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.

In this study, the authors propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The purpose of this study is to harness the combined power of deep learning (DL) and physics-based methods (PBM) to create an active virtual replica of the physical system.

To achieve this goal, we introduce a deep neural network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is used to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop.

The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems.

The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining.

Renal failure is an end-stage consequence after persistent hyperglycemia during diabetic nephropathy (DN), and the etiology of DN has been linked to oxidative stress. The purpose of this research was to determine the beneficial synergistic effects of S-Allyl Cysteine (SAC) and Taurine (TAU) on oxidative damage in the kidneys of type 2 diabetic rats induced by hyperglycemia.

Experimental diabetes was developed by administering intraperitoneal single dose of streptozotocin (STZ; 65 mg/kg) with nicotinamide (NA; 230 mg/kg) in adult rats. Diabetic and control rats were treated with SAC (150 mg/kg), TAU (200 mg/kg) or SAC and TAU combination (75 + 100 mg/kg) for four weeks. The estimation of body weight, fasting blood glucose (FBG), oral glucose tolerance test (OGTT), oxidative stress markers along with kidney histopathology was done to investigate the antidiabetic potential of SAC/TAU in the NA/STZ diabetic group.

The following results were obtained for the therapeutic efficacy of SAC/TAU: decrease in blood glucose level, decreased level of thiobarbituric acid reactive substances (TBARS) and increased levels of GSH, glutathione-s-transferase (GST) and catalase (CAT). SAC/TAU significantly modulated diabetes-induced histological changes in the kidney of rats.

SAC/TAU combination therapy modulated the oxidative stress markers in the kidney in diabetic rat model and also prevented oxidative damage as observed through histopathological findings.

In recent years, there has been significant interest in adopting XR (extended reality) technologies such as VR (virtual reality) and AR (augmented reality), particularly in retail. However, extending activities through reality-mediation is still mostly believed to offer an inferior experience due to their shortcomings in usability, wearability, graphical fidelity, etc. This study aims to address the research gap by experimentally examining the acceptance of metaverse shopping.

This study conducts a 2 (VR: with vs. without) × 2 (AR: with vs. without) between-subjects laboratory experiment involving 157 participants in simulated daily shopping environments. This study builds a physical brick-and-mortar store at the campus and stocked it with approximately 600 products with accompanying product information and pricing. The XR devices and a 3D laser scanner were used in constructing the three XR shopping conditions.

Results indicate that XR can offer an experience comparable to, or even surpassing, traditional shopping in terms of its instrumental and hedonic aspects, regardless of a slightly reduced perception of usability. AR negatively affected perceived ease of use, while VR significantly increased perceived enjoyment. It is surprising that the lower perceived ease of use appeared to be disconnected from the attitude toward metaverse shopping.

This study provides important experimental evidence on the acceptance of XR shopping, and the finding that low perceived ease of use may not always be detrimental adds to the theory of technology adoption as a whole. Additionally, it provides an important reference point for future randomized controlled studies exploring the effects of technology on adoption.

Strategic flexibility (SF) has become increasingly important for firms because of the fast changes in the external environment. In line with the practical importance of SF, an emerging research field has developed around it that has attempted to understand the nature of SF and the key relationships. The aim of this study is to unveil the semantic structure of the recent literature on SF and to suggest new promising areas for future research.

The authors conduct a systematic literature review with a bibliographic analysis technique, which allows authors to identify the main recent streams in the literature, as well as offer reflections and suggestions for future research.

The authors uncover three main emerging areas in the research on SF, namely SF as a dynamic capability, the role of knowledge management for SF and the relationship between a firm SF and the external environment. The authors put forward three avenues for future research on SF: Avenue 1. SF, business model innovation (BMI) and other dynamic capabilities (DC), Avenue 2. Digital technologies and SF/organizational agility and Avenue 3. SF and sustainability. Articles included in the special issue entitled “A strategic perspective on flexibility, agility and adaptability in the digital era” contribute to Avenue 2, thus paving the way for filling some of the identified gaps regarding the relationship between SF and digitalization.

To the best of authors’ knowledge, this is the first literature review on SF that uses a bibliometric approach to draw conclusions on the findings in the literature. The review contributes to the theoretical understanding of SF by illustrating and explicating core topics that have persisted over time, as well as by presenting three main avenues for further developing authors’ knowledge around SF.

This study aims to investigate the impact of service quality (SQ), perceived value (PV) and consumer satisfaction on Thai street food, with customer satisfaction (CS) as a mediator for customer loyalty and repurchase intention (RI). It also explores how consumer trust (CT) in Thai street food safety moderates these relationships.

Structural equation modelling (SEM) was utilised to analyse the complex interrelationships between various constructs. Multi-group analyses were conducted to investigate the moderating effects of CT on the structural model, considering two distinct groups based on trust levels: low and high.

The findings revealed that SQ and PV significantly influenced CS and behavioural intention, while the perceived quality of Thai street food had no significant impact on post-COVID-19 consumer satisfaction. The study highlighted the critical role of CT in moderating the relationships between SQ, PV and CS, with distinct effects observed in groups with varying trust levels.

The research emphasises the importance of enhancing SQ and delivering value to customers in the context of Thai street food, which can contribute to increased CS, RI and positive word-of-mouth. Furthermore, the study underscores the critical role of building CT in fostering enduring customer relationships and promoting consumer satisfaction and loyalty.

This research offers valuable insights into consumer behaviour and decision-making processes, particularly within the realm of Thai street food. It underscores the significance of understanding and nurturing CT, especially in the post-COVID-19 landscape, emphasising the need for effective business strategies and consumer engagement.