Search Results (195)

Aerial situational awareness (SA) faces significant challenges due to inherent complexity involving large-scale dynamic entities and intricate spatio-temporal relationships. While deep learning advances SA for specific data modalities (static or time-series), existing approaches often lack the holistic, vision-centric perspective essential for human decision-making. To bridge this gap, we propose a unified GNN-CV framework for operational-level SA. This framework leverages mature computer vision (CV) architectures to intelligently process radar-map-like representations, addressing diverse SA tasks within a unified paradigm. Key innovations include methods for sparse entity attribute transformation graph neural networks (SET-GNNs), large-scale radar map reconstruction, integrated feature extraction, specialized two-stage pre-training, and adaptable downstream task networks. We rigorously evaluate the framework on critical operational-level tasks: aerial swarm partitioning and configuration recognition. The framework achieves an impressive end-to-end recognition accuracy exceeding 90.1%. Notably, in specialized tactical scenarios featuring small, large, and irregular flight intervals within formations, configuration recognition accuracy surpasses 85.0%. Even in the presence of significant position and heading disturbances, accuracy remains above 80.4%, with millisecond response cycles. Experimental results highlight the benefits of leveraging mature CV techniques such as image classification, object detection, and image generation, which enhance the efficacy, resilience, and coherence of intelligent situational awareness. Full article

Effective situation awareness relies on the robust processing of high-dimensional data streams generated by onboard sensors. However, the application of deep generative models to extract features from complex UAV sensor data (e.g., GPS, IMU, and radar feeds) faces two fundamental challenges: critical training instability and the difficulty of representing multi-modal distributions inherent in dynamic flight maneuvers. To address this, this paper proposes a novel unsupervised sensor data processing framework to overcome these issues. Our core innovation is a deep generative model, VAE-WRBM-MDN, specifically engineered for stable feature extraction from non-linear time-series sensor data. We demonstrate that while standard Variational Autoencoders (VAEs) often struggle to converge on this task, our introduction of Weighted-uncertainty Restricted Boltzmann Machines (WRBM) for layer-wise pre-training ensures stable learning. Furthermore, the integration of a Mixture Density Network (MDN) enables the decoder to accurately reconstruct the complex, multi-modal conditional distributions of sensor readings. Comparative experiments validate our approach, achieving 95.69% classification accuracy in identifying situational patterns. The results confirm that our framework provides robust enabling technology for real-time intelligent sensing and raw data interpretation in autonomous systems. Full article

This study conducts a systematic bibliometric review of artificial intelligence (AI)-based approaches to tacit knowledge extraction and management. Drawing on data retrieved from Scopus and Web of Science, this study analyzes 126 publications published between 1985 and 2025 using VOSviewer and Biblioshiny to map citation networks, keyword co-occurrence patterns, and thematic evolution. The results identify nine major clusters spanning machine learning, natural language processing, semantic modeling, expert systems, knowledge-based decision support, and emerging hybrid techniques. Collectively, these findings indicate a field-wide shift from manual codification toward scalable, context-aware, and semantically enriched approaches that better support tacit knowing in organizational practice. Building on these insights, the paper introduces the AI–Tacit Knowledge Co-Evolution Model, which situates AI as an epistemic partner—augmenting human interpretive processes rather than merely codifying experience. The framework integrates Polanyi’s concept of tacit knowing, Nonaka’s SECI model, and sociotechnical learning theories to elucidate how human–AI interaction transforms the dynamics of knowledge creation. The review consolidates fragmented research streams and provides a conceptual foundation for guiding future methodological development in AI-enabled tacit knowledge management. Full article

