Search Results (368)

Structured quantitative data, such as survey responses in human resource management research, are often analysed using machine learning methods, including logistic regression. Although these methods provide accurate statistical predictions, their results are frequently abstract and difficult for non-specialists to comprehend. This limits their usefulness in practice, particularly in contexts where eXplainable Artificial Intelligence (XAI) is essential. This study proposes a domain-independent approach for the autonomous classification and interpretation of quantitative data using visual processing. This method transforms individual responses based on rating scales into visual representations, which are subsequently processed by Convolutional Neural Networks (CNNs). In combination with Class Activation Maps (CAMs), image-based CNN models enable not only accurate and reproducible classification but also visual interpretability of the underlying decision-making process. Our evaluation found that CNN models with bar chart coding achieved an accuracy of between 93.05% and 93.16%, comparable to the 93.19% achieved by logistic regression. Compared with conventional numerical approaches, exemplified by logistic regression in this study, the approach achieves comparable classification accuracy while providing additional comprehensibility and transparency through graphical representations. Robustness is demonstrated by consistent results across different visualisations generated from the same underlying data. By converting abstract numerical information into visual explanations, this approach addresses a core challenge: bridging the gap between model performance and human understanding. Its transparency, domain-agnostic design, and straightforward interpretability make it particularly suitable for XAI-driven applications across diverse disciplines that use quantitative response data. Full article

Air pollution poses significant risks to built heritage, yet traditional methods for diagnosing degradation patterns remain largely fragmented, often relying on isolated data streams and/or subjective comparative interpretations. This study proposes a novel modular workflow that integrates Raman spectroscopy and micro-XRF spectrometry data with user-defined contextual metadata to automate the characterisation of pollution-induced degradation layers on monuments. This method utilises algorithms for peak detection, dimensionality reduction, unsupervised machine learning clustering, variance analysis across centroids, and correlation analysis, as well as steps for data re-encoding and visualisation of the results, allowing for scalable and reproducible analyses on heterogeneous multidimensional datasets. Applied to case studies from Athens, Piraeus, and Eleusis, Greece, the workflow successfully identified pollution sources and degradation patterns, while also quantifying the contribution of features, including contextual variables such as surface orientation and sampling height. The results validate the method’s capacity to combine molecular and elemental data streams, to enhance interpretive clarity, and to minimise manual effort and subjectivity. This work showcases the potential of algorithmic approaches in cultural heritage diagnostics to adapt dynamically and incorporate additional datasets and informs future applications of automated methods in the broader field of heritage science. Full article

Background: Preventing nutritional decline during hospitalisation is imperative in reducing the development of complications such as malnutrition and pressure injuries. However, existing malnutrition screening and assessment tools employ a reactive rather than proactive approach, using predictors to identify inpatients who are already malnourished instead of those at risk of developing hospital-acquired malnutrition. Therefore, this review aimed to identify key contextual and individual factors contributing to nutritional deterioration and their interrelatedness, and to inform strategies for preventing hospital-acquired malnutrition. Methods: A scoping review of five databases (Medline, CINAHL, Embase, All EBM Reviews and PsycINFO) up to June 2024 was conducted to include English-language studies that reported statistically significant risk factors for changes in nutritional status during hospitalisation. A directed acyclic graphing method was used to visualise the interlinkage between contextual and individual risk factors identified. PRISMA Extension for Scoping Reviews was followed in reporting. Results: Of 8215 retrieved abstracts, 51 studies were included. Four contextual (ward type; food service satisfaction; medical-related mealtime interruption; nutrition care collaboration) and four individual factors (nutritional status prior admission; hospital length of stay; multimorbidity; disease acuity) were found to significantly predict nutritional decline during hospitalisation and were closely interrelated. Conclusions: More contextual risk factors are modifiable, suggesting a need for organisational strategies to optimise collaborative nutrition care and improve patient satisfaction with hospital food services to promote early nutritional intervention, particularly within the first three days of admission and for inpatients with multimorbidity, high disease acuity, or pre-existing malnourishment. Full article

