Statistical optimization and artificial neural network modelling of Annona Muricata (soursoup) leaves in supercritical carbon dioxide extraction / Muslihah Yusof ... [et al.]
Supercritical fluid extraction (SFE) using carbon dioxide as a solvent is one of the non-conventional method recently used in extraction. Carbon dioxide is used as a solvent in this extraction because it is a non-toxic solvent. From the previous study, Annona Muricata Leaves have effectiveness as an...
Tallennettuna:
| Päätekijät: | , , , |
|---|---|
| Aineistotyyppi: | Kirja |
| Julkaistu: |
2020.
|
| Aiheet: | |
| Linkit: | Link Metadata |
| Tagit: |
Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!
|
| Yhteenveto: | Supercritical fluid extraction (SFE) using carbon dioxide as a solvent is one of the non-conventional method recently used in extraction. Carbon dioxide is used as a solvent in this extraction because it is a non-toxic solvent. From the previous study, Annona Muricata Leaves have effectiveness as an antiinflammatory, anticancer and also antioxidant. Response Surface Methodology (RSM) and Artificial Neural Network (ANN) were used in this research to investigate and compare the performance of RSM and ANN in optimization total yield, antioxidant activity and total phenolic content from extract of Annona Muricata Leaves using SFE technique. All the responses (optimization total yield, antioxidant activity and total phenolic content) were modeled and optimized as functions of four independent parameters with were temperature, pressure, size of particle and percentage of co-solvent using RSM and ANN. the coefficient of determination (R2) and root mean square error (RMSE) were employed to compare the performance of both modelling tools. From the results, ANN show higher predictive potential compare to RSM with higher correlation coefficient 0.9594, 0.9876, 0.917 for total yield, antioxidant activity and total phenolic content respectively. ANN also shows the lower RMSE compare to RSM with 0.461 for total yield, 0.998 for antioxidant activity and 23.697 for total phenolic content. Thus, as conclusion ANN model could be a better alternative in data fitting for SFE for extraction of total yield, antioxidant activity and total phenolic content from Annona Muricata Leaves. |
|---|---|
| Huomautukset: | https://ir.uitm.edu.my/id/eprint/81543/1/81543.pdf |