Search Results (4,985)

Cybersecurity operations in IoT and edge environments require fast, evidence-grounded decisions under strict resource and trust constraints. While large language models can support triage and incident analysis, their parametric knowledge may be outdated and prone to hallucination. Retrieval-augmented generation (RAG) improves grounding by conditioning responses on retrieved evidence, but also introduces new risks such as knowledge-base poisoning, indirect prompt injection, and embedding leakage. Federated learning enables collaborative adaptation without centralizing sensitive data, motivating federated RAG (FedRAG) architectures for distributed cybersecurity deployments. This study presents a deployment-oriented scoping review of FedRAG for cybersecurity. The review follows PRISMA-ScR reporting guidance and synthesizes 82 studies published between 2020 and 2026, identified through keyword search and citation snowballing over OpenAlex, arXiv, and Crossref. We develop a taxonomy that clarifies the components of federated systems, deployment locations, trust boundaries, and protected assets. We further map the combined RAG+FL attack surface, summarize practical defenses and system patterns, and distill actionable guidance for secure, privacy-preserving, and efficient FedRAG deployment in real-world IoT and edge scenarios. Our synthesis highlights recurring trade-offs among robustness, privacy, latency, communication overhead, and maintainability, and identifies open research priorities in benchmark design, governance mechanisms, and cross-silo evaluation protocols for practical deployment. Full article

Candidozyma auris (formerly Candida auris) is an emerging multidrug-resistant pathogenic fungus with an increased ability to cause outbreaks in healthcare facilities, leading to poor patient outcomes. Since its initial discovery in 2009, C. auris has spread rapidly across continents and is now classified by both the Centers for Disease Control and Prevention (CDC) and the World Health Organization (WHO) as a critical-priority pathogen. This review summarizes current knowledge on the origin, taxonomy, microbiology, and virulence mechanisms of C. auris, emphasizing its thermotolerance, osmotolerance, and biofilm-forming capacity on biotic and abiotic surfaces, as well as aspects related to its antifungal drug resistance and management. These features, together with its genomic plasticity, contribute to persistence, transmission, and drug resistance. Emerging evidence also supports a potential link between climate change and C. auris evolution, highlighting environmental adaptation as a driver of pathogenicity. Combating C. auris will require multidisciplinary efforts to mitigate its expanding global impact. Full article

Chryseobacterium indologenes MA9 is a causative agent of root rot disease in Panax notoginseng (P. notoginseng), with its high incidence being a major manifestation of continuous cropping barriers, severely hindering the sustainable development of the P. notoginseng industry. In this study, a novel lytic bacteriophage, MA9V-3, was isolated from wastewater, targeting C. indologenes MA9. The phage produced clear plaques, ranging from 1 to 3 mm in diameter, with a surrounding halo. Phage MA9V-3 achieved an adsorption rate of up to 80% after 30 min of contact with C. indologenes MA9, a latent period of approximately 40 min, and an average burst-size if 160 PFU/cell. Transmission electron microscopy revealed that phage MA9V-3 possesses an icosahedral head and a contractile tail, exhibiting a typical myovirus-like morphology. According to the latest ICTV taxonomy, MA9V-3 belongs to the class Caudoviricetes, and the phage’s biocontrol efficacy and inhibitory capacity were evaluated at different multiplicity of infection (MOI s). The results showed that the highest titer recorded at 1.6 × 10¹⁰ PFU/mL. Whole-genome sequencing revealed that MA9V-3 is a double-stranded circular DNA virus, with a genome length of 103,203 bp, GC content of 34.29%, and 150 open reading frames (ORFs), one of which is related to tRNA. Only 13 of these ORFs encode known functional sequences, likely due to the limited available gene data for such phages in the database, with additional details on hypothetical proteins yet to be uncovered. Comparative database analysis confirmed that the phage genome contains no antibiotic resistance or toxin-related genes. Phage therapy experiments were performed using MA9V-3 and two other phages screened in our laboratory. The experimental results showed that phage MA9V-3 may be a potential candidate for effectively controlling the infection of Panax notoginseng by C. indologenes MA9, and offering valuable insights into the potential application of phage therapy for managing bacterial plant diseases. Full article

