Vibralytics
Faster, More Cost-Effective Measurements with Spectroscopy and Chemometrics
- From experimental design to fully validated methods ready for routine use.
- Chemometric Model Development
- Hyperspectral Image Analysis
- FTIR and Raman Spectroscopy Solutions
Welcome to Vibralytics
Rapid, nondestructive analysis, calibrated against your reference method.
We work with food producers, ingredient suppliers and analytical labs who need routine quality control that doesn’t slow down production. Our NIR models are calibrated against your own reference data, so what you get isn’t a generic tool, it’s built around how your lab actually works.
Our background in this is peer reviewed, not just internal experience.
Before founding Vibralytics, we published research on detecting honey adulteration with FTIR and deep learning, predicting fungal infection in tomatoes, macronutrients in cheese, frying time in potatoes. Across different journals and food matrices, tested and accepted by other scientists in the field before it ever became a service we offer.
We stay involved from the first feasibility test to a model you can run without us.
Experimental design, sample strategy, development, validation against your reference method. We don’t hand off a black box halfway through and disappear.
We built our own software to do this properly.
Our platform covers the full modeling pipeline: loading and visualizing spectral data, outlier screening with PCA, UMAP, DBSCAN, Isolation Forest or Mahalanobis distance, variable selection, and calibration/validation splitting that keeps replicates of the same sample together. Latent variable selection in PLS and PLS-DA is based on RMSEP curves from cross validation or a tuning set. Every model is validated with a full metrics report: RMSEC, RMSEP and R² for regression, confusion matrices, sensitivity, specificity, balanced accuracy and F1 for classification.
The same platform supports what comes after the model is built: monitoring new samples in routine use, hyperspectral image analysis, calibration transfer between instruments, and internal verification routines to confirm equipment performance.
My colleagues say
“I had the pleasure of working with Mercedes Bertotto, and I can say she is a fantastic colleague. We worked together on planning experiments and tackled a difficult exam for a course, which showed how well we could collaborate as a team. Before Mercedes moved to another country for work, she kindly shared her knowledge of NIR technology with me, proving how dedicated she is to helping others. Her positive attitude and support make her a great team player. I strongly recommend her for any future opportunities, as she will be a valuable addition to any workplace.”Georgina Soledad — Lic. Industrial Food Technology
“I have always worked in a very pleasant way with Mercedes and her knowledge about NIR is really incredible! She is a very honest person, which I appreciate greatly. She tells the truth, no matter what. And always in a constructive manner, so the things that she says are very valuable. And we are writing these papers, and I think they are great. That is due to her contributions and of the others of course, but she is really in the lead, and she knows what she wants to say (write). Informally we also really get along very well.”Hajo Rijgersberg — Ontology of units of Measure (OM) | Semantic Web | Bayesian networks
“I had the pleasure of working with Mercedes during our PhD studies. She was always well organized and prepared, showing quick learning skills. She is well known for her expertise in the field of data analysis and chemometrics, and has a broad knowledge in analytical methods. Always with a ‘can do attitude’ you will definitely benefit from her collaboration.”Cueto Mario — Solutions Manager @DBSchenker
“I had the pleasure of collaborating with Mercedes Bertotto on several research projects, and I was consistently impressed by her ability to tackle complex problems with both rigor and creativity. Mercedes approaches her work with meticulous attention to detail and discipline, making her an exceptional professional in her field. In addition to her technical excellence, she is a great communicator and a strong team player, always willing to share her knowledge and help others achieve their goals. Her dedication and passion for research are evident in everything she does, and I have no doubt that she will continue to achieve great things in her career.”Pablo Calello — Actuary, Universidad de Buenos Aires
“I am pleased to recommend Mercedes, who has worked with SoftLab on two separate occasions. Mercedes first joined as a trainee in programming, quickly demonstrating a strong ability to learn and adapt. Later, from February 2019 to June 2022, she worked as a NIR Consultant, showing exceptional skills in data handling and analysis. Mercedes is highly responsible, loves working in teams, and brings valuable expertise to any project.”Walter Otto Krause — Software & Hardware Development Manager, SoftLab SRL
Our opening hours
| Monday | 09:00 – 18:00 |
| Tuesday | 09:00 – 18:00 |
| Wednesday | 09:00 – 18:00 |
| Thursday | 09:00 – 18:00 |
| Friday | 09:00 – 18:00 |
| Saturday | Closed |
| Sunday | Closed |
Questions?
Send us a message