Search Results (71)

This research develops a dual physics-based machine learning system to forecast fuel consumption and CO₂ emissions for a 100 m oil tanker across six operational scenarios: Original, Paint, Advanced Propeller, Fin, Bulbous Bow, and Combined. The combination of hydrodynamic calculations with Monte Carlo simulations provides a solid foundation for training machine learning models, particularly in cases where dataset restrictions are present. The XGBoost model demonstrated superior performance compared to Support Vector Regression, Gaussian Process Regression, Random Forest, and Shallow Neural Network models, achieving near-zero prediction errors that closely matched physics-based calculations. The physics-based analysis demonstrated that the Combined scenario, which combines hull coatings with bulbous bow modifications, produced the largest fuel consumption reduction (5.37% at 15 knots), followed by the Advanced Propeller scenario. The results demonstrate that user inputs (e.g., engine power: 870 kW, speed: 12.7 knots) match the Advanced Propeller scenario, followed by Paint, which indicates that advanced propellers or hull coatings would optimize efficiency. The obtained insights help ship operators modify their operational parameters and designers select essential modifications for sustainable operations. The model maintains its strength at low speeds, where fuel consumption is minimal, making it applicable to other oil tankers. The hybrid approach provides a new tool for maritime efficiency analysis, yielding interpretable results that support International Maritime Organization objectives, despite starting with a limited dataset. The model requires additional research to enhance its predictive accuracy using larger datasets and real-time data collection, which will aid in achieving global environmental stewardship. Full article

Autonomous Unmanned Surface Vehicle (USV) operations in complex ocean engineering scenarios necessitate robust navigation, guidance, and control technologies. These systems require reliable sensor-based object detection and efficient, safe, and energy-aware path planning. To address these multifaceted challenges, this paper proposes a novel synergistic AI framework. The framework integrates (1) a novel adaptation of the Swin-Transformer to generate a dense, semantic risk map from raw visual data, enabling the system to interpret ambiguous marine conditions like sun glare and choppy water, enabling real-time environmental understanding crucial for guidance; (2) a Transformer-enhanced A-star (T-ASTAR) algorithm with spatio-temporal attentional guidance to generate globally near-optimal and energy-aware static paths; (3) a domain-adapted TD3 agent featuring a novel energy-aware reward function that optimizes for USV hydrodynamic constraints, making it suitable for long-endurance missions tailored for USVs to perform dynamic local path optimization and real-time obstacle avoidance, forming a key control element; and (4) CUDA acceleration to meet the computational demands of real-time ocean engineering applications. Simulations and real-world data verify the framework’s superiority over benchmarks like A* and RRT, achieving 30% shorter routes, 70% fewer turns, 64.7% fewer dynamic collisions, and a 215-fold speed improvement in map generation via CUDA acceleration. This research underscores the importance of integrating powerful AI components within a hierarchical synergy, encompassing AI-based perception, hierarchical decision planning for guidance, and multi-stage optimal search algorithms for control. The proposed solution significantly advances USV autonomy, addressing critical ocean engineering challenges such as navigation in dynamic environments, object avoidance, and energy-constrained operations for unmanned maritime systems. Full article

