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.

This study proposes a collaborative federated learning (CFL) framework to address personal data transmission and retention issues for artificial intelligence (AI)-enabled video surveillance in public spaces.

This study examines specific challenges for long-term people monitoring in public spaces and defines AI-enabled video surveillance requirements. Based on the requirements, this study proposes a CFL framework to gradually adapt AI models’ knowledge while reducing personal data transmission and retention. The framework uses three different federated learning strategies to rapidly learn from different new data sources while minimizing personal data transmission and retention to a central machine.

The findings confirm that the proposed CFL framework can help minimize the use of personal data without compromising the AI model's performance. The gradual learning strategies help develop AI-enabled video surveillance that continuously adapts for long-term deployment in public spaces.

This study makes two specific contributions to advance the development of AI-enabled video surveillance in public spaces. First, it examines specific challenges for long-term people monitoring in public spaces and defines AI-enabled video surveillance requirements. Second, it proposes a CFL framework to minimize data transmission and retention for AI-enabled video surveillance. The study provides comprehensive experimental results to evaluate the effectiveness of the proposed framework in the context of facial expression recognition (FER) which involves large-scale datasets.

The construction industry has struggled to deliver schemes on time to budget and right-first-time (RFT). There have been many studies into nonconformance and rework through quantitative research over the years to understand why the industry continues to see similar issues of failure. Some scholars have reported rework figures as high as 12.6% of total contract value, highlighting major concerns of the sustainability of construction projects. Separately, however, there have been few studies that explore and detail the views of industry professions who are caught in the middle of quality issues, to understand their perceptions of where the industry is failing. As such, this paper interrogates qualitative data (open-ended questions) on the topic of nonconformance and rework in construction to understand what industry professionals believe are the causes and suggested improvement areas.

A qualitative approach is adopted for this research. An industry survey consisting of seven open-ended questions is presented to two professional working groups within a Tier 1 contractor, and outputs are analysed using statistic software (NVivo 12) to identify prominent themes for discussion. Inductive analysis is undertaken to gain further insight into responses to yield recurrent areas for continuous improvement.

Qualitative analysis of the survey reveals a persistent prioritisation of cost and programme over quality management in construction project. Furthermore, feedback from construction professionals present a number of improvement areas that must be addressed to improve quality. These include increased training and competency investment, overhauling quality behaviours, providing greater quality leadership direction and reshaping the way clients govern schemes.

There are limitations to this paper that require noting. Firstly, the survey was conducted within one principal contractor with varying levels of knowledge across multiple sectors. Secondly, the case study was from one major highways scheme; therefore, the generalisability of the findings is limited. It is suggested that a similar exercise is undertaken in other sectors to uncover similar improvement avenues.

The implications of this study calls for quality to be re-evaluated at project, company, sector and government levels to overhaul how quality is delivered. Furthermore, the paper identifies critical learning outcomes for the construction sector to take forward, including the need to reassess projects to ensure they are appropriately equip with competent personnel under a vetted, progressive training programme, share collaborative behaviours that value quality delivery on an equal standing to safety, programme and cost and tackle the inappropriate resource dilemmas projects finding themselves in through clear tendering and accurate planning. In addition, before making erratic decisions, projects must assess the risk profiling of proceed without approved design details and include the client in the decision-making process. Moreover, the findings call for a greater collaborative environment between the construction team and quality management department, rather than being seen as obstructive (i.e. compliance based policing). All of these must be driven by leadership to overhaul the way quality is managed on schemes. The findings demonstrate the importance and impact from open-ended survey response data studies to enhance quantitative outcomes and help provide strengthened proposals of improvement.

This paper addresses the highly sensitive area of quality failure outcomes and interrogates them via an industry survey within a major UK contractor for feedback. Unique insights are gained into how industry professionals perceive quality in construction. From previous research, this has been largely missing and offers a valuable addition in understanding the “quality status quo” from those delivering schemes.

This study aims to synthesize existing findings in the gig worker training literature and identify the training rationales adopted by these studies, using a synthesized framework of organizational training rationales. This study seeks to delineate the rationales behind gig worker training and highlight unaddressed training needs within digital platforms, ultimately proposing a research agenda for future studies in this area.

A systematic review methodology is adopted to synthesize and analyze empirical, peer-reviewed studies on gig worker training.

