Search Results (1,875)

As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction. Full article

Background/Objectives: Deep learning models for digital mammography sensor data are increasingly deployed across hospitals using different X-ray detector technologies and patient populations. Whether models trained on one sensor platform and population maintain accuracy when transferred to another has not been tested for the latest generation of mammography-specific foundation models under one controlled protocol. Methods: We fine-tuned five backbone architectures (ResNet-50, DINOv2-B14, Rad-DINO, Mammo-CLIP B5, and Mammo-FM) on CBIS-DDSM (film-digitized, USA, n = 714 validation) with three seeds, ablated a density-aware focal loss across three auxiliary weights, and evaluated transfer to three external sensor cohorts: CMMD (full-field digital, China, n = 1032), DMID (mixed digital, India, n = 509), and MIAS (film-digitized, UK, n = 322). Significance used paired DeLong z-tests with Benjamini–Hochberg FDR correction; temperature scaling tested post hoc recalibration at all transfer targets. Results: Within this single-source three-seed evaluation, ResNet-50 outperformed all four foundation models on CBIS-DDSM (AUC 0.867 vs. 0.847, 0.846, 0.813, and 0.703; all gaps p_adj < 0.05). The density-aware focal loss degraded both AUC and calibration at every weight tested. At transfer, every model lost 0.165 to 0.320 AUC points relative to in-distribution performance, with sensitivity at 95% specificity collapsing from 0.31 to 0.47 in-distribution to 0.11 to 0.22 across the three external targets. A per-seed Stouffer meta-analysis confirms that Mammo-CLIP B5 and Mammo-FM significantly outperformed ResNet-50 on DMID and Mammo-CLIP on CMMD, after BH-FDR; MIAS comparisons remained directional only. In the extremely dense subgroup (BI-RADS D4), Mammo-FM reached AUC 0.870 versus ResNet-50 at 0.842, a directional observation whose 95% CIs overlap heavily at the n = 140 sample size and which we do not interpret as a statistically supported advantage. Conclusions: In this single training-source, three-seed protocol, mammography-specific pretraining did not deliver the in-distribution AUC premium reported in the originating papers, and no architecture reached a level at which transfer deployment without local validation would be defensible. We frame these as observations specific to the present protocol rather than as broader conclusions about foundation models for mammography classification. The findings argue for sensor-stratified and population-stratified external validation and for local recalibration as practical prerequisites before clinical use. Code and weights are released under MIT license. Full article

Autonomous ship maneuvering in harbor environments is increasingly supported by advances in model predictive control, reinforcement learning, digital twins, multi-sensor fusion, berth allocation, and multi-agent coordination. However, these developments are often studied as separate technological domains, while real harbor autonomy requires coordinated operation across vessels, port infrastructure, regulatory systems, cybersecurity mechanisms, and human supervisory processes. This study presents an architecture-oriented critical review of autonomous ship and harbor maneuvering research published between 2015 and May 2026. The review synthesizes literature from control engineering, maritime artificial intelligence, sensor fusion, digital twins, port logistics, cyber-physical systems, regulation, cybersecurity, and human–AI supervision. The analysis introduces two conceptual contributions: a layered cyber-physical taxonomy and an integration maturity model. The taxonomy organizes autonomous harbor maneuvering into seven interdependent layers: physical dynamics, perception and sensor fusion, prediction and state estimation, control, decision and coordination, digital twin federation, and regulatory–supervisory governance. The maturity model distinguishes isolated vessel autonomy, assisted coordination, shared digital synchronization, agent-based coordination, and fully federated maritime cyber-physical autonomy. The reviewed evidence shows substantial progress in individual layers, especially control, perception, digital twins, and berth allocation. However, major gaps remain in cross-layer synchronization, semantic interoperability, regulation-aware decision-making, cybersecurity integration, and validated ship–shore federation. To address these gaps, this study proposes a Federated Maritime Cyber-Physical Architecture for autonomous harbor maneuvering. The architecture integrates vessel autonomy cores, port intelligence cores, semantic federation middleware, agent-based negotiation, regulatory verification, cybersecurity safeguards, and human supervisory interfaces. This review argues that future progress in autonomous harbor operations depends not only on stronger algorithms, but on interoperable, explainable, regulation-aware, and cyber-resilient ship–shore ecosystems. Full article

