Digital, Volume 6, Issue 3 (September 2026) – 27 articles

Data are becoming increasingly crucial to business and social digitalization, as such data have become a strategic asset that accelerates economic competitiveness and digitalization of society. In a societal context, it is important to maintain complete control over data, mainly once it is to be exchanged or shared. Another challenge is associated with who has control over data produced from digital platforms used by citizens. This ability is termed data sovereignty. Digital sovereignty refers to the concept of control, self-determination, and the ability of individuals or business entities to govern and exercise their right to utilize their data. As such, digital and data sovereignty is of paramount importance to enhance data usage and ownership policies. However, less attention has been given to exploring how digital sovereignty can be achieved by digital platforms used by citizens and what policies should be put in place to re-enforce the digital rights of citizens. Moreover, there are fewer guidelines on digital sovereignty requirements in the literature. This article employs qualitative review and comparative policy analysis of European Union (EU)–United States (US) digital initiatives to identify and aggregate policies aimed at providing a common understanding of digital and data sovereignty. This study contributes to addressing challenges faced by companies in implementing initiatives needed to ensure that the digital sovereignty of citizens is preserved when they use digital platforms. Findings from this study present key requirements (technical, legal–institutional, individual, infrastructural, and cross-cutting dimensions) and digital sovereignty initiatives that apply to citizens within the EU–US. Full article

Digital transformation can improve supply chain sensing, but recovery depends on whether reliable information is converted into coordinated operational action. This study develops a simulation-based case study that integrates data-quality-adjusted indicator fusion, a six-dimensional resilience index, system dynamics, and phase-based constrained policy search. The case represents a component-intensive discrete-manufacturing network with 28 tier-1 suppliers, nine qualified alternatives, seven logistics nodes, and five product families. A reproducible 36-month supplier-product panel (5040 unit-month records) is generated from a fixed seed and an explicit machine-readable configuration; it is not presented as confidential company data. Completeness, timeliness, cross-source consistency, and out-of-sample predictive contribution are defined explicitly, and an event-preserving gate prevents reliability shrinkage from attenuating logged disruption signals. Twelve indicators measure robustness, redundancy, agility, visibility, collaboration, and adaptive recovery; time-to-recovery is reserved as an outcome rather than included in the input index. The dynamic model is solved at a 0.25-month step over a 24-month policy horizon. Under a compound supplier-capacity, demand, and logistics shock, the balanced phase-based portfolio increases minimum resilience from 0.490 to 0.680 and reduces time-to-recovery from 8.4 to 3.5 months relative to the efficiency baseline. At an equal 6.9% incremental-cost budget, the integrated portfolio retains a 0.029–0.071 advantage in minimum resilience over single-mechanism alternatives. Holdout replay, alternative weighting schemes, event-gate tests, parameter perturbations, and unseen shock combinations establish numerical robustness but do not constitute external empirical validation. The findings indicate, for this specified model and case, that visibility creates resilience value when coupled with response authority, supplier coordination, flexible capacity, and targeted buffers. Full article

Human Digital Twins (HDTs) extend traditional Digital Twin (DT) concepts by modeling both humans and hospital processes to support smarter and more human-centered healthcare. By integrating Industry 4.0 (I4.0) technologies with the human-centric principles of Industry 5.0 (I5.0), HDTs offer new opportunities to improve hospital operations. This study presents a PRISMA-based systematic literature review to examine the role of HDTs in hospital operations. A total of 329 papers were identified through the initial search, and after the screening process, 22 studies were included for in-depth analysis. The review combines bibliometric analysis to examine publication trends, leading authors, contributing countries, and keyword co-occurrence with a content analysis to identify the main research themes. Three major themes emerged: (1) HDT architectures and data integration, (2) human-centric and governance aspects, including explainable artificial intelligence and privacy, and (3) operational and clinical outcomes, including patient flow, resource utilization, and staff support. Based on these findings, the study proposes a four-layer HDT framework for practical implementation in hospital operations. Although the reviewed studies indicate that HDTs have considerable potential to improve operational efficiency and strengthen human involvement, most existing research remains conceptual or simulation-based. Future research should therefore prioritize real-world implementation and validation while incorporating ethical, explainable, and sustainable design principles. Full article

