Optimised ANN and SVR models for online prediction of moisture content and temperature of lentil seeds in a microwave fluidised bed dryer

Taheri, Saeedeh; Brodie, Graham; Gupta, Dorin

doi:10.1016/j.compag.2021.106003

Cited by 46 publications

(26 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a study conducted by Abdollahpour et al [58], they reported that the ANN model has a greater ability than the SVR model to predict the moisture content of wheat at harvest time. In another study, Taheri et al [59] modeled the moisture content for drying the lentil seeds in a microwave fluidized bed dryer using the SVR and ANN. They showed that the ANN model performed better with R 2 = 0.999 than the SVR with R 2 = 0.995.…”

Section: Comparison Of Ann Anfis and Svrmentioning

confidence: 99%

Application of Artificial Neural Networks, Support Vector, Adaptive Neuro-Fuzzy Inference Systems for the Moisture Ratio of Parboiled Hulls

Sharabiani

Kaveh²,

Taghinezhad

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Drying as an effective method for preservation of crop products is affected by various conditions and to obtain optimum drying conditions it is needed to be evaluated using modeling techniques. In this study, an adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and support vector regression (SVR) was used for modeling the infrared-hot air (IR-HA) drying kinetics of parboiled hull. The ANFIS, ANN, and SVR were fed with 3 inputs of drying time (0–80 min), drying temperature (40, 50, and 60 °C), and two levels of IR power (0.32 and 0.49 W/cm2) for the prediction of moisture ratio (MR). After applying different models, several performance prediction indices, i.e., correlation coefficient (R2), mean square error index (MSE), and mean absolute error (MAE) were examined to select the best prediction and evaluation model. The results disclosed that higher inlet air temperature and IR power reduced the drying time. MSE values for the ANN, ANFIS tests, and SVR training were 0.0059, 0.0036, and 0.0004, respectively. These results indicate the high-performance capacity of machine learning methods and artificial intelligence to predict the MR in the drying process. According to the results obtained from the comparison of the three models, the SVR method showed better performance than the ANN and ANFIS methods due to its higher R2 and lower MSE.

show abstract

Section: Comparison Of Ann Anfis and Svrmentioning

confidence: 99%

Application of Artificial Neural Networks, Support Vector, Adaptive Neuro-Fuzzy Inference Systems for the Moisture Ratio of Parboiled Hulls

Sharabiani

Kaveh²,

Taghinezhad

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Some ANN models were also compared with other mathematical models and showed better performance. Taheri et al 30 implemented both the ANN and support vector regression (SVR) models to study the microwave drying results of lentil seeds. Both models can act as multi-objective modeling tools that allow the prediction of several target outputs.…”

Section: Ann Models For Predicting Drying Performancementioning

confidence: 99%

Recent application of artificial neural network in microwave drying of foods: a mini‐review

Yang

Chen

2022

J Sci Food Agric

View full text Add to dashboard Cite

The microwave-assisted thermal process is a high-efficiency drying method and is promising to be applied in the food industry. However, the prediction of the thermal treatment results from such a dynamic and complicated process can be difficult. Additionally, the determination of the optimal drying parameters, such as drying temperature, microwave power, and drying time for optimized performance can also be hard. Recently, extensive research has been focusing on the use of artificial neural network (ANN) models in the laboratory-scale microwave drying processes and has shown the feasibility of such application. As a regression tool, the ANN models have been widely used in predicting drying performance; when integrated with additional optimizing algorithms, the ANN models could be used for drying parameter optimization; and when combined with real-time measuring techniques (e.g. nuclear magnetic resonance), the ANN models could be used for monitoring and controlling the drying process in a dynamic sense. Future research could focus on testing the developed ANN models in industrial-scale microwave drying processes and applying the ANN models in microwave drying kinetics research for optimizing the dynamic drying processes.

show abstract

“…Machine learning and computer vision algorithms provide new opportunities to noninvasively examine farm animals in terms of behavior (Stewart et al, 2017;Fuentes et al, 2020a), physiology (Jorquera-Chavez et al, 2019;Fuentes et al, 2020b), and production changes (Fuentes et al, 2020c). Artificial neural networks (ANN) are widely applied in multiple agricultural fields, designed to learn, and find patterns among the input data to predict specific outputs (Gonzalez Viejo et al, 2019;Taheri et al, 2021). Model development is achieved by a process of training where these algorithms process the data by modifying weights and biases to obtain the best correlation (Taheri et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…Artificial neural networks (ANN) are widely applied in multiple agricultural fields, designed to learn, and find patterns among the input data to predict specific outputs (Gonzalez Viejo et al, 2019;Taheri et al, 2021). Model development is achieved by a process of training where these algorithms process the data by modifying weights and biases to obtain the best correlation (Taheri et al, 2021). Applications of IRT and ANN have been recently implemented to analyze environmental-related stress responses in farm animals based on changes in body temperature (Jorquera-Chavez et al, 2019;Fuentes et al, 2020b).…”

Section: Introductionmentioning

confidence: 99%

“…Applications of IRT and ANN have been recently implemented to analyze environmental-related stress responses in farm animals based on changes in body temperature (Jorquera-Chavez et al, 2019;Fuentes et al, 2020b). However, using the ANN technique usually requires selecting the best neural network structure with optimum model factors such as the number of hidden layers, neurons, training function, and the activation function for hidden layers and the output function (Taheri et al, 2021). A hidden layer is located between the input and output of the algorithm, in which the function applies weights to the inputs and directs them through an activation function as the output.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Non-invasive measure of heat stress in sheep using machine learning techniques and infrared thermography

Joy

Taheri

Dunshea

et al. 2022

Small Ruminant Research

View full text Add to dashboard Cite

Optimised ANN and SVR models for online prediction of moisture content and temperature of lentil seeds in a microwave fluidised bed dryer

Cited by 46 publications

References 14 publications

Application of Artificial Neural Networks, Support Vector, Adaptive Neuro-Fuzzy Inference Systems for the Moisture Ratio of Parboiled Hulls

Application of Artificial Neural Networks, Support Vector, Adaptive Neuro-Fuzzy Inference Systems for the Moisture Ratio of Parboiled Hulls

Recent application of artificial neural network in microwave drying of foods: a mini‐review

Non-invasive measure of heat stress in sheep using machine learning techniques and infrared thermography

Contact Info

Product

Resources

About