Robotic belt grinding is an effective and widely adopted finishing method for superalloys, offering notable advantages such as high material removal capability, low heat input, and reduced workpiece damage. In addition, robots can readily integrate multiple sensors—such as infrared radiation cameras, force sensors, and high-speed cameras—which facilitate real-time monitoring of the grinding process and thereby enhance grinding quality control. With the establishment and continuous advancement of large-scale artificial intelligence (AI) data models, new breakthroughs have emerged in the optimization of robotic grinding processes. Owing to its dexterous workspace and advantages in high flexibility and cost-effectiveness, robotic belt grinding has become a critical process for the precision forming of complex curved components such as aero-engine blades and blisks. However, factors such as the limited absolute accuracy of industrial robots, time-varying grinding contact states, and significant transient boundary effects make it difficult for the current constant-parameter open-loop machining mode to simultaneously meet the demands for high material removal efficiency and high surface integrity on complex profiles. This paper systematically reviews the technologies for precision control and process optimization of robotic belt grinding aimed at pointwise precise material removal. First, the structural composition of the robotic belt grinding system and the material removal mechanism are analyzed. Then, centered on the compensation concept, a hierarchical progressive technical framework is outlined, covering geometric calibration compensation, force/position hybrid online compensation, transient entry boundary compensation, and system-level comprehensive compensation of multi-source errors, with a comparison of the applicable scenarios and the effects on shape and property control at each level. Furthermore, under the support of effective compensation, the collaborative optimization methods of material removal modeling, multi-objective optimization of process parameters, force-constrained trajectory planning, and intelligent adaptive processes are elaborated. Finally, current technical bottlenecks are summarized, and future trends in next-generation adaptive grinding technology driven by digital twins and embodied intelligence are envisioned. This review aims to provide a systematic theoretical reference for the high-precision and intelligent upgrading of robotic precision grinding systems. Full article

Recent advances in satellite technology have significantly progressed, yet acquiring high-quality images with meaningful labels for Earth observation missions remains a costly and time-intensive process. Furthermore, captured scenes frequently exhibit defects such as misaligned color channels, extensive cloud cover, or repetitive patterns in similar environments. Fortunately, the evolution of generative artificial intelligence offers a solution by enabling the creation of realistic synthetic scenes, simulating the characteristics of any targeted imager, and thereby mitigating the scarcity of authentic data. This paper demonstrates the feasibility of transferring knowledge from specialized AI-generated datasets to Earth observation missions. Leveraging a novel dataset of Spanish map tiles, Pix2Pix, CUT, and ControlNet models were implemented to synthesize satellite imagery. To analyze structural and topological generalizability, identical U-Net instances were trained on the resulting collections for building, road, and water segmentation tasks, and subsequently tested on independent authentic imagery. The results reveal a clear decoupling between visual realism and functional utility. Incorporating synthetic samples into hybridized training datasets successfully surpassed the limitations of using real data alone, increasing maximum Dice scores by 0.9% (to 54.1% for buildings), 2.3% (to 38.6% for roads), and 4.1% (to 46.5% for waterbodies). This systematic validation establishes structural-guided synthetic data augmentation as a robust, adaptable strategy for Earth observation applications across diverse sensors and geometric objectives. Full article

