Full paper: A Bayesian model for real-time safety management in construction sites (original) (raw)

Application of Bayesian Networks to Analyze in Analyzing Incidents and Decision-Making

2005

Incident management requires a full understanding of the characteristics of incidents to accurately estimate incident durations and to help make more efficient decisions, reducing the impact of non-recurring congestion. The goal of this paper is to have an articulate description of incident clearance patterns and to represent these findings with formalisms based on Bayesian Networks (BNs). BNs can be an innovative tool for incident management practice and can be used to create dynamic estimation trees that are extracted in the presence of an incident, enabling operators to create case-specific incident management strategies. We introduce the use of BNs to the transportation field to better understand the prevailing circumstances of incidents. This can only be accomplished by considering the stochastic variation of the data and bi-directional induction in decision-making. After a comprehensive review of the application of BNs to our problem, the dependency relations among all variables in a BN that can be used for quantitative and qualitative analysis are also presented.

Development of an Expert Model to Assess Falls from Height Hazards in Construction Sites

Journal of Civil Engineering and Architecture, 2014

This paper reports on the current state of an ongoing research project which is aimed at implementing intelligent models for hardly predictable hazard scenarios identification in construction sites. As any programmatic actions cannot deal with the unpredictable nature of many risk dynamics, an attempt to improve the current approach for safety management in the construction industry will be presented in this paper. To this aim, the features offered by Bayesian networks have been exploited. The present research has led to the definition of a probabilistic model using elicitation techniques from subjective knowledge. This model, which might be meant as a reliable knowledge map about accident dynamics, showed that a relevant part of occurrences fall in the "hardly predictable hazards" category, which cannot be warded off by programmatic safety measures. Hence, more effort turned out to be needed in order to manage those hardly predictable hazardous scenarios. Consequently, further developments of this research project will focus on a real time monitoring system for the identification of unpredictable hazardous events in construction.

Decision Support Software for Probabilistic Risk Assessment Using Bayesian Networks

IEEE Software, 2000

Decision makers in all areas of life (including physicians, generals, scientists, bankers and politicians) must often assess and manage risk when there is little or no direct historical data to draw upon, or where relevant data is difficult to identify. The international credit crisis was not predicted by the world's leading financial analysts because they relied on models based on historical statistical data that could not adapt to new circumstances even when those circumstances (in this case the collapse of the mortgage sub-prime market) were foreseeable by experts with more intimate knowledge of the market place. The challenges are similarly acute when the source of the risk is novel: terrorist attacks, ecological disasters, major project failures, and more general failures of novel systems, market-places and business models.

International Journal on Recent and Innovation Trends in Computing and Communication Implementation of Knowledge-Based Expert System Using Probabilistic Network Models

The latest development in machine learning techniques has enabled the development of intelligent tools which can identify anomalies in the system in real time. These intelligent tools become expert systems when they combine the algorithmic result of root cause analysis with the domain knowledge. Truth maintenance, fuzzy logic, ontology classification are just a few out of many techniques used in building these systems. Logic is embedded in the code in most of the traditional computer program, which makes it difficult for domain experts to retrieve the underlying rule set and make any changes. These system bridge the gap by making information explicit rather than implicit. In this paper, we present a new approach for developing an expert system using decision tree analysis with probabilistic network models such as Bayes-network. The proposed model facilitate the process of correlation between belief probability with the unseen data by use of logical flowcharting, loopy belief propagation algorithm, and decision trees analysis. The performance of the model will be measured by evaluation and cross validation techniques.

Building probabilistic networks: "Where do the numbers come from?" - Guest editors' introduction

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2000

the relationships between them from domain experts is comparable, to at least some extent, to knowledge engineering for other artificial-intelligence representations and, although it may require significant effort, is generally considered doable. The last task in building a probabilistic network is to obtain the probabilities that are required for its quantitative part. This task often appears more daunting: "Where do the numbers come from?" is a commonly asked question. The three tasks in building a probabilistic network are, in principle, performed one after the other. Building a network, however, often requires a careful trade-off between the desire for a large and rich model to obtain accurate results on the one hand, and the costs of construction and maintenance and the complexity of probabilistic inference on the other hand. In practice, therefore, building a probabilistic network is a process that iterates over these tasks until a network results that is deemed requisite.