Non-destructive evaluation techniques using infrared and terahertz waves were employed to examine an aged violin and an inlaid dish. The results suggest that active thermography can rapidly reveal the general features of deterioration, while optical coherence tomography and THz imaging visualise cross-sectional images by scanning. These techniques are complementary and provide useful information for conservation planning. Full article

Background and Objective: The intricate connection between daily behaviours and health necessitates robust monitoring, particularly with the advent of Internet of Things (IoT) systems. This study introduces an innovative approach that exploits the synergy of information from various IoT sources to assess the alignment of behavioural routines with health guidelines. The goal is to improve the readability of behaviour models and provide actionable insights for healthcare professionals. Method: We integrate data from ambient sensors, smartphones, and wearable devices to acquire daily behavioural routines by employing process mining (PM) techniques to generate interpretable behaviour models. These routines are grouped according to compliance with health guidelines, and a clustering method is used to identify similarities in behaviours and key characteristics within each cluster. Results: Applied to an elderly care case study, our approach categorised days into three physical activity levels (Insufficient, Sufficient, Desirable) based on daily step thresholds. The integration of multi-source data revealed behavioural variations not detectable through single-source monitoring. We demonstrated that the proposed visualisations in calendar and timeline views aid health experts in understanding patient behaviours, enabling longitudinal monitoring and clearer interpretation of behavioural trends and precise interventions. Notably, the approach facilitates early detection of behaviour changes during contextual events (e.g., COVID-19 lockdown and Ramadan), which are available in our dataset. Conclusions: By enhancing interpretability and linking behaviour to health guidelines, this work signifies a promising path for behavioural analysis and discovering variations to empower smart healthcare, offering insights into patient health, personalised interventions, and healthier routines through continuous monitoring with IoT-driven data analysis. Full article

Data of operational conditions of structural components, acquired, e.g., in structural health monitoring (SHM), is of great interest to optimise products from one generation to the next, for example, by adapting them to occurring operational loads. To acquire data for this purpose in the desired quality, an optimal sensor placement for so-called shape and load sensing is required. In the case of large-scale structural components, wireless sensor networks (WSN) could be used to process and transmit the acquired data for real-time monitoring, which furthermore requires an optimisation of sensor node positions. Since most publications focus only on the optimal sensor placement or the optimisation of sensor node positions, a methodology for both is implemented in a Python tool, and an optimised WSN is realised on a demonstration part, loaded at a test bench. For this purpose, the modal method is applied for shape sensing as well as a physics-informed neural network for solving inverse problems in shape sensing (iPINN). The WSN is realised with strain gauges, HX711 analogue-digital (A/D) converters, and Arduino Nano 33 IoT microprocessors for data submission to a server, which allows real-time visualisation and data processing on a Python Flask server. The results demonstrate the applicability of the presented methodology and its implementation in the Python tool for achieving high-accuracy shape sensing with WSNs. Full article

Digital technologies significantly influence architectural heritage perception, preservation, and presentation, particularly in reconstructing fragmented archaeological sites. This study explores innovative applications of algorithmic design, Heritage Building Information Modelling (HBIM), and interactive visualisation through the virtual reconstruction of the Roman Forum Transitorium in Musti, Tunisia—a complex historical site influenced by Numidian, Roman, and Byzantine cultures. The research integrates algorithmic modelling, digital surveying, and cloud-based collaboration, employing software tools such as Archicad, Rhino, Grasshopper, and Virtual Tour platforms. Central to this approach is a parametric, hypothesis-driven methodology, enabling the iterative exploration of multiple reconstruction scenarios informed by historical sources, architectural analyses, and scanned archaeological fragments. Immersive technologies enhance user engagement, allowing for the transparent exploration and interpretation of the site’s historical uncertainties. The results highlight the effectiveness of algorithmic methods in managing interpretative variability, offering flexible, academically rigorous, and publicly accessible virtual reconstructions. By emphasising the hypothetical nature of digital reconstructions and interactive visualisations, this research contributes meaningfully to digital archaeology, demonstrating how innovative algorithmic approaches can bridge academic scholarship and broader heritage preservation practices. Full article