Introduction: Pedestrians lying on the road—collapsed through medical emergency, intoxication, or displacement following a prior collision—represent a disproportionately lethal and underaddressed category in road traffic safety. Forensic database analyses derived from Japan’s national police records document a fatality rate of 33.0% for collisions involving pedestrians lying on the road, more than double the rate for upright pedestrian collisions. Standard Advanced Driver-Assistance Systems (ADAS) yield a True Positive Rate (TPR) of only 21.4% for detecting pedestrians lying on the road under night conditions—a classification gap of 73.3 percentage points. Methods: In simulation trials, we evaluated the Advanced Falling Object Detection System (AFODS—where “falling object” denotes the low-profile human form at road level, distinguishing the prone pedestrian from the upright postures addressed by conventional ADAS) on a composite dataset of 3200 annotated fall events and 12,000 negative samples (training/validation), with 320 independent controlled simulation trials used for performance evaluation, spanning real-world, forensic-reconstruction, and Total Human Body Model for Safety (THUMS)-validated synthetic scenarios. No physical prototype has been evaluated; all performance data are derived from simulation, and 37.5% of positive samples are synthetically generated. These simulation conditions represent a first feasibility demonstration pending real-world hardware validation. This paper introduces three original contributions absent from prior work: a three-stage quantitative injury-risk model, a formal ISO 26262 Hazard Analysis and Risk Assessment (HARA), and a medicolegal SHAP interpretability framework. The injury-risk model translated detection latency via impact velocity to Head Injury Criterion (HIC) and estimated fatal injury probability (AIS ≥ 5); these model outputs should be interpreted as exploratory estimates pending ATD validation. Reporting follows principles consistent with the TRIPOD statement. Results: Under clear daytime conditions, AFODS demonstrated a TPR of 98.2% (95% CI: 97.4–98.8%) in simulation, decreasing to 95.6% under night dry-road conditions and 89.4% under night rain. The system achieved an AUC of 0.981 and a mean end-to-end latency of 46.5 ms, representing a 76.8 percentage-point improvement in simulation over the monocular RGB baseline (p < 0.001). The injury-risk model projects a reduction in estimated fatal head injury probability from 66.2% (Monte Carlo mean) (no detection, 50 km/h full-speed impact) to 0.7% under AFODS worst-case night/rain conditions, and to ≈0% under clear daytime simulation conditions. Conclusions: A 73.3 percentage-point classification gap places pedestrians lying on the road outside the effective detection envelope of current ADAS, compounded by the systematic exclusion of non-upright postures from regulatory test protocols and benchmark datasets. AFODS supports proof-of-concept feasibility under simulation conditions. Three translational steps are required: prototype validation on real-world hardware using instrumented Anthropomorphic Test Devices (ATDs); prone-posture biomechanical injury modelling using HIC and BrIC criteria; and regulatory extension of pedestrian AEB test standards to non-upright scenarios. Full article

Wearable healthcare technologies are transforming the healthcare landscape by enabling remote, real-time health data collection, supporting early diagnosis, personalizing treatment plans, and reducing healthcare costs and medical burdens. Central to these advancements are wearable sensors, which continuously capture physiological data such as heart rate, temperature, activity levels, and biomarker concentrations. However, the large volume and complexity of this data demand effective processing to extract meaningful medical insights. Artificial intelligence (AI) and machine learning (ML) have significantly enhanced the capabilities of wearable sensors by enabling advanced data analysis, pattern recognition, and predictive modeling. AI-enhanced wearable sensors can detect early signs of health issues, such as heart attacks, chronic diseases, and mental health conditions like stress, often before clinical symptoms become apparent. This review examines the integration of AI/ML models with wearable sensors across physical activity recognition, stress assessment, cardiovascular monitoring, personal exposure monitoring, and sweat biomarker detection. Unlike prior application-centered reviews, we emphasize methodological and translational evaluation by comparing task formulations, sensing modalities, dataset scale, validation protocols, performance metrics, and deployment constraints across domains. We further discuss advanced architectures, multimodal fusion, explainable AI, edge deployment, privacy and regulatory considerations, and the translational gap between research prototypes and clinically deployable wearable AI systems. Full article

