To gain responsiveness and quality

Development of authentication and identification models

You are involved in the production or R&D industry and you are faced with the problems of identifying raw materials upon receipt or detecting non-conformities on finished products?


You want to


precise and robust models for authentication

Maintenance des calibrations spectroscopiques


your existing identification models

transfert de calibrations spectroscopiques


these models from one production line to another

idenftification - authentification

Data analysis methods for discrimination, classification and identification of products and fault detection are your solution. These “Pattern Recognition” models make the sorting of your raw materials more reliable upon receipt and qualify your finished products, to significantly reduce your production costs and batch release times.

Data used for the construction of product authentication models can have very diverse origins, such as optical spectral measurements (near infrared spectroscopy (SPIR-NIR), mid infrared (MIR – FTIR), Raman, UV, etc.) or still physico-chemical measurements from a wet chemistry laboratory, chromatographic or mass spectroscopy measurements (HPLC, GC, GC-MS, etc.)… All these parameters from different sources can be combined by multi-block methods in order to produce more precise identification models.

Thanks to our knowledge in Chemometrics and Machine Learning applied to data from spectroscopy, laboratory measurements or industrial processes, we assist you in the various stages of development, optimization and maintenance of identification models and authentication for precise and robust classifications.

Classification, discrimination, identification
  • Classification (PLS-DA, SIMCA, Support Vector Machines (SVM), Decision trees (CART, RF, XGBoost…)
  • Validation and model robustness
  • Transfer of calibrations (standardization (PDS, etc.), orthogonalization methods, etc.)
  • Model update
  • Implementation of models for routine use

Software implementation

We develop your calibrations with all the Chemometrics software on the market (Unscrambler®, SOLO® or PLS_Toolbox® in the MATLAB® environment, SIMCA®, etc.), as well as those provided by spectroscopy equipment manufacturers (OPUS, WinISI, NIRCal, TQ Analyst, etc…), but also free software (R, Python…).

Our expertise for the analysis of your data

With more than 15 years of experience in data analysis (chemometrics and Machine Learning), in particular applied to measurements from spectrometers, laboratory data or processes, the experts of our teams support you at each stage of your projects.

They talk about Ondalys

« We call for Ondalys for exploiting our data. »

Eric SERRANO, Manager of the French Wine Institue - IFV Sud Ouest

Register to
receive Ondalys newsletter