Under the context of non-dyadic human–machine interaction in intelligent coal mines, this study investigates the impact of different dyadic collaboration modes on Team Situation Awareness (TSA). Based on a simulated coal mine monitoring task, the experiment compares four working modes—Individual Operation, Supervised Operation, Cooperative Operation, and Divided-task Operation—across tasks of varying complexity. TSA was assessed using both objective (SAGAT) and subjective (SART) measures, alongside parallel evaluations of task performance and workload (NASA-TLX). The results demonstrate that, compared to Individual or Supervised Operation, both Cooperative and Divided-task Operation significantly enhance TSA and task performance. Cooperative Operation improves information integration and comprehension, while Divided-task Operation enhances response efficiency by enabling focused attention on role-specific demands. Moreover, dyadic collaboration reduces cognitive workload, with the task-sharing mode showing the lowest cognitive and temporal demands. The findings indicate that clear task structuring and real-time information exchange can alleviate cognitive bottlenecks and promote accurate environmental perception. Theoretically, this study extends the application of non-dyadic interaction theory to intelligent coal mine scenarios and empirically validates a “Collaboration Mode–TSA–Performance” model. Practically, it provides design implications for adaptive collaboration frameworks in high-risk, high-complexity industrial systems, highlighting the value of dynamic role allocation in optimizing cognitive resource utilization and enhancing operational safety. Full article

This paper presents the design, development, and field testing of an Operational Fire Management System (OFMS) aimed at enhancing situational awareness and improving the safety and efficiency of firefighting operations. The system integrates real-time intelligence and remote monitoring to provide emergency management personnel and first responders with accurate information on vehicle location, communication status, and water level monitoring. Developed in collaboration with the Australian Capital Territory Rural Fire Service (ACT RFS), the OFMS prototype encompasses three core subsystems: the Monitoring and Environmental Sensing Subsystem (MESS), the Communication and Vital Monitoring Subsystem (CVMS), and the Command-and-Control Interface Subsystem (CCIS). MESS introduces a tilt-compensated ultrasonic algorithm for accurate water level estimation in moving fire trucks, CVMS leverages an open-source smartwatch with LoRa communication for real-time physiological tracking, and CCIS offers a cloud-based interface for live visualisation and coordination. Together, these subsystems form a practical and scalable framework for supporting frontline operations, particularly in rural firefighting contexts where vehicles are required to operate off-road and deliver large volumes of water to isolated locations. By providing real-time visibility of resource availability and crew status, the system strengthens operational coordination and decision-making in environments where connectivity is often limited. This paper discusses the design and implementation of the prototype, highlights key performance results, and outlines opportunities for future development, including improved environmental resilience, expanded sensor integration, and multi-agency interoperability. The findings confirm that the OFMS represents a novel and field-ready approach to fireground management, empowering firefighting teams to respond more effectively to emergencies and better protect lives, property, and the environment. Full article

Accurate vessel track association is a key requirement for maritime traffic monitoring and collision-avoidance systems, yet the Automatic Identification System (AIS) records commonly contain noise, missing intervals, and overlapping trajectories in congested coastal waters. We propose a Dilated Residual Connection Temporal Convolutional Network (DRC-TCN) tailored to AIS sequences; residual dilated blocks with layer normalization enable stable training while capturing long-range temporal dependencies under imperfect data. Beyond kinematic inputs, we augment AIS with buoy-based meteorological variables (wind direction and speed, gust, pressure, air temperature, and sea surface temperature) via time-aligned nearest-station fusion, allowing the model to account for environmental effects on vessel motion. Experiments on New York coastal AIS data show that DRC-TCN outperforms CNN-LSTM and vanilla TCN baselines, improving F1 score by up to 99.3% and achieving 99.7% accuracy. The results indicate that environment-aware temporal modeling strengthens the robustness of track association and supports situational awareness for next-generation intelligent navigation and ocean engineering applications. Full article