Industrial control systems (ICS), which manage critical infrastructure such as power grids and water treatment, are increasingly exposed to cyber threats and operational faults as their connectivity to external networks grows. AI-based anomaly detection has emerged as a key defense, yet three limitations restrict its practical deployment: (i) detected anomalies are treated uniformly without distinguishing between transient faults and intentional attacks, hindering tailored incident response; (ii) the trade-off between detection accuracy and the false-positive rate burdens experts with extensive manual triage and delays prompt action; and (iii) prevailing feature-attribution Explainable AI (XAI) techniques such as SHAP and LIME produce fragmented sensor-level explanations and fail to capture correlations among sensors in time-series data, undermining trust in model decisions. To address these gaps, this paper proposes a graph-based deep learning framework that (a) defines anomaly types in terms of the anomalous-sensor ratio measured before and after smoothing—which operationalizes the correlation-maintenance principle that faults keep coupled sensors jointly anomalous while attacks isolate them—enabling explicit separation of faults, attacks, false positives, and false negatives; (b) identifies ambiguous decisions near the detection threshold as candidate false alarms via dynamic threshold smoothing; and (c) provides correlation-aware graph visualizations for intuitive interpretation. Experiments on the Secure Water Treatment (SWaT) dataset center on this post-detection layer: built on a standard graph-based detector (F1-score 0.787 at Top-K = 10) that serves only as the substrate, the categorization separates faults from attacks, and the subsequent ambiguity analysis identifies false negatives with 83% precision and false positives with 73% precision. By separating attacks from faults and surfacing high-likelihood false alarms together with intuitive sensor-correlation explanations, the proposed approach reduces analyst workload and supports more reliable, prioritized incident response in ICS environments. Full article

SWANP-AI (Smart Water Network Partitioning with Artificial Intelligence) is a web application with AI natively embedded in its core engines for automated Water Network Partitioning (WNP) of water distribution networks. It is presented as the web-based evolution of SWANP 4.0, whose computational routines have already been tested in operational and research applications. The paper clarifies the full development chain of the platform, from graph-based grouping of candidate District Metered Areas/pressure management Areas (DMA/PMA) to multi-objective boundary pipe optimization and operational decision support. The methodology combines spectral and multilevel k-way partitioning for district generation, NSGA-II for cost–resilience boundary selection, hydraulic simulation through EPANET/WNTR, and AI-supported modules for solution interpretation, sensor placement, natural language editing, and Bayesian leak localization. The application to a real water distribution network shows that SWANP-AI can transform natural language engineering requests into formal optimization tasks, identify hydraulically meaningful candidate interventions, and select balanced solutions through Utopia point analysis, thus reducing manual trial-and-error in DMA/PMA design. The main contribution is a structural generative AI workflow that supports engineers not only in analyzing a network as it is, but also in designing how the network should be partitioned and operated. Full article

This bibliometric study maps olive (Olea europaea L.) yield prediction research as a coherent scientific domain for the first time. A Scopus query (27 February 2026) yielded 84 peer-reviewed articles (2002–2025), from which co-authorship network analysis, Bradford’s and Lotka’s Laws, Latent Dirichlet Allocation topic modelling (LDA), and OLS regression on citation counts were applied. Publication output increased nearly fourfold across three periods: 1.7 articles yr⁻¹ (2002–2014), 4.4 yr⁻¹ (2015–2019), and 6.7 yr⁻¹ (2020–2025). The 84 articles involve 382 authors, 61 journals, and 1551 citations (H-index = 22). Network analysis reveals a concentrated Spanish–Italian co-authorship axis. OLS regression (adj. R² = 0.267) identifies article age and abstract length as the only significant citation predictors, consistent with cumulative exposure time and study scope as structural drivers. Term-frequency screening against 18 a priori concepts finds that transfer learning, federated learning, hyperspectral imaging, digital twins, and SHAP-based explainability are absent or marginal. The field is producing more papers than ever on a narrowing methodological base geographically concentrated in the Mediterranean basin. Priority gaps—explainable AI, multi-region datasets, sensor-fusion pipelines, and federated data infrastructure—align directly with European Farm to Fork and Horizon Europe objectives. Full article

