Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #25-30, 2017

Leider ist der Eintrag nur auf English verfügbar.

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #21-24, 2017

Leider ist der Eintrag nur auf English verfügbar.

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #17-18, 2017


Conferentia Chemometrica 2017, 3–6 September 2017, Gyöngyös, Farkasmály, Hungary. | chemometrics LINK

“Chaos theory in chemistry and chemometrics: a review” LINK

Predicting herbivore faecal nitrogen using a multispecies near-infrared reflectance spectroscopy calibration. LINK

Calibration transfer of flour NIR spectra between benchtop & portable instruments | directstandardization spectro LINK

Near Infrared

Fast Detection of Paprika Adulteration Using FT-NIR Spectroscopy LINK

How to analyze food and future requirements for NIR spectroscopy LINK


“On-Site Analysis of Cannabis Potency Using Infrared Spectroscopy” LINK


5th International Taiwan Symposium on Raman Spectroscopy (TISRS 2017) 27–30 June 2017, Chiayi, Taiwan. LINK


Corning and PrecisionHawk and partnership enables hyperspectral imaging on drones LINK

Employing NIR-SWIR hyperspectral imaging to predict the smokiness of scotch whisky LINK

Defect detection of green coffee by NIR-hyperspectral imaging and multivariate pattern recognition LINK


Getting ready for the LinkSquare SDK kickstarter with some beauty shots of our handheld spectrometer! LINK!

“Learning about Spectroscopy with Ocean Optics” LINK


Analysis of multiple soybean phytonutrients by near-infrared reflectance spectroscopy LINK


A great demonstration of why we need to plot the data and never trust statistics tables! LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #16, 2017

Get the Chemometrics and Spectroscopy News in real time on Twitter @ CalibModel and follow us.


UV/Vis spectroscopy combined with chemometrics for monitoring solid-state fermentation with … LINK

What is MODEL SELECTION? What does MODEL SELECTION mean? MODEL SELECTION meaning & explanation: LINK

Model selection with multiple regression on distance matrices leads to incorrect inferences LINK


Tiny spectrometer turns smartphone into molecular analyst LINK

High-grade, compact spectrometers for Earth observation from SmallSats LINK


Miniature and Micro Spectrometers End-Users Needs, Market & Trends 2015-2021 – Research and Markets – Yahoo Finance LINK


Prediction of milk fatty acid content with mid-infrared spectroscopy in Canadian dairy cattle using differently… LINK!


Smallest seismic sensor uses vibration spectral analysis LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #5+6, 2017


Non-Destructive Sensor-Based Prediction of Maturity and Optimum Harvest Date of Sweet Cherry Fruit | sensors LINK

IDC unveils its Top 10 Predictions for global Robotics Industry Industry40 Robotics LINK


Global Molecular Spectroscopy Market is expected to reach USD 6.712 billion till 2024. htt… LINK!

Near Infrared

Assessing pre-harvest sprouting in cereals using near-infrared spectroscopy-based metabolomics LINK

Rapid screening of commercial extra virgin olive oil products for authenticity: Performance of a handheld NIR device LINK


Imec () launches TDI, multispectral and hyperspectral sensors | imaging HSI LINK

Near-infrared hyperspectral imaging of lamination and finishing processes in textile technology LINK

Spectral Imaging

Viavi Solutions and ESPROS Photonics Corporation Debut New Miniaturized Spectral Sensor and Multispectral Sensor LINK


Meta-lenses bring benchtop performance to small, hand-held spectrometer – Science Daily LINK

Scan anywhere with Neospectra Spectrometer Case powered by XPNDBLS PhotonicsWest … LINK!


World feed production exceeds 1 billion MT LINK

Chemometric soil analysis on the determination of specific bands for the detection of magnesium & potassium by … LINK


This app uses spectral analysis to analyze objects and their makeup HawkSpex LINK

Research details developments in the multivariate analysis software industry | MVA LINK

“The worlds first ever spectroscopy enabled iPhone!” Check out our video to see it in action: LINK

Investments in AI will triple in 2017. ($47 billion by 2020 per ) CIO CMO | LINK

Some aspects of fetal development have long puzzled scientists, but new molecular technologies are shining a light: https:/… LINK!


