Hazard analysis: A deep learning and text mining framework for accident prevention

Learning from past accidents is pivotal for improving safety in construction. However, hazard records are typically documented and stored as unstructured or semi-structured free-text rendering the ability to analyse such data a difficult task. The research presented in this study presents a novel and robust framework that combines deep learning and text mining technologies that provide the ability to analyse hazard records automatically. The framework comprises four-step modelling approach: (1) identification of hazard topics using a Latent Dirichlet Allocation algorithm (LDA) model; (2) automatic classification of hazards using a Convolution Neural Network (CNN) algorithm; (3) the production of a Word Co-occurrence Network (WCN) to determine the interrelations between hazards; and (4) quantitative analysis by Word Cloud (WC) technology of keywords to provide a visual overview of hazard records. The proposed framework is validated by analysing hazard records collected from a large-scale transport infrastructure project. It is envisaged that the use of the framework can provide managers with new insights and knowledge to better ensure positive safety outcomes in projects. The contributions of this research are threefold: (1) it is demonstrated that the process of analysing hazard records can be automated by combining deep learning and text learning; (2) hazards are able to be visualized using a systematic and data-driven process; and (3) the automatic generation of hazard topics and their classification over specific time periods enabling managers to understand their patterns of manifestation and therefore put in place strategies to prevent them from reoccurring.     

Automated text classification of near-misses from safety reports: An improved deep learning approach

Examining past near-miss reports can provide us with information that can be used to learn about how we can mitigate and control hazards that materialise on construction sites. Yet, the process of analysing near-miss reports can be a time-consuming and labour-intensive process. However, automatic text classification using machine learning and ontology-based approaches can be used to mine reports of this nature. Such approaches tend to suffer from the problem of weak generalisation, which can adversely affect the classification performance. To address this limitation and improve classification accuracy, we develop an improved deep learning-based approach to automatically classify near-miss information contained within safety reports using Bidirectional Transformers for Language Understanding (BERT). Our proposed approach is designed to pre-train deep bi-directional representations by jointly extracting context features in all layers. We validate the effectiveness and feasibility of our approach using a database of near-miss reports derived from actual construction projects that were used to train and test our model. The results demonstrate that our approach can accurately classify ‘near misses’, and outperform prevailing state-of-the-art automatic text classification approaches. Understanding the nature of near-misses can provide site managers with the ability to identify work-areas and instances where the likelihood of an accident may occur.     

A small samples training framework for deep Learning-based automatic information extraction: Case study of construction accident news reports analysis

Knowledge management is crucial for construction safety management. Widely collected and well-organized safety-related documents are recognized to be significant in raising the workers' security awareness and then to prevent hazards and accidents. To improve document processing efficiency, automatic information extraction plays an important role. However, currently, automatic information extraction modeling requires large scale training datasets. It is a big challenge for the engineering industry, especially for the fields which heavily rely on the experts’ knowledge. Limited data sources, and high time and labor costs make it not practical to establish a large-scale dataset. This work proposed a natural language data augmentation-based small samples training framework for automatic information extraction modeling. With the designed cross combination-based text data augmentation algorithm, the deep neural network can be employed to build up automatic information extraction models without large-scale raw data and manual annotations. Characters semantic coding is employed to avoid word segmentation and make sure that the framework can be utilized in different writing language systems. The BiLSTM-CRF model is adopted as the detection core to conduct character classification. Through a case study of two independent accident news report datasets analysis, the proposed framework has been validated. A reliable and robust automatic information extraction model can be established, even though with small samples training.     

Automatic classification of construction safety reports using semi-supervised YAKE-Guided LDA approach

Literature on supervised Machine-Learning (ML) approaches for classifying text-based safety reports for the construction sector has been growing. Recent studies have emphasized the need to build ML approaches that balance high classification accuracy and performance on management criteria, such as resource intensiveness. However, despite being highly accurate, the extensively focused, supervised ML approaches may not perform well on management criteria as many factors contribute to their resource intensiveness. Alternatively, the potential for semi-supervised ML approaches to achieve balanced performance has rarely been explored in the construction safety literature. The current study contributes to the scarce knowledge on semi-supervised ML approaches by demonstrating the applicability of a state-of-the-art semi-supervised learning approach, i.e., Yet, Another Keyword Extractor (YAKE) integrated with Guided Latent Dirichlet Allocation (GLDA) for construction safety report classification. Construction-safety-specific knowledge is extracted as keywords through YAKE, relying on accessible literature with minimal manual intervention. Keywords from YAKE are then seeded in the GLDA model for the automatic classification of safety reports without requiring a large quantity of prelabeled datasets. The YAKE-GLDA classification performance (F1 score of 0.66) is superior to existing unsupervised methods for the benchmark data containing injury narratives from Occupational Health and Safety Administration (OSHA). The YAKE-GLDA approach is also applied to near-miss safety reports from a construction site. The study demonstrates a high degree of generality of the YAKE-GLDA approach through a moderately high F1 score of 0.86 for a few categories in the near-miss data. The current research demonstrates that, unlike the existing supervised approaches, the semi-supervised YAKE-GLDA approach can achieve a novel possibility of consistently achieving reasonably good classification performance across various construction-specific safety datasets yet being resource-efficient. Results from an objective comparative and sensitivity analysis contribute to much-required knowledge-contesting insights into the functioning and applicability of the YAKE-GLDA. The results from the current study will help construction organizations implement and optimize an efficient ML-based knowledge-mining strategy for domains beyond safety and across sites where the availability of a pre-labeled dataset is a significant limitation.     

