Search Results (143)

Cross-material continuous tool wear prediction is difficult because a model must preserve the physical wear scale, not only align high-dimensional sensor features. This limitation is critical in milling, where the target variable is the continuous flank wear width ($\mathrm{VB}$) and material shift can distort the mapping from sensor response to wear magnitude. We address this problem by recasting cross-domain tool wear prediction as monotone wear-scale adaptation. We propose Multi-Physics Monotone Score Transport (MPMST), a monotone score transport framework that constructs a tool-wear-oriented score from sensor-derived candidate cues, transports the target-domain score onto the source-domain wear scale, and then predicts wear through isotonic regression. We also evaluate One-Physics Monotone Score Transport (OPMST), a force-only variant that uses the same score-transport pipeline with a restricted cue family. On Mondragon Unibertsitatea–Tool Condition Monitoring (MU-TCM) with two cross-material transfer tasks, the validation-driven MPMST configuration reduces mean absolute error by approximately 63% relative to Correlation Alignment (CORAL) and by approximately 31% relative to a physics-informed Gaussian process baseline. The results support monotone score construction and score transport as practical mechanisms for continuous tool wear prediction under domain shift, while also showing that MU-TCM is strongly force dominated. Full article

Coral reefs support marine biodiversity, fisheries, tourism, and coastal protection, but they are increasingly threatened by environmental stress and bleaching. Satellite-based reef monitoring has mainly relied on thermal metrics, especially Degree Heating Weeks (DHW), to represent bleaching risk. However, thermal exposure alone may not fully describe reef stress in optically complex coastal waters, where light availability, water clarity, and water-quality conditions can modify coral response. This limitation is important in Indonesia, where reefs span diverse coastal environments and many bleaching observations occur under relatively low DHW. In this study, we develop the Coral Reef Environmental Stress Index (CRESI), implemented as CRESI-Mamba, to estimate coral reef stress in Indonesia as a continuous and interpretable satellite-based stress index. CRESI-Mamba uses 26-week sequences of thermal variables from NOAA Coral Reef Watch and ocean-color variables from NASA Visible Infrared Imaging Radiometer Suite (VIIRS). The model decomposes the inferred stress into thermal, optical, and water-quality pathways, and maps the resulting stress index to bleaching probability for event-based evaluation. CRESI-Mamba was trained and evaluated using 8424 reef observations from eight Indonesian regions. In Leave-One-Region-Out cross-validation (LORO-CV), the model achieved a mean area under the receiver operating characteristic curve (AUC) of $0.795\pm 0.087$. In grouped 5-fold cross-validation, it achieved an AUC of $0.802\pm 0.024$, exceeding the DHW-only baseline ($0.627\pm 0.021$) and performing comparably to stronger thermal-only models, while providing a pathway-decomposed stress index. The estimated stress index separated bleached and not-bleached observations, with paired stress differences of $0.299\pm 0.098$ in LORO-CV and $0.281\pm 0.032$ in grouped 5-fold CV. Pathway analysis showed that the dominant stress pathway differed among regions, with optical stress dominant in several low-DHW bleaching cases. These results show that reef stress in Indonesia is better represented as a multi-pathway environmental condition than as thermal exposure alone. CRESI-Mamba provides a framework for interpreting satellite environmental histories as reef stress, while retaining bleaching probability as an evaluation output. Full article

Monitoring biodiversity in coastal and marine ecosystems is essential for supporting conservation strategies, sustaining ecosystem services, and meeting policy commitments at multiple scales, including the European Union’s Habitats Directive, Sustainable Development Goal 14 (SDG 14, Life Below Water), and the Kunming–Montreal Global Biodiversity Framework (GBF). However, many benthic habitats remain insufficiently mapped or monitored due to the spatial, temporal, and logistical limitations of traditional field-based approaches. Optical Remote Sensing (ORS), based on the use of optical sensors to retrieve spectral information from shallow-water environments, has emerged as a powerful tool for mapping and monitoring these ecosystems. This study presents a systematic review aimed at providing a comprehensive synthesis of above-water ORS applications for benthic biodiversity and habitat monitoring over the period 2014–2023. A total of 179 peer-reviewed studies were analyzed to identify temporal trends, geographic patterns, target ecosystems, and methodological workflows. The review considered observation platforms including satellite, airborne, unmanned aerial vehicles (UAVs), and field spectrometry systems, together with key preprocessing procedures required for reliable benthic detection, such as atmospheric correction, water column correction, and sunglint removal, alongside validation using independent measurements. The analysis reveals a rapid expansion of ORS applications, with a strong geographic concentration in tropical and subtropical regions. Studies focusing on specific benthic groups predominantly target coral reefs and seagrass ecosystems, although many adopt integrative benthic habitat classifications that incorporate multiple benthic components at the habitat level. However, significant limitations persist, including inconsistent preprocessing workflows, limited reporting transparency, and the underrepresentation of several ecologically important taxa (e.g., annelids, mollusks, echinoderms). Despite these challenges, ORS has become a cornerstone of large-scale and repeatable coastal monitoring. By analyzing methodological practices, ecological targets, and geographic biases, this review provides a critical foundation for improving the robustness, scalability, and global applicability of ORS in benthic habitat mapping, biodiversity monitoring, and ecosystem-based management. Full article

