Estimation of algal colonization growth on mortar surface using a hybridization of machine learning and metaheuristic optimization

• Published in: Sadhana (Bangalore) Vol. 42; no. 6; pp. 929 - 939
• Main Authors: Tran, Thu-Hien, Hoang, Nhat-Duc
• Format: Journal Article
• Language: English
• Published: New Delhi Springer India 01.06.2017; Springer Nature B.V
• Subjects: Algae; Artificial intelligence; Carbonation; Cements; Decision making; Engineering; Heuristic methods; Information dissemination; Least squares method; Machine learning; Mean square values; Optimization; Optimization techniques; Parameter identification; Porosity; Regression analysis; Root-mean-square errors; Support vector machines; Surface roughness; biodegradation; Alga; machine learning; least squares support vector regression; flower pollination algorithm
• ISSN: 0256-2499; 0973-7677
• DOI: 10.1007/s12046-017-0652-6

Estimation of the algal colonization growth on façade structure can provide useful information for the task of building maintenance. This research proposes a machine learning method based on the least squares support vector regression (LS-SVR) for modelling the growth time of the green alga Klebsormidium flaccidum on mortar surfaces. Furthermore, to identify an appropriate set of the LS-SVR hyper-parameters, the flower pollination algorithm (FPA) is employed as an optimization technique. The characteristics of the mortar samples, including surface roughness, porosity, surface pH, carbonated condition and type of cement, are employed as input factors for the analysing process. This study relies on a dataset that records 539 laboratory experiments to establish a hybrid model of the LS-SVR and the FPA. The cross-validation process reveals that the proposed method can successfully capture the functional relationship between the algal colonization growth and its influencing factors with a satisfactory outcome (the coefficient of determination R 2  = 0.94 and the root mean square error RMSE = 4.55). These facts demonstrate that the hybrid model is a promising tool for assisting the decision-making process in building maintenance planning.