Each of the stages of the New Product Development (NPD) process is vulnerable to different forms of risk. The existing categorizations of these risks are partial, ill-defined, or lack depth. Deploying a systematic literature review methodology, we identify 65 empirical studies that identify sources of risk in NPD. Synthesizing this information, we develop a broad, meaningful, and recognizable taxonomy with five main categories of risk, each with a number of sub-categories. It also takes into consideration the increasingly significant role of sustainability-oriented innovation, including how environmental, technological, and operational risks interact in influencing sustainable performance and resilience in NPD systems. This taxonomy is then used to identify the existing risks inherent in each stage of the NPD process, revealing areas for future research and the applicability of the taxonomy for resolving current issues in NPD risk management theory and practice. Linking the issues of NPD risks with sustainability challenges, this study contributes to innovation management theory and the sustainable development of new products. Full article

Collaboration between humans and robots (HRC) is advancing rapidly due to the intersection of robotics and generative artificial intelligence (GenAI). The current paper includes a systematic review of 103 studies on the role of generative models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion models, and Large Language Models (LLMs) in improving the safety, trust, and adaptability of collaborative robotics using a PRISMA-based systematic approach. The review recognizes four major themed areas of GenAI-based safety frameworks—namely, data-driven simulation to synthesize hazards, predictive reasoning to forecast human motion, adaptive control to reduce risks dynamically, and trust-aware cognition to explain human–robot interaction. Findings indicate that generative models transform robotic safety from a reactive mechanism to proactive, contextual and interpretable systems. Nevertheless, real-time performance, interpretability, standard benchmarking, and ethical assurance are still some of the challenges to be overcome. The paper proposes a taxonomy linking generative modeling layers and physical, cognitive and ethical aspects of HRC safety, and gives a roadmap of certifiable hybrid systems with generative foresight and deterministic control. This synthesis provides a foundation for developing transparent, adaptive, and trustworthy collaborative robotic systems. Full article

The integration of human judgment into artificial intelligence (AI) systems has emerged as a key research direction, particularly for high-stakes applications where full automation remains insufficient. Human-in-the-Loop (HITL) AI represents a field that combines machine learning capabilities with human oversight, feedback, and decision-making at various stages of the AI pipeline. This survey provides a systematic review of HITL approaches, covering theoretical foundations, technical methods, ethical considerations, and domain-specific applications. We propose a unified taxonomy that categorizes HITL systems based on loop placement, interaction granularity, and temporal characteristics. This review synthesizes findings from healthcare, autonomous systems, cybersecurity, and other high-risk domains where human oversight is essential. We also examine the challenges of scalability, cognitive load, and trust calibration that affect the practical deployment of HITL systems. The final section outlines open research directions and introduces a framework for designing effective human–AI collaborative systems. Full article

Drought is a major constraint on crop productivity, and microbial inoculants are increasingly explored to mitigate plant water stress. However, most inoculant discovery pipelines rely on trait-based screening performed outside the ecological context in which beneficial plant-microbe interactions naturally arise. In natural soils, drought-exposed plants can reshape the rhizosphere environment by altering carbon allocation and root exudation, thereby selectively recruiting microorganisms compatible with water-limited conditions and effectively performing an ecological pre-selection. Here, we captured this process during early seedling establishment and leveraged drought-driven rhizosphere recruitment as a nature-guided strategy to nominate bacterial inoculant candidates. Tomato seedlings were grown in natural agricultural soil microcosms under well-watered and drought-stressed regimes, and cultivable bacteria were comparatively isolated from rhizosphere and bulk soil fractions. Recruitment-prioritized isolates were subsequently characterized through biochemical assays and genome-informed analyses to provide functional and taxonomic context and were evaluated in early inoculation assays under water stress. Drought-recruited isolates displayed distinct plant-associated responses, and genome-scale taxonomy indicated that one drought-associated isolate represents a genomically distinct lineage within the genus Paracoccus. Together, these findings highlight drought-driven rhizosphere recruitment as an ecologically grounded framework for identifying stress-compatible bacterial candidates and uncovering previously undescribed rhizosphere diversity. Full article

