Validating LOCAL Models (Petfood)

Whenever possible I use LOCAL Models because they are quite easy to maintain. These are routine samples analyzed with the reference methods and plotted versus the predicted values. The statistics performs well and were into the error limits expected when the LOCAL Model was laoded for routine. There are small  slope shifts, but these validation samples will be included in the database to improve the model and make it more robust.

User also analyzed some special pet-food samples which have much more moisture (red crosses) and we can se how the moisture performs well, but with a high bias.

Statistics for Ash (Cenizas)
Samples used for Statistics    81
Slope                                 0.962
Intercept                            0.233
Bias                                  -0.075
SEP                                   0.649
SEP(C)                               0.649
RSQ                                   0.869

Statistics for Protein (Proteína)
Samples used for Statistics    98
Slope                                 1.011
Intercept                            0.153
Bias                                   0.439
SEP                                   0.714
SEP(C)                               0.566
RSQ                                   0.991

Statistics for Fat (Grasa)
Samples used for Statistics    83
Slope                                 0.915
Intercept                            1.094
Bias                                   0.084
SEP                                   0.649
RSQ                                   0.975


Statistics for Moisture (Humedad)
Without red ones
 Samples used for Statistics    116
Slope                                 1.021
Intercept                          -0.082
Bias                                   0.074
SEP                                   0.528
SEP(C)                               0.525
RSQ                                   0.786

If you are interested in LOCAL Models you can click on the LOCAL label, to see other posts like:
Studing structure in LOCAL for validation
LOCAL: Batch Mode to select Max Number of Samples
LOCAL: Creating the RED files



 

UCD: Applications or NIR Hyperspectral Image Analysis.

There are more and more articles about NIR Hyperspectral image analysis, in the specialized NIR magazines, like "NIR News".

 

It is clear that this technique will become more and more used, so it is time for me to introduce myself in this technique. Fortunally in the last three magazines of "NIR News", there was three articles written by Aoife Gowen (School of Biosystems Engineering ,University College Dublin), with a very nice tutorial about "NIR infrared hyperspectral image analysis using R".

 

It is great to see that R is becoming more and more recognized in the NIR world, and these articles really help.

 

Visit the page of  School of Biosystems Engineering ,University College Dublin, where you can find very interesting articles about the use of NIR Hyperspectral Image Analysis.

 

Detection by Near-Infrared Spectroscopy of Large Lipid Core Plaques

American College of Cardiology Foundation | JACC: Cardiovascular Interventions | Detection by Near-Infrared Spectroscopy of Large Lipid Core Plaques at Culprit Sites in Patients With Acute ST-Segment Elevation Myocardial Infarction

See this video

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.

NIR to monitor Wheat products processing

NIR technology can be applied to Wheat product processing to monitor the characteristics of the dough mixing. Apart from the rheological properties, chemical properties can be monitored to improve the quality of the dough with the correct formation of the gluten network .

This of course can be done on line with appropriate probes.

Qualitative models could help to determine the optimum moment for the mixing.

In this link you can see applications for the wheat product processing.
Dynamic NIR Spectroscopy to Monitor Wheat Product Processing: A Short Review

Water Spectrum - "Aquaphotomics"

As a reply to an e-mail I have received from Ronald (thanks for reading this blog regularly) I write this post, hoping it will be helpful for people working with spectra of water.
Water Spectrum is as you can see in this link quite complex, that is the reason a new term appears to describe the understanding of interaction of water with light: Aquaphotomics. This name was given by Prof. Roumiana Tsenkova.
You will find insteresting this link:
http://nirslab.org/en/research/aquaphotomics-introduction.html
There are some articles in the NIRnews magazine about "Aquaphotonics", and one of them about the Aquaphotomics: wavelengths involved in the speciation of metal ions (Zn 2+ , Pb 2+ and Ag + ) in aqueous solutions.

Homemade Spectroscopy

Can you imagine, a spectrophotometer with a digital photo frame for the source, salt and pepper shakers for the sample presentation and a digital camera for the detector?.

This work:

Spectroscopy for Secondary Students: Exploring the Limits of Analysis at Home

was awarded from CAMO at the Eight Winter Symposium on Chemometric with the second place in the poster presentations.

Eight Winter Symposium on Chemometrics (WSC-8) took place in Moscow oblast, Feb 27-March 2 2012 in park hotel Drakino  with about 60 participants

CAMO awards for the best poster presentation were given to
             1st place: Alexej Skvortsov (SPb Polytechnic University)
             2d place: Chris Marks Richmond USA
             3d place: Elena Vostroknutova (Ural Electrochemical Integrated Plant)

Postcard from Antequera

Hacía tiempo que no ponía una postal en el Blog. Hoy me he animado a perderme por las calles de Antequera (Malaga) en busca de alguna postal para el blog y esta es la que más me ha gustado, porque transmite la tranquilidad de esta bonita ciudad en esta época del año.

Aprovecho el post para comentar algunas de las aplicaciones para que más se utiliza el NIR (Near Infrared Reflectance) en esta zona de Andalucia.

Por supuesto se trata aplicaciones relacionadas con su fruto más emblemático: "la aceituna". Las almazaras están a pleno rendimiento en esta campaña  y el NIR es una herramienta que predice la "humedad" y el "rendimiento graso" a la entrada del fruto (después de ser molida y de preparar una pasta) de una manera rápida y fiable. Se está trabajando también para obtener resultados aceptables para la acidez (en la pasta de aceituna), aunque se trata de un parámetro más complicado.

En el aceite se están analizando por NIT (Near Infrared Transmitance) parámetros como la acidez ( en este caso los resultados son buenos), peróxidos, Ks, humedad, ceras, eritrodiol + uvaol, acidos grasos,.....

Se esta trabajando también para obtener resultados adecuados para algunos de los parámetros importantes de la hoja de olivo (foliares).

Hablando de esta última opción hoy he leído en un artículo de un periódico local el gran potencial de propiedades para la salud (algunas de ellas anticancerígenas) de los extractos de hoja de olivo. Se trata de un estudio de la UCO (Universidad de Córdoba) publicado en la revista Mutation Research.

¿Podemos analizar la Sal por NIR?.

Una interesante respuesta a la pregunta de si la Sal, puede ser analizada por NIR,  (en el NIR Discussion Forum) merece ser reflejada en el Blog para diferentes consultas que puedan surgir sobre este tema en un futuro.

En teoría las sales no pueden ser analizadas por IR, y de hecho se utilizan como cristales para poner las muestras, dada su transparencia a la radiación IR. Así la respuesta es clara “No”.

En la última opinión al respecto, Tony Davies facilita la información de unos trabajos donde se demuestra que se puede analizar NaCl  por NIR, y nos da las razones.

El NaCl se forma por un enlace iónico y forma un anión, estos aniones forman puentes de hidrógeno con las moléculas de agua,  (otro tipo de aniones forman también estos puentes, pero con distintas distancias, por lo que se pueden distinguir). Estos puentes se reflejaran en el propio espectro del agua (en la anchura de sus bandas, desplazamientos,…).

Por tanto queda vinculado que podamos determinar la cantidad de sales en función del agua. En muestras más secas (piensos) será por tanto más complejo y no se ha facilitado bibliografía al respecto.