Search Results (319)

This study aims to develop effective screening tools for cognitive impairment by integrating optimised speech classification features with various machine learning models. A total of 65 patients diagnosed with early-stage Mild Cognitive Impairment (MCI) and 55 healthy controls (HCs) were included. Audio data were collected through a picture description task and processed using the Python-based Librosa library for speech feature extraction. Three machine learning models were constructed: the Random Forest (RF) and Support Vector Machine (SVM) models utilised speech classification features optimised via the Sequential Forward Selection (SFS) algorithm, while the Extreme Gradient Boosting (XGBoost) model was trained on preprocessed speech data. After parameter tuning, the Librosa library successfully extracted 41 speech classification features from all participants. The application of the SFS optimisation strategy and the use of preprocessed data significantly improved identification accuracy. The SVM model achieved an accuracy of 0.825 (AUC: 0.91), the RF model reached 0.88 (AUC: 0.86), and the XGBoost model attained 0.92 (AUC: 0.91). These results suggest that speech-based machine learning models markedly improve the accuracy of distinguishing MCI patients from healthy older adults, providing reliable support for early cognitive deficit identification. Full article

This study investigates the design of bio-hybrid sandwich composites by combining polyester/glass skins with cores reinforced by continuous Musa paradisiaca fibres. The aim is to quantify how fibre weight fraction and alkaline surface treatment control the Charpy impact performance of these systems. Sandwich laminates were manufactured with three fibre loadings in the core (20, 25 and 30 wt.%), using fibres in the as-received condition and after alkaline treatment in NaOH solution. Charpy impact specimens were machined from the laminates and tested according to ISO 179-1. Fibre morphology and fracture surfaces were examined by scanning electron microscopy, while Fourier-transform infrared spectroscopy was used to monitor changes in surface chemistry after alkaline treatment. The combined effect of fibre content and treatment on absorbed energy was assessed through a two-way analysis of variance. Increasing Musa paradisiaca fibre content up to 30 wt.% enhanced the impact energy of the sandwich composites, and alkaline treatment further improved performance by strengthening fibre–matrix adhesion and promoting fibre pull-out, crack deflection and bridging mechanisms. The best Charpy impact response was obtained for cores containing 30 wt.% NaOH-treated fibres, demonstrating that surface modification and optimised fibre loading are effective design parameters for toughening polyester/glass bio-hybrid sandwich composites. Full article

The Internet of Military Things (IoMT) relies on Long-Range Wide Area Networks (LoRaWAN) for low-power, long-range communication in critical applications like border security and soldier health monitoring. However, conventional priority-based flow control mechanisms, which rely on static classification thresholds, lack the adaptability to handle the nuanced, continuous nature of physiological data and dynamic network states. To overcome this rigidity, this paper introduces a novel, domain-adaptive Fuzzy Logic Flow Control (FFC) protocol specifically tailored for LoRaWAN-based IoMT. While employing established Mamdani inference, the FFC system innovatively fuses multi-parameter physiological data (body temperature, blood pressure, oxygen saturation, and heart rate) into a continuous Health Score, which is then mapped via a context-optimised sigmoid function to dynamic transmission intervals. This represents a novel application-layer semantic integration with LoRaWAN’s constrained MAC and PHY layers, enabling cross-layer flow optimisation without protocol modification. Simulation results confirm that FFC significantly enhances reliability and energy efficiency while reducing latency relative to traditional static priority architectures. Seamlessly integrated into the NS-3 LoRaWAN simulation framework, the FFC protocol demonstrates superior performance in IoMT communications. Simulation results confirm that FFC significantly enhances reliability and energy efficiency while reducing latency compared with traditional static priority-based architectures. It achieves this by prioritising high-priority health telemetry, proactively mitigating network congestion, and optimising energy utilisation, thereby offering a robust solution for emergent, health-critical scenarios in resource-constrained environments. Full article

