Search results

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

While stress, anxiety and depression rank as the second leading cause of work-related ill health in the UK construction sector, there exists a scarcity of empirical studies explicitly focused on investigating the sources of occupational stress among construction workers and professionals at both the construction project and supply chain levels. This study seeks to identify and investigate the primary stressors (sources of stress) in UK construction projects and to propose effective strategies for preventing or reducing stress in this context.

The study adopted a qualitative multi-methods research approach, comprising the use of a comprehensive literature review, case study interviews and a focus group. It utilised an integrated deductive-inductive approach theory building using NVivo software. In total, 19 in-depth interviews were conducted as part of the case-study with a well-rounded sample of construction professionals and trade supervisors, followed by a focus group with 12 policy influencers and sector stakeholders to evaluate the quality and transferability of the findings of the study.

The results reveal seven main stressors and 35 influencing factors within these 7 areas of stress in a UK construction project, with “workflow interruptions” emerging as the predominant stressor. In addition, the results of the focus-group, which was conducted with a sample of 12 prominent industry experts and policy influencers, indicate that the findings of the case study are transferrable and could be applicable to other construction projects and contexts. It is, therefore, recommended that these potential stressors be addressed by the project team as early as possible in construction projects. Additionally, the study sheds empirical light on the limitations of the critical path method and identifies “inclusive and collaborative planning” as a proactive strategy for stress prevention and/or reduction in construction projects.

The findings of this study are mainly based on the perspectives of construction professionals at managerial and supervisory levels. It is, therefore, suggested that future studies are designed to focus on capturing the experiences and opinions of construction workers/operatives on the site.

The findings from this study have the potential to assist decision-makers in the prevention of stress within construction projects, ultimately enhancing workforce performance. It is suggested that the findings could be adapted for use as Construction Supply Chain Management Standards to improve occupational stress management and productivity in construction projects. The study also provides decision-makers and practitioners with a conceptual framework that includes a list of effective strategies for stress prevention or reduction at both project and organisational levels. It also contributes to practice by offering novel ideas for incorporating occupational stress and mental health considerations into production planning and control processes in construction.

To the best of the authors’ knowledge, this is the first, or one of the very few studies, to explore the concept of occupational stress in construction at the project and supply chain levels. It is also the first study to reveal “workflow” as a predominant stressor in construction projects. It is, therefore, suggested that both academic and industry efforts should focus on finding innovative ways to enhance workflow and collaboration in construction projects, to improve the productivity, health and well-being of their workforce and supply chain. Further, it is suggested that policymakers should consider the potential for incorporating “workflow” into the HSE's Management Standards for stress prevention and management.

The catastrophic effects of the COVID-19 pandemic have considerably impacted the labour market and increased job insecurity among workers. This study systematically reviews the literature on job insecurity conducted in the context of the COVID-19 pandemic with three key objectives. First, to identify the key antecedents of job insecurity during the pandemic. Second, to identify the outcomes associated with job insecurity during the pandemic. Third, to identify the underlying boundary conditions that strengthened or alleviated the association between the antecedents of job insecurity and its associated outcomes.

The study followed PRISMA 2020 guidelines for the selection and inclusion of scientific literature by systematically searching five electronic databases, namely, Scopus, ScienceDirect, PubMed, Web of Science and Psych Info.

A perception of health-related risks, negative economic consequences and organizational restructuring during the pandemic were the primary factors contributing to job insecurity among workers. The consequences encompassed detrimental impacts on health and well-being, proactive measures undertaken by employees to alleviate the threat of job loss, and a variety of tactics employed to cope with stress arising from job insecurity. The boundary conditions elucidate the factors that alleviated job insecurity among workers and influenced both their work and non-work outcomes.

This is the first systematic review summarizing the literature on employees' experiences with job insecurity amid the COVID-19 pandemic. Based on a systematic review, this study provides doable steps that HR managers can take to effectively manage job insecurity among workers, particularly during a crisis.

This study uses big data analysis aimed at discovering city bus passenger ridership patterns. Hence, marketing managers can get sufficient insights to formulate effective business plans and make timely decisions about company operations.

This study uses a mixed-method analysis to analyze the results. First uses the RFM (recency, frequency, and monetary) model combined with a big data technique (K-means) to analyze bus passenger boarding behavior. In order to improve the validity and quality of the research, this study also conducted interviews with senior managers of the bus company from which the data was obtained.

The study identifies six distinct groups of passengers with different boarding behaviors, ranging from “general passengers” to “most valuable passengers”. General passengers constituted the largest group. As such, they should be the main target for municipal governments when promoting bus ridership as part of energy conservation and carbon-reduction activities. This group of passengers should be encouraged to take public transport vehicles more, instead of relying on personal vehicles. The fourth group identified included elderly passengers with hospitals as their destinations. Bus companies can cooperate with municipal government to provide morning “medical bus” services for the elderly. Interviews with bus company managers confirmed that the analytical results of this study correspond with the observations, experiences, and actual business operating plans of bus companies.

Only few studies have analyzed passengers' boarding behavior applying a mixed-method analysis.