Electroencephalography (EEG) offers a noninvasive, high-temporal-resolution modality for estimating mental workload. However, session-to-session variability limits the generalizability of workload classifiers, and few systematic cross-session evaluations are reported in the literature. This study systematically evaluates domain adaptation methods for cross-session mental workload classification using the publicly available COG-BCI dataset within an evaluation framework that may guide future studies on EEG-based classification models. We make four contributions: (i) integration of Optimal Transport (OT) with Graph Neural Networks (GNNs) to model spatial relationships and align feature distributions under strict session-wise separation; (ii) a data-centric evaluation pipeline incorporating Self-Organizing Map (SOM) visualizations for data exploration and a heuristic loss function for model selection; (iii) a strict cross-session protocol examining the effects of graph construction, feature selection, and data splits; and (iv) comparison of OT with CORrelation ALignment (CORAL) and GNN with EEGNet. Incorporating OT improved test accuracies across all experimental configurations. SOM visualizations confirmed enhanced feature alignment after OT. Our results highlight the potential of OT for mitigating session-to-session variability and underscore the importance of a data-centric approach and rigorous cross-session evaluation when developing classifiers for complex cognitive state estimation. Future work should explore semi-supervised OT strategies and scalable implementations for real-time applications. Full article

Coral reefs are among the most important and vulnerable marine ecosystems worldwide. AI-powered underwater visual monitoring has become essential for effective reef conservation, yet current methods still face severe limitations: spectral ambiguity caused by underwater turbidity, fine-grained confusion in early coral health assessment, and discrete forecasting models that cannot represent continuous ecological degradation dynamics. To address these issues, we propose Spectral-YOLOv13, a dual-domain vision-Mamba sensing framework for high-precision coral health evaluation and continuous ecological forecasting. The framework incorporates three novel components: a Wavelet-Integrated Omni-Neck (WIO-Neck) to perform multi-scale spectral filtering and suppress turbidity-induced noise; a Contrastive Prototype Head (CP-Head) to enhance discriminability between visually similar health states; and a Bio-Mamba Predictor based on state-space models to capture long-term continuous health trajectories. Extensive experiments on the CR-Mix++ dataset demonstrate that Spectral-YOLOv13 achieves 53.8% mAP with strong robustness in turbid underwater environments. It reduces four-week forecasting error by 26.8% and maintains real-time inference speed at 112 FPS. This work provides a reliable and high-performance vision framework for practical underwater coral reef monitoring and proactive conservation management. Full article

Coastal small-scale fishers in the Asia-Pacific region (APR) face mounting challenges from climate change (CC), with vulnerability shaped by ecological exposure, socio-economic dependence, and limited adaptive capacity. This study reflects on two contrasting cases, Taiwan and Papua New Guinea (PNG), to explore fishers’ perceptions and perspectives on CC and practical adaptation strategies. In PNG, 209 respondents from Momase, the Islands, and Southern regions participated. In Taiwan, 45 respondents from the Yunlin and Chiayi coastal regions participated. Significant correlations in coastal communities’ vulnerabilities and perceptions towards CC were revealed. Small-scale fishers perceive rising sea temperatures, shifting fish stocks, and intensifying typhoons as disruptive shocks to livelihoods and eroding traditional fishing practices. In Taiwan, despite relatively stronger infrastructure, household income, and access to technology, adaptation remains constrained by market pressures, declining youth participation, and regulatory complexities. In PNG, fishers deeply rely on natural resources and coastal ecosystems for subsistence and income, yet face acute risks from sea-level rise, coral bleaching, and unpredictable weather. With limited financial resources, weak institutional support, and geographic isolation, fishers perceive CC as an amplifying factor to existing vulnerabilities, leaving communities dependent on traditional knowledge and communal coping strategies. Fishers’ perceptions of CC are shaped by lived experiences rather than scientific discourse, influencing adaptation choices ranging from livelihood diversification to migration. Perceptions of CC drivers, their distal and proximal impacts on coastal fishing community livelihoods are viewed as siloed; yet, remote sensing data revealed that the impacts are transboundary. The findings underscore the urgent need for context-sensitive policies that integrate local knowledge, science-based data (such as remote sensing CC maps) to strengthen institutional support, and enhance resilience among vulnerable and underserved coastal small-scale fishers. Full article