Fermentation is a complex biochemical process that transforms brewer’s wort into beer. Beer fermentation is driven by yeast and is influenced by process parameters such as the content of fermentable sugars in wort, temperature, and pH. Traditional methods of modelling this process rely heavily on empirically tuned kinetic models. However, these models tend to be recipe-specific and often require retuning when processes change. This paper proposes a data-driven approach using a Long Short-Term Memory (LSTM) network, a type of recurrent neural network, to model beer fermentation dynamics. By training the LSTM model on real-world fermentation data (1305 fermentations across ales, IPAs, lagers, and mixed-culture beers), including variables such as apparent extract (derived from specific gravity), temperature, and pH, we demonstrate that this technique can accurately predict key fermentation trajectories and support process monitoring and optimisation. When evaluated on representative medoid fermentations as one-step-ahead roll-outs over 0–300 h, the model produces accurate predictions with low errors and minimal residuals. These results show that the LSTM-based model provides accurate and robust predictions across beer styles and operating conditions, offering a practical alternative to traditional mechanistic kinetic models. This work highlights the potential of LSTM networks to enhance our understanding, monitoring, and control of fermentation processes, providing a scalable and efficient tool for both research and industrial applications. The findings suggest that LSTM models can be effectively adapted to model other fermentation processes in beverage production, opening new possibilities for advancing food science and engineering. Full article

In deep-sea mining operations, the seabed sediments (mud and sand) are very soft and slippery. This often causes tracked vehicles to slip and veer off course when they are driving on the seafloor. To solve the path-tracking problem for deep-sea mining vehicles, this study suggests a path-tracking controller that can adapt to the seabed environment. Firstly, it is necessary to establish a kinematic and dynamic model of the mining vehicle’s motion, analysing its seabed slippage and force application. The system has been developed on the basis of the Stanley algorithm and utilises a two-degree-of-freedom kinematic model, with lateral deviation and heading deviation acting as inputs. The establishment of fuzzy rules to adjust the gain parameter K enables the mining vehicle to adaptively modify its gain parameters according to the seabed environment and path. Secondly, a fuzzy PID controller is established and optimised to address the limitation that fuzzy PID control rules are constrained by the designer’s experience. At the same time, a relationship was established between how fast the drive wheel accelerates and the slip rate based on the dynamic model. This stops the drive wheel from slipping by limiting how fast it can go. Finally, a mechanical model of the mining vehicle was created in Recurdyn and a system model was developed in MATLAB/Simulink for joint simulation analysis. The simulation results demonstrate the efficacy of the proposed control strategy, establishing it as a reliable method for tracking the path of subsea mining vehicles. Full article

Background: Tuberculosis (TB) is a significant global health issue, particularly in resource-limited regions where radiological expertise is constrained. This project aims to develop a scalable deep learning system that safeguards privacy and achieves high accuracy in the early identification of tuberculosis using chest X-ray images. The objective is to implement federated learning with an adaptive-weighted ensemble optimised by a Genetic Algorithm (GA) to address the challenges of centralised training and single-model approaches. Method: We developed an ensemble learning method that combines multiple locally trained models to improve diagnostic consistency and reduce individual-model bias. An optimisation system that autonomously selected the optimal ensemble weights determined each model’s contribution to the final decision. A controlled augmentation process was employed to enhance the model’s robustness and reduce the likelihood of overfitting by introducing realistic alterations to appearance, geometry, and acquisition conditions. Federated learning facilitated collaboration among universities for training while ensuring data privacy was maintained during the establishment of the optimal ensemble at each location. In this system, just model parameters were transmitted, excluding patient photographs. This enabled the secure amalgamation of global data without revealing sensitive clinical information. Standard diagnostic metrics, including accuracy, sensitivity, precision, F1 score, AUC, and confusion matrices, were employed to evaluate the model’s performance. Results: The proposed federated, GA-optimized ensemble demonstrated superior performance compared with individual models and fixed-weight ensembles. The system achieved 98% accuracy, 97% F1 score, and 0.999 AUC, indicating highly reliable discrimination between TB-positive and typical cases. Federated learning preserved model robustness across heterogeneous data sources, while ensuring complete patient privacy. Conclusions: The proposed federated, GA-optimized ensemble achieves highly accurate and robust early tuberculosis detection while preserving patient privacy across distributed clinical sites. This scalable framework demonstrates strong potential for reliable AI-assisted TB screening in resource-limited healthcare settings. Full article

