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

---

Predicting Corn Moisture Content in Continuous Drying Systems Using LSTM Neural Networks

Foods, Journal Year: 2025, Volume and Issue: 14(6), P. 1051 - 1051

Published: March 19, 2025

As we move toward Agriculture 4.0, there is increasing attention and pressure on the productivity of food production processing. Optimizing efficiency in critical processes such as corn drying essential for long-term storage economic viability. By using innovative technologies machine learning, neural networks, LSTM modeling, a predictive model was implemented past data that include various parameters weather conditions. collection 3826 samples not originally intended dataset models, imputation techniques were used to ensure integrity. The imputed multilayer network consisting an layer three dense layers. Its performance evaluated four objective metrics achieved RMSE 0.645, MSE 0.416, MAE 0.352, MAPE 2.555, demonstrating high accuracy. Based results visualization, it concluded proposed could be useful tool predicting moisture content at outlets continuous systems. research contribute further development sustainable demonstrate potential data-driven approach improve process efficiency. This method focuses reducing energy consumption, improving product quality, profitability

Language: Английский

---

Applications of Machine Learning Technology in Agricultural Data Mining

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(10), P. 5286 - 5286

Published: May 9, 2025

The global agricultural sector is undergoing a revolutionary transformation with the growing integration of machine learning (ML) technologies into traditional farming and agronomic practices [...]

Language: Английский

---

Prediction and influencing factors analysis of stored grain temperature and intergranular relative humidity

Food and Bioproducts Processing, Journal Year: 2025, Volume and Issue: unknown

Published: June 1, 2025

Language: Английский

---