Combining Hard and Soft Voting Machine Learning Algorithms for Soil Classification
Keywords: Soil Classification, Machine Learning, Voting Ensemble, Balanced accuracy
TL;DR: This paper talks about how multiple machine learning algorithm are applied and evaluated in place of traditional methods in soil classification, in the field of Geotechnical Engineering.
Abstract: Civil engineers need to possess knowledge about soil properties and structure through soil classification to construct reliable and long-lasting structures. However, traditional soil classification methods are both expensive and time-consuming. Recently, machine learning has become increasingly popular in solving complex problems in Geotechnical Engineering, leading to novel approaches for automating soil classification. This research evaluates the effectiveness of various machine learning algorithms, including Multinomial Logistic Regression (MLR), Gaussian Naive Bayes (GNB), Extreme Gradient Boosting (XGBoost), Random Forest, and Artificial Neural Network-Multilayer Layer Perceptron (ANN-MLP), in classifying soils. The study also implemented Hard and Soft Voting Ensemble Learners. Each model was quantitatively evaluated and compared using various metrics. Empirical findings suggest that all models are effective in classifying soils, with the hard voting model outperforming the others.
Submission Category: Machine learning algorithms
Submission Number: 28
Loading