Analysis of bigger and bigger data sets are the core value of chemometric model to better describe complex problems and ADAPT aid to interpret, document and ultimately, create a commercial value.
Data are becoming a highly valued commodity and should be handled with care, where ADAPT can assist in experimetal planning
As an active participant with the customer, ADAPT wishes to develop chemometric models to describe complex problems and aid to interpret, document and ultimately, creating commercial value.
Processing tools are an essential part of how data being generated and the quality, which are needed for at better product control as a feed forward model, which can be achived using ADAPT
Targets for ADAPT are primary personal and small medium businesses with limited or no ressources within chemometrics, data processing and development of analytical chemistry projects.
Chemometrics and data mining are becoming more and more important in many aspects of handling data, feature extraction, classification and (quantitative) modelling.
If one, visit Linkedin or similar social media platforms, there exist a lot of different approaches and definition of data miners and data scientist, which be quite confusing and bringing clarity on the subject.
There exist a list of very good introductions to the world of chemometrics, which combined both data mining, the data scientist area including deep learning and machine learning, which are listed here.
The first paper (Amigo J.M, 2021) give a good introduction to chemometrics and the confusion around data science and stresses that it is paramount to know you data, the origin and what the outcome should be. And last but not least validate your models and remember the GI-GO principle (Garbage In – Garbage Out)
Amigo, J. M. (2021). Data mining, machine learning, deep learning, chemometrics: Definitions, common points and trends (Spoiler Alert: VALIDATE your models!). Brazilian Journal of Analytical Chemistry, 8(32), 22–38. https://doi.org/10.30744/BRJAC.2179-3425.AR-38-2021
Wold, S.; Sjöström, M.; Eriksson, L. Chemom. Intell. Lab. Syst., 2001, 58 (2), pp 109–130 (https://doi. org/10.1016/S0169-7439(01)00155-1)
Bro, R. Crit. Rev. Anal. Chem., 2006, 36 (3-4), pp 279–293 (https://doi.org/10.1080/10408340600969965)
Bro, R. Chemom. Intell. Lab. Syst., 1997, 38 (2), pp 149–171 (https://doi.org/10.1016/S0169- 7439(97)00032-4).