Effectiveness Of Spectral Analysis Research Articles

Tracing pistachio nuts’ origin and irrigation practices through hyperspectral imaging

Pistachio trees have become a significant global agricultural commodity because their nuts are renowned for their unique flavour and numerous health benefits, contributing to their high demand worldwide. This study explores the application of Hyperspectral Imaging (HSI) and Machine Learning (ML) to determine pistachio nuts' geographic origin and irrigation practices, alongside predicting essential commercial quality and yield parameters. The study was conducted in two Spanish orchards and employed HSI technology to capture spectral data. It used ML models like Partial Least Squares (PLS), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) for analysis.The results demonstrated high accuracy in classifying pistachios based on origin, with accuracies exceeding 94%, and in assessing water content and colour pigments, where both PLS and SVM models achieved 99% accuracy. The research highlighted distinct spectral signatures associated with different irrigation treatments, particularly in the Near-Infrared (NIR) region, with PLS showing an accuracy of 92%. However, challenges were noted in predicting fruit orientation, while predicting height location within the tree was more successful, reflecting clearer spectral distinctions. Regression models also showed promise, particularly in predicting yield (R2 = 0.89 with PLS) and percentage of blank nuts (R2 = 0.71 with PLS). The correlation analysis revealed key insights, such as an inverse relationship between blank nuts and yield, and a strong correlation between yield and split nuts. Despite challenges in predicting fruit orientation, the research showed promising results in forecasting yield and commercial quality factors, indicating the effectiveness of spectral analysis in optimising pistachio production and sustainability.

Cuttlefish Species Authentication: Advancing Label Control through Near-Infrared Spectroscopy as Rapid, Eco-Friendly, and Robust Approach.

Accurate species identification, especially in the fishery sector, is critical for ensuring food safety, consumer protection and to prevent economic losses. In this study, a total of 93 individual frozen-thawed cuttlefish samples from four different species (S. officinalis, S. bertheloti, S. aculeata, and Sepiella inermis) were collected from two wholesale fish plants in Chioggia, Italy. Species identification was carried out by inspection through morphological features using dichotomic keys and then through near-infrared spectroscopy (NIRS) measurements. The NIRS data were collected using a handled-portable spectrophotometer, and the spectral range scanned was from 900-1680 nm. The collected spectra were processed using principal component analysis for unsupervised analysis and a support vector machine for supervised analysis to evaluate the species identification capability. The results showed that NIRS classification had a high overall accuracy of 93% in identifying the cuttlefish species. This finding highlights the robustness and effectiveness of spectral analysis as a tool for species identification, even in complex spatial contexts. The findings emphasize the potential of NIRS as a valuable tool in the field of fishery product authentication, offering a rapid and eco-friendly approach to species identification in the post-processing stages.

Adaptive variant of the surrogate data technology for enhancing the effectiveness of signal spectral analysis using eigenstructure methods

The problem of enhancing the effectiveness of spectral analysis of signals observed against the background of noise by the Root-MUSIC method has been considered using the surrogate data technology implemented by adapting the algorithm of phase randomization of the Fourier transform samples of the initial data in relation to the signal-to-noise ratio (SNR). The proposed variant of the surrogate data technology was shown to be effective at low values of SNR and a small number of samples. At large values of SNR an additive variant of the surrogate data technology actually does not cause an emergence of surrogate interference typical for nonadaptive variant. The proposed variant of the technology can be applied in combination with other methods of spectral analysis.