Early monitoring of drought stress in safflower (Carthamus tinctorius L.) using hyperspectral imaging: a comparison of machine learning tools and feature selection approaches DOI Creative Commons

Fatemeh Salek,

Seyed Ahmad Mireei, Abbas Hemmat

et al.

Plant Stress, Journal Year: 2024, Volume and Issue: unknown, P. 100653 - 100653

Published: Oct. 1, 2024

Language: Английский

Shortwave near Infrared–Hyperspectral Imaging Spectra to Detect Pork Adulteration in Beef Using Partial Least Square Regression Coupled with VIP Wavelength Selections Method DOI Creative Commons
Rudiati Evi Masithoh, Reza Adhitama Putra Hernanda, Muhammad Fahri Reza Pahlawan

et al.

Optics, Journal Year: 2025, Volume and Issue: 6(1), P. 1 - 1

Published: Jan. 3, 2025

Pork adulteration detection in beef is important due to health, economic, and religious concerns. This study explored the use of a Shortwave Near Infrared–Hyperspectral Imaging (SWNIR–HSI) system which captured spectral data across 894–2504 nm detect pork beef. In this study, minced various concentrations ranging from 0–50% (w/w) were added pure Spectra obtained SWNIR–HSI used develop partial least square regression (PLSR) model. The compared PLSR results between full wavelengths (variables) selected via variable importance projection (VIP) method. best full-wavelength model yielded prediction accuracy (R2P) 0.940 standard error (SEP) 4.633%, while using VIP-selected improved performance, with R2P 0.955 SEP 3.811%. demonstrates potency SWNIR–HIS, particularly wavelengths, as an effective nondestructive tool for accurately predicting levels

Language: Английский

Citations

1
A Non-Destructive Moisture Detection System for Unshelled Green Tea Seed Kernels Based on Microwave Technology with Multi-Frequency Scanning Signals DOI Creative Commons
Bo Zhou, Ye Yuan,

Zhenbo Wei

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1324 - 1324

Published: Feb. 21, 2025

A self-developed microwave moisture detection system (ranged from 2.00 GHz to 10.00 GHz) based on multi-frequency sweep technology was used quickly determine the content of tea seed kernels without breaking shells. evaluation method combined cross-validation and majority voting rules proposed select optimal features original signals. Firstly, detected by system, determination coefficients ANN model established seven attenuations six phase-shifts were over 0.999. Then, unshelled seeds detected, 13 preferred frequency 0.995. Moreover, predicted values calibrated accurately a function (y = −0.017x2 + 1.431x − 1.019). Above all, could achieve non-destructive prediction kernels.

Language: Английский

Citations

0
Establishing a Low-Temperature Maize Kernel Moisture Content Prediction Model Based on Dielectric Constant Measurement DOI Creative Commons
Shuhao Wang, Shaoyan Du,

Yuanyuan Yin

et al.

Agriculture, Journal Year: 2025, Volume and Issue: 15(5), P. 507 - 507

Published: Feb. 26, 2025

Detecting the moisture content of stored maize kernels is critical for minimizing post-harvest losses. To measure under low-temperature conditions, a small-strip transmission line device was employed to construct non-destructive measurement platform. The dielectric constant with varying measured at temperatures ranging from −15 °C 20 and frequencies between 1 200 MHz. By using constant, frequency, temperature as input variables, along volume density scattering parameter characteristics, three prediction models—SPO-SVM, XGBoost, GA-BP—were established. results show that significantly affects kernels, especially when levels exceed 22.4%. model improves accuracy conditions after introducing feature. Furthermore, incorporating multi-phase amplitude characteristics parameters further model’s performance. This study verifies mechanism behavior variations in conditions. proposed effectively mitigates errors caused by icing free water well suited measuring

Language: Английский

Citations

0
Near-Infrared Spectroscopy for Nutrient Analysis in Manure DOI
Anupama Rawat, Kumar Gaurav, Pallavi Bhatt

et al.

Advances in chemical and materials engineering book series, Journal Year: 2025, Volume and Issue: unknown, P. 295 - 328

Published: Feb. 14, 2025

Organic sources of nutrients provides nutrition to the crops in balanced amount. To properly manage manuring soil, knowledge nutrient profiling is essential. Underapplication manure can reduce crop quality and yield while overapplication cause environmental deterioration. Near-Infrared spectroscopy (NIRS) has emerged as a potential rapid technique that be utilized examine mineral contents, including carbon, nitrogen, ammonia, phosphorus potassium various types manures. This analysis then used generate insight on composition applied adjust quantity required. In contrast conventional laboratory method manure, NIRS offers rapid, real-time, on-site more efficient for optimizing application practices enhancing soil fertility minimising product wastage. NIR radiation waves have wavelength ranging from 700 nm - 2500 works principle Beer- Lambert law.

Language: Английский

Citations

0
Early monitoring of drought stress in safflower (Carthamus tinctorius L.) using hyperspectral imaging: a comparison of machine learning tools and feature selection approaches DOI Creative Commons

Fatemeh Salek,

Seyed Ahmad Mireei, Abbas Hemmat

et al.

Plant Stress, Journal Year: 2024, Volume and Issue: unknown, P. 100653 - 100653

Published: Oct. 1, 2024

Language: Английский

Citations

1