Background: A patient’s lung condition can be estimated using mechanical ventilation waveform data. These procedures are often labour-intensive and error-prone, especially during large-scale health crises, leading to infrequent executions. Automated diagnostic techniques in healthcare are currently limited by the lack of large, labelled datasets required for effective machine learning applications. Analytical modelling of the mechanical ventilator-patient (MV-P) system is complex, and existing models fail to fully integrate adjustable parameters for patient, ventilation, and disease conditions. Methods: This article presents an expanded system model developed in MATLAB^® Simulink^®. The model accommodates adjustments to anthropometric parameters, ventilator settings for the three most common modes in ICU sedation, and disease progression simulations. Other uniquely combined aspects include the ability to perform an end-inspiratory hold manoeuvre and per-breath optimisation of PI control parameters. Results: The system has been validated against clinical techniques, compared to real-world data, and verified with accuracy within 3% and average normalised standard deviation of 3.4% for all adjustable parameters. Conclusions: Based on this model, which introduces high-fidelity disease progression modelling, a fully labelled synthetic dataset of nearly 2M breaths over a range of health conditions was generated. This addresses the critical shortage of labelled data needed for developing early proof-of-concept, resource-efficient diagnostic tools for automatically estimating lung conditions. Full article

Background/Objectives: Combat trauma involving large joints is associated with a high risk of thromboinflammatory complications. Early identification of laboratory markers for hypercoagulability is essential to optimise perioperative management. This study aimed to evaluate the dynamics of inflammation and haemostasis indicators in patients with combat-related joint trauma and to identify the most informative markers for preoperative risk assessment. Methods: A total of 29 patients with combat injuries to the hip, knee, elbow, or ankle joints were examined. Blood samples were taken 1–3 days prior to surgery and again on the first postoperative day. Parameters of coagulation (e.g., PT, INR, fibrinogen, D-dimer, soluble fibrin complexes, antithrombin III), fibrinolysis, and inflammation (e.g., CRP, haptoglobin, sialic acid, ESR, LSI, LII) were analysed and compared to those of 30 healthy controls. Statistical analysis included Student’s t-test and Pearson’s correlation. Results: At baseline, patients demonstrated significant increases in inflammatory markers (CRP 64.2 ± 7.3 mg/L, ↑738.9%; haptoglobin 3.25 ± 0.4 g/L, ↑164.3%; ESR 46.8 ± 5.2 mm/h, ↑313.8%) and procoagulant activity (D-dimer 1.42 ± 0.18 µg/mL, ↑136.6%; fibrinogen 6.12 ± 0.51 g/L, ↑102.4%; soluble fibrin complexes 38.7 ± 4.9 mg/L, ↑597.3%), together with a reduction in antithrombin III activity (63.5 ± 6.2%, ↓39.5%) and prolonged fibrinolysis time (increase by 197%). Postoperatively, these abnormalities intensified, indicating a sustained thromboinflammatory response. Strong correlations were found between inflammatory and haemostatic markers. Conclusions: Combat trauma of large joints is associated with preoperative thromboinflammatory dysregulation, which is exacerbated by surgery. Monitoring specific biochemical and haematological markers—such as CRP, fibrinogen, D-dimer, and soluble fibrin complexes—may support preoperative risk assessment and postoperative monitoring strategies for hypercoagulable states in this high-risk group. These findings lay the groundwork for future prospective studies aimed at developing stratified therapeutic protocols and predictive models for thromboinflammatory complications in orthopaedic trauma care. Full article

Deep and ultra-deep drilling operations commonly encounter fractured and fracture-vuggy formations, where weak wellbore strength and well-developed fracture networks lead to frequent lost circulation, presenting a key challenge to safe and efficient drilling. Existing diagnostic practices mostly rely on drilling fluid loss dynamic models of single fractures or simplified discrete fractures to invert fracture geometry, which cannot capture the spatiotemporal evolution of loss in complex fracture networks, resulting in limited inversion accuracy and a lack of quantitative, fracture-network-based loss-dynamics support for bridge-plugging design. In this study, a geologically realistic wellbore–fracture-network coupled loss dynamic model is constructed to overcome the limitations of single- or simplified-fracture descriptions. Within a unified computational fluid dynamics (CFD) framework, solid–liquid two-phase flow and Herschel–Bulkley rheology are incorporated to quantitatively characterise fracture connectivity. This approach reveals how instantaneous and steady losses are controlled by key geometrical factors, thereby providing a computable physical basis for loss-zone inversion and bridge-plugging design. Validation against experiments shows a maximum relative error of 7.26% in pressure and loss rate, indicating that the model can reasonably reproduce actual loss behaviour. Different encounter positions and node types lead to systematic variations in loss intensity and flow partitioning. Compared with a single fracture, a fracture network significantly amplifies loss intensity through branch-induced capacity enhancement, superposition of shortest paths, and shortening of loss paths. In a typical network, the shortest path accounts for only about 20% of the total length, but contributes 40–55% of the total loss, while extending branch length from 300 mm to 1500 mm reduces the steady loss rate by 40–60%. Correlation analysis shows that the instantaneous loss rate is mainly controlled by the maximum width and height of fractures connected to the wellbore, whereas the steady loss rate has a correlation coefficient of about 0.7 with minimum width and effective path length, and decreases monotonically with the number of connected fractures under a fixed total width, indicating that the shortest path and bottleneck width are the key geometrical factors governing long-term loss in complex fracture networks. This work refines the understanding of fractured-loss dynamics and proposes the concept of coupling hydraulic deviation codes with deep learning to build a mapping model from mud-logging curves to fracture geometrical parameters, thereby providing support for lost-circulation diagnosis and bridge-plugging optimisation in complex fractured formations. Full article

