Data Analytics, Statistics, Chemometrics, and Artificial Intelligence

Here are the top five articles that the editors of Spectroscopy published this week.

In a recent study from Cairo University, researchers examined fixed-dose combination drug formulations using chemometrics and artificial neuron networks (ANNs).

Spectroscopy spoke with the CEO and CCO of the instrument manufacturer PerkinElmer to discuss trends in the analytical and life sciences industry.

Peter M. Carlson will take over as CEO of Spectral AI, replacing Wensheng Fan.

Juergen Popp of the Leibniz Institute of Photonic Technology presented at Pittcon 2024 about how artificial intelligence (AI) can help scientists with tumor removal processes.

Nano-X received clearance from the U.S. Food and Drug Administration for its HealthFLD artificial intelligence (AI) software, which is designed to perform automated qualitative and quantitative analysis of liver attenuation from CT scans.

At SPIE Photonics West 2024, Jiachi Ye of the University of Florida held a presentation about a 4f-based free-space optical system (light-based computer) to address power consumption and speed limitations of calculations performed with convolutional neural networks (CNNs).

At SPIE Photonics West, Spectroscopy spoke with Ana Doblas of the University of Massachusetts, Dartmouth about artificial intelligence, deep learning, and their potential in microscopy.

Ana Doblas of the University of Massachusetts Dartmouth presented her team’s findings on how models based on deep learning (DL) can enhance different microscopy imaging infrastructures.

Chengjie Xi of the University of Florida held a lecture on how terahertz time-domain spectroscopy (THz-TDS) can be used to detect changes in integrated-circuit (IC) packaging materials.

In this column and its successor, we describe and explain some algorithms and data transforms beyond those commonly used. We present and discuss algorithms that are rarely, if ever, used in practice, despite having been described in the literature. These comprise algorithms used in conjunction with continuous spectra, as well as those used with discrete spectra.

Researchers in Brazil leverage artificial intelligence algorithms and Vis-NIR-SWIR hyperspectroscopy to achieve precise pigment phenotyping and classification of eleven lettuce varieties, showcasing the potential of integrating advanced technologies in agriculture.

A recent study from Jeonbuk National University introduces a novel technique for orchard management: tackling intertwined fruit trees' precise segmentation using deep learning models.

This interview with Pola Goldberg Oppenheimer of the University of Birmingham highlights new research her team is working on that includes a Raman-based system for detecting early traumatic brain injuries.

Scientists have created a new means of identifying insect species using ATR-FTIR spectroscopy and machine learning methods.

Scientists in Ireland recently tested the effectiveness of different machine learning (ML) methods for measuring contamination levels on wind turbine blades.

John H. Kalivas, a professor in the Department of Chemistry at Idaho State University, has been named the winner of the 2023 EAS Award for Outstanding Achievements in Chemometrics.

Felipe Bachion de Santana of Teagasc in Wexford, Ireland, is exploring new ways to monitor soil quality through using spectroscopic techniques. Spectroscopy spoke to him about his team’s work in monitoring the quality of soil to improve agricultural efficiency.

A team of scientists have used airborne lidar mapping to study Mayan architecture, seeing how certain buildings’ construction can hint at the social status of their inhabitants.

In the Chemometrics in Food and Agriculture oral symposia today at SciX 2023, Barry Lavine of Oklahoma State University delivered a talk titled, “Authentication of Edible Oils Using an Infrared Spectral Library and Digital Sample Sets for Calibrated and Uncalibrated Adulterants.” Here is a brief reflection of his talk.

As a preview to SciX 2023, Spectroscopy magazine sat down with Ishan Barman of Johns Hopkins University to ask him about his thoughts on how artificial intelligence may impact spectroscopic research going forward.

There is a variation of the MLR calibration algorithm that can reduce sensitivity to repacked sample measurements. We explore that MLR method here in detail.

To effectively classify tobacco stems and impurities, a group of scientists from Jiangsu, China used hyperspectral superpixels to separate classify compounds and avoid the influence of interference fringes.

A group of researchers from Beijing Technology and Business University developed a couple extraction algorithms and classification methods that could contribute toward ensuring the quality of wheat flour.

In this interview, Peter Griffiths, 2023 recipient of the Ellis R. Lippincott Award, reflects over his storied career, as well as his most recent work, which focuses on measuring fine airborne particles within mining environments.

In this interview, James Chapman discusses his current and future research efforts, and how combining spectroscopy with machine learning tools can change how bacterial research is conducted.

In this interview, Jürgen Popp discusses the importance of Raman spectroscopy, where it can make a difference, and how it can be evolved and improved on in the future.

Researchers have developed an eco-friendly method using chemometric techniques and artificial neural networks for simultaneous determination of aspirin, clopidogrel, and either atorvastatin or rosuvastatin in their fixed-dose combination (FDC) formulations using ultraviolet (UV) spectrophotometry.

A team of researchers has developed a novel algorithm for rapid peak fitting and resolution enhancement in Raman hyperspectra analysis. The algorithm offers significant advancements in processing large datasets, improving peak resolution, and extracting valuable information about analytes.

A research team has utilized the Allan variance technique to analyze the performance characteristics of compact Fourier transform infrared (FT-IR) spectrometers. The study provides insights into the noise sources and instabilities of these handheld instruments, offering guidance for improving their accuracy and stability in real-time material detection and quantification applications.