Google Earth Engine (GEE) has become a central platform for planetary-scale geospatial analysis, but its rapid evolution in the last few years is not yet reflected in the existing review literature. Earlier reviews mainly describe the platform’s architecture and its initial application domains, whereas a structured bibliometric and thematic overview of the post-2022 phase of GEE is still lacking. In this more recent phase, the platform has introduced foundation models, satellite embeddings, and native links to cloud databases. Drawing on a structured bibliometric analysis of 5591 Scopus and Web of Science indexed documents published between 2011 and 2025, the results reveal sustained long-term growth, with annual publications increasing from 3 records in 2011 to 1371 records in 2025, corresponding to a compound annual growth rate (CAGR) of 54.88%, indicating a shift from exploratory testing of the platform to more operational use. Logistic growth modelling ($R^2=0.991$) suggests that GEE research is transitioning from rapid expansion towards a scientific maturity phase, where the platform increasingly functions as a normalized analytical infrastructure embedded within broader cloud-native geospatial ecosystems. The full 2011–2025 corpus is used to establish long-term bibliometric trajectories, whereas the thematic synthesis focuses on the post-2022 transition towards Geospatial Artificial Intelligence(GeoAI), satellite embeddings, and cloud-database interoperability. The review examines how new satellite embedding datasets and BigQuery integrations help close the gap between raster-centric Earth observation (EO) workflows and tabular data science. We summarise methodological changes from traditional pixel-based classifiers to multimodal fusion approaches that combine Synthetic Aperture Radar (SAR), Global Ecosystem Dynamics Investigation (GEDI), and optical sensors, and we discuss how GEE’s highly integrated ecosystem influences reproducibility and the risk of vendor lock-in. Finally, we propose a roadmap for the ongoing transition of GEE towards GeoAI, offering researchers and policymakers a transparent and reproducible framework for deploying the platform in high-impact environmental governance. Full article

Accelerometer sensors and artificial intelligence (AI) are reshaping automated behavior monitoring in precision livestock management, yet their joint deployment on extensive rangelands is constrained by energy and bandwidth budgets. Low-Power Long-Range Wide-Area Network (LoRaWAN) collars address these constraints by compressing the raw tri-axial signal on the device into a single scalar per reporting interval, the Motion Index (MI). This onboard compression preserves enough signal to separate active behaviors but discards the per-axis and frequency content that fine-grained classification typically relies on. On a dataset of 9222 labeled observations from 24 cows across four breeds, MI distinguishes walking from grazing reliably but fails to separate ruminating from resting; both correspond to a stationary animal and yield near-zero, statistically indistinguishable distributions. Earlier MI-only models reached only about 65% four-class accuracy, and ruminating was commonly merged into resting. We show that much of this loss can be recovered by treating the MI stream as a time series. Session-aware lag features, rolling statistics, and an autoregressive previous-behavior feature lift four-class macro-F1 from 0.647 to 0.94, with per-class F1 of 0.95 for ruminating and 0.92 for resting (and at least 0.92 for every behavior). In autonomous deployment the previous behavior must be predicted rather than observed; for this setting we add a Viterbi sequence-decoding step that combines the classifier’s per-step outputs with a learned behavior-transition model, recovering a substantial part of the ruminating signal from the activity stream alone while keeping walking and grazing reliable. The gain is consistent across seven classifiers and four genetically distinct breeds, indicating that it is driven by the features rather than by a specific model. Full article

