Statistical and nature-inspired metaheuristics analysis on flexirubin production

• Main Authors: Suhaimi, Siti Nurulasilah, Hasan, Shafaatunnur, Shamsuddin, Siti Mariyam, Ahmad, Wan Azlina, Kulandaisamy Veni, Chidambaram
• 格式: Article
• 語言: English
• 出版: International Center for Scientific Research and Studies 2018
• 主題: Q Science (General)
• 在線閱讀: http://eprints.utm.my/id/eprint/84599/1/SitiNurulasilahSuhaimi2018_StatisticalandNatureinspiredMetaheuristicsAnalysisonFlexirubin.pdf; http://eprints.utm.my/id/eprint/84599/; http://www.home.ijasca.com/article-in-press/volume-10-2018/vol-10-2/

Nowadays, demand for natural pigments has increased dramatically due to the awareness of the toxicity of some synthetic pigments. Because of the high cost of growth medium for natural pigment production, various studies have been carried out to explore medium which are less costly, such as agricultural waste. This study highlight on the application of firefly algorithm (FA) and bat algorithm (BA) in optimizing yellowish-orange pigment production (flexirubin) from the agricultural waste material. At present, response surface methodology (RSM) is the most preferred statistical method in optimizing pigment production. However, in the last two decades, nature-inspired metaheuristics approach has been used extensively in the fermentation process and have continually improve the efficiency in the optimization problem especially in pigment production. This study compared the analytics studies of RSM, FA and BA in the estimation of fermentation parameters (Lactose, Ltryptophan, and KH2PO4) in flexirubin production from Chryseobacterium artocarpi CECT8497T. All models provided similar quality predictions for the above three independent variables in term of flexirubin production with bat algorithm showing more accurate in estimation, with the coefficient value of 98.87% compare to RSM 98.20% and FA 98.38%.