Safety Risk Evaluations of Deep Foundation Construction Schemes Based on Imbalanced Data Sets

Abstract

Safety risk evaluations of deep foundation construction schemes are important to ensure safety. However, the amount of knowledge on these evaluations is large, and the historical data of deep foundation engineering is imbalanced. Some adverse factors influence the quality and efficiency of evaluations using traditional manual evaluation tools. Machine learning guarantees the quality of imbalanced data classifications. In this study, three strategies are proposed to improve the classification accuracy of imbalanced data sets. First, data set information redundancy is reduced using a binary particle swarm optimization algorithm. Then, a classification algorithm is modified using an Adaboost-enhanced support vector machine classifier. Finally, a new classification evaluation standard, namely, the area under the ROC curve, is adopted to ensure the classifier to be impartial to the minority. A transverse comparison experiment using multiple classification algorithms shows that the proposed integrated classification algorithm can overcome difficulties associated with correctly classifying minority samples in imbalanced data sets. The algorithm can also improve construction safety management evaluations, relieve the pressure from the lack of experienced experts accompanying rapid infrastructure construction, and facilitate knowledge reuse in the field of architecture, engineering, and construction.

Research Trends on Machine Learning in Construction Management: A Scientometric Analysis

“…Hence, construction safety is a top priority on all job sites, and machine learning offers a high-tech solution to this problem. That is why applying machine learning in construction safety has been attracted numerous researches to date [8,14,[19][20][21][22][23][24][25][26][27][28]. In the study [21], neural network and decision tree analyses were implemented to assess the unsafe act of not anchoring harnesses while working on a scaffold of 40 migrant workers, whereas, with an accident data from the Singapore construction industry, a neural network analysis was performed on a quantitative occupational safety and health management system audit [22].…”

Analysis of influencing factors of construction safety of prefabricated buildings based on Fuzzy-ISM and MICMAC

“…Liu Guanquan et al [4] used DEMATEL-ISM method to analyze the mutual in-fluence degree and logical structure of influencing factors of prefabricated con-struction, and put forward suggestions. Duan Yonghui et al [5] used structural equation model to calculate the weight of construction risk indicators and ana-lyze potential influencing factors. Most of the above studies build the assembly-type construction safety risk assessment model through cloud model, fuzzy comprehensive evaluation method and analytic hierarchy process, so there is strong subjectivity in the analysis of risks, and there is a lack of risk relationship re-search, that is, most scholars regard risk factors as a single individual, ignoring the inherent hierarchical relationship, transmission path and size of risks.…”

Safety Evaluation Modelling of Hydrogen Energy Industrial Chain for Transportation-energy Integration System in China

“…Before establishing the necessary safety measures, safety evaluation can grasp the possible types of hazards, the degree of hazards and the consequences of hazards in the system by analyzing them quantitatively and qualitatively. Various safety evaluation methods have been widely used in different field, Binary particle swarm optimization algorithm, Adaboost-enhanced support vector machine classifier and ROC curve are used in evaluating the safety of construction [3]. Low-level theory is used to interpret the evaluation of road safety [4].…”