Objective: To evaluate patient perceptions regarding ultrasound-guided embryo transfer, visualisation of embryos prior to transfer, and continuity of care with the same physician during in vitro fertilisation (IVF) treatments. Setting: Between January and September 2023, this study was conducted at the IVF MOMO’ FertiLIFE centre in Bisceglie, Italy. Design: Descriptive and observational study based on an anonymous survey administered to IVF patients at the time of embryo transfer. The goal was to assess the subjective emotional and psychological response to selected procedural elements of the embryo transfer process. Participants: Out of 284 distributed questionnaires, 200 were included in the final analysis. Inclusion required fully completed responses. Questionnaires with incomplete, unclear answers or patient refusal were excluded. The study group was compared with the general IVF patient population treated at the centre over the past 5 years to ensure representativeness. Methods: Patients completed a structured questionnaire using a five-point Likert scale. Statistical analysis included descriptive statistics, Spearman’s rank correlation, Friedman test, and exploratory factor analysis. Ethical approval was obtained (CELFer no. 07/2021), and all participants provided written informed consent. Results: The majority of patients reported a heightened sense of calm and reassurance during ultrasound-guided embryo transfer. Viewing embryos on a monitor before transfer was also positively perceived. A strong preference emerged for continuity of care with the same physician throughout the IVF process. While this study did not assess objective stress levels or clinical outcomes, the findings highlight the psychological comfort associated with these patient-centred practices. Limitations: This single-centre study is based on self-reported data and lacks objective assessments of psychological well-being. Therefore, results reflect personal perceptions rather than measurable clinical outcomes. Broader, multicentre research using validated psychological tools is needed to confirm and expand these findings. Furthermore, the questionnaire used in this study was developed internally and not validated externally with standardised psychometric instruments. Conclusions: This study provides insight into IVF patients’ subjective experiences, emphasising the perceived emotional benefits of specific procedural and relational aspects of care. These findings support the integration of patient-centred strategies—such as visual engagement and physician continuity—into routine IVF practice to enhance overall patient well-being. Full article

Handling preliminary information appropriately is a critical challenge for many aspects of systems engineering design. The topic is gaining renewed visibility due to the expanding possibilities to apply AI to preliminary information to support systems design, engineering, and management. However, there are few empirical studies of the practicalities of handling immature information and there is a lack of concretely developed, empirically evaluated, and practical approaches for clarifying information maturity levels, needed to ensure such information is appropriately used. This article addresses the gap, contributing new insight into how immature information is handled in industrial practice that is derived from interviews with 15 engineering and product development professionals from 5 companies. Thematic analysis reveals how practitioners work with preliminary information and where they require support. A solution was developed to address the empirically identified needs. In 5 follow-up interviews, practitioner feedback on this concept demonstrator was supportive. The main result of this research, in addition to the insights into practice, is a practical maturity grid-based assessment system that can help the providers of preliminary information self-assess and communicate information maturity levels. The assessments may be stored alongside the information and may be aggregated and visualised in CAD, augmented reality, or a range of charts to make information maturity visible and hence allow it to be more deliberately considered and managed. Implications of this research include that managers should promote greater awareness and discussion of preliminary information’s maturity and should introduce structured processes to track and manage the maturity of key information as it is progressively developed. The detailed maturity grids presented in this article may provide a foundation for such processes and can be adapted for particular situations. Full article

