interrelation equations. In the ‘Validation Phase’, fat, SNF and protein are regarded as unknown components and estimated using voltage data (from the ‘MilkTester’). The error between the estimated value (from regression analysis) and true value (obtained from the “MilkoScreen’) is also evaluated for all the three parameters for randomly chosen samples. The maximum error, 12.21 %, is found for estimation of protein. But the difference of absolute value is only 0.59. Maximum error for fat estimation is 10.01 %, where absolute difference is 0.63. The SNF estimation shows error of 4.61 % with absolute error of 0.45.