Continuous unidirectional (UD) thermoplastic composite tapes are increasingly used in aerospace, automotive, and energy applications because of their high specific strength, low weight, recyclability, and compatibility with automated manufacturing. Since final component performance strongly depends on tape quality, reliable defect characterization and detection are essential. In this study, manufacturing-induced defects in polypropylene-based UD tapes reinforced with carbon and glass fibers were investigated using real images acquired directly from laboratory-scale production without synthetic data. Defects related to interfacial integrity, matrix distribution, fiber architecture, and surface irregularities were systematically analyzed, and a practical four-class defect taxonomy was established. To enable automated inspection under limited-data conditions, lightweight YOLOv8, YOLOv11, and the new YOLO26 models were comparatively evaluated using a UD tape-specific augmentation strategy combining physically constrained Albumentations and on-the-fly augmentation. Among the tested models, YOLO26-s achieved the best overall performance, reaching a mean mAP@0.5 of 0.87 ± 0.03, outperforming YOLOv11 (0.83) and YOLOv8 (0.78), with 0.90 precision and 0.85 recall. Interfacial (0.92 mAP) and matrix-related (0.90 mAP) defects were detected most reliably, whereas fiber-related (0.89 mAP) and surface defects (0.79 mAP) remained more challenging, particularly in glass-fiber-reinforced tapes due to transparency-masking effects. The results demonstrate the potential of compact deep learning models for computationally efficient and manufacturing-relevant in-line quality monitoring of UD tape production. Full article

This manuscript presents a comprehensive taxonomy of Riemann solitons within the framework of a spacetime manifold endowed with a metric exhibiting both spatial homogeneity and rotational characteristics. Furthermore, we undertake an analysis to determine the geometric nature of these solitons by establishing their correspondence to Killing vector fields, Ricci collineation vector fields, and gradient vector fields. Full article

The generation of examination questions from examiner-provided marking schemes remains a critical yet underexplored challenge in automated assessment. This study proposes an AI-powered natural language processing (NLP) framework that reverse-engineers exam questions using transformer-based generative modeling, semantic reconstruction, and pedagogical constraints. Marking schemes are encoded with MPNet embeddings and decoded into candidate questions by a T5-small model, with a reconstruction module ensuring semantic fidelity and Bloom-level embeddings enforcing cognitive alignment. Evaluation on a dataset of 7021 marking schemes from Sol Plaatje University demonstrated strong performance, with BLEU = 0.71, ROUGE-L = 0.68, METEOR = 0.65, reconstruction fidelity = 0.84, and Bloom-level accuracy = 0.79. Comparative baselines, including an unconstrained T5 (BLEU = 0.62, RF = 0.68, Bloom = 0.56) and rule-based methods (BLEU = 0.48, RF = 0.51, Bloom = 0.43), confirmed the effectiveness of the proposed approach. The results indicate that the framework generates questions that are semantically accurate, structurally coherent, and pedagogically valid, offering a scalable solution for adaptive assessment, digital archiving, and automated exam construction. Full article

The maritime industry is under increased challenges of balancing operational effectiveness and environmental responsibility. This study examines the application of intelligent agents as a technology that can align these two goals in the triple-bottom-line model that involves social responsibility, environmental footprint, and economic sustainability. An agent architecture taxonomy is outlined and adapted to the maritime industry, distinguishing between reactive, deliberative, hybrid, and multi-agent systems (MAS). The application of these architectures is analysed throughout the maritime domain. In the ship-centric environment, the analysis highlights the role of agents in autonomous navigation, energy-efficient meteorological routing, and predictive maintenance. The analysis in the port and supply-chain domain demonstrates a shift towards decentralized asset orchestration and logistic coordination rather than centralized control. The paper outlines certain barriers to widespread adoption, namely the reality gap of simulation-based training and the lack of transparency in deep-learning models (“black box” problem). The paper concludes by outlining a future research agenda proposing a use of explainable artificial intelligence (XAI), high-fidelity simulation-to-real transfer, and communication protocol standardization to continue the trend of developing strong autonomous capabilities in sustainable maritime logistics. Full article

Construction accident reports contain rich causal evidence; however, their unstructured narratives make systematic analysis difficult. Recent advances in large language models (LLMs) have created new opportunities to leverage such information at scale. This study develops an integrated LLM–BERT–network framework for analyzing construction accident causation. Based on 347 official construction accident investigation reports, a DeepSeek-based pipeline with human-in-the-loop quality control was used to extract causal keywords describing direct and indirect causes, yielding 2572 keywords. A BERT-based semantic normalization procedure then consolidated synonymous expressions, reducing 811 deduplicated keywords to 104 normalized terms (an 87.2% reduction in vocabulary size). A manual sample-based evaluation further supported the reliability of the LLM-based extraction and BERT-based normalization procedures. The normalized keywords were further organized into a hierarchical taxonomy and used to construct a directed keyword-association network linking indirect and direct causes for structured relational analysis. To strengthen methodological rigor, additional validation and analytical experiments were conducted, including manual sample-based evaluation of keyword extraction, sensitivity analysis of normalization settings, and examination of representative failure cases. The results support the reliability and robustness of the proposed framework. The analysis indicates that behavior-related factors and management deficiencies occupy structurally important positions in the directed network. Overall, the findings suggest that construction accidents arise from the interaction of human, managerial, environmental, material, and technical factors rather than isolated single causes. Effective prevention therefore requires system-oriented interventions that strengthen worker competence, supervision, training, accountability, and hazard identification. Full article

