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 paper aims to (1) identify the different performance drivers (lead indicators) and outcome measures (lag indicators) investigated in the literature concerning the four balanced scorecard (BSC) perspectives in operations management (OM) contexts and (2) understand how performance drivers and outcome measures (and substantiated perspectives) are related.

We undertake a systematic literature review of the BSC literature in OM journals. From the final sample of 40 articles, performance drivers and outcome measures have been identified, and the relationships amongst them have been synthesised according to the system dynamics approach.

Findings show (1) the most relevant performance drivers and outcome measures within each BSC perspective, (2) their relationships, (3) how the perspectives are linked through the performance drivers and outcome measures and (4) how the different measures relate systemically. Accordingly, four causal loops amongst identified measures have been built, which – jointly considered – allowed for the creation of a dynamic strategy map for OM.

This study is the first one that provides a comprehensive and holistic view of how the different performance drivers and outcome measures within and between the four BSC perspectives in OM relate systemically, increasing the knowledge and understanding of scholars and practitioners.

This study aims to systematise the links between firms’ strategies (corporate and business) and the cluster dynamics (through the cluster life cycle [CLC] perspective) and propose an integrative framework bridging firms’ strategic behaviour and cluster dynamics (CLC).

The methodology used is an integrative literature review, which provides a distinctive form of research.

The study identifies several links between firms’ strategies (corporate and business) and the cluster dynamics (CLC), namely: (1) firms’ strategies as a triggering factor of cluster evolution; (2) firms’ strategies and path's decline; (3) firms’ strategies and cluster’s renewal; (4) resilience strategies and the cluster life cycle; and (5) cluster’s features and firms’ strategies.

This study contributes to developing strategic management theory and cluster theory by bridging firms' strategies and cluster dynamics (CLC). It proposes a new conceptualisation of the impact of cluster dynamics on firms' strategic choices – firstly, it proposes a specific approach to identify the CLC; and secondly, it develops an integrative framework model that relates firms' strategies and each stage of the CLC. These are theoretical tools relevant for further advancements in this area of research, as they can be applied in studies of different clusters for validation, something that was not done.

The integrative framework is expected to be helpful to company managers, allowing them to design better strategies that account for dynamic cluster environments.

This study aims to fill this gap in the literature by systematising the links between firms' strategies (corporate and business) and the cluster dynamics (CLC).

The purpose of this paper is to investigate the most recurrent variables characterizing the collaborative relationships of industrial symbiosis (IS) (hereinafter also referred to as “anatomic” variables) established in the attempt to adopt circular economy (CE) by collecting evidence from a rich empirical set of implementation cases in Italy.

The current literature on IS was reviewed, and a content analysis was performed to identify and define the “anatomic” variables affecting its adoption in the circular economy. We followed a multiple-case study methodology investigating 50 cases of IS in Italy and performed a content analysis of the “anatomic” variables characterizing each case.

This research proposes the “anatomic” variables (i.e. industrial sectors involved, public actors involvement, governmental support, facilitator involvement and geographical proximity) explaining the cases of IS in the circular economy. Each “anatomic” variable is discussed at length based on the empirical evidence collected, with a particular reference to the impact on the different development strategies (i.e. “bottom-up” and “top-down”) in the cases observed.

Current literature on IS focuses on a sub-set of variables characterizing collaboration in IS. This research builds on extant literature to define a new framework of five purposeful “anatomic” variables defining IS in the circular economy. Moreover, we also collect and discuss a broad variety of empirical evidence in what is a still under-investigated context (i.e. Italy).

The study aims to investigate the influence of corporate governance practices on enhancing firm value in manufacturing industries in Bangladesh.

The study sample consists of 131 companies from 10 manufacturing industries listed in Dhaka stock exchange (DSE). Using the multiple regression method, the study analyzed 1,193 firm-year observations from 2012 to 2021.

The outcome reveals that managerial ownership, foreign ownership, ownership concentration, board size, board independence, board diligence and auditor quality have a significant positive influence on firm value. In contrast, audit committee size has no significant influence on firm value.

The practical implications of the current study demonstrated that good corporate governance creates value and must be invigorated for the interest of all stakeholders. Policymakers should formulate specific guidelines regarding firms' ownership structure and audit quality issues.

Machine learning (ML) analytical tools are increasingly being considered as an alternative quantitative methodology in management research. This paper proposes a new approach for uncovering the antecedents behind product and product–service innovation (PSI).

The ML approach is novel in the field of innovation antecedents at the country level. A sample of the Equatorian National Survey on Technology and Innovation, consisting of more than 6,000 firms, is used to rank the antecedents of innovation.

The analysis reveals that the antecedents of product and PSI are distinct, yet rooted in the principles of open innovation and competitive priorities.

The analysis is based on a sample of Equatorian firms with the objective of showing how ML techniques are suitable for testing the antecedents of innovation in any other context.

The novel ML approach, in contrast to traditional quantitative analysis of the topic, can consider the full set of antecedent interactions to each of the innovations analyzed.

The authors have carried out a research project on artisanal salt activity in the Gulf of Cadiz, providing a new vision of the theories of intangible cultural heritage. The main objective has been to characterise artisanal salt activity in terms of its cultural and sustainable values, a perspective that had not been addressed until now. Moreover, the replacement of this activity by a more industrialised one has contributed to problems in the preservation of this heritage and a transformation of its places.

The research has combined qualitative methodology, based on observation and fieldwork, with a statistical review of the phenomenon under study. Finally, the data has been triangulated to understand the heritage and sustainable value, as well as its historical evolution.

All this contributes to understanding the importance of artisanal salt activity as an element of the intangible cultural heritage of the region, for the conservation of biodiversity and sustainable ways of life in the marshes of the Gulf of Cadiz, and the possibility of preserving it in the face of the problems of globalisation.

To date, there has been no research that combines sustainability and heritage in the field of salt activity. Likewise, until this study was carried out, there had been no research on salt activity from the perspective of intangible cultural heritage.