Automated bridge surface defect detection is essential for improving the efficiency and objectivity of infrastructure inspection under complex field imaging conditions. This study proposes a Multi-Scale Detection Transformer (MS-DETR), an RT-DETR-based detector that integrates HeteroFusionNet, a multi-objective scale-aware integration network (MOSAIN), and a global attention two-dimensional module (GATM). HeteroFusionNet combines shared shallow feature extraction with heterogeneous dual-branch deep modelling to reduce redundant computation and enhance complementary local and global representations. MOSAIN injects high-resolution shallow details into the P3 feature path to improve small-defect recognition, whereas GATM adapts high-level attention encoding to dense two-dimensional visual features. On the self-built bridge defect dataset, MS-DETR achieved a mAP50 of 65.4% and an F1-score of 0.64, with 14.33 M parameters, 39.1 GFLOPs, and 62.3 FPS on an RTX 4090 GPU. On the RDD (China) road defect dataset and the VisDrone2019 dataset, MS-DETR achieved mAP50 values of 88.9% and an AP50 of 0.487, respectively. These results demonstrate that MS-DETR achieves competitive detection accuracy while maintaining a favorable balance between model complexity and inference speed under the evaluated experimental settings. Full article

The increasing integration of Artificial Intelligence (AI) into classroom practice has created the need for valid instruments to assess teachers’ readiness for AI integration. The present study developed and psychometrically validated the Teachers’ Readiness to integrate Artificial Intelligence (TRi-AI) scale, conceptualizing readiness as a multidimensional construct comprising Cognitive Conditions, Affective Conditions, Commitment, Self-efficacy, Ethical Considerations, and Worries. A total of 645 in-service primary and secondary school teachers participated in the study. The findings from Exploratory and Confirmatory Factor Analyses supported the hypothesized six-factor structure. The final scale comprised 36 items, χ²(579) = 1098.950, p < 0.001, CFI = 0.943, TLI = 0.938, RMSEA = 0.037, 90% CI [0.034, 0.041], and SRMR = 0.044. Reliability, convergent validity, discriminant validity, and evidence of practical measurement invariance across gender substantiated the psychometric adequacy of the instrument. Additionally, Exploratory Graph Analysis, Item Stability Analysis, and Network Comparison Test provided complementary psychometric evidence for the robustness of the proposed framework. The TRi-AI scale is proposed as a reliable and valid multidimensional instrument that can support both future research and educational practice. Full article

STEAM approaches create new opportunities for students to develop thinking skills connected to technical and scientific education. By combining different areas of knowledge, STEAM encourages students to explore ideas from multiple perspectives and find creative solutions to challenges. This approach is highly relevant in teacher training, as it prepares educators to create innovative and engaging learning experiences. This study examines how an accredited teacher professional development workshop supported in-service secondary teachers in designing mobile game-based learning experiences for sustainability through the integration of STEAM, Universal Design for Learning, and Open Schooling. The study adopted a qualitative case study design based on thematic analysis of documents related to games created by teachers, implementation presentations, and teachers’ reflections. The analysis shows that teachers engaged with educational technology in an authorial and design-oriented role, creating and refining situated digital resources. Teacher authorship and mobile learning design capacity were most prominent; UDL appeared mainly through multimodal and motivational features, alongside perceived student engagement. Technological reliability, accessibility, and data-validity issues remained important constraints. This context supported professional development by enhancing teachers’ capacity to design STEAM, multimodal, and place-based digital learning experiences for sustainability, while articulating the OpenUS4ALL and EduCITY projects. Full article