Spectroscopy and Chemometrics News Weekly 3+4, 2017 | Spectroscopy NIRS MVDA… LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich 3+4, 2017 | NIRS Spektroskopie Chemometrie Multivariate LINK

Spettroscopia e Chemiometria Weekly News 3+4, 2017 | NIRS Spettroscopia Chemiometria news LINK

WHITE PAPER: A novel knowledge-based Chemometric Software Framework for quantitative NIRS Calibration Modeling LINK

Improve Accuracy of fast non-destructive NIR Measurements by Optimal Calibration | spectroscopy sensor modeling LINK

NIRS as a secondary method requires extensive calibration on an ongoing basis | foodindustry Digitalization IoT LINK

Services for Optimization of Chemometric Application Methods of Near-Infrared Spectroscopy | Quality Control NIRS LINK

► Timesaving NIRS Calibration ► near-infrared spectroscopy | protein fat moisture sensor measurement scanning LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #3+4, 2017


Fast sampling, analyses and chemometrics for plantbreeding: Bitter acids, xanthohumol and terpenes in lupulin … LINK

Near Infrared

Measurement of Soy Contents in Ground Beef Using Near-Infrared Spectroscopy LINK

Near infrared spectroscopy for body fat sensing in neonates: quantitative analysis by GAMOS simulations | Bodyfat LINK

Fatty acids and fat-soluble vitamins in ewe’s milk predicted by near infrared reflectance spectroscopy. | NIRS LINK

NeoSpectra Micro, a small, chip-scale, near infra-red (NIR) spectral sensor – LINK


Drones on the Farm: Agribotix Partners with senseFly, and Sentera Announces Real-Time NDVI Streaming LINK

Early Detection of Aspergillus parasiticus Infection in Maize Kernels Using NIR Hyperspectral Imaging and MDA LINK

Nondestructive Estimation of Moisture Content, pH and Soluble Solid Contents in Intact Tomatoes Using HSI LINK


Spectrometers: Excitation source parameters dictate Raman spectroscopy outcomes LINK


Is molecular scanning the next killer smartphone app? killerapp futuretrends sensorik sensor LINK


It took 50 years for the world to install the first million industrial robots. The next million will take only eight … LINK!

“How Statistics lost their power – and why we should fear what comes next” | BigDataAnalytics bigdata LINK

Spectroscopy and Chemometrics News Weekly #47, 2015

Near Infrared

NIR-Sensor ermittelt Trockensubstanz während der Mischwagenbefüllung | Futterkomponente LINK

Ultra-low maintenance FTNIR analyzer for the refining & petrochemical industries | pauto LINK


Seeing Through Crude Oil for Efficient Oil Separations using Short-Wave Infrared (SWIR) Cameras – AZoSensors LINK


RoboBees Can Fly and Swim. What’s Next? Laser Vision – Smithsonian UAS UAV LINK


Scientists create an all-organic UV on-chip spectrometer – The U.S. Department of Energy’s Ames LINK


… detection of contaminants in agro-food products, … melamine levels in milk using vibrational spectroscopy LINK


Examining Pigmented Human Tissue using SWIR Raman Spectroscopy – AZoSensors LINK


SCiO Molecular Scanner UNBOXING – Video LINK


Dear NIR-Spectrometer vendors, this is about how you can improve customer web-traffic | NIRS Spectrometer LINK

Efficient development of new quantitative prediction equations for multivariate NIR spectra | spectra LINK

How to Develop Chemometric Near-Infrared Spectroscopy Calibrations in the 21st Century? | NIR LINK

How to Develop Near-Infrared Spectroscopy Application Today? | pharma lab analysis chemist TechTrends LINK

Improve chemical analysis accuracy by optimized chemometric models for Near-Infra-Red (NIR) Spectroscopy LINK

Improving Accuracy, Precision and Robustness of NIR-analysis LINK

NewsLetter: Spectroscopy and Chemometrics News Weekly 46, 2015 | Molecular Spectroscopy NIRS Chemometrics Raman LINK

Pro Tip: The NIR calibration is the central key to accurate NIR measurement LINK

Services for professional Development of Near-Infrared Spectroscopy Calibration Methods | NIR Quality Testing LINK

Arbeitsweisen zur NIR Kalibrierung – Erstellung von NIRS-Spektroskopie Kalibrierungskurven

Kennen Sie den Effekt, dass Sie bevorzugt ihre Lieblings-Datenvorbehandlungen in Kombination durchprobieren und oft die gleichen Wellenlängen-Selektionen anhand der visualisierten Spektren ausprobieren?

Man probiert z.B. sechs bis zehn Kombinationen aus, bis man davon sein favorisiertes Kalibrationsmodell auswählt, um es dann weiter zu optimieren. Da fallen dann plötzlich Ausreisser (Outlier) auf, weil man in die Tiefe geht, also mit den Daten vertraut ist, man kennt mittlerweile die Spektren-Nummern der Ausreisser und ist mit den Extremwerten vertraut.

