Parametric analysis and soft-computing prediction of sweet potatoes ( Ipomoea batatas L ) starch drying using machine le
- PDF / 1,311,750 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 50 Downloads / 199 Views
Parametric analysis and soft‑computing prediction of sweet potatoes (Ipomoea batatas L) starch drying using machine learning techniques E. O. Oke1 · B. I. Okolo1 · O. Adeyi1 · F. N. Osuolale2 · P. C. Nnaji1 · C. Ude1 · J. Ayanyemi1 Received: 9 December 2019 / Accepted: 19 August 2020 © Springer Nature Switzerland AG 2020
Abstract This study is based on parametric selection and prediction of sweet potatoes starch drying using Regression Tree (RT), Support Vector Machine (SVM) and Neuro-Fuzzy (NF) soft-computing techniques. The drying experiments are conducted at Drying Temperature (DT): 40–60 °C, Drying Time (DTi): 0–780 min, Ambient Temperature (AT): 27.2–30 °C and Relative Humidity (RH): 70–80%. Exhaustive search model is used to determine the most and least relevant drying parameters. NF, RT and SVM programming codes are developed in Matlab 9.2 (2017a) with four, three and two-input variable combination NFs (4-1NF, 3-1NF and 2-1NF), RTs (4-1 RT, 3-1 RT and 2-1 RT) and SVMs (4-1SVM, 3-1SVM and 2-1SVM) for the prediction of the starch drying. Exhaustive NF parametric analysis results show that DT-DTi-AT and DT-DTi are the most influential combined variables for three and two variables combinations respectively. DTi and RH are also the most and least influential parameters, respectively. The 3-1NF with neighbourhood radius 0.7 gave the uppermost correlation coefficient (R2) 0.999; and the lowermost root mean square error as well as mean square error 0.0025 and 0.00000625 respectively. The results obtained show that exhaustive search and 3-1NF models are suitable for the prediction of sweet potatoes starch drying. Keywords Exhaustive search · Sweet potatoes · Starch drying · Neuro-fuzzy
1 Introduction Sweet potato (Ipomoea batatas L.) is a significant tuber crops in the world. China is globally ranked as the main producer of sweet potato; while Nigeria is categorised as the second producer in Africa and third in the world [1]. Sweet potato has been a high starch-yielding tuber crop with the advantage of harvesting twice in a year as cassava crop [2]. A high amount of sweet potato tuber harvested during the peak season is significantly deteriorating due to poor storability and low marketability. Recently, the government has emphasised the exportation of industrial product derived from agricultural produce in Nigeria. Thus, there is a need to transform the unprocessed sweet potato
into a more usable and refined form, such as dried sweet potato starch, for industrial applications. Starch is one of the essential ingredients in pharmaceutical, food, cosmetic and petroleum industries. Starch pastes are used as thickeners and other additive ingredients in food systems and pharmaceutical sectors [3–5]. It is a white and tasteless complex polymer, which is plentifully obtained in large quantities in roots and tubers such as cassava, yam, and potato [5–7]. Previous researches show that the starch from potato has a high hot paste viscosity, unlike cereal starches, which makes it preferable for the manufacture of adhesive
Data Loading...
