Developing a CBR-based adjudication system for fatal construction industry occupational accidents. Part I: Building the system framework

doi:10.1016/j.eswa.2009.12.028

Expert Systems with Applications

Volume 37, Issue 7, July 2010, Pages 4867-4880

https://doi.org/10.1016/j.eswa.2009.12.028 Get rights and content

Abstract

A framework for a decision-support system for adjudicating construction industry occupational accidents is developed using case-based reasoning (CBR) with a nearest-neighbor retrieval (NNR) search mechanism. One hundred thirty-three guilty verdicts of trial court judgments resulting from fatal construction occupational accidents (COAs) with injuries/deaths are collected, and 26 attributes, including 17 problem attributes (PAs) and nine solution attributes (SAs), are identified to describe the causalities between the accidents’ characteristics and the adjudgment results. Interpretive structural modeling (ISM) is used to build a three-layer hierarchy structure and to classify the 17 PAs into four aspect subsets (adjudgment background, accident condition, working environment and defendant). Each aspect and PA is weighted by using the AHP (analytic hierarchical process). Filter rules (FRs) for construction accidents and adaptation rules (ARs) to adjust for differences in accidents are formulated. The proposed system framework provides a platform for engineering professionals to understand the jurisprudence of occupational injuries/deaths in the construction industry and also serves as a reference to attorneys and justices. Additionally, the decision-support system may also educate the public in liability issues involved in COAs. An operational system is now under development based on the proposed system framework.

Introduction

A fatal injury or death of a worker or member of the general public on a construction site poses a substantial risk to the construction industry professional. Construction occupational accidents (COAs) not only endanger the lives of workers and affect their families but also delay construction project schedules, damage equipment and cause other societal and economic losses. In this paper, the term “fatal COA” means an accident involving: (1) death or (2) injury of at least three workers for one or more lost workdays. The fatal COA must be reported within 24 h to the appropriate inspection agency.

Once the project owner experiences a fatal COA because of his/her own negligence, a lawsuit seeking a large award is likely to follow. The responsible parties may be legally liable. The causes of a COA involving various aspects extensively are complicated and result in difficulty of determining the liability. This is especially true for project owners and engineering staff who lack a legal background, so that predicting the adjudication results from an abstruse law clause is extremely difficult.

Because the adjudication results of a fatal COA may be influenced by variables including adjudgment background, accident condition, working environment and defendants, it cannot be predicted simply in accordance with laws and regulations. Because predicting the adjudication results of a fatal COA is beneficial to court defense strategic planning, how to obtain accurate adjudication prediction has became one of the most important issues for construction practitioners. Similar COAs in the past provide comprehensive and effective information to practitioners. Therefore, development of a systematic database composed of fatal COA adjudications of past cases will help in the prediction of adjudication results for new fatal COA adjudgments.

As the cause of fatal COAs may be extremely complicated, determining the liability of the responsible parties may be difficult. Therefore, this study focuses on the legal issues accompanying the fatal COAs and proposes a CBR-based framework of a fatal COA adjudication system based on previous judgments to provide a platform for construction practitioners to understand the jurisprudence of fatal COAs and also to serve as a reference for attorneys and justices. To implement CBR, attributes of construction accident causalities are identified, the rules among the attributes and the verdicts are built, and a framework of a fatal COA adjudication system based on previous cases is developed to provide a reference in future fatal COA cases.

Section snippets

Construction occupational accidents

For COAs, most studies have addressed the issues of accident causation and safety control. Stanton and Willenbrock (1990) established a conceptual framework consisting of fundamental safety and health, management control, and management-information-system (MIS) concepts. The safety MIS furnishes project managers and supervisors with the timely and complete information they need to respond to safety and health problems and hazards as they occur. The framework serves as the analytical basis for

Basic principle of CBR

CBR is a problem-solving paradigm for solving new problems based on previously solved problems (Aha, 1998). CBR simulates human-thinking processes and problem-solving strategies. For example, a person experiencing a problem tends to evaluate possible solutions by referring to similar situations experienced previously. Derived from the processes employed by humans to solve problems by drawing from experience, CBR can be used to develop a framework of a fatal COA adjudication system by drawing

Developing the COA adjudication system

Fig. 2 depicts the procedure for developing the proposed fatal COA adjudication system using CBR. The entire procedure can be divided into six recurring steps as described below.

Step 1.
Collecting the cases: Previous fatal COA adjudgments are collected and analyzed to identify the attributes describing the causalities of each case. The attributes are then categorized into problem attributes and solution attributes based on their cause–effect relationships.
Step 2.
Developing the case database: The attribute

Conclusions

As the causes of fatal COAs are extremely complicated, determining liability is difficult. This study focused on the legal issues resulting from fatal COAs and developed an adjudication system framework for fatal COAs by applying the CBR concept. One hundred thirty-three guilty verdicts of trial court judgments resulting from fatal COAs with injuries/deaths were collected. The cases showed that factory buildings, apartment buildings, and office buildings are the top three types of projects for

Acknowledgements

The authors appreciate the National Science Council of the Republic of China, Taiwan for financially supporting the research under Contract No. (NSC93-2211-E-224-024). Special thanks go to all survey participants and reviewers of the paper.

