Classification of Biodegradable Substances Using Balanced Random Trees and Boosted C5.0 Decision Trees

Abstract

Substances that do not degrade over time have proven to be harmful to the environment and are dangerous to living organisms. Being able to predict the biodegradability of substances without costly experiments is useful. Recently, the quantitative structure–activity relationship (QSAR) models have proposed effective solutions to this problem. However, the molecular descriptor datasets usually suffer from the problems of unbalanced class distribution, which adversely affects the efficiency and generalization of the derived models. Accordingly, this study aims at validating the performances of balanced random trees (RTs) and boosted C5.0 decision trees (DTs) to construct QSAR models to classify the ready biodegradation of substances and their abilities to deal with unbalanced data. The balanced RTs model algorithm builds individual trees using balanced bootstrap samples, while the boosted C5.0 DT is modeled using cost-sensitive learning. We employed the two-dimensional molecular descriptor dataset, which is publicly available through the University of California, Irvine (UCI) machine learning repository. The molecular descriptors were ranked according to their contributions to the balanced RTs classification process. The performance of the proposed models was compared with previously reported results. Based on the statistical measures, the experimental results showed that the proposed models outperform the classification results of the support vector machine (SVM), K-nearest neighbors (KNN), and discrimination analysis (DA). Classification measures were analyzed in terms of accuracy, sensitivity, specificity, precision, false positive rate, false negative rate, F1 score, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUROC).

Structural complexity characterizes fine‐scale forest conditions used by Pacific martens

“…We separated the dataset into random iterations of training (90%) and test data (10%) and trained the boosted C5.0 algorithm using 100 decision trees. The algorithm had 2 main meta parameters, including number of trees and minimum number of samples (MinCases) placed in at least 2 splits (Elsayad et al 2020). We used early stopping to prevent model overfitting (Caruana et al 2000, Jabbar and Khan 2015), which reduced the final number of trees.…”

Near-infrared spectroscopy for early selection of waxy cassava clones via seed analysis

“…C5.0 is an algorithm based on decision trees ( Elsayad et al., 2020 ), which involve a set of decision nodes, among which the root and each internal node are labeled with a question ( Pradhan, 2013 ). The arcs descend from each root node to leaf nodes, where a solution to the associated issue is offered.…”

Comparison of machine learning algorithms applied to symptoms to determine infectious causes of death in children: national survey of 18,000 verbal autopsies in the Million Death Study in India

“…The features that do not contribute to the splits are removed from the final model. While C5 algorithms are easy to implement and interpret, it requires categorical (ordinal/nominal) data as target variable and may not work well on small datasets [ 31 , 36 ].…”