Jetzt fokussiert man sich auf die Hauptkomponenten (Principal Components, Latent Variables, Faktoren) und achtet darauf nicht zu über-fitten und nicht zu unter-fitten. Das ganze dauert ein paar Stunden und schliesslich begnügt man sich mit dem gefundenen Modell.

Was wäre nun, wenn man in all den zu Beginn ausprobierten Varianten, die gefundenen Ausreisser entfernt und nochmals berechnet und vergleicht? Wären die Ergebnisse besser als die von der bisherigen Modell Wahl? Man probiert es nicht aus? Weil es mühsam ist und wieder Stunden dauert?

Wir haben eine Software entwickelt die dies so vereinfacht, dass auch die Anzahl der Modell Variationen beliebig erhöht werden kann. Die Varianten Erzeugung läuft automatisiert mit einem intelligenten Regelsystem, so auch die Optimierung und das Vergleichen der Modelle und schliesslich die finale Auswahl des Besten Kalibrations Modell.

Unsere Software beinhaltet alle üblichen bekannten Datenvorbehandlungs Methoden (Preteatments) und kann diese sinnvoll kombinieren. Da viele Preteatments direkt abhängig sind von der Wellenlängen Selektion, so z.B. die Normalisierungen die innerhalb eines Wellenlängen-Bereiches die Skalierungsfaktoren ermittelt, um die Spektren damit zu normieren, werden die Pretreatments mit dem Wellenlängen-Bereichen kombiniert. So kommt eine Vielzahl von sinnvollen Modell Einstellungen zusammen die alle berechnet und optimiert werden.

Für die automatische Auswahl der relevanten Wellenlängen Bereiche kommen verschiedene Methoden zum Einsatz, die sich an den Spektren Intensitäten orientieren. So werden z.B. Bereiche mit Totalabsorption nicht verwendet, oftmals störende Wasserbanden entfernt oder beibehalten.

Über all die berechneten Modell Variationen können so zusammenfassende Outlier Analysen gemacht werden. Werden durch die gefahrenen Versuche neue Outlier (Hidden Outlier) entdeckt, können alle bisherigen Modelle automatisch ohne diese Ausreisser nachberechnet, optimiert und verglichen werden.

Aus dieser Vielzahl berechneter Modelle mit deren Statistischen Güte Bewertungen (Prediction Performance) kann nun die optimale Kalibration ausgewählt werden. Dazu wird nicht einfach nach dem Vorhersage Fehler (Prediction Error, SEP, RMSEP) oder nach dem Bestimmtheitsmaß (Coefficient of Determination r2) sortiert, sondern mehrere Statistik- und Testwerte gemeinsam zur umfänglichen Beurteilung der optimalen Kalibration herangezogen.

Somit haben wir eine Plattform geschaffen, die es ermöglicht hochgradig automatisiert das zu tun, was ein Mensch niemals mit einer handelsüblichen Software tun kann.

Wir bieten damit die grösste Anzahl auf Ihr Applikations-Problem angepasste Modellierungs-Berechnungen und wählen die beste Kalibration für Sie aus!

Das heisst, unsere Ergebnisse sind schneller, genauer, robuster und objektiv ausgewählt (Personen unabhängig) und für Sie ganz einfach anzuwenden.

Die Kontrolle über die von uns gelieferten Modelle haben Sie vollumfänglich, denn wir liefern einen klar strukturierten und detaillierten Bauplan der  kompletten Kalibration, mit allen Einstellungen und Parametern, mit allen notwendigen Statistischen Kenngrössen und Grafiken.

Anhand dieses Bauplans können Sie das quantitative Kalibrations Modell selbst in der von Ihnen verwendeten Software nachstellen, nachvollziehen und vergleichen. Sie haben so alles im Griff, für die Modell-Validierung und die Modellpflege.

Der Datenschutz ist uns sehr wichtig. Die NIR Daten, die Sie uns für die Kalibrations-Erstellung kurzzeitig zu Verfügung stellen bleiben selbstverständlich Ihr Eigentum. Ihre NIR Daten werden nach Abschluss des Auftrags bei uns gelöscht.

Interessiert, dann zögern Sie nicht uns zu kontaktieren.

NIRS Calibration Model Equation – Optimal Predictive Model Selection

To give you an insight what we do to find the optimal model, imagine a NIR data set, where a NIR specialist works hard for 4 hours in his chemometric software to try what he can with his chemometric-, NIR spectroscopic- and his product-knowledge to get a good model. During the 4 hours he finds 3 final candidate models for his application. With the RMSEP of 0.49 , 0.51 and 0.6. Now he has to choose one or to test all his three models on new measured NIR spectra.

That is common practice. But is this good practice?

