Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models
Artificial neural networks (ANN) and traditional regression models were developed for prediction of thermal properties of sweet sorghum bagasse as a function of moisture content and room temperature. Predictions were made for three thermal properties: 1) thermal conductivity, 2) volumetric specific...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2017-06-01
|
| Series: | Acta Technologica Agriculturae |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/ata-2017-0006 |
| _version_ | 1798018336048545792 |
|---|---|
| author | Gosukonda Ramana Mahapatra Ajit K. Ekefre Daniel Latimore Mark |
| author_facet | Gosukonda Ramana Mahapatra Ajit K. Ekefre Daniel Latimore Mark |
| author_sort | Gosukonda Ramana |
| collection | DOAJ |
| description | Artificial neural networks (ANN) and traditional regression models were developed for prediction of thermal properties of sweet sorghum bagasse as a function of moisture content and room temperature. Predictions were made for three thermal properties: 1) thermal conductivity, 2) volumetric specific heat, and 3) thermal diffusivity. Each thermal property had five levels of moisture content (8.52%, 12.93%, 18.94%, 24.63%, and 28.62%, w. b.) and room temperature as inputs. Data were sub-partitioned for training, testing, and validation of models. Backpropagation (BP) and Kalman Filter (KF) learning algorithms were employed to develop nonparametric models between input and output data sets. Statistical indices including correlation coefficient (R) between actual and predicted outputs were produced for selecting the suitable models. Prediction plots for thermal properties indicated that the ANN models had better accuracy from unseen patterns as compared to regression models. In general, ANN models were able to strongly generalize and interpolate unseen patterns within the domain of training. |
| first_indexed | 2024-04-11T16:22:22Z |
| format | Article |
| id | doaj.art-977a74cb5ce94bad8e56039ddf7ea7d6 |
| institution | Directory Open Access Journal |
| issn | 1338-5267 |
| language | English |
| last_indexed | 2024-04-11T16:22:22Z |
| publishDate | 2017-06-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Acta Technologica Agriculturae |
| spelling | doaj.art-977a74cb5ce94bad8e56039ddf7ea7d62022-12-22T04:14:19ZengSciendoActa Technologica Agriculturae1338-52672017-06-01202293510.1515/ata-2017-0006ata-2017-0006Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression ModelsGosukonda Ramana0Mahapatra Ajit K.1Ekefre Daniel2Latimore Mark3College of Agriculture, Family Sciences and Technology, Fort Valley State University, Fort Valley, USACollege of Agriculture, Family Sciences and Technology, Fort Valley State University, Fort Valley, USACollege of Agriculture, Family Sciences and Technology, Fort Valley State University, Fort Valley, USACollege of Agriculture, Family Sciences and Technology, Fort Valley State University, Fort Valley, USAArtificial neural networks (ANN) and traditional regression models were developed for prediction of thermal properties of sweet sorghum bagasse as a function of moisture content and room temperature. Predictions were made for three thermal properties: 1) thermal conductivity, 2) volumetric specific heat, and 3) thermal diffusivity. Each thermal property had five levels of moisture content (8.52%, 12.93%, 18.94%, 24.63%, and 28.62%, w. b.) and room temperature as inputs. Data were sub-partitioned for training, testing, and validation of models. Backpropagation (BP) and Kalman Filter (KF) learning algorithms were employed to develop nonparametric models between input and output data sets. Statistical indices including correlation coefficient (R) between actual and predicted outputs were produced for selecting the suitable models. Prediction plots for thermal properties indicated that the ANN models had better accuracy from unseen patterns as compared to regression models. In general, ANN models were able to strongly generalize and interpolate unseen patterns within the domain of training.https://doi.org/10.1515/ata-2017-0006annsweet sorghum bagassemoisture contentthermal properties |
| spellingShingle | Gosukonda Ramana Mahapatra Ajit K. Ekefre Daniel Latimore Mark Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models Acta Technologica Agriculturae ann sweet sorghum bagasse moisture content thermal properties |
| title | Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models |
| title_full | Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models |
| title_fullStr | Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models |
| title_full_unstemmed | Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models |
| title_short | Prediction of Thermal Properties of Sweet Sorghum Bagasse as a Function of Moisture Content Using Artificial Neural Networks and Regression Models |
| title_sort | prediction of thermal properties of sweet sorghum bagasse as a function of moisture content using artificial neural networks and regression models |
| topic | ann sweet sorghum bagasse moisture content thermal properties |
| url | https://doi.org/10.1515/ata-2017-0006 |
| work_keys_str_mv | AT gosukondaramana predictionofthermalpropertiesofsweetsorghumbagasseasafunctionofmoisturecontentusingartificialneuralnetworksandregressionmodels AT mahapatraajitk predictionofthermalpropertiesofsweetsorghumbagasseasafunctionofmoisturecontentusingartificialneuralnetworksandregressionmodels AT ekefredaniel predictionofthermalpropertiesofsweetsorghumbagasseasafunctionofmoisturecontentusingartificialneuralnetworksandregressionmodels AT latimoremark predictionofthermalpropertiesofsweetsorghumbagasseasafunctionofmoisturecontentusingartificialneuralnetworksandregressionmodels |