Accurate identification of rear light signals in preceding vehicles is pivotal for Advanced Driver Assistance Systems (ADAS), enabling early detection of driver intentions and thereby improving road safety. In this work, we present a novel approach that leverages a meta-learning-enhanced YOLOv8 model to detect left and right turn indicators, as well as brake signals. Traditional radar and LiDAR provide robust geometry, range, and motion cues that can indirectly suggest driver intent (e.g., deceleration or lane drift). However, they do not directly interpret color-coded rear signals, which limits early intent recognition from the taillights. We therefore focus on a camera-based approach that complements ranging sensors by decoding color and spatial patterns in rear lights. This approach to detecting vehicle signals poses additional challenges due to factors such as high reflectivity and the subtle visual differences between directional indicators. We address these by training a YOLOv8 model with a meta-learning strategy, thus enhancing its capability to learn from minimal data and rapidly adapt to new scenarios. Furthermore, we developed a post-processing layer that classifies signals by the geometric properties of detected objects, employing mathematical principles such as distance, area calculation, and Intersection over Union (IoU) metrics. Our approach increases adaptability and performance compared to traditional deep learning techniques, supporting the conclusion that integrating meta-learning into real-time object detection frameworks provides a scalable and robust solution for intelligent vehicle perception, significantly enhancing situational awareness and road safety through reliable prediction of vehicular behavior. Full article

The rapid growth of urban vehicle and pedestrian flows has intensified congestion, delays, and safety concerns, underscoring the need for sustainable and intelligent traffic management in modern cities. Traditional centralized traffic signal control systems often face challenges of scalability, heterogeneity of traffic patterns, and limited real-time adaptability. To address these limitations, this study proposes a decentralized Multi-Agent Reinforcement Learning (MARL) framework for adaptive traffic signal control, where Deep Reinforcement Learning (DRL) agents are deployed at each intersection and trained on local conditions to enable real-time decision-making for both vehicles and pedestrians. A key innovation lies in the integration of Visible Light Communication (VLC), which leverages existing LED-based infrastructure in traffic lights, streetlights, and vehicles to provide high-capacity, low-latency, and energy-efficient data exchange, thereby enhancing each agent’s situational awareness while promoting infrastructure sustainability. The framework introduces a queue–request–response mechanism that dynamically adjusts signal phases, resolves conflicts between flows, and prioritizes urgent or emergency movements, ensuring equitable and safer mobility for all users. Validation through microscopic simulations in SUMO and preliminary real-world experiments demonstrates reductions in average waiting time, travel time, and queue lengths, along with improvements in pedestrian safety and energy efficiency. These results highlight the potential of MARL–VLC integration as a sustainable, resilient, and human-centered solution for next-generation urban traffic management. Full article

Current generative AI systems, despite extraordinary progress, face fundamental limitations in temporal reasoning, contextual understanding, and ethical decision-making. These systems process information statistically without authentic comprehension of experiential time or intentional context, limiting their applicability in security-critical domains where reasoning about past experiences, present situations, and future implications is essential. We present Phase 3 of the Sophimatics framework: Super Time-Cognitive Neural Networks (STCNNs), which address these limitations through complex-time representation T ∈ ℂ where chronological time (Re(T)) integrates with experiential dimensions of memory (Im(T) < 0), present awareness (Im(T) ≈ 0), and imagination (Im(T) > 0). The STCNN architecture implements philosophical constraints through geometric parameters α and β that bound memory accessibility and creative projection, enabling neural systems to perform temporal-philosophical reasoning while maintaining computational tractability. We demonstrate STCNN’s effectiveness across five security-critical applications: threat intelligence (AUC 0.94, 1.8 s anticipation), privacy-preserving AI (84% utility at ε = 1.0), intrusion detection (96.3% detection, 2.1% false positives), secure multi-party computation (ethical compliance 0.93), and blockchain anomaly detection (94% detection, 3.2% false positives). Empirical evaluation shows 23–45% improvement over baseline systems while maintaining temporal coherence > 0.9, demonstrating that integration of temporal-philosophical reasoning with neural architectures enables AI systems to reason about security threats through simultaneous processing of historical patterns, current contexts, and projected risks. Full article