Transverse fetal head position during labor is associated with increased rates of operative deliveries and cesarean sections. Traditional assessment methods rely on digital examination, which can be inaccurate in cases of prolonged labor. Intrapartum ultrasound offers improved diagnostic capabilities, but standardized interpretation frameworks are needed. This study aimed to evaluate the significance of appropriate assessment and management of transverse fetal head position during labor, with particular emphasis on the correlation between geometric parameters and delivery outcomes. Additionally, the investigation analyzed the potential role of Artificial Intelligence Dystocia Algorithm (AIDA) as an innovative decision support system in standardizing diagnostic approaches and optimizing clinical decision-making in cases of fetal malposition. This investigation was conducted as a focused secondary analysis of data originally collected for the development and validation of the Artificial Intelligence Dystocia Algorithm (AIDA). The study examined 66 cases of transverse fetal head position from a cohort of 135 nulliparous women with prolonged second-stage labor across three Italian hospitals. Cases were stratified by Midline Angle (MLA) measurements into classic transverse (≥75°), near-transverse (70–74°), and transitional (60–69°) positions. Four geometric parameters (Angle of Progression, Head–Symphysis Distance, Midline Angle, and Asynclitism Degree) were evaluated using the AIDA classification system. The predictive capabilities of three machine learning algorithms (Support Vector Machine, Random Forest, and Multilayer Perceptron) were assessed, and delivery outcomes were analyzed. The AIDA system successfully categorized labor dystocia into five distinct classes, with strong predictive value for delivery outcomes. A clear gradient of cesarean delivery risk was observed across the spectrum of transverse positions (100%, 93.1%, and 85.7% for near-transverse, classic transverse, and transitional positions, respectively). All cases classified as AIDA Class 4 required cesarean delivery regardless of the specific MLA value. Machine learning algorithms demonstrated high predictive accuracy, with Random Forest achieving 95.5% overall accuracy across the study cohort. The presence of concurrent asynclitism with transverse position was associated with particularly high rates of cesarean delivery. Among the seven cases that achieved vaginal delivery despite transverse positioning, none belonged to the classic transverse positions group, and five (71.4%) exhibited at least one parameter classified as favorable. The integration of artificial intelligence through AIDA as a decision support system, combined with intrapartum ultrasound, offered a promising approach for objective assessment and management of transverse fetal head position. The AIDA classification system’s integration of multiple geometric parameters, with particular emphasis on precise Midline Angle (MLA) measurement in degrees, provided superior predictive capability for delivery outcomes compared to qualitative position assessment alone. This multidimensional approach enabled more personalized and evidence-based management of malpositions during labor, potentially reducing unnecessary interventions while identifying cases where expectant management might be futile. Further prospective studies are needed to validate the predictive capability of this decision support system and its impact on clinical decision-making in real-time labor management. Full article

In modern manufacturing, ensuring quality control for geometric features is critical, yet detecting anomalies in circular components remains underexplored. This study proposes a real-time defect detection framework for metal parts with holes, optimized for deployment on a Raspberry Pi 5 edge device. We fine-tuned and evaluated three deep learning models ResNet50, EfficientNet-B3, and MobileNetV3-Large on a grayscale image dataset (43,482 samples) containing various hole defects and imbalances. Through extensive data augmentation and class-weighting, the models achieved near-perfect binary classification of defective vs. non-defective parts. Notably, ResNet50 attained 99.98% accuracy (precision 0.9994, recall 1.0000), correctly identifying all defects with only one false alarm. MobileNetV3-Large and EfficientNet-B3 likewise exceeded 99.9% accuracy, with slightly more false positives, but offered advantages in model size or interpretability. Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations confirmed that each network focuses on meaningful geometric features (misaligned or irregular holes) when predicting defects, enhancing explainability. These results demonstrate that lightweight CNNs can reliably detect geometric deviations (e.g., mispositioned or missing holes) in real time. The proposed system significantly improves inline quality assurance by enabling timely, accurate, and interpretable defect detection on low-cost hardware, paving the way for smarter manufacturing inspection. Full article

