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 investigate whether professional data analysts’ trust of black-box systems is increased by explainability artifacts.

The study was developed in two phases. First a black-box prediction model was estimated using artificial neural networks, and local explainability artifacts were estimated using local interpretable model-agnostic explanations (LIME) algorithms. In the second phase, the model and explainability outcomes were presented to a sample of data analysts from the financial market and their trust of the models was measured. Finally, interviews were conducted in order to understand their perceptions regarding black-box models.

The data suggest that users’ trust of black-box systems is high and explainability artifacts do not influence this behavior. The interviews reveal that the nature and complexity of the problem a black-box model addresses influences the users’ perceptions, trust being reduced in situations that represent a threat (e.g. autonomous cars). Concerns about the models’ ethics were also mentioned by the interviewees.

The study considered a small sample of professional analysts from the financial market, which traditionally employs data analysis techniques for credit and risk analysis. Research with personnel in other sectors might reveal different perceptions.

Other studies regarding trust in black-box models and explainability artifacts have focused on ordinary users, with little or no knowledge of data analysis. The present research focuses on expert users, which provides a different perspective and shows that, for them, trust is related to the quality of data and the nature of the problem being solved, as well as the practical consequences. Explanation of the algorithm mechanics itself is not significantly relevant.

The aim of this study was to determine data literacy (DL) training needs of researchers at South African public universities. The outcome of this study would assist librarians and researchers in developing a DL training programme which addressed identified needs.

A survey research method was used to gather data from researchers at these universities by convenience. Online questionnaires were distributed to public universities through library directors for further distribution to researchers.

The results indicate low levels of DL training at the respondent South African public universities with most researchers indicating that they had not received any formal training on DL. A few researchers indicated that they would welcome DL training.

This study was exploratory in nature and data was received from eight universities, which is not representative of all the 26 public universities in South Africa. Nonetheless, the low DL confirmed by the majority in the realised sample is indicative of the need to further investigate the subject.

Librarians and research support personnel should collaborate on the development of DL training courses, workshops and materials used by researchers at institutions of higher learning to enhance DLs on campus.

This study may be novel in South Africa in investigating the DL training needs of researchers at several universities and contributes to the growing body of literature on research data management

This paper aims to focus on academic library managers’ learning practices in the context of cooperative work supported by computational artefacts. Academic library managers’ everyday work is mainly cooperative. Their cooperation is supported predominantly by computational artefacts. Learning how to use the computational artefacts efficiently and effectively involves understanding the changes in everyday work that affect managers and, therefore, it requires deep understanding of their cooperative work practices.

Focused ethnography was conducted through participant observations, interviews and document analysis. Ten managers from a university library in Sweden participated in the research. A thematic method was used to analyse the empirical material. Computer supported cooperative work (CSCW) and work-integrated learning was used as the conceptual lens.

Five learning practices were identified: collaboration, communication, coordination, decision-making processes and computational artefacts’ use. The findings show that learning is embedded in managers’ cooperative work practices, which do not necessarily include sufficient training time. Furthermore, learning was intertwined with cooperating and was situational. Managers learned by reflecting together on their own experiences and through joint cooperation and information sharing while using the computational artefacts.

The main contribution lies in providing insights into how academic library managers learn and cooperate in their everyday work, emphasizing the role of computational artefacts, the importance of the work context and the collective nature of learning. It also highlights the need for continual workplace learning in contemporary knowledge work environments. Thus, the research generates contributions to the informatics field by extending the understanding of managers’ work-integrated learning in their everyday cooperative work practices supported by computational artefacts’ use. It also contributes to the intersection of CSCW and work-integrated learning.

In order to estimate the value of semi-automated subject indexing in operative library catalogues, the study aimed to investigate five different automated implementations of an open source software package on a large set of Swedish union catalogue metadata records, with Dewey Decimal Classification (DDC) as the target classification system. It also aimed to contribute to the body of research on aboutness and related challenges in automated subject indexing and evaluation.

On a sample of over 230,000 records with close to 12,000 distinct DDC classes, an open source tool Annif, developed by the National Library of Finland, was applied in the following implementations: lexical algorithm, support vector classifier, fastText, Omikuji Bonsai and an ensemble approach combing the former four. A qualitative study involving two senior catalogue librarians and three students of library and information studies was also conducted to investigate the value and inter-rater agreement of automatically assigned classes, on a sample of 60 records.

The best results were achieved using the ensemble approach that achieved 66.82% accuracy on the three-digit DDC classification task. The qualitative study confirmed earlier studies reporting low inter-rater agreement but also pointed to the potential value of automatically assigned classes as additional access points in information retrieval.

The paper presents an extensive study of automated classification in an operative library catalogue, accompanied by a qualitative study of automated classes. It demonstrates the value of applying semi-automated indexing in operative information retrieval systems.

Create and share a MATLAB library that performs data augmentation algorithms for audio data. This study aims to help machine learning researchers to improve their models using the algorithms proposed by the authors.