This exploratory mixed-methods study examines how an edge artificial intelligence (edge AI) gas-sensing project is associated with vocational upper-secondary students’ self-reported problem-solving attitudes in an authentic classroom setting. Thirty-eight students specializing in Electrical, Electronics, and Automation addressed the same design problem: developing a gas-sensing prototype by collecting sensor data, training a machine-learning classifier, and deploying the model on embedded hardware for local inference and real-time decision support without continuous reliance on cloud processing. Three instructional pathways were compared: (i) Maker Learning (ML; n = 12) with hands-on prototyping and on-device testing, (ii) Virtual Learning (VL; n = 13) with simulation-based activities, and (iii) Traditional Learning (C; n = 13) with teacher-guided instruction. Quantitative data were collected through three administrations of the Problem-Solving Inventory (PSI), complemented by post-intervention semi-structured interviews. Exploratory analyses indicated statistically significant changes in total PSI scores across all pathways (p ≤ 0.003), reflecting more favourable problem-solving appraisals. At post-test, the ML and VL pathways showed more approach-oriented profiles than the Traditional Learning pathway, with large effect-size estimates (ML − C: r = 0.714; VL − C: r = 0.611), while for problem-solving confidence, the pattern favoured the Maker Learning pathway (ML − VL: r = 0.496). Interviews provided complementary interpretive context, highlighting iterative debugging, feedback, collaboration, and artefact ownership. Within the limits of this exploratory vocational-school classroom implementation, the findings and effect-size estimates were interpreted cautiously. Overall, the study contributes by depicting how edge AI gas-sensing projects may support positive problem-solving appraisals and outlining a meaningful pathway for the integration of edge AI technologies in vocational education. Full article

Wireless Sensor Networks (WSNs) are fundamental to the expansion of the Internet of Things (IoT), yet severe node energy constraints remain the primary bottleneck for remote environmental monitoring where power infrastructure is unavailable. Because these devices rely on finite battery capacities, optimizing energy usage is critical for maximizing network longevity and architectural sustainability. Sourcing literature across the Scopus, IEEE Xplore, and Elsevier digital databases, this study executes a systematic review evaluating a final cohort of $n=86$ contemporary energy management frameworks published between 2020 and 2026. The analysis synthesizes advanced multi-tier optimization techniques, specifically focusing on hierarchical clustering methodologies, metaheuristic routing protocols, and advanced scheduling algorithms. Beyond traditional approaches, the technical findings investigate the cross-layer impacts of duty cycle scheduling, transmission power control, and sleep protocols on maintaining rigid network coverage and connectivity. Ultimately, this review identifies significant research gaps regarding topological fault tolerance and localized load imbalances near base stations. The findings highlight how the strategic integration of cohesive, cross-layer hybrid optimization strategies can mitigate active energy dissipation, providing actionable technical recommendations for future IoT-based WSN architectures. Full article

Manufacturing sectors and ecosystems can improve their innovation performance through digital platforms, connected intelligence, and organisational settings that enable collaboration among experts and ecosystem members. The convergence of skills and capabilities distributed across humans, organisations, communities, and AI agents creates intelligent environments that can support ecosystemic and transformative innovation. To examine this hypothesis, we follow a three-stage methodology. First, we develop a modelling framework based on a vector autoregressive model, in which a weighted matrix representing directed binary couplings among human, collective, and machine intelligence drives the transition of a manufacturing ecosystem from a baseline innovation state to a more advanced one. Second, we present the SmartGreenEcos experiment, which develops an intelligent environment adapted to a specific manufacturing ecosystem. The experiment demonstrates the feasibility of the model’s abstract architecture by implementing digital platforms, e-services, and AI agents that facilitate inter-company collaboration, experimentation, and innovation. Third, we use simulations and analyse the eigenvalues and eigenvectors of the weighted matrix to examine the internal dynamics of intelligent environments and identify key thresholds and drivers of change. The results of this three-stage methodology provide insights into the design of intelligent environments and the interaction parameters through which connected intelligence can improve innovation performance. Full article

Transitioning cultivated land from a narrowly defined production resource into a coordinated multifunctional asset is a cornerstone of agricultural modernization. Despite this imperative, current land utilization in China remains largely constrained by a singular production focus, resulting in suboptimal multifunctionality. Although digitally driven agricultural new quality productive forces (ANQPFs) are posited as a critical catalyst for functional restructuring, empirical evidence quantifying their relationship with cultivated land multifunctionality (CLM) remains limited. To examine the association between ANQPF and CLM, this study employs panel data from 115 prefecture-level cities across the Yangtze River Basin, China, spanning the period 2013–2023. The empirical results indicate that ANQPF is significantly and positively associated with CLM. These associations are robust to a battery of robustness checks, and endogeneity tests provide additional evidence supportive of a positive association. Transmission pathway analysis suggests that the positive association operates through three pathways: increasing the main business revenue of agricultural product processing enterprises above a designated size, expanding the number of agricultural technology patents, and improving the level of agricultural socialized services. Subgroup analyses, supplemented by Chow tests of coefficient equality, reveal that these associations tend to be larger in non-major grain-producing regions, areas with lower per capita GDP, and the upper and middle reaches of the Yangtze River Basin. Threshold effect analysis further demonstrates that once ANQPF exceeds a certain level, the positive association exhibits diminishing marginal returns; a similar but weaker pattern is observed for leading enterprises. These findings provide policy implications for developing ANQPF in accordance with local conditions and for synergistically optimizing CLM patterns. Full article

