The main research areas are related to development and application of multivariate data analysis tools, including novel algorithms and codes, in the context of data driven discovery. The use of chemometrics to extract relevant information from instrumental data ranging from hyphenated analytical techniques to imaging, find broad application in several fields, such as material design and characterization, process and product control, food authentication, environmental and biomedical research, etc..

Main Research topics:

-Integration of latent variables methods and signal processing methodologies.
-Developing Multivariate Images Analysis tools to attain spatial and spectral resolution
-Improving state-of the art hyperspectral imaging to resolve complex chemical samples.
-Development of classification models and pattern recognition tools.
-Development and application of Data Fusion methodologies
-Development, optimization and validation of analytical methodologies for the authentication and the traceability of foodstuffs and their supply chain. Optimization by experimental design (DoE) of sampling, sample preparation and instrumental settings. Data Fusion applied to the outcome of several analytical techniques that potentially can provide origin-related markers.
- Application of Experimental Design methodology to optimization of analytical procedures, formulation problems, and to optimize simulation experiments.

 

Main Expertise:

- Multivariate (PCA, PLS, SIMCA, Cluster Analysis,..), Multi-way (PARAFAC, Tucker, N-PLS) and Multiset (Multivariate Curve Resolution) data analysis.
- Multi-way classification (NSIMCA, NPLS-DA).
- Data Fusion procedures.
- Wavelet Transform 1D and 2D, elaboration of algorithms performing feature selection in Wavelet Domain for classification and regression tasks.
- Signals processing tools.
- Images elaboration.
- Quantitative Structure Property Relationships (QSPR) and structure-activity (QSAR and 3D-QSAR).