Optimization of total phenolic content extracted from Garcinia mangostana Linn. hull using response surface methodology versus artificial neural network
Abstract
The optimum conditions of extraction time, solid to solvent ratio, and methanol concentration for extracting total phenolic content (TPC) from mangosteen (Garcinia mangostana L.) hull powder have been investigated using response surface methodology. The experimental data obtained was adequately fitted into second-order polynomial models with coefficient of determination (R²) of 0.897. Response surface analysis showed that the optimal extraction parameters which gave a maximum TPC yield of 140.66mg gallic acid equivalent (GAE)/g powder were from a 2h extraction with 0.05 solid to solvent ratio and at 69.77% methanol concentration. Analysis using artificial neural network (ANN) predicted data which showed a higher R² value of 0.945 and average absolute deviation (ADD) values of 4.01% versus 5.37% for the RSM. This suggests that ANN is a better modelling technique for nonlinear data for predicting TPC extracted from mangosteen hull powder compared to the response surface methodology (RSM).
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The R2 and R2 adj obtained (0.836 and 0.794, respectively) support the acceptability of the model and allow its use for optimization purposes.
“The R2 and R2 adj obtained (0.836 and 0.794, respectively) support the acceptability of the model and allow its use for optimization purposes since the mathematical model fits above 70 % of the response behavior in terms of the R2 adj as established by Cheok et al. (2012), [6].”
From Optimized microwave-assisted azadirachtin extraction using response surface methodology (2024) · cites this paper as Cheok et al. (2012), [6]
Cites
Chirinos, R., Rogez, H., Campos, D., Pedreschi, R., & Larondelle, Y. (2007) · Separation and Purification Technology · doi:10.1016/j.seppur.2006.12.005 · Cited by 320 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Optimized microwave-assisted azadirachtin extraction using response surface methodology
Martínez-Castro, R., Flórez-Santiago, J., Valle-Molinares, R., Cabrera-Barraza, J., & Espitia-Almeida, F. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e31504 · Cited by 6 · see citing works
“The R 2 and R 2 adj obtained (0.836 and 0.794, respectively) support the acceptability of the model and allow its use for optimization purposes since the mathematical model fits above 70 % of the response behavior in terms of the R 2 adj as established by Cheok et al. (2012), [6].”
MethodInfluential
- Authors
- Cheok, C. Y., Chin, N. L., Yusof, Y. A., Talib, R. A., & Law, C. L.
- Affiliations
- Universiti Putra Malaysia (MY)
- University of Nottingham Malaysia Campus (MY)
- Corresponding author
- Chin, Nyuk Ling
- Venue
- Industrial Crops and Products
- Publisher
- Elsevier BV
- Published
- 2012-11
- Volume
- 40
- Pages
- 247-253
- ISSN
- 0926-6690 (ISSN-L)
- OpenAlex
- W2029445284
- Cited by
- 114
- References
- 1
- Citations by year
- 2026: 6 · 2025: 4 · 2024: 7 · 2023: 7 · 2022: 15 · 2021: 7 · 2020: 9 · 2019: 8 · 2018: 11 · 2017: 10 · 2016: 9 · 2015: 5 · 2014: 9 · 2013: 5 · 2012: 2
- FWCI
- 7.66
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Industrial Crops and Products (publishedVersion)
- Topics
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Natural Compound Pharmacology Studies
- Health Sciences › Medicine › Biochemistry › Phytochemicals and Antioxidant Activities
- Life Sciences › Agricultural and Biological Sciences › Food Science › Agricultural and Biological Research
- Keywords
- Garcinia mangostana, total phenolic content, methanol extraction, solid-to-solvent ratio, extraction time, artificial neural networks, response surface methodology, gallic acid equivalent, fruit waste valorization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
