Automating the Optimization of Locally Weighted Models is a Solution

Automation of Local Regression Model Building for Spectroscopic Data, JChem2024 Pell et alA calibration model tends to improve as additional calibration samples are added to the library. If the samples reflect variation in the chemical composition, the model then expands its zone of relevance. Ultimately, as these new zones expand calibration scope, the model can degrade in performance due to nonlinearities and may require adding to the model rank, which can make the model fragile. Building local models is one answer to gain the best of both worlds, but optimizing a locally weighted model is tricky and time consuming. Automating the optimization of locally weighted models is a solution.

http://doi.org/10.1002/cem.3637

For additional information or questions, contact info@infometrix.com.

#chemometrics #LWR #spectroscopy #regression

Industrial Grade Chemometrics: from Laboratory to Process Implementation – APACT 2024 Program

Venue: April 24, 2024, 8:30am – 9:10am Hyatt Regency Hotel, New Brunswick, NJ Industrial Grade Chemometrics: from Laboratory to Process Implementation Presented by: Brian Rohrback, President, Infometrix, Inc. Abstract: The use of multivariate statistics, whether termed chemometrics or machine learning or (fill in the blank), is critical for industry to move from human-centered processing to more automated, objectively reliable processes. In the laboratory world, we seek to discover new routes for solving problems that will give us better solutions than previous methods. And this largely university-based effort is critical for enabling improvements in product manufacturing and the quality control process that accompanies it. But, given academia’s limited access to commercial application samples, most chemometrics publications deal only with the method development side of a given problem. If we are going to benefit a manufacturing organization, an industry, or especially society, the emphasis needs to be on the shift from this laboratory origin to a solid process implementation. Anything useful we devise must ultimately get used; if we fail to integrate proven technology into the day-to-day, the development process is simply an expense. The experience through the now five decades of implementing multivariate solutions has identified some steps, some barriers, and some low-hanging fruit. How do we succeed in pushing new technology the last mile? Register at APACT 2024.

APACT 2024 Program is available

APACT USA 2024Venue: April 23-25, 2024 Hyatt Regency Hotel, New Brunswick, NJ Infometrix is a proud sponsor for APACT USA 2024 Conference. Get the program, list of key speakers, registration information and other details from the APACT website. Don’t miss out on this incredible opportunity to connect, learn, and grow at APACT USA 2024 Conference. Register at APACT 2024.

APACT 2024 (Plenary) – Industrial Grade Chemometrics: from Laboratory to Process Implementation

APACT 2024Venue: April 23-25, 2024 Hyatt Regency Hotel, New Brunswick, NJ Presented by: Brian Rohrback, Ph.D., MBA, President, Infometrix, Inc. Abstract: The use of multivariate statistics, whether termed chemometrics or machine learning or (fill in the blank), is critical for industry to move from human-centered processing to more automated, objectively reliable processes. In the laboratory world, we seek to discover new routes for solving problems that will give us better solutions than previous methods. And this largely university-based effort is critical for enabling improvements in product manufacturing and the quality control process that accompanies it. But, given academia’s limited access to commercial application samples, most chemometrics publications deal only with the method development side of a given problem. If we are going to benefit a manufacturing organization, an industry, or especially society, the emphasis needs to be on the shift from this laboratory origin to a solid process implementation. Anything useful we devise must ultimately get used; if we fail to integrate proven technology into the day-to-day, the development process is simply an expense. The experience through the now five decades of implementing multivariate solutions has identified some steps, some barriers, and some low-hanging fruit. How do we succeed in pushing new technology the last mile? Register at APACT 2024.

IFPAC 2024 – Chemometrics in the Cloud

IFPAC 2024Venue: March 3-6, 2024 Bethesda North Marriott Hotel and Conference Center Presented by: Brian Rohrback, Ph.D., MBA, President, Infometrix, Inc. Abstract: In the spirit of automation, there are cloud-based tools from both the chemometrics and the general statistics realms that can be applied to simplify the work involved in optimizing a calibration. Robust statistical techniques require some set-up of parameters, but once established for an application, they are often usable in every other instance of that application. The result is a one-pass automated means of selecting optimal samples for a calibration problem and, in turn, simplifies and automates the assignment of model rank. In the end case, this means that a spectrometer can essentially become an appliance; take it out of the box, plug it in, and enjoy. The capability exists to have a spectrometer self-tune and adapt to a specific application, then keep the spectrometer in appropriate calibration completely through closed-loop control. Automation of best practices needs to include how to match laboratory reference data to spectral data, an unbiased approach to selecting validation samples, an optimal mechanism for model construction, establishing standards for quality reports, tracking model performance over time, handling process or ingredient transitions, and much more. Register at www.IFPACglobal.org/attendee-registration.