Crime offense descriptions are often recorded as unstructured text, making large-scale analysis and categorization difficult. This study proposes a semantic clustering framework for Thai crime offense descriptions using sentence embeddings, dimensionality reduction, and unsupervised clustering. Two datasets were obtained from Thonglor Metropolitan Police Station and Mueang Nonthaburi Police Station, Thailand. After preprocessing, the datasets contained 962 and 902 unique offense descriptions, respectively. Each description was transformed into a 768-dimensional embedding using SimCSE-PhayaThaiBERT. The embeddings were represented in Principal Component Analysis (PCA) Space and Uniform Manifold Approximation and Projection (UMAP) Space and clustered using K-Means, DBSCAN, HDBSCAN, and OPTICS. The results showed that UMAP Space generally provided more useful clustering results than PCA Space. Although DBSCAN achieved the highest internal clustering scores, it classified most records as noise. In contrast, HDBSCAN provided a more balanced result by maintaining strong clustering quality while retaining more records for interpretation. Qualitative analysis showed that the discovered clusters corresponded to meaningful offense categories. The proposed framework can support exploratory analysis of Thai crime records without requiring manually labeled data. Full article

Today, data are no longer confined to numerical values arranged in row-by-column matrices or stored neatly within relational databases. One of the defining characteristics of big data is its high variety, encompassing unstructured and multimodal forms such as text, audio, images, and video. These data types dominate contemporary domains including social media, digital humanities, biomedical research, education, and surveillance systems. Yet these data types remain difficult to manage and analyze using traditional data management architectures. To cope with this shift, modern data management systems must move beyond schema-driven designs and incorporate multimodal artificial intelligence capable of understanding, integrating, and reasoning across heterogeneous data modalities. This article examines how multimodal AI, in particular large multimodal foundation models, can be leveraged to support the ingestion, representation, organization, and analysis of unstructured data. It discusses emerging multimodal data management frameworks, outlines a conceptual pipeline for multimodal data analysis, and highlights key challenges related to scalability, interpretability, and governance. By situating multimodal AI at the core of data management, this work argues that effective data analysis in the era of big data requires systems that treat meaning, context, and cross-modal relationships as first-class computational objects rather than afterthoughts. Full article

Recent lunar missions have generated a growing demand for automated and reliable processing of lunar regolith images. However, imaging degradations, limited annotations, and the lack of paired clean–degraded reference data still hinder the robustness and transferability of existing methods. Unlike previous studies focusing primarily on high-level geological interpretation, this review emphasizes the foundational role of low-level restoration and reconstruction in lunar regolith analysis. We organize recent progress into a full-pipeline framework spanning image reconstruction, morphology extraction, and geological interpretation, while clarifying the evidential roles of regolith-specific, lunar-surface-transferable, and general computer-vision references. Specifically, we review physically guided restoration, particle segmentation, and three-dimensional morphological quantification for irregular regolith grains, with particular attention to dense packing, occlusion, boundary ambiguity, and limited global-context reasoning in CNN-based segmentation. We further discuss downstream applications including mineralogical inversion, space-weathering characterization, multimodal fusion, and cross-modal collaborative representation linking microscopic regolith characterization with macroscopic orbital and in situ observations. The review also identifies degradation-induced error propagation across the pipeline, where unresolved low-level degradations may bias boundary delineation, morphological statistics, and downstream compositional and geological interpretation. We conclude that physically constrained benchmarks, joint restoration-analysis models, and lightweight transferable vision models are critical for improving scientific fidelity in data-limited and resource-constrained lunar exploration. Full article

