Blog
Understanding Regression: Theory to Real-World Use
Regression models turn an NIR spectrum into a number: fat in olives, moisture in meat, API content in a tablet. PCR, PLS, SVR and neural networks explained.
Understanding Classification Problems: Theory to Real-World applications with NIRLAB
Classification models sort NIR spectra into categories: genuine or counterfeit, THC or CBD cannabis, PA6 or PA66. How the algorithms work, with real cases.
Portable vs. Benchtop NIR – Which One Will Lead the Future of Spectroscopy?
In the world of Near-Infrared spectroscopy, the debate between handheld and benchtop devices has been ongoing for years.
Sustainable Farming with NIRLAB’s Real-Time Analysis
What portable NIR sensors measure for farmers: moisture and NPK in soil and crop tissue, protein, fiber and fat in feed, with results in the field.
Current Drug Situation in Europe 2024: An Insightful Analysis
The drug landscape in Europe is continually evolving, driven by the emergence of new substances, shifting usage patterns, and changing policies.
The PA6 and PA66 Challenge: Distinguishing the Indistinguishable
In the intricate dance of molecules that shapes the materials of our daily lives, polyamides play a leading role.
Plastic Recycling Revolution: NIR Spectroscopy’s Transformative Role
In our modern world, the issue of plastic recycling has evolved into a global environmental crisis, with millions of tons of plastic produced, used, and discarded each year.
Asbestos Detection: Unmasking the Hidden Danger with Advanced Techniques in Using NIR Spectroscopy
Asbestos, once prized in construction, remains a hidden hazard. The limits of traditional detection and how NIR spectroscopy can help identify it on site.
Good start for the drug control center: scanned 170 samples
In six months, the Lausanne facility has attracted 90 consumers wishing to test their drugs. The canton is considering the future of the programme.
Providing illicit drugs results in five seconds using ultra-portable NIR technology
The analysis of illicit drugs faces many challenges, mainly regarding the production of timely and reliable results and the production of added value from the generated data.