Artificial neural network incorporated decision support tool for point velocity prediction. Issue 1 (2nd January 2020)

• Record Type: Journal Article
• Authors: Simsek, Serhat; Genc, Onur; Albizri, Abdullah; Dinc, Semih; Gonen, Bilal
• Is Part Of: Journal of Business Analytics. Volume 3:Issue 1(2020)
• Page Start: 67
• Page End: 78
• Publication Date: 2020-01-02
• Subjects: Artificial neural networks -- decision support systems -- machine learning -- predictive modelling -- Bayesian network; Business intelligence -- Periodicals; Management -- Statistical methods -- Periodicals; Decision making -- Statistical methods -- Periodicals; 658.403
• DOI: 10.1080/2573234X.2020.1751569
• Languages: English
• ISSNs: 2573-234X

Abstract

ABSTRACT: This study aims to develop a decision support tool for identifying the point velocity profiles in rivers. The tool enables managers to make timely and accurate decisions, thereby eliminating a substantial amount of time, cost, and effort spent on measurement procedures. In the proposed study, three machine learning classification algorithms, Artificial Neural Networks (ANN), Classification & Regression Trees (C&RT) and Tree Augmented Naïve Bayes (TAN) along with Multinomial Logistic Regression (MLR), are employed to classify the point velocities in rivers. The results showed that ANN has outperformed the other classification algorithms in predicting the outcome that was converted into 10 ordinal classes, by achieving the accuracy level of 0.46. Accordingly, a decision support tool incorporating ANN has been developed. Such a tool can be utilized by end-users (managers/practitioners) without any expertise in the machine learning field. This tool also helps in achieving success for financial investors and other relevant stakeholders.