Potato quality is determined by multiple physicochemical indicators, including dry matter content (DC), starch content (SC), and color parameters (lightness L*, redness a*, yellowness b*, and browning index (BI)). Conventional spectrometers are costly, non-portable and lack wireless in-situ monitoring, restricting efficient postharvest quality assessment. Chemical methods are destructive and inefficient for field inspection and high-throughput detection. The primary objective of this study was to develop and validate a low-cost wireless 12-channel visible/near-infrared (Vis/NIR) spectral sensing system, comprising 6 Vis channels and 6 NIR channels, for the real-time non-destructive prediction of six potato quality indicators. After preprocessing the spectral data with mean normalization, a multiple linear regression (MLR) model was established to optimize the prediction performance of quality parameters. The six indicators evaluated were DC, SC, L*, a*, b*, and BI. Statistical analysis and cross-validation were further conducted to quantitatively evaluate the stability and credibility of the prediction model. Among these, the b* parameter demonstrated the most robust predictive performance, achieving a cross-validated coefficient of determination (R²_CV) of 0.881. The MLR model was integrated into the sensing hardware to realize synchronous data collection and prediction. This study provides a validated, low-cost, wireless solution for rapid potato quality assessment under controlled conditions, offering a potential alternative to conventional spectrometers and destructive chemical methods. Full article

Image interpolation plays an important role in many computer vision and image processing tasks, such as image resizing, denoising, and restoration. Most traditional interpolation algorithms work on the time domain and deal with all image regions in a similar manner and do not differentiate between edges and smooth areas, resulting in blurring effects. To achieve high efficiency, all these methods are complex and time-consuming. To tackle these challenges, this work offers a low-cost image interpolation algorithm and a high-quality image-scaling method. The algorithm starts by applying edge detection operators to estimate detailed sub-bands that are required by the inverse WT to construct high-quality scaled images with low-cost calculations. The algorithm is evaluated on twenty different datasets including 5500 images overall. The results indicate the high restoration quality of the proposed algorithm compared to state-of-the-art techniques. The proposed algorithm achieved the highest average SSIM and PSNR values of $0.998$ and 50 dB, respectively. Moreover, the rational cost of the proposed work was reduced to $1.75$ compared to the highest existing method with a rational cost of 8437. Full article

This paper provides a comprehensive and systematic review of artificial intelligence (AI) integration in smart logistics management, evaluating seven core technology clusters: machine learning (ML), deep learning (DL), natural language processing (NLP), computer vision (CV), internet of things (IoT), blockchain, and data mining. While the prior literature reviews analyze these technologies in isolation, this study directly addresses the critical research gap of technology fragmentation and integration challenges across the supply chain. Our main contribution is a novel, three-layered conceptual framework that structures smart logistics into interdependent layers: data collection (IoT, RFID, GPS), intelligent processing (ML/DL, NLP, computer vision), and logistics decision-making (route optimization, warehouse automation, risk management). By detailing the theoretical foundations (information processing, dynamic capabilities, and Cybernetics), inter-module correlations, and a phased four-stage deployment roadmap, this review provides a unified, practical blueprint for organizations transitioning from legacy systems to fully autonomous, cognitive logistics networks. Full article

(1) Background: Hypertension is a prevalent chronic condition requiring sustained self-management to prevent complications; however, long-term adherence to monitoring, medication, and lifestyle modification remains suboptimal. Mobile health (mHealth) technologies, supported by cloud-based connectivity, offer scalable platforms for structured remote monitoring and patient engagement. This study aimed to design, develop, and validate MyHTCare, a user-centered mHealth application for comprehensive hypertension self-management and connected remote monitoring. (2) Methods: An Agile-based, three-iterative development framework was adopted, incorporating clinical recommendations and inputs from patients, caregivers, and physicians. The application was developed using Flutter and integrated with Cloud Fire store to enable secure cloud-based data storage and real-time synchronization. Core modules included blood pressure tracking, medication reminders, infographic-based lifestyle education, and automated clinical alerts. Content validation involved 10 experts (clinicians and IT professionals) and 30 end users (adults with hypertension or caregivers). Usability was assessed using a pre-tested structured questionnaire, and educational materials were evaluated using the Patient Education Materials Assessment Tool for Audiovisual Materials (PEMAT-A/V). (3) Results: End-user validation demonstrated high usability, with mean scores ranging from 4.4 to 5.0 on a 5-point scale. Educational materials achieved 100% actionability and 92–100% understandability. Expert evaluation showed high ratings across usability domains, with acceptability scores exceeding 70%. (4) Conclusions: MyHTCare demonstrated strong content validity and usability, supporting further clinical evaluation to determine its effectiveness in improving blood pressure control and self-management. Full article

