Differentiation of rubber cup coagulum through machine learning
College
College of Science
Department/Unit
Biology
Document Type
Article
Source Title
Scientia Agriculturae Bohemica
Volume
50
Issue
1
First Page
51
Last Page
55
Publication Date
3-1-2019
Abstract
A support vector machine classification algorithm was formulated to differentiate rubber cup coagulum according to the type of acid coagulant used. Two classification models were established, a binary classification algorithm and a model that can identify if formic, acetic, sulfuric acid, or no acid was used to induce coagulation. The models were based on the properties of the rubber cup coagulum that are easy to measure, such as tensile strength, water contact angle, and density. The binary classification model, which differentiates the industry-accepted formic acid-coagulated rubber cup coagulum from those which are not, exhibited satisfactory reliability, as evidenced by a 92% overall prediction accuracy and 71.4% cross-validation accuracy. Moreover, it was also determined that the rubber properties density, and water contact angle were important contributors for the classification. Acid-induced rubber coagulation is an important post-harvest process that influences the resulting rubber quality. Thus, the accurate differentiation of the rubber samples is useful for quality assurance purposes, as well as in policy enforcement. © 2019 M.R.J. Nepacina et al., published by Sciendo 2019.
html
Digitial Object Identifier (DOI)
10.2478/sab-2019-0008
Recommended Citation
Nepacina, M. J., Foronda, J. F., Haygood, K. F., Tan, R. S., Janairo, G. C., Co, F. F., Bagaforo, R. O., Narvaez, T. A., & Janairo, J. B. (2019). Differentiation of rubber cup coagulum through machine learning. Scientia Agriculturae Bohemica, 50 (1), 51-55. https://doi.org/10.2478/sab-2019-0008
Disciplines
Biology
Keywords
Coagulants; Coagulation; Rubber plants--Analysis
Upload File
wf_no