Augmented reality (AR) in industry improves training and technical assistance by overlaying digital information on real environments, facilitating the visualisation and understanding of complex processes. It also enables more effective remote collaboration, optimising problem solving and decision making in real time. This paper proposes a scoping review, using PRISMA guidelines, on the optimisation of industrial processes through the application of AR. The objectives of this study included characterising successful implementations of AR in various industrial processes, comparing different hardware, graphics engines, associated costs, and determining the percentage of optimisation achieved through AR. The databases included were Scopus, SpringerLink, IEEExplore, and MDPI. Eligibility criteria were defined as English-language articles published between 2019 and 2024 that provide significant contributions to AR applications in engineering. The Cochrane method was used to assess bias. The rigorous selection process resulted in the inclusion of 38 articles. Key findings indicate that AR reduces errors and execution times, improves efficiency and productivity, and optimises training and maintenance processes, leading to cost savings and quality improvement. Unity 3D is the most widely used graphics engine for AR applications. The main applications of AR are in maintenance, assembly, training and inspection, with maintenance being the most researched area. Challenges include the learning curve, high initial costs, and hardware limitations. Full article

Background: Gestational diabetes mellitus (GDM) is a prevalent pregnancy complication globally. Maternal vitamin D deficiency has been linked to the risk of GDM. The aim of this study was to explore and synthesise current evidence on the association between vitamin D deficiency and the development of gestational diabetes in Western countries. Methods: A scoping review was conducted in accordance with the Joanna Briggs Institute (JBI) methodological framework. Relevant studies were identified through a comprehensive search across seven databases: ProQuest Public Health, Google Scholar, PubMed, ScienceDirect, The Lancet, BMC Public Health, the International Journal of Women’s Health, and Scopus. Studies were included based on predefined inclusion and exclusion criteria relevant to the research question. The review followed the JBI protocol, and the PRISMA flowchart was used to guide and visualise the study selection process. Results: Nineteen studies were included in the final analysis, comprising research predominantly from Australia (5), the United States (5), and Canada (4). The findings indicate a notable association between vitamin D deficiency and GDM risk, moderated by factors such as maternal age, ethnicity, seasonal variation, and body mass index (BMI). Older maternal age and higher BMI were linked with lower vitamin D levels and a higher incidence of GDM. Ethnic groups with darker skin tones showed higher rates of vitamin D deficiency, increasing vulnerability to GDM. Seasonal patterns revealed lower vitamin D levels during winter months, correlating with greater GDM risk. These patterns underscore the need for targeted preventive strategies, including the potential role of vitamin D supplementation. Conclusions: This review supports an observed association between maternal vitamin D deficiency and increased GDM risk, influenced by demographic and environmental factors. While the evidence points to a potential preventative role for vitamin D, further high-quality research, including systematic reviews and meta-analyses, is essential to establish causality and inform clinical guidelines. The review identifies knowledge gaps and suggests directions for future research and clinical practice. Full article

This study aimed to develop a Causal Loop Diagram (CLD) to visualise how urban environment factors impact dementia and cognitive decline, and potential causal mechanisms. In Group Model Building workshops with 12 researchers, a CLD was created to identify factors contributing to cognitive decline, and the dynamic interrelationships between these factors. The factors were classified in nine main themes: urban design, social environment, travel behaviours, urban design by-products, lifestyle, mental health conditions, disease/physiology, brain physiology, and cognitive decline outcomes. Five selected feedback loops illustrated some dynamics in the system. The workshops helped develop a shared language and understanding of different perspectives from an interdisciplinary team. The CLD creation was part of a comprehensive modelling approach based on experts’ knowledge which informed other research outputs such as an evidence gap map and an umbrella review, helped the identification of environmental variables for future studies and analyses, and helped to identify future possible systems-based interventions to prevent cognitive decline. The study highlights the utility of CLDs and Group Model Building workshops in interdisciplinary research projects investigating complex systems. Full article