References (32)

D.W. Aha
The omnipresence of case-based reasoning in science and application
Knowledge-based Systems
(1998)
M.Y. Cheng et al.
Fuzzy case-based reasoning for coping with construction disputes
Expert Systems with Applications
(2009)
J.S. Chou
Web-based CBR system applied to early cost budgeting for pavement maintenance project
Expert Systems with Applications
(2009)
G.H. Hong et al.
An effective supplier selection method for constructing a competitive supply-relationship
Expert Systems with Applications
(2005)
H.C. Huang
Designing a knowledge-based system for strategic planning: A balanced scorecard perspective
Expert Systems with Application
(2009)
P. Humphreys et al.
Using case-based reasoning to evaluate supplier environmental management performance
Expert Systems with Applications
(2003)
C. Johnson
Software tools to support incident reporting in safety-critical systems
Safety Science
(2002)
D.Y. Kim et al.
Structuring the prediction model for project performance for international construction projects: A comparative analysis
Expert Systems with Applications
(2009)
Y.T. Lai et al.
AHP- and simulation-based budget determination procedure for public building construction projects
Automation in Construction
(2008)
H. Li
Case-based reasoning for intelligent support of construction negotiation
Infrastructure Management
(1996)

H.J. Wang et al.

Decision support model based on case-based reasoning approach for estimating the restoration budget of historical buildings

Expert Systems with Applications

(2008)

D. Arditi et al.

Using case-based reasoning to predict the outcome of construction litigation

Computer-Aided Civil and Infrastructure Engineering

(1999)

W.T. Chen et al.

Using factor analysis to assess route construction priority for common duct network in Taiwan

Journal of Marine Science and Technology

(2008)

T.F. Chiu

An application of hierarchy-oriented case-based reasoning in the pilot production

Chung Hua Journal of Management

(2001)

Chou, K., & Chen, W. T. (2003). Using CBR to build an adjudication system for construction accidents. In Proceedings of...

Chua, D. K. H., & Goh. Y. M. (2002). Application of case based reasoning in construction safety planning. In...

Cited by (29)