The integration of sensor technology and artificial intelligence is revolutionizing athletic training. This paper presents a novel cost-effective smart table tennis racket embedded with a nine-axis inertial measurement unit (IMU) for real-time stroke classification directly on the device. Unlike systems that are reliant on external computation, our approach leverages Tiny Machine Learning (TinyML) to deploy a customized Convolutional Neural Network (CNN) model onto a microcontroller unit (STM32F7), enabling real-time inference at the edge. The system captures accelerometer and gyroscope data, which is automatically segmented via a recursive algorithm and classified into six fundamental strokes (e.g., forehand/backhand stroke, pull, and chop) or a non-swing state. The classified results are wirelessly transmitted to a computer application for real-time feedback. Experimental results with actual players demonstrate that the optimized CNN model achieves an average classification accuracy of 98.3% in controlled tests and over 94% in mixed-stroke scenarios, validating the system’s high accuracy and robustness. This work exemplifies the practical implementation of an end-to-end intelligent sensor system, highlighting the potential of TinyML to enable advanced, low-power motion analysis in sports. Full article

UAV-based remote sensing systems are increasingly deployed in smart surveillance, disaster response, environmental monitoring, and critical infrastructure inspection. In these applications, aerial sensing platforms must transmit telemetry, control commands, and observation data securely and reliably under strict latency, energy, and computational constraints. However, existing security approaches often fail to jointly provide lightweight payload confidentiality, quantum-resilient key establishment, and adaptive communication protection suitable for dynamic and resource-constrained aerial sensing environments. To address this challenge, this paper proposes an energy-aware post-quantum hybrid cryptographic framework for secure and low-latency UAV remote sensing communications in UAV–IoT mission networks. The proposed framework integrates Ascon-based authenticated encryption for low-overhead protection of remote sensing payloads and mission telemetry, ML-KEM-based post-quantum session-key establishment for long-term resilience against quantum-era threats, and an AI-driven adaptive rekeying mechanism that dynamically adjusts key-refresh decisions according to threat level, residual energy, mobility state, channel stability, anomaly density, traffic sensitivity, link type, and mission progression. Accordingly, rekeying is treated not as a static maintenance process but as an intelligent and context-aware cryptographic control function that adapts communication security to evolving mission and sensing conditions. The framework is evaluated across twenty progressively demanding scenarios involving different UAV counts, sensor densities, payload sizes, communication modes, and adversarial settings relevant to real-time remote sensing operations. Experimental results demonstrate a secure delivery rate of 99.2%, attack detection and mitigation effectiveness of 98.9%, end-to-end encryption latency of 8.7 ms, throughput of 5.03 Mbps, energy overhead of 11.6 mJ/session, rekeying overhead of 2.9 mJ/event, session resilience of 96.4%, and integrity verification success of 99.1%. These findings show that the proposed framework provides a practical and scalable contribution to post-quantum secure UAV remote sensing by unifying lightweight authenticated encryption, ML-KEM-based quantum-resilient key establishment, and AI-driven adaptive rekeying within a resilient aerial–terrestrial communication architecture. Full article

With the growing global population, intensifying resource constraints, and deepening climate change impacts, agriculture faces dual challenges of ensuring food security and advancing sustainable development. Artificial intelligence (AI) has emerged as a transformative technology, penetrating the entire crop production chain and offering innovative solutions to traditional agricultural bottlenecks. This paper systematically reviews AI applications in five core domains: biotic stress monitoring, soil health management, precision operation, supply chain optimization, and climate-resilient agriculture. It further categorizes and analyzes four key technical pathways—deep learning, sensor fusion, data-driven methods, and hybrid modeling—while critically examining major challenges across data, technology, implementation, and ethics/policy dimensions. Future directions are discussed from technological innovation, scenario expansion, implementation guarantees, and sustainability orientation. Research findings show that AI has achieved technical validation in pest/disease detection, soil parameter modeling, and intelligent spraying, with accuracy exceeding 85% in some cases. However, regional data bias, insufficient model generalization, and the digital divide still hinder large-scale deployment. Moving forward, coordinated efforts in technological innovation and policy support are required to promote inclusive, standardized, and sustainable AI applications in crop production. Full article