Building Probabilistic Networks: Where Do the Numbers Come From? --- a Guide to the Literature

the relationships between them from domain experts is comparable, to at least some extent, to knowledge engineering for other artificial-intelligence representations and, although it may require significant effort, is generally considered doable. The last task in building a probabilistic network is to obtain the probabilities that are required for its quantitative part. This task often appears more daunting: "Where do the numbers come from?" is a commonly asked question. The three tasks in building a probabilistic network are, in principle, performed one after the other. Building a network, however, often requires a careful trade-off between the desire for a large and rich model to obtain accurate results on the one hand, and the costs of construction and maintenance and the complexity of probabilistic inference on the other hand. In practice, therefore, building a probabilistic network is a process that iterates over these tasks until a network results that is deemed requisite.

Bayesian Network Modelling the risk analysis of complex socio technical systems

2006

The risk analysis of a system is a multidisciplinary process in constant evolution. Indeed, if a few years ago, analyses were limited at the technical level, it is today necessary to consider the system in a global way, by including Human beings and Organisations. But this involves an increasing complexity of the studied system, because of the widening of its limits and the diversity of considered disciplines. This article proposes a method to structure the knowledge in a decisionmaking model.

Probabilistic Model For Predicting Construction Worker Accident Based On Bayesian Belief Networks

IPTEK Journal of Proceedings Series, 2017

The construction industry has a very important role to the growth of a country. The unique characteristics and dynamic nature of the construction industry lead to a dangerous condition and prone to accidents. The death rate due to accidents in the construction industry in 2015 increased by 4% compared to 2014. The number of occupational accidents in Indonesia from year to year experienced a trend of an increase of 5%. Unsafe behavior of workers was the main cause of 88% of accidents in the construction site, 10% due to unsafe conditions, and 2% due to the unavoidable things. In addition, the complexity of construction equipment and unsafe environment significantly determined the type of accident and severity of injuries. This study aims to propose the probability model to predict the construction worker accidents in construction projects. To improve the accuracy of the assessment of workplace accidents, Bayesian Belief Networks used as a study analysis to represent the relationship among unsafe factors such as unsafe behavior factors, unsafe environment and unsafe equipment that lead to accidents. The data was collected through project site survey, questionnaire, and interview to OSH Managers in ten construction projects. The validation is done by applying the model on four case of a high rise building. This finding shows both the probability and accurate prediction of work accidents with APE mean is 4,564 that is useful to assist the practitioners and all stakeholders especially those directly involved in construction industry and to get some recommendations steps and preventive actions in order to minimize the occurrence of fatal work accidents and improve occupational safety and health (OSH) as well as to contribute knowledge about the factors that influence the occurrence of accidents.

Introducing Bayesian Networks 2.1 Introduction

Having presented both theoretical and practical reasons for artificial intelligence to use probabilistic reasoning, we now introduce the key computer technology for dealing with probabilities in AI, namely Bayesian networks. Bayesian networks (BNs) are graphical models for reasoning under uncertainty, where the nodes represent variables (discrete or continuous) and arcs represent direct connections between them. These direct connections are often causal connections. In addition, BNs model the quantitative strength of the connections between variables, allowing probabilistic beliefs about them to be updated automatically as new information becomes available. In this chapter we will describe how Bayesian networks are put together (the syntax) and how to interpret the information encoded in a network (the semantics). We will look at how to model a problem with a Bayesian network and the types of reasoning that can be performed.

Using Bayesian Networks for Risk Assessment in Healthcare System

Using Bayesian Networks for Risk Assessment in Healthcare System, 2019

To ensure patient safety, the healthcare service must be of a high quality, safe and effective. This work aims to propose integrated approaches to risk management for a hospital system. To improve patient’s safety, we should develop methods where different aspects of risk and type of information are taken into consideration. The first approach is designed for a context where data about risk events are available. It uses Bayesian networks for quantitative risk analysis in the hospital. Bayesian networks provide a framework for presenting causal relationships and enable probabilistic inference among a set of variables. The methodology is used to analyze the patient’s safety risk in the operating room, which is a high risk area for adverse event. The second approach uses the fuzzy Bayesian network to model and analyze risk. Fuzzy logic allows using the expert’s opinions when quantitative data are lacking and only qualitative or vague statements can be made. This approach provides an actionable model that accurately supports human cognition using linguistic variables. A case study of the patient’s safety risk in the operating room is used to illustrate the application of the proposed method.