The authors structured our library into methods to augment raw audio data and spectrograms. In the paper, the authors describe the structure of the library and give a brief explanation of how every function works. The authors then perform experiments to show that the library is effective.

The authors prove that the library is efficient using a competitive dataset. The authors try multiple data augmentation approaches proposed by them and show that they improve the performance.

A MATLAB library specifically designed for data augmentation was not available before. The authors are the first to provide an efficient and parallel implementation of a large number of algorithms.

The main purpose of this paper is to explore telepresence robots are being used in libraries to facilitate library services and also to explain the future trend in the application of robots in libraries.

Through a review of the literature, this paper analyzes various library websites and consults literature relating to the use of telepresence robots in libraries; the current application of robots in libraries has been highlighted along with case studies of libraries currently adopting telepresence robots.

The uses of telepresence technology in libraries help to enhance library services, reach new users and provide a more inclusive and accessible library experience. Telepresence robots enhance the quality and accessibility of library services, expand library outreach and provide new opportunities for virtual engagement and programming. The application of telepresence robots in libraries can offer many benefits, but there are also several challenges that libraries must address to ensure successful implementation.

This paper highlights how the application of telepresence robots in libraries improves service productivity in libraries and creates a more engaging environment for the user group. The benefits and challenges of using robots in the library and the future trend in the application of telepresence robots in libraries are also discussed.

Although universities have extensive research and initiatives in place that align with the United Nations’ Sustainable Development Goals (SDGs), there is still a significant gap in documenting and assessing these efforts. This paper aims to discuss how academic libraries can apply their information management skills and open-access platforms, to facilitate the discoverability and retrieval of evidence on SDGs.

Introduced by a brief literature review on the role of libraries in contributing to the SDGs in general, the authors draw on their personal experiences as metadata specialists, participating in a project aimed at linking their university’s research output to the SDGs. A case study, from the University of Pretoria’s Veterinary Science Library, is used as an example to demonstrate the benefits of resourceful metadata in organising, communicating and raising awareness about the SDGs in the field of veterinary science.

Through practical examples and recommended workflows, this paper illustrates that metadata specialists are perfectly positioned to apply their information management skills and library platforms to facilitate the discoverability and retrieval of evidence on SDGs.

Although there are increasing reports on the contributions of libraries to support the successful implementation of the SDGs, limited information exists on the role of metadata specialists, as well as those with a practical focus.

This article sets out to show how principles and questions about method that underlie a way of interpreting the discipline of conservation and restoration can find results in research and studies, aiming at achieving even conscious reuse process. The occasion is the very recent research performed on the former Church of Saints Gerolamo and Francesco Saverio in Genoa, Italy, the Jesuit church annexed to the 17th-century College of the order. It is a small Baroque jewel in the heart of the ancient city, former University Library and actually abandoned, forgotten for years, inaccessible and awaiting a new use.

The two-year work carried out on the monumental building was conducted according to a study and research methodology developed and refined over the years within the activities of the School of Specialisation in Architectural Heritage and Landscape of the University of Genoa. It is a multidisciplinary and rigorous approach, which aims to train high-level professionals, up-to-date and aware of the multiple problems that interventions on existing buildings, especially of a monumental nature, involve.

The biennal study has been carried out within the activities of the Post-Graduate Programme in Architectural Heritage and Landscape of the University of Genoa. The work methodology faces the challenges of the contemporary complexity, raised by the progressive broadening of the concept of cultural “heritage” and by the problems of its conservation, its active safeguard and its reuse: safety in respect of seismic risk, fire and hydro geological instability, universal accessibility – cognitive, physical and alternative – resource efficiency, comfort and savings in energy consumption, sustainability, communication and involvement of local communities and stakeholders.

The goals of the work were the following: understanding of the architectural heritage, through the correlated study of its geometries, elements and construction materials, surfaces, structures, spaces and functions; understanding of the transformations that the building has undergone over time, relating the results of historical reconstructions from indirect sources and those of direct archaeological analysis; assessment of the state of conservation of the building recognising phenomena of deterioration, damage, faults and deficits that affect materials, construction elements, systems and structures; identification of the causes and extent of damage, faults and deficits, assessing the vulnerability and level of exposure of the asset to the aggression of environmental factors and related risks; evaluation of the compatibility between the characteristics of the available spaces, the primary needs of conservation, the instance of regeneration and possible new uses; the definition of criteria and guidelines for establishing the planning of conservation, restoration and redevelopment interventions.

This paper aims to provide a reflection on innovating and repurposing collection development and marketing strategy, particularly for eBooks in libraries.

This paper provides a general review where previous research papers on the phenomenon of the study have been consulted.

The findings indicate that there is a lack of awareness of eBooks and marketing, and virtual bookshelves in the form of LibGuide gallery boxes are identified as a solution in promoting these resources.

This is a valuable contribution that sheds insight on the usage of LibGuide gallery boxes as virtual bookshelves in marketing library resources, particularly eBooks.