Data Analytics, Statistics, Chemometrics, and Artificial Intelligence

A sample library of selected references discussing the application of artificial intelligence (AI) in analytical chemistry and molecular spectroscopy is presented.

A new publication explores the concept of secondary model-based examination of model-free analysis results in chemical data, revealing hidden insights. His research highlights the significance of integrating quantitative model-based evaluations to enhance data interpretation and extract valuable information.

A researcher team questions the effectiveness of core consistency as a diagnostic tool in fluorescence analysis of complex samples. This new study suggests the need for alternative methods to accurately determine model complexity in such analyses.

We interviewed an AI program (ChatGPT) for Spectroscopy asking questions about AI and its role in various applications for vibrational and atomic spectroscopy, including data analysis.

The relationship between leaf nitrogen content (LNC) and hyperspectral remote sensing imagery (HYP) was determined to construct an estimation model of the LNC of drip-irrigated sugar beets, to enable real-time monitoring of sugar beet growth and nitrogen management in arid areas.

In combination with attenuated total reflectance (ATR), Fourier transform infrared (FT-IR) spectroscopy can be used to classify different moss species.

Are you intrigued by artificial intelligence, but unsure what it really means for analytical chemistry? Read on.

The purpose of this work is to achieve rapid and nondestructive determination of tilapia fillets storage time associated with its freshness. Here, we investigated the potential of hyperspectral imaging (HSI) combined with a convolutional neural network (CNN) in the visible and near-infrared region (vis-NIR or VNIR, 397−1003 nm) and the shortwave near-infrared region (SWNIR or SWIR, 935−1720 nm) for determining tilapia fillets freshness.

The past decision to use binary representation in computer architectures affects the results of chemometric-based outputs, especially if different data values are used.

We examine variations of the multiple linear regression (MLR) algorithm confer special properties on the model that the algorithm produces and critique the use of derivatives in calibration models.

Software tools for ICP-MS and ICP-OES can help analysts to simplify method setup and reduce the potential for errors.

High-performance instrumentation requires many critical components. We focus here on energy sources, lasers, and detectors.

Raw data produced by an NIR instrument undergoes some sort of processing, or transformation, to make them easier to use. In this series, we explore options for that data transformation, starting with multiple linear regression (MLR).

In this study, we propose a low-altitude unmanned aerial vehicle (UAV) hyperspectral visible near-infrared (vis-NIR) remote sensing hardware platform, which combines efficiency and accuracy for high-precision remote sensing-based ecological surveys and statistical data collection on grassland desertification.

As forensic analysis continues to advance, such as in the understanding of source identification and analysis of trace quantities of bodily fluids, spectroscopic techniques and machine learning are playing a significant role. Igor K. Lednev, a chemistry professor at the University at Albany, SUNY, in Albany, New York, has been working in this field with his team. The analytical methods currently under investigation include Raman spectroscopy, attenuated total reflection Fourier transform infrared (ATR FT-IR) spectroscopy, and advanced chemometric classification and analysis methods. We recently interviewed him about his work.

Classification and identification of different wood species are demonstrated using a portable near-infrared spectrometer, combined with four spectral pretreatment methods and three pattern recognition methods. Additional chemometric tools were used for comprehensive evaluation of classification model accuracy and complexity.

Given that grape seed oil has shown beneficial effects for consumers, there is a interest in measuring oil quality and potential adulteration. This study demonstrates an effective near-infrared (NIR) spectroscopy method, using a series of machine learning approaches for wavelength variable selection, to rapidly discriminate grape seed oil adulteration.

The second in a two-part series highlighting key explanatory or tutorial references for each of 29 chemometric methods.

Igor K. Lednev at the University at Albany SUNY in New York explains advances in forensic analysis using a variety of chemometrics techniques to classify ATR FT-IR and Raman spectra of bodily fluids.

The carefully selected literature references in this curated set describe the application of 29 major chemometric methods used for analyzing molecular spectroscopy data.

L. Scott Ramos will receive the 2021 Eastern Analytical Symposium (EAS) Award for Outstanding Achievements in Chemometrics at the EAS Symposium taking place November 15–17, 2021, in Plainsboro, New Jersey.

“SneakerNet,” or the manual transfer of data using a disk or USB stick from one computer system to another, should be long dead, but this noncompliant transfer process still survives.

The details of applying deep learning algorithms and FT-IR spectra are described for classification research using the spectra of strawberries as an example.

Mathematics is a formal logic system, perhaps the ultimate formal logic system. Here we describe the elegance of the foundations of the mathematics that chemometrics is based on.

We explore how different algorithms and different numbers of factors affect the results.