Women exhibit marked physiological transformations in pregnancy, mandating regular and holistic assessment. Maternal and fetal vitality is governed by a spectrum of clinical, demographic, and lifestyle factors throughout this critical period. The existing maternal health monitoring techniques lack precision in assessing pregnancy-related risks, often leading to late interventions and adverse outcomes. Accurate and timely risk prediction is crucial to avoid miscarriages. This research proposes a deep learning framework for personalized pregnancy risk prediction using the NFHS-5 dataset, and class imbalance is addressed through a hybrid NearMiss-SMOTE approach. Fifty-one primary features are selected via the LASSO to refine the dataset and enhance model interpretability and efficiency. The framework integrates a multimodal model (NFHS-5, fetal plane images, and EHG time series) along with two core architectures. ResRNN-Net further combines Bi-LSTM, CNNs, and attention mechanisms to capture sequential dependencies. MultiScaleFusion-Net leverages GRU and multiscale convolutions for effective feature extraction. Additionally, TabNet and MLP models are explored to compare interpretability and computational efficiency. SHAP and Grad-CAM are used to ensure transparency and explainability, offering both feature importance and visual explanations of predictions. The proposed models are trained using 5-fold stratified cross-validation and evaluated with metrics including accuracy, precision, recall, F1-score, and ROC–AUC. The results demonstrate that MultiScaleFusion-Net balances accuracy and computational efficiency, making it suitable for real-time clinical deployment, while ResRNN-Net achieves higher precision at a slight computational cost. Performance comparisons with baseline machine learning models confirm the superiority of deep learning approaches, achieving over 80% accuracy in pregnancy complication prediction. Full article

To address issues of food authenticity, such as fraud and origin tracing, it is essential to employ methods in food fingerprinting that are efficient, economical, and easy to use. This review highlights the capabilities of vibrational spectroscopy techniques, including mid-infrared (MIR), near-infrared (NIR), and Raman spectroscopy, as non-invasive tools for food authentication. These methods offer rapid, cost-effective, and environmentally friendly analysis across diverse food matrices. This review further discusses recent advances such as hyperspectral imaging, portable devices, and data fusion strategies that integrate chemometrics and artificial intelligence. Despite their promise, challenges remain, including limited sensitivity for certain compounds, spectral overlaps, fluorescence interference in Raman spectroscopy, and the need for standardized validation protocols. Looking forward, trends such as the miniaturization of devices, real-time monitoring, and AI-enhanced spectral interpretation are expected to significantly advance the field of food authentication. Full article

Transformer winding faults (TWFs) can lead to insulation breakdown, internal short circuits, and catastrophic transformer failure. Due to their low current magnitude—particularly at early stages such as inter-turn short circuits, axial or radial displacement, or winding looseness—TWFs often induce minimal impedance changes and generate fault currents that remain within normal operating thresholds. As a result, conventional protection schemes like overcurrent relays, which are tuned for high-magnitude faults, fail to detect such internal anomalies. Moreover, frequency response deviations caused by TWFs often resemble those introduced by routine phenomena such as tap changer operations, load variation, or core saturation, making accurate diagnosis difficult using traditional FRA interpretation techniques. This paper presents a novel diagnostic framework combining Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM) classification to improve the detection of TWFs. The proposed system employs region-based statistical deviation labeling to enhance interpretability across five well-defined frequency bands. It is validated on five real FRA datasets obtained from operating transformers in Gauteng Province, South Africa, covering a range of MVA ratings and configurations, thereby confirming model transferability. The system supports post-processing but is lightweight enough for near real-time diagnostic use, with average execution time under 12 s per case on standard hardware. A custom graphical user interface (GUI), developed in MATLAB R2022a, automates the diagnostic workflow—including region identification, wavelet-based decomposition visualization, and PDF report generation. The complete framework is released as an open-access toolbox for transformer condition monitoring and predictive maintenance. Full article

Accurate classification of sulfide minerals during combustion is essential for optimizing pyrometallurgical processes such as flash smelting, where efficient combustion impacts resource utilization, energy efficiency, and emission control. This study presents a deep learning-based approach for classifying visible and near-infrared (VIS-NIR) emission spectra from the combustion of high-grade sulfide minerals. A one-dimensional convolutional neural network (1D-CNN) was developed and trained on experimentally acquired spectral data, achieving a balanced accuracy score of 99.0% in a test set. The optimized deep learning model outperformed conventional machine learning methods, highlighting the effectiveness of deep learning for spectral analysis in high-temperature environments. In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to enhance model interpretability and identify key spectral regions contributing to classification decisions. The results demonstrated that the model successfully distinguished spectral features associated with different mineral species, offering insights into combustion dynamics. These findings support the potential integration of deep learning for real-time spectral monitoring in industrial flash smelting operations, thereby enabling more precise process control and decision-making. Full article