Background: The Functional Resonance Analysis Method (FRAM) analyses discrepancies between written protocols (Work-as-Imagined) and real-world practice (Work-as-Done) in healthcare. Work-as-Done is created based on multiple stakeholders, leading to variability in reported functions. No guidance exists how to manage this variability. This study examines between-stakeholder variation in Work-as-Done and its impact on differences from Work-as-Imagined in FRAM visualisations. Methods: Two FRAM studies were analysed: delirium diagnosis and treatment (1) and perioperative anticoagulant management in two hospitals (2). Heatmaps visualised between-stakeholder variability of reported functions in Work-as-Done. We assessed the impact of including only functions shared by multiple stakeholders on Work-as-Imagined versus Work-as-Done comparisons. Results: In study 1, 23 of 33 functions were shared among at least two stakeholders. In study 2, stakeholders shared 30 of 33 functions in Hospital 1 and 29 of 32 functions in Hospital 2. Including or excluding functions, e.g., only mentioned by one stakeholder, influenced the observed differences between Work-as-Imagined and Work-as-Done. Conclusions: Between-stakeholder variability in both studies influenced differences between Work-as-Imagined and Work-as-Done, which often is the starting point improving the process. Showing between-stakeholder variability in FRAM studies enhances transparency in researcher decision-making. This supports more informed analysis and discussion in process improvement efforts. Full article

Decentralized desalination systems driven by renewable energy sources have surfaced as a feasible way to alleviate water scarcity in arid and rural areas. This bibliometric study aims to clarify the research trends, conceptual frameworks, and cooperative dynamics in the scientific literature on decentralized renewable-powered desalination techniques. Using a thorough search approach, 1354 papers were found. Duplicates, thematically unrelated works, and entries with poor information were removed using the PRISMA 2020 framework. A selected 832 relevant papers from a filtered dataset were chosen for in-depth analysis. Quantitative measures were obtained by means of Bibliometrix; network visualisation was obtained by means of VOSviewer (version 1.6.19) and covered co-authorship, keyword co-occurrence, and citation structures. Over the previous 20 years, the data show a steady rise in academic production, especially in the fields of environmental science, renewable energy engineering, and water treatment technologies. Author keyword co-occurrence mapping revealed strong theme clusters centred on solar stills, thermoelectric modules, reverse osmosis, and off-grid systems. Emphasizing current research paths and emerging subject borders, this paper clarifies the intellectual and social structure of the field. The outcomes are expected to help policy creation, cooperative projects, and strategic planning meant to hasten innovation in sustainable and decentralized water desalination. Full article

Project delays remain a persistent challenge in the construction industry, having significant financial implications and contributing to disputes between project participants. Forensic Delay Analysis (FDA) has emerged as a specialised function that identifies the root causes of such delays, quantifies their duration, and assigns responsibility to the appropriate parties. While FDA is a widely practised process, it has yet to fully exploit the potential of emerging technologies. This study explores the integration of both existing and emerging technologies for enhancing FDA processes. A Design Science Research (DSR) approach is adopted, with data collection methods that involve the use of the literature, archival materials, case studies and survey methods. The research demonstrates how the use of technologies, such as database management systems (DBMSs), building information modelling (BIM), artificial intelligence (AI) and games engines, can improve the analytical efficiency, data management, and presentation of findings through a case study. The study showcases the transformative potential of these interventions in streamlining FDA processes, ultimately leading to more accurate and efficient resolution of construction disputes. The proposed process is exemplified by the development of a prototype: the Forensic Information Modelling Visualiser (FIMViz). The FIMViz is a practical tool that has received positive evaluation by FDA experts. The prototype and the enhanced FDA process model that underpins it demonstrate significant advancement in FDA practices, promoting improved decision-making and collaboration between project participants. Further development is needed, but the results could ultimately streamline the FDA process and minimise the uncertainties in FDA outcomes, thus reducing the incidence of costly disputes to the wider economic benefit of the industry generally. Full article