Case-based reasoning approach for decision-making in building retrofit: A review
2024, Building and Environment
The rapid development of computer science has brought inspirations to building retrofit. Artificial intelligence (AI) provides more possibilities in decision-making for building retrofit, could be regarded as an alternative strategy compared to the abundant research time spent in the early decision-making stage of traditional retrofit approaches. This paper reviews the application of the statistic algorithm and AI approach, including CBR, in building retrofit decision-making, and the essential process of CBR, such as workflow, similarity degree calculation method, weight factors correction manner, and input or output content using building design to provide a synthetic overview of CBR utilisation in the building retrofit realm. Among those different models, Case-Based Reasoning (CBR) is valuable in providing references and avoiding possible failures, which is a promising approach for building retrofit. Yet, current research mainly focused on its utilisation to solve specific issues. There is still a lack of systematically summarised research on Case-Based Reasoning solution. Therefore, this study analyses the methods used for CBR approach in the field of building retrofit decision-making process, aiming to find the characteristics of internal commonness. It concludes that CBR has two significant impact factors: similarity attribute type and similarity calculation manner, which determines the judgement process. The results show that the CBR solution has great application potential in further building retrofit design.
Using cased based reasoning for automated safety risk management in construction industry
2023, Safety Science
The purpose of this study is to develop a CBR-based platform that integrates all steps of safety risk management (SRM) for the realization of automation in construction safety risk management. To realize this purpose, accident data from 2015 to 2020 in China has been collected and analyzed. Based on the collected data, this study adopts system thinking and stakeholder theory to establish an accident attribute system for accurate and comprehensive case representation, which was usually ignored in the previous study. Following case representation, the development process of case-based reasoning (CBR) is introduced in detail. The core of CBR—case retrieval is designed with the k-Nearest Neighbor (k-NN) algorithm and rough set theory to improve retrieval accuracy. In terms of case reuse and revise, a hybrid risk response model based on historical experience and risk factor control is proposed. Finally, the practical application of this study is illustrated with a specific construction project. The findings of this study confirm the feasibility of machine learning in improving safety performance at construction sites. Construction accidents can be effectively prevented by identifying the potential safety risks, and employing on-site management.
Modeling classification of textile engineering problems
2021, Advances in Modeling and Simulation in Textile Engineering: New Concepts, Methods, and Applications
Modeling is a diverse concept that comprises different techniques that can be adopted to solve problems using engineering knowledge and principles of physical processes. In textile engineering, different problems can be approached using numerous tools, and choosing the right techniques is a very important step toward solving a problem. There are many modeling classifications, but, in this chapter, more attention is tailored to typical problems in textile engineering. This chapter will explore different modeling methods such as mathematical modeling, numerical modeling, analytical modeling, and case-based reasoning models that employ artificial intelligence to predict future events from current or previous data. This chapter is aimed at abstractively describing different cases in textile engineering that can be solved with these modeling tools.
Safety assessment in megaprojects using artificial intelligence
2019, Safety Science
Citation Excerpt :
If it is not, the introduced case will be revised to get a more suitable outcome while predicting current problems. In the last phase of CBR, each output will be assessed and retained in the case base for future work (Chen et al., 2010). In the retrieving step, CBR takes the problems and matches the features of cases with the instances in the case base.
Record keeping systems are gaining more importance in addressing safety problems in megaprojects. The information recorded is being converted into large data domains since it has become necessary to examine problems down to the last detail to deal with them properly. Due to a high number of attributes and the type of information, the data has a high level of heterogeneity. The aim of this paper is to propose an innovative safety assessment methodology to predict the possible scenarios and determine preventative actions. The study introduces predictive models based on factual information and shows how to deal with the safety data which has a significant level of heterogeneity. Latent Class Clustering Analysis (LCCA) was performed to reduce the heterogeneity and extract homogenous subgroups from the data. For predictive purposes, Artificial Neural Network (ANN) and Case-Based Reasoning (CBR) were employed to estimate the outcome of incidents in terms of severity. CBR gave promising results and exhibited better performance than ANN. CBR achieved results in 86% of the test cases with 18% error at most. Moreover, the overall prediction accuracy of fatal incidents was equal to 86.33%. As a final step, the study presented preventative actions to eliminate safety failures. Ultimately, the proposed methodology can assist construction industry professionals in examining future safety problems by utilizing the collected large scale data. Furthermore, the study provides necessary preventative measures to be implemented before and during the construction stage.
An optimization-based decision tree approach for predicting slip-trip-fall accidents at work
2019, Safety Science
Slip-trip-fall (STF) accident is one of the leading causes of injuries. Therefore, prediction of STF is necessary prior to its occurrence at workplaces. Although there exist a number of studies analysing STFs, machine learning (ML)-based approaches for both predicting STF and analysing its factors remain an unexplored area of research. Therefore, the aim of the study is to develop a novel methodology for prediction of STF occurrences using decision tree (DT) classifiers, namely C5.0, classification and regression tree (CART) and random forest (RF). The parameters of the classifiers are optimized using two state-of-the-art optimization algorithms, namely particle swarm optimization (PSO), and genetic algorithm (GA) for enhanced prediction accuracy. Experimental results reveal that PSO-RF algorithm produces the best accuracy as compared to others. Finally, the proposed method generates a set of 20 interpretable safety decision rules explaining the factors behind the occurrences of STFs.
Experience mining based on case-based reasoning for dispute settlement of international construction projects
2019, Automation in Construction
Citation Excerpt :
Considering the limitations in existing dispute settlement methods, therefore, it is necessary to conduct further research that addresses dispute problems from a new perspective. CBR, as a decision support system based on the psychological theory of human reasoning [18], has been progressively used for project management [17,40]. Its main purpose is to hold a minimum amount of information relating to past (historical) project disputes in a single, well-structured, repository so that many relevant aspects to a similar new (target) project situation are easily identified and retrieved for consideration before taking decisions and also enabling all sources of a particular dispute to be analyzed simultaneously [15].
Considering the experience-orientation of the construction industry, the valuable experience of similar historical cases is important reference to resolve new problems, while research concerning this issue in dispute settlement is still relatively scarce. The objectives of this study are to (1) propose a pragmatic method for generating dispute settlement for international construction projects based on Case-Based Reasoning (CBR); and (2) validate the CBR model by a specific dispute case. To achieve the research objectives, successful historical cases are collected, and attributes that influence dispute-related problems are derived. A two-step refinement process is then conducted to extract similar cases. Finally, a dispute case in Ethiopia is used to demonstrate the application of developed model. This innovative dispute settlement model enriches the theoretical framework in the field of experience mining for decision maker, and the selected experiences provide an effective reference to resolve new dispute problems and reduce the transaction costs of dispute settlement.

View all citing articles on Scopus

View full text

Developing a CBR-based adjudication system for fatal construction industry occupational accidents. Part I: Building the system framework

Abstract

Introduction

Section snippets

Construction occupational accidents

Basic principle of CBR

Developing the COA adjudication system

Conclusions

Acknowledgements

Knowledge-based Systems

Expert Systems with Applications

Expert Systems with Applications

Expert Systems with Applications

Expert Systems with Application

Expert Systems with Applications

Safety Science

Expert Systems with Applications

Automation in Construction

Infrastructure Management

Expert Systems with Applications

Using case-based reasoning to predict the outcome of construction litigation

Computer-Aided Civil and Infrastructure Engineering

Using factor analysis to assess route construction priority for common duct network in Taiwan

Journal of Marine Science and Technology

An application of hierarchy-oriented case-based reasoning in the pilot production

Chung Hua Journal of Management