Machine Learning Approaches for Binary Classification of Sorghum (Sorghum bicolor L.) Seeds from Image Color Features

Journal of Food Composition and Analysis, Journal Year: 2025, Volume and Issue: 140, P. 107208 - 107208

Published: Jan. 8, 2025

Language: Английский

---

Comparative Analysis of Visible and Near-Infrared (Vis-NIR) Spectroscopy and Prediction of Moisture Ratio Using Machine Learning Algorithms for Jujube Dried under Different Conditions

Applied Food Research, Journal Year: 2025, Volume and Issue: unknown, P. 100699 - 100699

Published: Jan. 1, 2025

Language: Английский

---

A step forward in food science, technology and industry using artificial intelligence

Trends in Food Science & Technology, Journal Year: 2023, Volume and Issue: 143, P. 104286 - 104286

Published: Dec. 4, 2023

Language: Английский

---

Exploration of machine learning models based on the image texture of dried carrot slices for classification

Journal of Food Composition and Analysis, Journal Year: 2024, Volume and Issue: 129, P. 106063 - 106063

Published: Feb. 9, 2024

Language: Английский

---

Far‐infrared drying influence on machine learning algorithms in improving corn drying process with graphene irradiation heating plates

Journal of Food Process Engineering, Journal Year: 2024, Volume and Issue: 47(4)

Published: April 1, 2024

Abstract Drying methods often suffer from appropriate drying process modeling, low heating efficiency, and high‐energy consumption. However, graphene may provide significant improvements during the due to its ability save energy convert electro‐thermal effectively. In this study, random forest (RF), surface vector machine (SVM), artificial neural network (ANN), k‐nearest neighbor (kNN) were four machine‐learning algorithms employed analyze of two types corn (ZD88 RP909) at varying temperatures 35, 45, 55°C in a far‐infrared drying. The study found that showed decrease moisture ratio falling rate period 35 55°C. diffusivity increased with rise temperature, ranging 2.74 4.36 × 10 −8 m 2 /s for ZD88 2.05 3.07 RP909. heat efficiency 81.62% results learning revealed 1–6 ANN was best architecture. Normalized PUK SVM filters. A k = 3 s‐fold 5 values k‐NN RF, respectively. Among computed algorithms, tested data normalized Pearson universal kernel filters proved be most effective computing corn. Overall, dryer improved less consumption, providing new concept developing through strategies. Practical applications This provides irradiation plates achieved an infrared temperature Machine are intelligent models minimize limitations describing agricultural materials. computation filter. Therefore, using better alternative industrial applications, as it has potential improve consume energy, equipment modeling

Language: Английский

---

Recognition performance of different artificial neural networks for distinguishing banana slices subjected to different combinations of pretreatment and microwave drying

Food Control, Journal Year: 2024, Volume and Issue: 163, P. 110488 - 110488

Published: March 31, 2024

Language: Английский

---

Non-Invasive Prediction of Sweet Cherry Soluble Solids Content Using Dielectric Spectroscopy and Down-Sampling Techniques

Smart Agricultural Technology, Journal Year: 2025, Volume and Issue: unknown, P. 100782 - 100782

Published: Jan. 1, 2025

Language: Английский

---

Impacts of Non-Thermal Pretreatments on Banana Slices During Microwave Vacuum Dehydration Using THz-TDS and NIR-HSI Techniques

Journal of Food Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 112518 - 112518

Published: Feb. 1, 2025

Language: Английский

---

Model comparison and hyperparameter optimization for visible and near-infrared (Vis-NIR) spectral classification of dehydrated banana slices

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127858 - 127858

Published: April 1, 2025

Language: Английский

---

Effect of Pulsed Electric Field on the Drying Kinetics of Apple Slices during Vacuum-Assisted Microwave Drying: Experimental, Mathematical and Computational Intelligence Approaches

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(17), P. 7861 - 7861

Published: Sept. 4, 2024

One of the challenges in drying process is decreasing time while preserving product quality. This work aimed to assess impact pulsed electric field (PEF) treatment with varying specific energy levels (15.2–26.8 kJ/kg) conjunction a microwave vacuum dryer (operating at 100, 200 and 300 W) on kinetics apple slices (cv. Gravenstein). The findings demonstrated notable reduction moisture ratio application treatment. Based findings, implementing PEF reduced from 4.2 31.4% compared untreated sample. Moreover, two mathematical models (viz. Page Weibull) machine learning techniques artificial neural network support vector regression) were used predict dried samples. Page’s Weibull’s predicted ratios R2 = 0.958 0.970, respectively. optimal topology was derived based influential parameters within (i.e., training algorithm, transfer function hidden layer neurons) regression (kernel function). performance (R2 0.998, RMSE 0.038 MAE 0.024) surpassed that 0.994, 0.012 0.009). Overall, approach outperformed terms performance. Hence, can be effectively for both predicting facilitating online monitoring control processes. Lastly, attributes slices, including color, mechanical properties sensory analysis, evaluated. Drying using 100 W not only reduces but also maintains chemical such as total phenolic content, flavonoid antioxidant activity), vitamin C, color qualities product.

Language: Английский

---