Traditional analyses of transport phenomena rely on prescribed geometric boundaries, yet natural flow systems dynamically evolve their architecture to maximize access to currents. To address this disparity, we propose a field-theoretic framework for the constructal law that treats physical geometry as a dynamic state variable, represented by a time-dependent conductivity tensor. Using a variational approach grounded in non-equilibrium thermodynamics, we derive a general tensor evolution equation. Within this framework, macroscopic flow architecture emerges deterministically from the continuous competition between non-linear flux-induced accretion, linear entropic relaxation, and spatial smoothing. Scaling analysis reduces this dynamic to a tri-parameter dimensionless phase space: a morphogenic number driving structural growth, a structural diffusion number governing spatial coherence, and a stochastic intensity number providing the microscopic seeds for symmetry breaking. Our principal result is the analytical prediction of a critical bifurcation. When the local morphogenic number strictly exceeds unity, the system escapes its stable, isotropic configuration and branches into highly conductive, anisotropic architectures. We demonstrate the predictive validity and trans-scalar applicability of this continuum theory by mapping it to highly diverse phase transitions, successfully capturing phenomena ranging from microscopic aerosol agglomeration and microbial resistance, to macroscopic coral plasticity and crystal growth instabilities, and finally to the astrophysical launching of relativistic jets from black holes. Full article

The San Andrés, Providencia, and Santa Catalina archipelago, located in the Colombian Caribbean, hosts diverse ecosystems, including coral reefs, mangroves, seagrass beds, and beaches, all of which are increasingly threatened by human activities. This research proposes a spatial analysis of ecological risk that integrates ecosystem vulnerability and anthropogenic pressures associated with land-use change to promote sustainable risk management. The vulnerability of island ecosystems was assessed by analyzing changes in cover across multiple time periods. At the same time, risks from anthropogenic pressures were determined based on marine protected area zoning and land-use planning regulations. Results show contrasting patterns: while several mangrove and beach sectors remained relatively stable, mangrove loss reached up to 65% in Providencia, and seagrass ecosystems experienced severe degradation, including a complete loss (100%) in western San Andrés. Risk maps indicate that the highest risk levels are consistently associated with Special Use Zones, where tourism infrastructure, navigation, and port activities are permitted. These findings highlight the importance of ecosystem-based risk management and adaptive governance in reducing anthropogenic pressures and preserving island ecosystem health. Full article

Coral reefs in the South China Sea (SCS) are critical for regional marine biodiversity and ecosystem services but face escalating threats from climate change and anthropogenic stressors. However, a holistic evaluation of habitat suitability spanning the distinct environmental gradients from low-latitude deep-water atolls to high-latitude marginal reefs remains limited. This study utilized high-resolution remote sensing data and the MaxEnt (Maximum Entropy) model combined with Principal Component Analysis (PCA) to systematically map potential habitat suitability and elucidate the multi-scale environmental drivers shaping the realized niche of SCS corals. The results revealed significant spatial heterogeneity characterized by a distinct “High South, Low North” latitudinal gradient, with Unsuitable areas dominating 85.5% of the study region, followed by Marginally Suitable habitats at 5.0%, while the northern Nansha Islands were identified as the core distribution area with the highest suitability and continuity. Minimum Phosphate (Min. Phos.) concentration and Sea Surface Temperature (SST) were identified as the core environmental factors determining the spatial distribution of coral reefs in the South China Sea. The optimal environmental ranges were identified as: SST between 28.52 °C and 29.41 °C, water depth shallower than 34 m, extremely low phosphate (0–0.005 mmol/m³), and low cumulative thermal stress (DHW < 0.83 °C-weeks). Crucially, PCA further quantified two potential climate refugia: low-latitude thermal refugia in the southern Nansha Islands, characterized by high environmental stability, and high-latitude marginal refugia in the Beibu Gulf, which offer physical buffering against warming, while necessitating targeted efforts to mitigate the risks of habitat degradation and eutrophication driven by intensifying anthropogenic activities These findings challenge the traditional conservation view relying solely on high-latitude migration, advocating for a climate-resilient spatial planning strategy that prioritizes strict protection of southern biodiversity source banks while enhancing the connectivity of northern marginal stepping stones. Full article