Developing effective CAR-T cell therapy for solid tumours remains challenging because of biological barriers such as antigen escape and an immunosuppressive microenvironment. The aim of this study is to develop a mathematical model of the spatio-temporal dynamics of tumour processes in order to assess key factors that limit treatment efficacy. We propose a reaction–diffusion model described by a system of partial differential equations for the densities of tumour cells and CAR-T cells, the concentration of immune inhibitors, and the degree of antigen escape. The methods of investigation include stability analysis and numerical solution of the model using a finite-difference scheme. The simulations show that antigen escape produces a resistant tumour core and relapse after an initial regression; increasing the escape rate from $\gamma =0.001$ to $0.1$ increases the final tumour volume at $t=100$ days from approximately 35.3 a.u. to 36.2 a.u. Parameter mapping further indicates that for $\gamma \le 0.01$ tumour control can be achieved at moderate killing rates ($k_{CT}\approx 1{\mathrm{day}}^{-1}$), whereas for $\gamma \ge 0.05$ comparable control requires $k_{CT}\approx 2$–$5{\mathrm{day}}^{-1}$. Repeated CAR-T administration improves durability: the residual normalised tumour volume at $t=100$ days decreases from approximately 4.5 after a single infusion to approximately 0.9 (double) and approximately 0.5 (triple), with a saturating benefit for further intensification. We conclude that the proposed model is a valuable tool for analysing and optimising CAR-T therapy protocols, and that our results highlight the need for combined strategies aimed at overcoming antigen escape. Full article

This study presents a frequency-domain analysis of a finite-element (FEM)-based rotor–nacelle model for wind turbines, validated against the open-source time-domain tool OpenFAST. The analysis was carried out using METHOD, an in-house computational framework implemented in Python. While time-domain models remain standard for nonlinear aeroelastic simulations, frequency-domain approaches offer advantages in early-stage design, control development, and system identification due to their efficiency, transparency, and suitability for parametric studies. The FEM model includes flexible blades, hub, and nacelle dynamics and includes tower and fixed or floating platform components with rotor–tower frequency interactions. In this work, a fixed tower is considered to isolate rotor behaviour. Beam-element formulation enables the computation of natural frequencies, mode shapes, and frequency response functions, and an equivalent rotor model is implemented in OpenFAST for consistent benchmarking. Validation results show close correspondence between the two modelling approaches. Key operational parameters agree within 3%, while structural responses, including flap-wise deflection, bending moments, and resultant quantities, typically fall within an overall accuracy range of 5–15%, consistent with expected differences arising from reference-frame conventions and modelling assumptions. Discrepancies are discussed in terms of numerical damping, model assumptions (differences in the axis system), and the influence of structural simplifications. Overall, the FEM model captures the dominant dynamic behaviour with satisfactory accuracy and a consistent orientation of global response. Computational efficiency results further highlight the advantages of the METHOD framework. Wind-field generation is completed roughly an order of magnitude faster, and long-duration aeroelastic simulations achieve substantial speed-ups, reaching more than one order of magnitude for multi-hour cases, demonstrating strong scalability relative to OpenFAST. Overall, the results confirm that a well-constructed yet still simplified frequency-domain FEM rotor model can provide a robust and computationally efficient alternative to conventional time-domain solvers. Moreover, the computational performance presented here represents a lower bound, as further improvements are readily achievable through parallelisation and solver-level optimisation. Future papers will present the full-system aero-hydro-elastic coupling for fixed and floating offshore wind turbine applications. Full article