And nobody asks, how long, how hard have you tried, how many trial have you done, if this really the best model that is possible from the data?
And imagine the cost of the data collection including the lab analytics!
And behind this costs, have you really tried hard enough to get the best out of your data? Was the calibration done quick and dirty on a Friday afternoon? Yes, time is limited and manually clicking around and wait in such kind of software is not really fun, so what are the consequences?

Now I come to the most important core point ever, if you own expensive NIR spectrometer system, or even many of them, and your company has collected a lot of NIR spectra and expensive Lab-reference data over years, do you spend just a few hours to develop and build that model, that will define the whole system’s measurement performance for the future? And ask yourself again (and your boss will ask you later), have you really tried hard enough, to get the best out of your data? really?

What else is possible? What does your competition do?

There is no measure (yet) what can be reached with a specific NIR data set.
And this is very interesting, because there are different beliefs if a secondary method like NIR or Raman can be more precise and accurate, as the primary method.

What we do different is, that our highly specialized software is capable of creating large amounts of useful calibrations to investigate this limits – what is possible. It’s done by permutation and combination of spectra-selection, wave-selection, pre-processing sequences and PC selections. If you are common with this, then you know that the possibilities are huge.

For a pre-screening, we create e.g. 42’000 useful calibrations for the mentioned data set. With useful we mean that the model is usable, e.g. R² is higher than 0.8, which shows a good correlation between the spectra and the constituent and it is well fitted (neither over-fitted nor under-fitted) because the PC selection for the calibration-set is estimated by the validation-set and the predictive performance of the test-set is used for model comparisons.

Here the sorted RMSEP values of the Test Set is shown for 42’000 calibrations.
You can immediately see that the manually found performance of 0.49 is just in the starting phase of our optimization. Interesting is the steep fall from 1.0 to 0.5 where manually optimization found it’s solutions. A range where ca. 2500 different useful calibrations exist. The following less steep fall from 0.5 to 0.2 contains a lot more useful models and between 0.2 to 0.08 the obvious high accurate models are around 2500 different ones. So the golden needle is not in the first 2500 models, it must be somewhere in the last 2500 models in the haystack.

Sorted RMSEP plot of 42'000 NIR Calibration Model Candidates

That allows us to pick the best calibration out of 42’000 models, depending on multiple statistical evaluation criteria, that is not just the R² or RPD, SEC, SEP or RMSEP, (or Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Multivariate AIC (MAIC) etc.) we do the model selection based on multiple statistical parameters.

Dengrogram plot of similar  NIR Calibration Models

To compare the calibration models by similarity it is best viewed with dendrogram plots like this (zoomed in), where the settings are shown versus the models overall performance similarity. In the settings you can see a lot of different permutations of pre-processings combined with different wave-selections.

NIR Spectroscopy Calibration Report for quantitative predictive models

When you send your quantitative NIR spectra data to our NIR Calibration Model Service, you get a detailed calibration report (calibration protocol) of the found optimal calibration settings, so you are able to see all insights and easily re-build the model in your NIR/Chemometric software.

Here is a part of our calibration report, that exactly describes the data used in the calibration set (CSet), the validation set (VSet) and the test set (TSet). The numbers are the number ids of the spectra in your delivered NIR data file.

The calibration method settings and parameters are
Waveselection : the variable selection or wavenumber selection or wavelength selection
Pretreatments : the spectral data pre-processing
PCs : the number of Principal Components (PC) or Latent Variables (LV)
Method : the modeling method algorithm used, e.g. PLS

Then the statistical analysis of the PLS model by the different sets (CSet, VSet, Tset).

Calibration Report

Statistical analysis of calibration, validation and test results : 1 Name, 2 Unit, 3 N : number of spectra, 4 N : number of samples, 5 Average spectra count per sample, 6 Reference values, 7 Min, 8 Mean, 9 Median, 10 Max, 11 Standard deviation, 12 Skewness : left (-) or right (+) lack of symmetry, 13 Kurtosis : flat (-) or peaked (+) shape, 14 Model statistics, 15 RPD, 16 R², 17 RMSEC, RMSEP, RMSET : root mean square of prediction errors, 18 SEC, SEP, SET : standard error (bias corrected), 19 Bias, 20 Skewness of prediction errors, 21 Kurtosis of prediction errors, 22 Intercept, 23 Slope, 24 Intercept (reverse), 25 Slope (reverse), 26 Sample Prediction Repeatability Error, 27 Sample Prediction Repeatability Error (of Missing data MSet)

This shows how we deliver the optimal settings. With the statistical values, the NIR model predicted values of all spectra and additional plots you are able to compare with your re-built model to verify that the models perform nearly equally.