The performance of six neural-evolutionary classification techniques combined with multi-layer perception in two-layered
- PDF / 3,128,082 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 41 Downloads / 147 Views
ORIGINAL ARTICLE
The performance of six neural‑evolutionary classification techniques combined with multi‑layer perception in two‑layered cohesive slope stability analysis and failure recognition Chao Yuan1 · Hossein Moayedi2,3 Received: 6 May 2019 / Accepted: 30 May 2019 © Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract Six population-based hybrid algorithms are applied to train the multilayer perceptron (MLP) to improve the classification accuracy, in the stability assessment. A complex problem of slope stability against failure is designed in Optum G2 software. Considering four key factors of shear strength of clayey soil, slope angle, the ratio of foundation distance from the slope to the foundation length, and the applied surcharge, the stability or failure of the proposed slope are anticipated. The provided data are used to develop the MLP combined with biogeography-based optimization (BBO), ant colony optimization (ACO), genetic algorithm (GA), evolutionary strategy (ES), particle swarm optimization (PSO) and probability-based incremental learning (PBIL). The results revealed that the BBO-MLP with the obtained area under the receiving operating characteristic curve (AUROC) of 0.995 and the classification ratio (CR) of 92.4% is the most accurate model followed by GA-MLP (AUROC = 0.960 and CR = 84.3%), PBIL-MLP (AUROC = 0.948 and CR = 79.3%), ES-MLP (AUROC = 0.879 and CR = 65.7%), PSO-MLP (AUROC = 0.878 and CR = 71.3%), and ACO-MLP (AUROC = 0.798 and CR = 60.7%). Keywords Classification · Evolutionary algorithms · Optum G2 · PBIL · BBO
1 Introduction The utilization of mathematical solutions and engineering computer software raised many improvements in these fields. Most recent investigations focused on enhancing the stability analysis through various novel mathematical solutions such as probabilistic stability analysis (e.g., Xiao et al. [1] and Li et al. [2]), robust design (e.g., Xu et al. [3] and Khoshnevisan et al. [4]), random field theory (e.g., Zhou et al. [5] and Li et al. [6]) or simplified design solution charts (e.g., Abusharar and Han [7], Georgiadis [8], Li et al. [9] and Qian et al. [10]). Additionally, by considering * Hossein Moayedi [email protected] 1
College of Architecture and Civil Engineering, Xi’an University of Science and Technology, Xi’an 710054, Shaanxi, China
2
Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam
3
Faculty of Civil Engineering, Ton Duc Thang University, Ho Chi Minh City, Vietnam
some constraints (e.g., time and cost, particularly for complex designs), it has been demonstrated that the application of numerical analysis cannot always be so favorable and warranted. Consequently, the utilization of slope stability design charts could be introduced as a convenient way to determine the N2c of the slope. One of the novel methods that can be used to analyze the slope conditions is an artificial neural network (ANN) that was introduced firstly by McCulloch and Pit
Data Loading...