Hyperspectral imaging is a well-established remote sensing technique for material detection and classification, relying on hundreds of reflectance bands to exploit the spectral signatures of surface materials. Although hyperspectral imagery has demonstrated excellent capabilities for material identification, its operational implementation may be constrained in some applications due to data volume and processing requirements. Consequently, there is growing interest in evaluating the capability of lower-dimensional multispectral imagery for material detection tasks. In this sense, this article proposes as its contribution the comparative evaluation of machine learning models and neural networks for asbestos–cement detection on VNIR imagery. For the development of this research, the CRISP-DM methodology was adapted into four phases: P1. Business and data understanding; P2. Data preparation; P3. Modelling and evaluation; P4. Model deployment. At the results level, three datasets with different numbers of bands were constructed, which were structured by adding to the original dataset an additional layer with the NDVI and two additional layers with the PCA components of the original image. Across the three datasets, four machine learning models and one neural network model were tuned and evaluated, yielding as a result that in all three datasets the KNN and neural network models achieved the best performance. Likewise, it was found that the detection capability of the models improved with the inclusion of the additional bands. The proposed approach serves as a reference to be extrapolated by research centres and universities for the detection of asbestos and other materials in VNIR images, with a view toward integration into resource-constrained systems and specifically into environmental monitoring systems. Full article

Customer prioritization in e-commerce remains dominated by value-based logics that allocate retention effort to the most profitable customers, even though risk-based targeting can be ineffective when intervention responsiveness is ignored. This study aims to develop and empirically test a Value–Risk–Recoverability (VRR) framework that prioritizes service-recovery effort under a fixed intervention budget. The framework draws its three axes from the synergy of three theoretical streams: customer-equity theory motivates the value axis, the churn and defection-management literature motivates calibrated dissatisfaction risk, and service-recovery theory—through the distinction between operational and structural causes of failure—motivates the recoverability axis, which operationalizes the intervention-responsiveness critique of risk-based targeting. The framework is instantiated on the public Brazilian marketplace dataset by Olist (91,954 customers; 93,663 delivered orders, 2016–2018) using unsupervised clustering for behavioral segmentation, calibrated gradient-boosting models to predict order-level dissatisfaction under a strictly temporal hold-out, and SHAP attribution to decompose predicted risk into operational and structural components. Results show that dissatisfaction becomes predictable mainly as fulfillment unfolds (out-of-sample AUC of 0.72 with in-fulfillment signals versus 0.61 at order time); that roughly 76% of predicted risk loads on operational, addressable factors; and that, at a 10% intervention budget, value-based targeting captures only about 30% of realized recoverable value against roughly 96% for risk-aware policies. The study contributes a theoretically grounded, interpretable, and reproducible prioritization logic for service recovery, together with an explicit account of the boundary conditions under which each axis carries decision-relevant information. Full article

This study describes the second iteration of VLEPIC, a gamified and personalised virtual learning environment (VLE) for secondary English students in Ecuador. Adopting a design-based research approach, it focuses on student interaction and system improvement. A mixed-methods design combined survey results, digital logs, and student comments. Results indicated acceptable usability; however, log data showed that platform use was episodic and task-oriented, with no evidence of daily use. Instead, students logged in repeatedly for specific tasks, and participation declined towards the end. Feedback pointed to mobile reading issues, slow loading times, and confusion around task submission. These findings refine design principles (DPs) for schools with limited resources. The resulting priorities are to design for frequent re-entry, simplify task submission, and present progress more clearly. Together, these DPs offer practical guidance for VLEs in such settings. They illustrate how design can support continuity, reduce uncertainty, and sustain learning routines when access is interrupted. Full article