Satellite imagery provides a rich source of information that serves as a comprehensive and synoptic tool for the continuous monitoring of active volcanoes, including those in remote and inaccessible areas. The huge influx of such data requires the development of automated systems for efficient processing and interpretation. Early warning systems, designed to process satellite imagery to identify signs of impending eruptions and monitor eruptive activity in near real-time, are essential for hazard assessment and risk mitigation. Here, we propose a machine learning approach for the automatic classification of pixels in SEVIRI images to detect and characterize the eruptive activity of a volcano. In particular, we exploit a semi-supervised GAN (SGAN) model that retrieves the presence of thermal anomalies, volcanic ash plumes, and meteorological clouds in each SEVIRI pixel, allowing time series plots to be obtained showing the evolution of volcanic activity. The SGAN model was trained and tested using the huge amount of data available on Mount Etna (Italy). Then, it was applied to other volcanoes, specifically, Stromboli (Italy), Tajogaite (Spain), and Nyiragongo (Democratic Republic of the Congo), to assess the model’s ability to generalize. The validation of the model was performed through a visual comparison between the classification results and the corresponding SEVIRI images. Moreover, we evaluate the model performance by calculating three different metrics, namely the precision (correctness of positive predictions), the recall (ability to find all the positive instances), and the F1-score (general model’s accuracy), finding an average accuracy of 0.9. Our approach can be extended to other geostationary satellite data and applied worldwide to characterize volcanic activity, allowing the monitoring of even remote volcanoes that are difficult to reach from the ground. Full article

Objectives: Hot-melt extrusion (HME) offers a solvent-free, scalable approach for manufacturing pharmaceutical co-crystals (CCs), aligning with the industry’s shift to continuous manufacturing (CM). However, challenges like undefined yield optimization, insufficient risk management, and limited process analytical technology (PAT) integration hinder its industrial application. This study aimed to develop a proof-of-concept HME platform for CCs, assess process risks, and evaluate PAT-enabled monitoring to facilitate robust production. Methods: Using carbamazepine (CBZ) and nicotinamide (NIC) as model compounds, an HME platform compatible with PAT tools was established. A systematic risk assessment identified five key risk domains: materials, machinery, measurement, methods, and other factors. A Box–Behnken design of experiments (DoE) evaluated the impact of screw speed, temperature, and mixing sections on CC quality. Near-infrared (NIR) spectroscopy monitored CBZ-NIC co-crystal formation in real time during HME process. Results: DoE revealed temperature and number of mixing sections significantly influenced particle size (D₅₀: 2.0–4.0 μm), while screw speed affected efficiency. NIR spectroscopy detected a unique CC absorption peak at 5008.3 cm⁻¹, enabling real-time structural monitoring with high accuracy (R² = 0.9999). Risk assessment highlighted material attributes, process parameters, and equipment design as critical factors affecting CC formation. All experimental batches yielded ≥ 94% pure CCs with no residual starting materials, demonstrating process reproducibility and robustness. Conclusions: Overall, this work successfully established a continuous hot-melt extrusion (HME) process for manufacturing CBZ-NIC co-crystals, offering critical insights into material, equipment, and process parameters while implementing robust in-line NIR monitoring for real-time quality control. Additionally, this work provides interpretable insights and serves as a basis for future machine learning (ML)-driven studies. Full article

