GA‐based multi-level association rule mining approach for defect analysis in the construction industry

Identifying the correlations between the attributes of severe accidents could be vital to preventing them. If such relationships were known dynamically, it would be possible to take preventative actions against accidents. The paper aims to develop an analytical model that is adaptable for each type of data to create preventative measures that will be suitable for any computational systems. The present model collectively shows the relationships between the attributes in a coherent manner to avoid severe accidents. In this respect, Association Rule Mining (ARM) is used as the technique to identify the correlations between the attributes. The research adopts a positivist approach to adhere to the factual knowledge concerning nine different accident types through case studies and quantitative measurements in an objective nature. ARM was exemplified with nine different types of construction accidents to validate the adaptability of the proposed model. The results show that each accident type has different characteristics with varying combinations of the attribute, and analytical model accomplished to accommodate variation through the dataset. Ultimately, professionals can identify the cause-effect relationships effectively and set up preventative measures to break the link between the accident causing factors.

Section: Analytical Models For the Construction Safetymentioning

confidence: 99%

An Association Rule Mining Model for the Assessment of the Correlations Between the Attributes of Severe Accidents

Ayhan

Doğan

Tokdemir

2020

“…Previous studies have applied ARM to construction defect analyses. For example, Cheng et al (2015) proposed a genetic algorithm-based approach that incorporated a hierarchical concept of construction defects to discover useful information in a construction defect database and to identify relationships between these defects. Lee et al (2016) used ARM to quantify causality between defect causes and utilized Social Network Analysis (SNA) to identify indirect causalities among defects in concrete.…”

Section: Data Miningmentioning

confidence: 99%

“…However, the correlations between inspection grades and defects and the influential power of particular defects are associated with construction quality and costs; these correlations are worthy of further investigations and analyses. Cheng et al (2015) believed that in the construction industry, defective building works will lead to time and cost overruns in the project, and disputes may arise among the construction participants in the construction and management stages, and also that, as of today, not a single analysis model is able to sufficiently retrieve useful information from the database of building defects.…”

Section: Introductionmentioning

confidence: 99%

Examining Association Between Construction Inspection Grades and Critical Defects Using Data Mining and Fuzzy Logic

Lin

Fan²

2018

This paper explores the relations between defect types and quality inspection grades of public construction projects in Taiwan. Altogether, 499 defect types (classified from 17,648 defects) were found after analyzing 990 construction projects from the Public Construction Management Information System of the public construction commission which is a government unit that administers all the public construction. The core of this research includes the following steps. (1) Data mining (DM) was used to derive 57 association rules which altogether contain 30 of the 499 defect types. (2) K-means clustering was used to regroup the 990 projects of two attributes (defect frequency and original grading score of each project) into four new quality classes, so the 990 projects can be more evenly distributed in the four new classes and the correctness and reliability of the following analyses can be ensured. (3) Finally analysis of variance (ANOVA), fuzzy logic, and correlation analysis were used to verify that the aforementioned 30 defect types are the important ones determining inspection grades. Results of this research can help stakeholders of construction projects paying more attention on the root causes of the critical defect types so to dramatically raise their management effectiveness.

“…Liao and Perng (2008) found through association rule mining that the effect of rain on the occurrence of fatalities is considerably significant. In terms of project quality management, Cheng et al (2015) proposed a genetic algorithm-based approach to discover multi-level patterns of construction defects for quality improvement. The SPC method dynamically monitors significant changes in key indicators by using statistical tools; this method was introduced by Shewhart (1931).…”

Section: Association Rule and Spc Usage In Construction Industrymentioning

confidence: 99%

A real-time control approach based on intelligent video surveillance for violations by construction workers

Guo

Xiong

Gong

2018

Abstract. The unsafe behavior of workers is the main object of construction safety management, in which violations require increased attention due to their pernicious consequences. However, existing studies have merely discussed violations separately from unsafe behaviors. To respond quickly to workers' violations on site, this study proposes a real-time control approach based on intelligent video surveillance. First, scenes reflecting unsafe behaviors are automatically acquired through camera-based behavior analysis technology. Meanwhile, the time corresponding to the construction phase is recorded. Second, the temporal association rule model of worker's unsafe behavior is constructed, and the rule "construction phase→unsafe behavior" is determined by the Apriori algorithm to identify target behaviors necessary for critical control in different construction phases. Finally, statistical process control is used to find the trends of violations with frequency and mass characteristics through the dynamic monitoring of target behavior. In addition, real-time alerts of these unsafe acts are produced simultaneously. A pilot study is conducted on the cross-river tunnel project in Wuhan city, Hubei, China, and the violations related to construction machineries is proven to be controllable. Thus, the proposed approach promotes behavioral safety management on construction since it effectively controls workers' violations by real-time monitoring and analysis.