The adoption of artificial intelligence (AI) in healthcare requires not only accurate predictions but also a clear understanding of its reliability. In safety-critical domains such as medical imaging and diagnosis, clinicians must assess the confidence in model outputs to ensure safe decision making. Uncertainty quantification (UQ) addresses this need by providing confidence estimates and identifying situations in which models may fail. Such uncertainty estimates enable risk-aware deployment, improve model robustness, and ultimately strengthen clinical trust. Although prior studies have surveyed UQ in centralized learning, a systematic review in the federated learning (FL) context is still lacking. As a privacy-preserving collaborative paradigm, FL enables institutions to jointly train models without sharing raw patient data. However, compared with centralized learning, FL introduces more complex sources of uncertainty. In addition to data uncertainty caused by noisy inputs and model uncertainty from distributed optimization, there also exists distributional uncertainty arising from client heterogeneity and personalized uncertainty associated with site-specific biases. These intertwined uncertainties complicate model reliability and highlight the urgent need for UQ strategies tailored to federated settings. This survey reviews UQ in medical FL. We categorize uncertainties unique to FL and compare them with those in centralized learning. We examine the sources of uncertainty, existing FL architectures, UQ methods, and their integration with privacy-preserving techniques, and we analyze their advantages, limitations, and trade-offs. Finally, we highlight key challenges—scalable UQ under non-IID conditions, federated OOD detection, and clinical validation—and outline future opportunities such as hybrid UQ strategies and personalization. By combining methodological advances in UQ with application perspectives, this survey provides a structured overview to inform the development of more reliable and privacy-preserving FL systems in healthcare. Full article

As cyberattacks grow increasingly sophisticated, the timely exchange of Cyber Threat Intelligence (CTI) has become essential to enhancing situational awareness and enabling proactive defense. Several challenges exist in CTI sharing, including the timely dissemination of threat information, the need for privacy and confidentiality, and the accessibility of data even in unstable network conditions. In addition to security and privacy, latency and throughput are critical performance metrics when selecting a suitable platform for CTI sharing. Substantial efforts have been devoted to developing effective solutions for CTI sharing. Several existing CTI sharing systems adopt either centralized or blockchain-based architectures. However, centralized models suffer from scalability bottlenecks and single points of failure, while the slow and limited transactions of blockchain make it unsuitable for real-time and reliable CTI sharing. To address these challenges, we propose a DDS-based framework that automates data sanitization, STIX-compliant structuring, and real-time dissemination of CTI. Our prototype evaluation demonstrates low latency, linear throughput scaling at configured send rates up to 125 messages per second, with 100% delivery success across all scenarios, while sustaining low CPU and memory overheads. The findings of this study highlight the unique ability of DDS to overcome the timeliness, security, automation, and reliability challenges of CTI sharing. Full article

Background/Objective: The growing volume and complexity of cases presented to emergency departments underline the urgent need for effective clinical-risk-management strategies. Increasing demands for quality and safety in healthcare highlight the importance of predictive tools in supporting timely and informed clinical decision-making. This study aims to evaluate the performance and usefulness of predictive models for managing the clinical risk of people who visit the emergency department. Methods: A systematic review was conducted, including primary observational studies involving people aged 18 and over, who were not pregnant, and who had visited the emergency department; the intervention was clinical-risk management in emergency departments; the comparison was of early warning scores; and the outcomes were predictive models. Searches were performed on 10 November 2024 across eight electronic databases without date restrictions, and studies published in English, Portuguese, and Spanish were included in this study. Risk of bias was assessed using the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies as well as the Prediction Model Risk-of-Bias Assessment Tool. The results were synthesized narratively and are summarized in a table. Results: Four studies were included, each including between 4388 and 448,972 participants. The predictive models identified included the Older Persons' Emergency Risk Assessment score; a new situation awareness model; machine learning and deep learning models; and the Vital-Sign Scoring system. The main outcomes evaluated were in-hospital mortality and clinical deterioration. Conclusions: Despite the limited number of studies, our results indicate that predictive models have potential for managing the clinical risk of emergency department patients, with the risk-of-bias study indicating low concern. We conclude that integrating predictive models with artificial intelligence can improve clinical decision-making and patient safety. Full article