Antepartum Cardiotocography (CTG) is a biomedical sensing technology widely used for fetal health monitoring. While the visual interpretation of CTG traces is highly subjective, with the inter-observer agreement as low as 29% and a false positive rate of approximately 60%, the Dawes–Redman system provides an automated approach to fetal well-being assessments. However, it is primarily designed to rule out adverse outcomes rather than detect them, resulting in a high specificity (90.7%) but low sensitivity (18.2%) in identifying fetal distress. This paper introduces PatchCTG, an AI-enabled biomedical time series transformer for CTG analysis. It employs patch-based tokenisation, instance normalisation, and channel-independent processing to capture essential local and global temporal dependencies within CTG signals. PatchCTG was evaluated on the Oxford Maternity (OXMAT) dataset, which comprises over 20,000 high-quality CTG traces from diverse clinical outcomes, after applying the inclusion and exclusion criteria. With extensive hyperparameter optimisation, PatchCTG achieved an AUC of 0.77, with a specificity of 88% and sensitivity of 57% at Youden’s index threshold, demonstrating its adaptability to various clinical needs. Its robust performance across varying temporal thresholds highlights its potential for both real-time and retrospective analysis in sensor-driven fetal monitoring. Testing across varying temporal thresholds showcased it robust predictive performance, particularly with finetuning on data closer to delivery, achieving a sensitivity of 52% and specificity of 88% for near-delivery cases. These findings suggest the potential of PatchCTG to enhance clinical decision-making in antepartum care by providing a sensor-based, AI-driven, objective tool for reliable fetal health assessment. Full article

Multi-temporal synthetic aperture radar interferometry (MT-InSAR) has evolved from a niche research technique into a powerful global monitoring tool. With the launch of nationwide and continent-wide ground motion services (GMSs), freely available deformation data can now be analyzed on a large scale. However, their applicability for monitoring critical infrastructure, such as dams, has not yet been thoroughly assessed, and several challenges have hindered the integration of MT-InSAR into existing monitoring frameworks. These challenges include technical limitations, difficulties in interpreting deformation results, and the rigidity of existing safety protocols, which often restrict the adoption of remote sensing techniques for operational dam monitoring. This study evaluates the effectiveness of persistent scatterer (PS) data from the German ground motion service (Bodenbewegungsdienst Deutschland, BBD) in complementing time-consuming in situ techniques. By analyzing a gravity dam in Germany, BBD time series were compared with in situ pendulum data. We propose a two-stage assessment procedure: First, we evaluate the dam’s suitability for PS analysis using the CR-Index to identify areas with good radar visibility. Second, we assess the interpretability of BBD data for radial deformations by introducing a novel index that quantifies the radial sensitivity of individual PS points on the dam. This index is universally applicable and can be transferred to other types of infrastructure. The results revealed a fair correlation between PS deformations and pendulum data for many PS points (up to $R^2$ = 0.7). A priori feasibility assessments are essential, as factors such as topography, land cover, and dam type influence the applicability of the PS technique. The dam’s orientation relative to the look direction of the sensor emerged as a key criterion for interpreting radial deformations. For angle differences (${\Delta }_{\mathrm{RAD}}$) of up to 20° between the true north radial angle of a PS point and the satellite’s look direction, the line-of-sight (LOS) sensitivity accounts for approximately 50 to 70% of the true radial deformation, depending on the satellite’s incidence angle. This criterion is best fulfilled by dams aligned in a north–south direction. For the dam investigated in this study, the LOS sensitivity to radial deformations was low due to its east–west orientation, resulting in significantly higher errors (6 mm $\le RMSE\le 43$ mm) compared to in situ pendulum data. Eliminating PS points with an unfavorable alignment with the sensor should be considered before interpreting radial deformations. For implementation into operational monitoring programs, greater effort must be spent on near-real-time updates of BBD datasets. Full article