The systematic review reveals that competency and economic rationales are predominantly adopted in gig worker training studies, with the relationship rationale, common in traditional training, notably absent. This study also outlines seven future research directions to highlight identified challenges and unaddressed training needs.

To the best of the author’s knowledge, this study is the first work that systematically reviews existing findings on gig worker training.

This study examines the relationship between servant leadership and its dimensions on firm performance, with big data playing the role of a mediator.

Survey responses used for analysis in this study have been taken from business managers associated reputed private sector organizations in India. A conceptual model is proposed grounded to the Conservation of Resource Theory (COR). Structural equation modeling has been used to test the proposed model.

Servant leadership significantly relates to firm performance, whereby Big Data is seen to play the role of a mediator. The results also indicate that none of the dimensions of servant leadership independently affect firm performance.

The study adds to extant research by examining the mediating mechanism of Big Data in servant leadership and firm performance. It also suggests that each dimension of servant leadership gets reflected in overall servant leadership. Here it is important to note that Big Data analytics partially mediate the effectiveness of servant leadership.

The research aims to develop an assessment framework that evaluates critical success factors (CSFs) for the Quality 4.0 (Q 4.0) transition among Indian firms.

The authors use the fuzzy-Delphi method to validate the results of a systematic literature review (SLR) that explores critical aspects. Further, the fuzzy decision-making trial and laboratory (DEMATEL) method determines the cause-and-effect link. The findings indicate that developing a Q 4.0 framework is essential for the long-term success of manufacturing companies. Utilizing the power of digital technology, data analytics and automation, manufacturing companies can benefit from the Q 4.0 framework. Product quality, operational effectiveness and overall business performance may all be enhanced by implementing the Q 4.0 transition framework.

The study highlights significant awareness of Q 4.0 in the Indian manufacturing sector that is acquired through various means such as training, experience, learning and research. However, most manufacturing industries in India still follow older quality paradigms. On the other hand, Indian manufacturing industries seem well-equipped to adopt Q 4.0, given practitioners' firm grasp of its concepts and anticipated benefits, including improved customer satisfaction, product refinement, continuous process enhancement, waste reduction and informed decision-making. Adoption hurdles involve challenges including reliable electricity access, high-speed Internet, infrastructure, a skilled workforce and financial support. The study also introduces a transition framework facilitating the shift from conventional methods to Q 4.0, aligned with the principles of the Fourth Industrial Revolution (IR).

This research exclusively examines the manufacturing sector, neglecting other fields such as medical, service, mining and construction. Additionally, there needs to be more emphasis on the Q 4.0 implementation frameworks within the scope of the study.

This may be the inaugural framework for transitioning to Q 4.0 in India's manufacturing sectors and, conceivably, other developing nations.

The purpose of this paper is to investigate the unexplored part of the historical evolution of travel agencies in Spain, from the end of the 20th century to the 21st century. When examining promotion strategies, the study focuses on the change in marketing and public relations strategies based on the incorporation of information and communication technologies and, in particular, the use of the internet.

This study draws on a qualitative analysis of the different strategies used by traditional agencies and online agencies in Spain from the mid-19th century to the present. This analysis shows how traditional communication strategies survived at the beginning of the 21st century, together with other more innovative ones, while some disappeared, being eliminated by the new online travel agencies, which created a particular conception of marketing and communication. This paper is divided into the following parts: the introduction; the beginnings of travel agency promotion in the 20th century; the evolution of promotion in travel agencies since the late 20th century; communication innovation at the beginning of the 21st century; online travel agencies; and conclusions.

This study shows that although online agencies did not manage to position themselves with a large turnover, they generated advantages and sharpened their imagination to create a new, more economical advertising model, eliminating the costs of public relations and advertising campaigns. In addition, they allowed clients to have greater independence when making their reservations, while enabling them to monitor the tastes of potential and real clients and add blogs so that consumers could express their degree of satisfaction with the product or services provided by the agency.

The focus of attention is the travel agency sector in Spain and, more specifically, communication. Studies on travel agencies and their marketing have been very scarce and partial, impeding professionals in the tourism sector from having a broad vision to direct their promotional and public relations actions. The originality of this article lies in its making a comparison between two different visions of tourism marketing and, specifically, of travel agencies, that is, the traditional vision and the innovative one. It thus helps all professionals in the sector to value and improve their marketing and communication strategies.