Accurate urban noise mapping requires granular traffic flow characterization aligned with specific acoustic models, such as CNOSSOS-EU. Existing monitoring solutions often lack the specific categorization capabilities, cost-effectiveness, or flexibility required for large-scale deployment in resource-constrained environments. To address this challenge, the present study describes the development of a real-time multi-vehicle recognition system based on low-cost edge computing hardware, specifically a Raspberry Pi 4 coupled with a Coral TPU accelerator. The proposed methodology integrates a quantized YOLOv8 convolutional neural network (CNN) with a tracking algorithm to enable real-time detection and classification of vehicles into five distinct classes, allowing for precise aggregation according to CNOSSOS-EU standards. The model was trained on a proprietary dataset of 15,000 images and subjected to 8-bit post-training quantization to optimize inference speed. Experimental results demonstrate that the system achieves an inference speed of 14 FPS and a mean Average Precision (mAP@50) of 92.2% in daytime conditions, maintaining robust performance on embedded devices. In a real-world case study, the proposed system significantly outperformed a commercial traffic monitoring solution, achieving a weighted percentage error of just 6.6% compared to the commercial system’s 59.9%, effectively bridging the gap between manual counting accuracy (1.4% error) and automated efficiency. Full article

The escalating global rates of traffic accidents in urban areas and the growing demands of smart cities underscore the urgent need for advanced real-time monitoring solutions. This paper presents an EdgeML-based system for vehicle tracking that performs real-time speed and distance analysis and traffic violation detection. This is achieved by deploying a YOLOv8 object detection model on a Raspberry Pi 5 with a Coral USB Edge TPU accelerator. The system integrates computer vision and IoT technologies to enable real-time processing. It utilizes the Message Queuing Telemetry Transport (MQTT) protocol to allow scalable communication between distributed edge devices and a central MongoDB database, facilitating real-time storage and analysis of traffic data. A synthetic dataset generated via the Blender 3D modeling tool validates the system’s accuracy, demonstrating average speed and distance measurement errors of ±2.11 km/h and ±0.58 m, respectively. These findings are further supported by preliminary practical experiments in a real-world environment, where speed estimation errors remained within 0–2 km/h and distance errors stayed below 0.11 m. Key innovations of this work include license plate recognition, speeding and collision detection, and context analysis using Google’s Gemini-2.5-Flash API. A Streamlit dashboard provides real-time visualization of traffic metrics, violations, and aggregated data. A comparative evaluation of YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n identifies YOLOv8n as the most suitable model for embedded deployment, achieving 91.07 ± 0.61% mAP@0.5 without quantization, 88.77 ± 3.31% mAP@0.5 with quantization, while maintaining real-time performance of 30–43 frames per second (FPS) on the Edge TPU. The system’s modular architecture, low latency, and robust performance highlight its suitability for smart city applications, enhancing traffic safety and enabling data-driven urban mobility management. Full article

Integrating high-performance computer vision (CV) into Industry 4.0 environments remains a challenge due to the computational disparity between state-of-the-art (SOTA) models and resource-constrained edge hardware. This study proposes a hardware-aware optimization framework designed to bridge this gap, focusing on real-time object detection for high-speed, omnidirectional conveyor systems. Unlike conventional benchmarking, the proposed framework employs a multi-stage optimization pipeline—integrating backbone refinement, hyperparameter tuning, and quantization—to transition diverse architectures from baseline configurations ($M_{base}$) to hardware-optimized variants ($M_{opt}$).The framework’s efficacy is validated using a custom-built standalone experimental platform detecting package features, brands, and disruptions on an omnidirectional-wheeled conveyor. A comprehensive comparative analysis is conducted across a heterogeneous edge ecosystem, including the NVIDIA Jetson Nano (GPU), Raspberry Pi 4 (CPU), and Google Coral (TPU). Our findings demonstrate that through systematic tuning, the YOLOv10n variant emerged as the superior architecture, achieving a precision of 98.1% and an mAP_50:95 of 81.22%. Post-deployment characterization reveals that the optimized YOLOv10n model on the NVIDIA Jetson Nano achieved a peak inference speed of 25 frames per second (FPS), successfully striking the “Pareto-optimal” balance between predictive accuracy and real-time processing. The primary contributions of this work include a reproducible optimization methodology, a comparative performance map across three distinct hardware backends, and the release of a specialized industrial conveyor dataset. Full article