The number of studies on submarine groundwater discharge (SGD) and the evidence of its significance in biogeochemical cycling and potential impacts on the chemical and ecological status of coastal waters is increasing globally. Here, we briefly present SGD studies from the Baltic Sea identified along the coastlines of Denmark, Finland, Germany, Poland, Sweden and Russia in the southwestern, southern and north–northeastern parts of the Baltic Sea. We introduce a digital SGD map viewer and information platform enabling easy overview and access to information on identified SGD sites in the coastal areas of the Baltic Sea. SGDs potentially transport critical pollutants from urban and agricultural areas on land to the marine environment. The pollutants include nutrients, dissolved organic and inorganic carbon, metals, pharmaceuticals, and other emerging contaminants, potentially harming marine ecosystems and biodiversity and possibly contributing to the poor chemical or ecological status of coastal waters, affecting human and environmental health. We focus on case studies from Finland, Germany, Poland and Denmark that include the results and interpretations from the applied geochemical, geophysical and geological methods, as well as bionic autonomous underwater vehicles (AUVs) for locating, investigating, modelling and visualizing SGD sites in 2D and 3D. The potential Pan-European or even global SGD information platform established within the European Geological Data Infrastructure (EGDI) enables the easy combination and comparison of map layers such as seabed sediment types and coastal habitats. The EGDI map viewer provides easy access to information from SGD studies and may serve as an entry point to relevant information on SGDs, including contents of pollutants, for the scientific community and policy-makers. The information potentially includes the results of model simulations, data from near real-time sensors at permanently installed monitoring stations and surveys in time and space conducted by AUVs. The presented digital SGD information platform is particularly pertinent to the UN Sustainable Development Goal (SDG) No. 14, which focuses on the conservation and sustainable use of oceans and marine resources. Full article

With the emergence of artificial intelligence and advancements in network technologies, the imminent arrival of 6G is not very far away. The 6G technology will introduce unique and innovative applications of the Tactile Internet in the near future. This paper highlights the evolution towards the Tactile Internet enabled by 6G technology, along with the details of 6G capabilities. It emphasizes the stringent requirements for emerging Tactile Internet applications and the critical role of parameters, such as latency, reliability, data rate, and others. The study identifies the important characteristics of future Tactile Internet applications, interprets them into explicit requirements, and then discusses the associated design considerations. The study focuses on the role of application characteristics of various applications, like virtual reality/augmented reality, remote surgery, gaming, smart cities, autonomous vehicles, industrial automation, brain–machine interface, telepresence/holography, and requirements in the design of 6G and the Tactile Internet. Furthermore, we discuss the exclusive parameters and other requirements of Tactile Internet to realize real-time haptic interactions with the help of 6G and artificial intelligence. The study deliberates and examines the important performance parameters for the given applications. It also discusses various types of sensors that are required for Tactile Internet applications. Full article

This study introduces an integrated lower limb robotic orthosis with near-field electrospinning (NFES) piezoelectric sensors and a fuzzy logic-based gait phase detection system to enhance mobility assistance and rehabilitation. The exoskeleton incorporates embedded pressure sensors within the insoles to capture ground reaction forces (GRFs) in real-time. A fuzzy logic inference system processes these signals, classifying gait phases such as stance, initial contact, mid-stance, and pre-swing. The NFES technique enables the fabrication of highly oriented nanofibers, improving sensor sensitivity and reliability. The system employs a master–slave control framework. A Texas Instruments (TI) TMS320F28069 microcontroller (Texas Instruments, Dallas, TX, USA) processes gait data and transmits actuation commands to motors and harmonic drives at the hip and knee joints. The control strategy follows a three-loop methodology, ensuring stable operation. Experimental validation assesses the system’s accuracy under various conditions, including no-load and loaded scenarios. Results demonstrate that the exoskeleton accurately detects gait phases, achieving a maximum tracking error of 4.23% in an 8-s gait cycle under no-load conditions and 4.34% when tested with a 68 kg user. Faster motion cycles introduce a maximum error of 6.79% for a 3-s gait cycle, confirming the system’s adaptability to dynamic walking conditions. These findings highlight the effectiveness of the developed exoskeleton in interpreting human motion intentions, positioning it as a promising solution for wearable rehabilitation and mobility assistance. Full article