Researcher agreed that job performance has a positive effect on productivity as well as an organisation’s efficiency. Thus, this study aims to investigate the impact of mindfulness skill, inclusive leadership (IL), employee work engagement and self-compassion on the overall job performance of secondary school teachers in Hong Kong. It then evaluates the mediating effect of employee work engagement between the relationships of mindfulness skill, IL and job performance, as well as the moderate effect of self-compassion between the relationships of mindfulness skill, IL and employee work engagement.

The sample comprised 263 teachers working from three secondary schools in Sha Tin, Hong Kong. The data was then analysed using Smart PLS version 4.0.9.

The results showed significant positive relationships between mindfulness skill and IL towards employee work engagement and between employee work engagement and job performance; meanwhile, there emerged a significant effect on the relationship between mindfulness skill and IL towards job performance. Furthermore, this research has confirmed that self-compassion did not moderate the relationship between mindfulness skill, IL and employee work engagement, but employee work engagement plays a mediating effect on the relationship between mindfulness skill, IL and job performance.

This research has helped to fill the literature gap by examining the mediating roles of employee work engagement and mediator role of self-compassion in the integrated relationship of multi-factor and job performance. Examining the mediating role of employee work engagement has helped to enhance the understanding of the underlying principle of the indirect influence of mindfulness skill, IL and job performance. The result of this research shows that self-compassion plays a vital role in influencing the employees’ work engagement. Hence, it is important that companies design human resource management policy that enables self-compassion to be used as a consideration psychological-related strategy when structing organisation or teams. It is also crucial for top management and policymakers to define and communicate the organisation’s operating principle, value and goals.

This study aims to provide an overall framework that connects and explains a macro-perspective of the findings from the five studies of this special issue. Through this, we aim to answer two main questions: How can Lean and Industry 4.0 be integrated, and what are the outcomes for workers from such integration?

The special issue received 64 papers that were evaluated in multiple stages until this final sample of five papers that describe different facets of the integration between Lean and Industry 4.0 and their relationship with worker activities. In this introduction, we review the main findings of these five studies and propose an integrative view and associated propositions. A discussion provides directions to advance the field further.

The framework shows that when Lean and Industry 4.0 are integrated, companies will face two types of tensions, dialectical and paradoxical, which require different managerial approaches. By managing such tensions, the Lean-Industry 4.0 integration can help improve social performance, as well as develop systematic problem-solving and cumulative learning capabilities. Five important themes for this field of research are outlined: the importance of work routines, legitimation, competence, sense and mental flexibility.

This study brings a new theoretical perspective to the integration of Lean with Industry 4.0-related digital technologies. The results go beyond the usual view of improving operational performance and dig into the effects on workers. It also shows that the integration process relies on and can enhance human capabilities such as learning and problem-solving.

In the realm of construction education, the investigation of immersive learning and extended reality (XR) technologies has experienced a surge in recent times. Nevertheless, there remains a notable lack of comprehension surrounding the most efficient ways to integrate these technologies into tailored teaching approaches for vocational construction training. This research study aims to pinpoint the key factors that construction vocational education and training (VET) providers must consider when introducing XR technologies into their training schemes.

This study conducted an in-depth literature review to develop an initial framework to summarise training, technology and institutional factors influencing the educational-technology integration of XR technologies in VET. In addition, this study utilised a Delphi technique, including semi-structured group discussions and two rounds of online follow-up questionnaires, to capture VET experts’ judgements on the importance of decision-making criteria.

This study has identified the critical factors to be considered in the VET sector when adopting XR technologies. Findings revealed institutional factors were the most important criteria for participants, followed by training and technology factors.

The current decision-making process focuses on selecting XR technologies rather than evaluating their performance after implementation. Therefore, more research is needed to monitor the implementation of this technology in curricula from a senior management perspective. This will help to understand the cost and value factors related to the value proposition of XR technologies in courses.

To ensure the success and long-term viability of the technology-curriculum interface, it is important to consider factors such as the availability of technical and educational support, data security and cost-effectiveness. It is also crucial to focus on ease of use and content development that emphasises instruction to create engaging content for learners.

The potential impact of this study is underpinned by two facts: (1) it constitutes the first effort made in the field to comprehensively elicit VET expert judgements in relation to XR technologies, and (2) it offers decision-making criteria that are at play in seeking to take advantage of high-cost technologies that are rapidly evolving. While there is no simple checklist for XR implementation, this study takes a step further to identify significant factors influencing XR integration in vocational construction training.