Understanding occupant behavior is critical for enhancing safety and situational awareness in intelligent transportation systems. This study investigates multimodal occupant behavior recognition using sequential inputs extracted from 2D pose, 2D gaze, and facial movements. We conduct a comprehensive comparative study of three distinct architectural paradigms: a static Multi-Layer Perceptron (MLP), a recurrent Long Short-Term Memory (LSTM) network, and an attention-based Transformer encoder. All experiments are performed on the large-scale Occupant Behavior Classification (OBC) dataset, which contains approximately 2.1 million frames across 79 behavior classes collected in a controlled, simulated environment. Our results demonstrate that temporal models significantly outperform the static baseline. The Transformer model, in particular, emerges as the superior architecture, achieving a state-of-the-art Macro F1 score of 0.9570 with a configuration of a 50-frame span and a step size of 10. Furthermore, our analysis reveals that the Transformer provides an excellent balance between high performance and computational efficiency. These findings demonstrate the superiority of attention-based temporal modeling with multimodal fusion and provide a practical framework for developing robust and efficient in-vehicle occupant monitoring systems. Implementation code and supplementary resources are available (see Data Availability Statement). Full article

To address the safety challenges for personnel in the complex and hazardous environments of offshore drilling platforms, this paper introduces the Platform Safety Detection YOLO (PSD-YOLO), an enhanced, real-time object detection framework based on YOLOv10s. The framework integrates several key innovations to improve detection robustness: first, the Channel Attention-Aware (CAA) mechanism is incorporated into the backbone network to effectively suppress complex background noise interference; second, a novel C2fCIB_Conv2Former module is designed in the neck to strengthen multi-scale feature fusion for small and occluded targets; finally, the Soft-NMS algorithm is employed in place of traditional NMS to significantly reduce missed detections in dense scenes. Experimental results on a custom offshore platform personnel dataset show that PSD-YOLO achieves a mean Average Precision (mAP@0.5) of 82.5% at an inference speed of 232.56 FPS. The efficient and accurate detection framework proposed in this study provides reliable technical support for automated safety monitoring systems, holds significant practical implications for reducing accident rates and safeguarding personnel by enabling real-time warnings of hazardous situations, fills a critical gap in intelligent sensor monitoring for offshore platforms and makes a significant contribution to advancing their safety monitoring systems. Full article

Hospital fraud detection has often relied on periodic audits that miss evolving, internet-mediated patterns in electronic claims. An artificial intelligence and machine learning pipeline is being developed that is leakage-safe, imbalance aware, and aligned with operational capacity for large healthcare datasets. The preprocessing stack integrates four tables, engineers 13 features, applies imputation, categorical encoding, Power transformation, Boruta selection, and denoising autoencoder representations, with class balancing via SMOTE-ENN evaluated inside cross-validation folds. Eight algorithms are compared under a fraud-oriented composite productivity index that weighs recall, precision, MCC, F1, ROC-AUC, and G-Mean, with per-fold threshold calibration and explicit reporting of Type I and Type II errors. Multilayer perceptron attains the highest composite index, while CatBoost offers the strongest control of false positives with high accuracy. SMOTE-ENN provides limited gains once representations regularize class geometry. The calibrated scores support prepayment triage, postpayment audit, and provider-level profiling, linking alert volume to expected recovery and protecting investigator workload. Situated in the Future Internet context, this work targets internet-mediated claim flows and web-accessible provider registries. Governance procedures for drift monitoring, fairness assessment, and change control complete an internet-ready deployment path. The results indicate that disciplined preprocessing and evaluation, more than classifier choice alone, translate AI improvements into measurable economic value and sustainable fraud prevention in digital health ecosystems. Full article