This systematic review examines how digital technologies enable circular economy (CE) transitions across sectors and value chains. Analysing 266 peer-reviewed publications (2016–2025), we develop a comprehensive taxonomy of digital enablers—including IoT, AI, blockchain, cloud computing, additive manufacturing, and digital platforms—and map their applications to circular strategies such as reuse, remanufacturing, and recycling. Our findings reveal that data-driven technologies dominate CE implementation, with 89% of studies involving data collection, storage, analysis, or sharing functions. IoT emerges as the foundational technology for real-time tracking and monitoring, while AI and big data analytics optimise circular processes and predict maintenance needs. Blockchain ensures traceability and trust in circular supply chains, and cloud computing provides scalable infrastructure for collaboration. Manufacturing (41%) and construction (15.5%) are the most studied sectors, with strong European research leadership reflecting policy drivers such as Digital Product Passports. We identify three impact types: enabling (process optimisation), disruptive (business model innovation), and facilitating (ecosystem collaboration). Key barriers include technical complexity, organisational resistance, high implementation costs, and regulatory gaps. The review concludes with recommendations for integrated, multi-stakeholder approaches to realise a digitally enabled circular economy. Full article

The integration of sustainability in higher education institutions (HEIs) is critical but often hindered by the limitations of existing sustainability assessment tools (SATs), which are complex, rigid, and not sufficiently adaptable to specific organizational and socio-economic or local contexts. This study presents the Sustainability Implementation Reflective Assessment Framework (SIRAF), a meta-framework designed to assist HEIs in developing their own reflective, flexible, and user-friendly tools. The SIRAF taxonomy was developed through the findings of: a. a systematic literature review retrieved in authors’ previous research, b. a comparative analysis and synthesis of 12 SATs, as well as c. a theory-building process. It features a taxonomy of six core indicators with multiple sub-indicators. Its “pick-and-mix” approach enables institutions to customize assessments to align with their distinct needs, objectives, and resources. The SIRAF model was assessed in eight Greek universities offering tourism studies programs. The assessment incorporated data from institutional websites and a qualitative analysis. An evaluation of three fundamental indicators—curriculum, research, and institutional identity—disclosed a paucity of sustainability integration in curricula and governance, notwithstanding the augmentation of sustainability-related research activity. The findings underscore the significance of meticulously designed yet user-centred tools that facilitate evaluation, organizational learning, and strategic planning. As SIRAF shifts its paradigm of sustainability reporting from external compliance to internal improvement, it concomitantly reduces technical barriers and fosters institutional change. Though initially implemented in tourism and higher education, its inherent flexibility suggests the potential for broader applications, while future enhancements could include weighted scoring and wider empirical validation. Full article

Agent-based systems built on large language models (LLMs) increasingly rely on complex internal reasoning processes, tool interactions, and memory mechanisms. However, the internal decision-making dynamics of such agents remain difficult to observe, analyze, and compare in a systematic manner. To address this limitation, we present AgentSec, a curated dataset of structured agent interaction traces designed to support the analysis of agent-level reasoning and action behaviors. The dataset consists of 30 deterministic and non-redundant scenario instances, each capturing a complete agent interaction session under a fixed and validated schema. Quantitatively, the 30 released sessions comprise 67 decision nodes and 45 tool calls (73.3% successful), with provenance graphs exhibiting an average depth of 4.53 (max 7) and a maximum branching factor of 3. Scenarios are organized according to a predefined taxonomy of agent behavioral patterns, including tool success and failure modes, fallback strategies, memory conflicts and overwrites, decision rollbacks, and provenance branching structures. Each scenario encodes a distinct analytical case rather than a parametric variation, enabling focused and interpretable study of agent decision-making processes. AgentSec provides detailed records of decision traces, tool calls, memory updates, and provenance relations, and is intended to facilitate reproducible research on agent behavior analysis, auditing, and evaluation. The dataset is released alongside its schema, scenario manifest, and validation tooling to support reuse and extension by the research community. Rather than serving as a large-scale performance benchmark, AgentSec is explicitly designed as a diagnostic and unit-test suite for auditing agent-level reasoning logic and provenance consistency under controlled structural conditions. Full article