In underwater detection tasks involving bleached corals, band disease corals, and white pox disease corals, several challenges persist, including high morphological variability, difficulty in identifying small pathological regions, interference from complex underwater environments, and constraints imposed by underwater hardware. To address these issues, a lightweight underwater diseased coral target detection method, termed CD-YOLO, is proposed. Specifically, (1) a lightweight network named CDShuffleNet is constructed to replace the YOLO11 backbone, aiming to reduce model complexity while preserving detection performance; (2) a SPDConv downsampling convolution module is introduced to reduce the loss of fine-grained coral detail information during the downsampling process; and (3) attention mechanisms are incorporated through an engineering-oriented integration of EMA into the C2PSA module and the adoption of SENetV2, in order to enhance the representation of color and shape features of pathological regions and suppress interference from complex underwater environments. Experimental results demonstrate that the proposed improvements yield consistent gains in both model lightweighting and detection performance under the adopted evaluation settings. Specifically, the number of parameters, computational cost, and model size are reduced by 20.6%, 21.9%, and 18.9%, respectively, while mAP increases by 4.3 percentage points. Comparative experiments further show that the proposed method achieves a markedly higher mAP than several other state-of-the-art models. In addition, experiments conducted on the BHD Coral dataset provide preliminary evidence of cross-dataset adaptability of the proposed model. Overall, this study presents a task-oriented and application-driven improvement, demonstrating that the effective integration of lightweight components can achieve a favorable balance between model efficiency and detection performance in underwater diseased coral detection tasks. Full article

Globally, sea turtles face significant threats from human activities, yet detailed information on their habitat use and specific anthropogenic impacts remains limited, particularly in key marine protected areas like Kenya’s Diani-Chale National Marine Reserve (DCNMR). This study utilized drone-based (UAV—unmanned aerial vehicle) monitoring and geospatial analysis to assess sea turtle distribution and habitat use, integrating data from the Allen Coral Atlas. Most sea turtle sightings occurred in reef zones (61.86%), while the reef slope was the most utilized geomorphic feature (26.7% of sightings). The study identified a significant sea turtle hotspot in the northern DCNMR, a region characterized by lower anthropogenic pressure and unique geomorphic features. Between February and July 2024, we conducted monthly UAV surveys (6–10 survey days per month) in the DDCNMR using a DJI Mavic 3 drone, completing multiple standardized 25-min flights per day that each covered ~1 km² via non-overlapping transects at 30–40 m altitude under optimal sea state and visibility conditions, resulting in 233 sea turtle sightings. UAV survey data were summarized descriptively, with sea turtle sightings mapped against geomorphological features as well as benthic habitats from an open source, high-resolution, satellite-based map and monitoring system for shallow-water coral reefs (ACA—Allen Coral Atlas). Allen Coral Atlas data and drone observations indicate that a widened reef slope and estuarine nutrient inputs provide a critical habitat gradient, offering turtles tidal-independent access to shallow foraging flats. Based on these findings, we recommend designating the northern reef slope as a priority no-take zone and conducting seagrass health assessments to guide potential restoration. This research demonstrates the utility of integrating drone surveys with open access geospatial tools to provide the actionable spatial data necessary for targeted sea turtle conservation and informed marine spatial planning. Full article

Live coral cover is a key indicator of coral reef composition, health, and functioning. Airborne imaging spectroscopy provides verifiably accurate estimates of live coral cover to seawater depths of 25 m, yet satellite-based approaches have not achieved the same level of performance. The new Tanager-1 satellite carries a high-fidelity imaging spectrometer in sun-synchronous Earth orbit, providing an opportunity to transition from airborne to spaceborne imaging of live corals and other benthic constituents. We coordinated overpasses of Tanager-1 and Global Airborne Observatory (GAO) imaging spectrometer measurements of coral reef to a depth of 25 m in Hawaiʻi. Tanager-1 has a spatial resolution of 30 m, while the GAO data were collected at 2 m resolution, requiring detailed modeling to simulate 30 m data for subsequent comparison to the satellite data. At 30 m resolution, the two sensors generated similar geographic patterns of live coral, macroalgal, and sand cover. Field validation indicated similar precision and accuracy of live coral cover estimates, and the ratio of live coral to macroalgal cover proved similar between sensors. Overall results indicate that live coral cover can be mapped with high-fidelity imaging spectroscopy from Earth orbit. With the advent of more spaceborne imaging spectrometers, a new era of live coral monitoring will be possible, filling a critical gap for repeated assessments of reef compositional change at a global level. Full article