Ecuador’s agricultural sector plays a strategic role in the national economy; however, agricultural data remains fragmented across heterogeneous and isolated sources, limiting integrated analysis and evidence-based decision-making. This study proposes and implements a Big Data analytics framework based on the Medallion architecture and interactive dashboards to integrate, process, and visualize agricultural indicators from INEC, ESPAC, Ecuador Open Data, and FAOSTAT for the 2010–2024 period. The proposed framework adopts the Team Data Science Process (TDSP) methodology and structures workflows into Bronze, Silver, and Gold layers using Databricks for scalable data ingestion, transformation, and dimensional modeling. Interactive dashboards were developed in Tableau Public to support dynamic analysis of agricultural production, trade, producer prices, losses, and producer profiles. A comparative performance evaluation between Databricks Free Edition and Azure Databricks was conducted using SQL analytical workloads and dashboard interaction tests. Results showed that Azure Databricks reduced query execution times by up to 57%, especially in aggregation and join operations. Usability validation with 31 agricultural stakeholders reported high acceptance levels, including a 100% recommendation rate and a data trust score of 4.45/5. The findings demonstrate that scalable and low-cost Big Data technologies can effectively support agricultural digital transformation. Full article

Deep Neural Networks (DNNs) are increasingly being used in the design of industrial safety-critical autonomous applications such as autonomous vehicles, industrial robotics, and medical instrumentation and control systems. Ensuring reliable and robust operation of the DNN-based safety-critical systems is challenging because of the complex structure of DNN hardware accelerators utilized for inference that are susceptible to the effects of multi-faults, common-cause fault models, data uncertainties, and unpredictable erroneous behavior. Additionally, transient, permanent, and timing faults affect the accelerator design of processing elements, memory arrays, and datapaths, propagate through DNN computations, and potentially can cause catastrophic failures at the system level. The objective of this survey paper is to systematically evaluate the state-of-the-art fault-tolerant DNN accelerator architectures with particular emphasis on their applicability to safety-critical autonomous systems in industry. The survey investigates architectural perspective, fault modeling, and platform-level trade-offs, runtime resilience, validation practices, and certification readiness, following a PRISMA methodology with evidence-driven synthesis and unbiased study selection. Database searches across IEEE Xplore, Scopus, and Web of Science identified 200 records, of which 82 studies were included based on predefined inclusion and exclusion criteria emphasizing industrial safety-critical relevance, fault modeling at the hardware level, and the implementation at the architectural level. The results indicate that there was a clear shift from traditional redundancy-based approaches to cross-layer and adaptive approaches that provide better trade-offs between performance, reliability, and hardware overhead. The current studies presented are based on simplified fault models, incomplete validation- procedures, and limited consideration of system-level and certification needs, which often do not consider critical failure modes such as Silent Data Corruption (SDC). This has resulted in a significant gap between research-level solutions and industrial deployment requirements. This survey underscores the need for scalable, integrated, and certification-aware design approaches to help connect fault modeling, architectural resilience, validation, and safety assurance to develop reliable and deployable DNN accelerator systems for next-generation industrial safety-critical autonomous applications. Full article

Digital twin (DT) technology has expanded far beyond its industrial origins, increasingly finding application across environmental and territorial domains. This review provides a structured mapping of DT deployments at environmental and territorial scales over the period 2020–2025, examining 117 peer-reviewed publications (109 applied studies and 8 review articles) through a structured 16-parameter classification framework. The review traces three major conceptual shifts in the DT paradigm: from industrial assets to living entities, from discrete systems to Earth-scale representations, and from closed deterministic models to ecological and systemic frameworks, as reflected in the emergence of ecological digital twins (EcoDTs), environmental digital twins (EDTs), and territorial digital twin (TDT) definitions. The results reveal a clear growth trajectory in DT applications across themes, with urban systems as the most consolidated application domain, and progressive diversification into marine, coastal, forestry, river/lake, and Earth system applications from 2022 onward. Institutional actors dominate production in this space, aligned with European flagship initiatives such as Destination Earth (DestinE) and the European Digital Twin of the Ocean (EDITO). The findings position and expand the notion of territorial digital twins as an evolving paradigm, underscoring both the momentum generated by EU digital and environmental policy and the need for integrated tools to answer and respond to key environmental challenges. Full article