nirperformance.com

Sponsored by FOSS, NIRperformance.com is a place for near infrared (NIR) analysis experts,NIR users and feed industry professionals to come together and discover more about NIR analysis and its potential in the feed industry.

For more info, listen our promotional video and explore the web site.

Improving my beginner function (still learning)

 Is always good to look  videos in the Web, trying to find some inspiration to improve a function in R. In this case I wanted to add a Normal Distribution line in order to compare the histogram of residuals with it. Looking to the video "Plotting in R: Part II" , I adapted some part of the script to the function.

If the Residual plot is well distributed, is good, that means that our calibration is quite robust without Bias and we have a very good idea of the errors we can expect in the future for our model.

In this case I have validated the Oleic Acid with NIT spectra  (850-1150 nm), the sample is Pig Fat and the idea of this calibration is to know how the pig was feed. Calibration gives also another fatty acids parameters.

Probably is not possible to improve the calibration to get a lower SEP (Standar Error of Prediction), but this error is good for some purposes.

The function tells me with an independent set of 158 samples:

Nº Validation Samples  = 158 
RMSEP    : 0.723 
Bias     : -0.0642 
SEP      : 0.722 
Corr     : 0.942 
RSQ      : 0.888 
Slope    : 0.962 
Intercept: 2.14 
RER      : 14.9   Fair 
RPD      : 2.97   Poor 
BCL(+/-): 0.114 
***Bias adjustment in not necessary***
Residuals into 68 %   prob= 138 
Residuals into 95 %   prob= 154 
Residuals into 99.5 % prob= 158 

It tells me also the number of samples that pass the LWL (lower warning limits = -2*SEP) and UWL(upper warning limits = 2*SEP) in this case "four":

$ResWarning
           id    y    x  res
[1,] 13319319 53.7 51.9 1.78
[2,] 13318734 55.9 54.4 1.52
[3,] 13313943 54.3 52.8 1.53
[4,] 13313933 53.5 51.4 2.08

Plots given by the Function:

If  interested you can see the video: Monitor function 12-02-2013

Metrohm and FOSS enter strategic alliance

Metrohm and FOSS enter strategic alliance

Feed Plant control with NIR

Interesting visit today to a feed plant (VERAVIC) to install a NIR to analyze the vegetable ingredients for feed manufacturing and also the final product.
Thanks to them for let me see the factory that will manufacture feed for their farms. The factory is really modern and the visit allow me to know more in deep the interesting process of feed manufacturing.
To know well the process, is really helpful to see where the NIR technology can help with process instruments.
One of the places can be at the output of the "mixer" in order to analyze the main constituents for all the batches (imagine, you have all the production under control).
Another application in the mixer could be the correct control for the homogenization of the ingredients.
Controlling the moisture in the mixer is also important in order to get a final product (pellet) not too dry or too wet.
They are not easy tasks, but think about the jump in quality control.

Anyway NIR lab instrumentation is a reality from long time ago, and NIR process control of the factories is on the way to be.

Checking validation statistics (Monitor function 030220139)

Forage Analysis (Sampling)

To get a representative sample is not easy in forage analysis. It is important to get as much sample as possible and to acquire all the subsamples in the NIR in order to get a representative result, this is one of the adventages of NIR as you can read in the article : "Uses and Abuses of NIR for Feed Analysis". 

You can visit the National Forage Testing Association  or read other papers as: "Forage Analysis: Three points to consider" to see the importance to acquire a representative sample.