Surface functionalisation of polymers is essential for enhancing properties such as wettability and mechanical resistance. This study presents a scalable, coating-free approach to fabricate hydrophobic and superhydrophobic Polydimethylsiloxane (PDMS) surfaces. Aluminium (AA2024) moulds were microstructured using a TruMicro femtosecond laser system to generate grid patterns with controlled hatch distances and depths, as well as laser-induced periodic surface structures (LIPSSs). These features were accurately replicated onto PDMS, as confirmed by scanning electron miscoscopy (SEM) and profilometry. Contact angle measurements showed a marked increase in hydrophobicity, reaching superhydrophobicity for optimised parameters, with surface stability maintained over four months without degradation. Full article

The Trepponti bridge in Comacchio (Italy) is a significant masonry landmark characterised by a complex geometry. Its structure comprises five irregularly connected segments, creating pronounced geometric discontinuities. Accurately modelling this configuration is challenging due to the highly complex mechanical behaviour of masonry. This study presents a robust computational strategy for the nonlinear structural assessment of such heritage bridges. The methodology integrates a parametric meshing environment (PoliBrick plugin) with nonlinear finite-element analysis in Straus7. An initial discretisation is generated through PoliBrick, undergoes geometric optimisation to produce an analysis-ready model. The bridge is homogeneously modelled and meshed through macro-blocks obeying a Mohr–Coulomb failure criterion. Material parameters are defined according to the LC1 knowledge level stipulated by the Italian structural code. Differential settlement scenarios are simulated by imposing controlled vertical displacements on individual and paired piers. This approach enables evaluation of structural displacement, stress distribution, and crack propagation. The analyses reveal a markedly asymmetric structural response, identifying two specific piers as critical vulnerable elements. The proposed framework demonstrates that parametric meshing effectively reconciles accurate geometric representation with computational efficiency. It offers a practical tool for guiding the conservation and safety evaluation of irregular vaulted masonry bridges. Full article

The preferential concentration of metals into finer size fractions (<19 mm) during breakage can be exploited for early rejection of low-grade material, reducing non-ore processing and improving energy and water efficiency. The Cooperative Research Centre for Optimising Resource Extraction (CRC ORE) established a testing regime and developed the Response Ranking (RR) factor to compare fractionation behavior across deposits. RR values range from 200 to negative, with higher values indicating breakage patterns favorable for ore liberation. This study evaluates geological parameters controlling rock breakage in the Gramalote and Telfer West Dome deposits, both intrusion-related gold systems. For this purpose, macroscopic description of drill core was carried out using the Anaconda methodology, along with uncrushed run-of-mine (ROM) samples. In addition, petrophysical datasets including hardness, magnetic susceptibility, hyperspectral data, geochemistry, and calculated mineralogy were used. These datasets were systematically compared with RR values to investigate the relationship between geological attributes and grade-by-size fractionation behavior. Geological description provides a practical basis to identify early separation opportunities and model optimization potential through grade-by-size fractionation. Full article

Humanoid robots have gained public awareness and intrigue over the last few years. During this time, there has been a greater push to develop robots to behave more like humans, not just in how they speak but also in how they move. A novel humanoid robotic head-and-neck platform designed to facilitate the investigation of movement characteristics is proposed. The research presented here aims to characterise the motion of a humanoid robotic head, Aquila, to aid the development of humanoid robots with head movements more similar to those of humans. This platform also aims to promote further studies in human head motion. This paper proposes a design for a humanoid robotic head platform capable of performing three principal human motion patterns: yaw, pitch, and roll. Using the Arduino IDE (2.3.2) and MATLAB/Simulink (2024b), all three types of movement were implemented and tested with various parameters. Each type of movement is quantified in terms of range, stability, and dynamic response using time-series data collected over 35 s of continuous observation. The results demonstrate that a humanoid robot head can mimic the range of displacement of a healthy human subject but does not exhibit the same smoothness and micro-adjustments observed in dynamic human head movements. An RMSE of under 0.3 rad is achieved for each motion axis—pitch, roll, and yaw—when comparing robotic head movement to human head movement. The investigation of preliminary results highlights the need for further system optimisation. This paper’s conclusion highlights that the bio-inspired control concept, paired with the proposed 8-stepper motor platform, enhances realism and interaction in the context of head movement in robotic systems. Full article