Spectroscopy and Chemometric Analyses

Spectroscopy-Based Machine Learning to Predict Stem-End Rot in Avocados with the Temporal Effects

This paper predicts stem-end rot in avocados using hyperspectral data and machine learning models, finding that physics-informed neural networks outperform traditional approaches by incorporating temporal dynamics.

One-dimensional CNNs for Near-Infrared Prediction of Protein and Moisture in Cereal Grains: The Effects of Architecture and Input Preparation

This study compares CNNs, PLSR, SVR, and XGBoost for NIR prediction of protein and moisture in cereal grains, finding that model accuracy depends more on input preparation and sample size than network architecture.

OPTIMIZING PRE-PROCESSING OF NEAR INFRARED SPECTRA FOR PHENOMIC PREDICTION USING SINGULAR VALUE DECOMPOSITION

This paper proposes using singular value decomposition in near infrared spectroscopy pre-processing for phenomic prediction, showing it performs as well as classical chemometrics methods with less parameter optimization.

Macronutrient Distribution and Protein Secondary Structure of Cool-Season Oats Revealed by Synchrotron-Based Mid-IR Spectroscopy and FTIR Chemical Imaging: Effects of Variety and Steam-Pressure Toasting Duration

This study uses FTIR imaging and spectroscopy to analyze protein secondary structures and macronutrient distribution in oats, showing that toasting significantly alters protein structure while variety effects are minor.

Near-infrared phenomic and genomic prediction for seed protein in winter legume white lupin (Lupinus albus L.): A utility comparison

The paper compares near-infrared spectroscopy (NIRS) and genomic selection for predicting seed protein in white lupin, finding NIRS provides accurate, low-cost screening while genomic prediction is better for parental selection.

Machine Learning-Enabled Raman Spectroscopy for Process Analytical Technology and Real-Time Release Testing in Bioprocess Manufacturing: A Comparative Predictive Modeling Study

This paper compares machine learning models for predicting glucose and acetate concentrations in E. coli fermentation using Raman spectroscopy, showing that PLS is better for glucose and XGBoost for acetate.

Single-kernel near-infrared spectroscopy enables haploid kernel sorting in field and sweet corn using high-oil haploid inducers across diverse donor-inducer combinations

This study shows a single-kernel NIR sorter can accurately identify haploid kernels in maize using a general model across diverse donor-inducer combinations.

Optimizing Signal Acquisition and Chemometric Pipelines for Micro NIR Plant Identification: Evaluating Spectral Backgrounds and Data Processing in Herbarium Specimens

This paper optimizes Micro NIR spectroscopy parameters for plant identification using herbarium specimens, achieving 99% accuracy with specific background, preprocessing, and model combinations.

Non-destructive Spatial Reconstruction of Plant Leaf Starch Using Reduced-Band SWIR Spectroscopy and Chemometric Modeling

This paper develops a reduced-band SWIR spectroscopy and chemometric model to non-destructively map starch distribution in strawberry leaves with high spatial resolution.

Hyperspectral imaging of Marchantia

The paper provides a protocol for hyperspectral imaging of Marchantia plants, including data processing and export as structured CSV files.

Impact of Cow Parity on the Accuracy of Near-Infrared Spectroscopy for Sustainable Milk Quality Monitoring during Milking

This study examines how cow parity affects the accuracy of near-infrared spectroscopy in assessing milk quality indicators like fat, lactose, and SCC, finding parity-dependent variations, especially for lactose.

Supporting the implementation of chemometrics models in bioprocess from development to commercial stage

This paper addresses challenges in implementing chemometrics models for bioprocesses by combining spectrometry data, machine learning, and domain knowledge to improve model performance and scalability.

A portable 3D-printed near-infrared spectrometer to screen maize for deoxynivalenol and zearalenone contamination

This paper develops a portable NIR spectrometer and chemometric model to screen maize for mycotoxin contamination, achieving 86.3% accuracy for zearalenone but lower accuracy for deoxynivalenol.

Geographical Origin and Cultivar Differentiation of Kava (Piper methysticum) using Artificial Neural Network with FTIR Spectroscopy: A Novel Method

This paper develops an ANN-FTIR method to authenticate kava origin and cultivar, achieving high accuracy for geographical and quality classification.

Discrimination of Annonaceae using herbarium leaf reflectance spectra under limited sample size conditions

This study evaluates if herbarium leaf reflectance spectra can reliably identify Annonaceae species under limited sample size conditions using multiple classification models.

Factors Influencing Phenomic Prediction: A Case Study on a Large Sorghum BCNAM Population

This study evaluates phenomic prediction in sorghum breeding, showing it can compete with genomic prediction and is less affected by population structure, though trait-dependent and requiring further optimization.

Identification of ketotic cattle based on milk spectroscopic characteristics: a chemometric modelling approach built upon the principles of Aquaphotomics

This paper develops a chemometric model using milk spectroscopy and aquaphotomics principles to identify ketotic cattle, enabling early diagnosis of metabolic disorders.

Rapid and In-situ Detection of Biological Agents via Near-Infrared Spectroscopy and Cloud-Powered Neural Networks

This paper develops a method using near-infrared spectroscopy and machine learning to rapidly detect biological agents in the field, achieving high accuracy in distinguishing them from non-biological substances.

Images in red: A methodological and integrative approach for the usage of Near-infrared Hyperspectral Imaging (NIR-HSI) on collection specimens of Orthoptera (Insecta)

The paper applies near-infrared hyperspectral imaging to Orthoptera specimens to develop a classification model for species discrimination, achieving 90% overall accuracy.

A Potential Method for Identifying Milk Adulteration and Pb(II) Contamination Scenarios Using Principal Component Analysis from Smartphone Photographs

This paper uses PCA on smartphone photographs to detect milk adulteration and Pb(II) contamination, finding effective clustering of control and contaminated samples but challenges with mixed adulterants.

EXPERIMENTAL DESIGN ISSUES ASSOCIATED WITH CLASSIFICATIONS OF HYPERSPECTRAL IMAGING DATA

The paper identifies and addresses two experimental design issues in hyperspectral imaging classification: the 'small N, large P' problem and lack of independent validation data, proposing a method to improve model reliability.

Validation of binary non-targeted approaches: mathematical framework and experimental designs

This paper develops a mathematical framework and experimental designs for validating binary non-targeted methods to improve their reliability and performance in food fraud detection.

AI-based identification of grain cultivars via non-target mass spectrometry

The paper uses AI and non-target mass spectrometry to distinguish wheat and spelt cultivars and validates the method's discriminatory power.

Functional data analysis techniques to improve the generalizability of near-infrared spectral data for monitoring mosquito populations

This paper develops a functional data analysis method to improve the generalizability of near-infrared spectral data for mosquito population monitoring across geographic regions.

Statistical loadings and latent significance simplify and improve interpretation of multivariate projection models

The paper introduces a strategy to improve OPLS model interpretation by using post-hoc linear regression and statistical t-values to enable multivariate analysis of variable significance.