UK rail workers' perceptions of accident risk factors: An exploratory study

Although non-fatal injuries remain a frequent occurrence in Rail work, very few studies have attempted to identify the perceived factors contributing to accident risk using qualitative research methods. This paper presents the results from a thematic analysis of ten interviews with On Track Machine (OTM) operatives. The inductive methodological approach generated five themes, of which two are discussed here in detail, ‘Pressure and fatigue’, and ‘Decision making and errors’. It is concluded that for companies committed to proactive accident risk reduction, irrespective of current injury rates, the collection and analysis of worker narratives and broader psychological data across safety-critical job roles may prove beneficial.     

Robotics in construction: A critical review of the reinforcement learning and imitation learning paradigms

The reinforcement and imitation learning paradigms have the potential to revolutionise robotics. Many successful developments have been reported in literature; however, these approaches have not been explored widely in robotics for construction. The objective of this paper is to consolidate, structure, and summarise research knowledge at the intersection of robotics, reinforcement learning, and construction. A two-strand approach to literature review was employed. A bottom-up approach to analyse in detail a selected number of relevant publications, and a top-down approach in which a large number of papers were analysed to identify common relevant themes and research trends. This study found that research on robotics for construction has not increased significantly since the 1980s, in terms of number of publications. Also, robotics for construction lacks the development of dedicated systems, which limits their effectiveness. Moreover, unlike manufacturing, construction's unstructured and dynamic characteristics are a major challenge for reinforcement and imitation learning approaches. This paper provides a very useful starting point to understating research on robotics for construction by (i) identifying the strengths and limitations of the reinforcement and imitation learning approaches, and (ii) by contextualising the construction robotics problem; both of which will aid to kick-start research on the subject or boost existing research efforts.     

LIFT: A new framework of learning from testing data for face recognition

In this paper, a novel learning methodology for face recognition, LearnIng From Testing data (LIFT) framework, is proposed. Considering many face recognition problems featured by the inadequate training examples and availability of the vast testing examples, we aim to explore the useful information from the testing data to facilitate learning. The one-against-all technique is integrated into the learning system to recover the labels of the testing data, and then expand the training population by such recovered data. In this paper, neural networks and support vector machines are used as the base learning models. Furthermore, we integrate two other transductive methods, consistency method and LRGA method into the LIFT framework. Experimental results and various hypothesis testing over five popular face benchmarks illustrate the effectiveness of the proposed framework.     

An estimation method of the average effect and the different accident risks when modelling a road safety measure: A simulation study

The combination of road accident frequencies before and after a similar change at a given number of sites are considered. Each target site includes different accident types and is linked to a specific control area. At any one target site it is assumed that the total number of accidents recorded is multinomially distributed between the before period and the after period and also between several mutually exclusive types. The parameter of the distribution depends on the different accident risks in the control area linked to each site as well as on the average effect of the change. A method of estimating simultaneously the average effect and the accident risks in control areas is suggested. Some simulated accidents data allow us to study the existence and consistence of the linear constrained estimator of the unknown vector parameter.     

Managing the risks of artificial general intelligence: A human factors and ergonomics perspective

Artificial General Intelligence (AGI) is the next and forthcoming evolution of Artificial Intelligence (AI). Though there could be significant benefits to society, there are also concerns that AGI could pose an existential threat. The critical role of Human Factors and Ergonomics (HFE) in the design of safe, ethical, and usable AGI has been emphasized; however, there is little evidence to suggest that HFE is currently influencing development programs. Further, given the broad spectrum of HFE application areas, it is not clear what activities are required to fulfill this role. This article presents the perspectives of 10 researchers working in AI safety on the potential risks associated with AGI, the HFE concepts that require consideration during AGI design, and the activities required for HFE to fulfill its critical role in what could be humanity's final invention. Though a diverse set of perspectives is presented, there is broad agreement that AGI potentially poses an existential threat, and that many HFE concepts should be considered during AGI design and operation. A range of critical activities are proposed, including collaboration with AGI developers, dissemination of HFE work in other relevant disciplines, the embedment of HFE throughout the AGI lifecycle, and the application of systems HFE methods to help identify and manage risks.     

A comparative study of important risk factors involved in offshore and domestic outsourcing of software development projects: A two-panel Delphi study

We investigated the risk factors of outsourced software development. Our first objective was to create empirically generated lists of risk factors for both domestically- and offshore-outsourced projects. Our second objective was to compare these two contexts: how do the risk factors change and which ones are most important in each. To address these objectives, we conducted two Delphi surveys to identify the important risk factors from a client perspective, in domestic and offshore settings. We qualitatively compared the results of the surveys to identify similarities and differences across their risk profiles. We identified three types of risks: those that appeared in both contexts; those that appeared in both but were exacerbated in the offshore context; and those that were unique to the offshore context. Our findings suggested that traditional project management risks were important in both contexts; however, the offshore context seemed to be more vulnerable to some traditional risks as well as factors that were unique to it.