Search Results (6,612)

This work presents the development of a web system using deep learning (DL) neural networks to solve the inverse kinematics problem of the Quetzal robotic arm, designed for academic and research purposes. Two architectures, LSTM and CNN, were designed, trained, and evaluated using data generated through the Denavit–Hartenberg (D-H) model, considering the robot’s workspace. The evaluation employed the mean squared error (MSE) as the loss metric and mean absolute error (MAE) and accuracy as performance metrics. The CNN model, featuring four convolutional layers and an input of 4 timesteps, achieved the best overall performance (95.9% accuracy, MSE of 0.003, and MAE of 0.040), significantly outperforming the LSTM model in training time. A hybrid web application was implemented, allowing offline training and real-time online inference under one second via an interactive interface developed with Streamlit 1.16. The solution integrates tools such as TensorFlow™ 2.15, Python 3.10, and Anaconda Distribution 2023.03-1, ensuring portability to fog or cloud computing environments. The proposed system stands out for its fast response times (1 s), low computational cost, and high scalability to collaborative robotics environments. It is a viable alternative for applications in educational or research settings, particularly in projects focused on industrial automation. Full article

As a high-frequency and essential type of special electromechanical equipment, a vertical elevator has a significant societal implication for their safe operation. The load-weighing module, serving as the core component for overload warning, is susceptible to precision degradation due to the nonlinear deformation of rubber buffers installed at the base of the elevator car. This deformation arises from the coupled effects of environmental factors such as temperature, humidity, and material aging, leading to potential safety risks including missed overload alarms and false empty status detections. To address the issue of accuracy deterioration in elevator load-weighing systems, this study proposes an online self-calibration method based on multimodal information fusion. A reference detection model is first constructed to map the relationship between applied load and the corresponding relative compression of the rubber buffers. Subsequently, displacement data from a draw-wire sensor are integrated with target detection model outputs, enabling real-time extraction of dynamic rubber buffers’ deformation characteristics under empty conditions. Based on the above, a displacement-based compensation term is derived to enhance the accuracy of load estimation. This is further supported by a dynamic error compensation mechanism and an online computation framework, allowing the system to self-calibrate without manual intervention. The proposed approach eliminates the dependency on manual tuning inherent in traditional methods and forms a highly robust solution for load monitoring. Field experiments demonstrate the effectiveness of the proposed method and the stability of the prototype system. The results confirm that the synergistic integration of multimodal perception and adaptive calibration technologies effectively resolves the challenge of load-weighing precision degradation under complex operating conditions, offering a novel technical paradigm for elevator safety monitoring. Full article

Accurate and non-invasive assessment of fat and muscle composition is crucial for biomedical monitoring to track health conditions in humans and pets, as well as for classifying meats in the meat industry. This study introduces a cost-effective, multifunctional ultra-wideband microwave system operating from 2.4 to 4.4 GHz, designed for rapid and non-destructive quantification of fat thickness, muscle thickness, and fat-to-muscle ratio in diverse ex vivo samples, including pork, beef, and oil–water mixtures. The compact handheld device integrates essential RF components such as a frequency synthesizer, directional coupler, logarithmic power detector, and a dual-polarized Vivaldi antenna. Bluetooth telemetry enables seamless real-time data transmission to mobile- or PC-based platforms, with each measurement completed in a few seconds. To enhance signal quality, a two-stage denoising pipeline combining low-pass filtering and Savitzky–Golay smoothing was applied, effectively suppressing noise while preserving key spectral features. Using a random forest regression model trained on resonance frequency and signal-loss features, the system demonstrates high predictive performance even under limited sample conditions. Correlation coefficients for fat thickness, muscle thickness, and fat-to-muscle ratio consistently exceeded 0.90 across all sample types, while mean absolute errors remained below 3.5 mm. The highest prediction accuracy was achieved in homogeneous oil–water samples, whereas biologically complex tissues like pork and beef introduced greater variability, particularly in muscle-related measurements. The proposed microwave system is highlighted as a highly portable and time-efficient solution, with measurements completed within seconds. Its low cost, ability to analyze multiple tissue types using a single device, and non-invasive nature without the need for sample pre-treatment or anesthesia make it well suited for applications in agri-food quality control, point-of-care diagnostics, and broader biomedical fields. Full article

Global navigation satellite systems (GNSS) can provide high-quality location information in outdoor environments. In indoor environments, GNSS cannot achieve accurate and stable location information due to the obstruction and attenuation of buildings together with the influence of multipath effects. Due to the rapid development of micro-electro-mechanical system (MEMS) sensors, today’s smartphones are equipped with various low-cost and small-volume MEMS sensors. Therefore, it is of great significance to study indoor pedestrian positioning technology based on smartphones. In order to provide pedestrians with high-precision and reliable location information in indoor environments, we propose a pedestrian dead reckoning (PDR) method based on Transformer+TCN (temporal convolutional network). Firstly, we use IMU (inertial measurement unit)/PDR pre-integration to suppress the inertial navigation divergence. Secondly, we propose a step length estimation algorithm based on Transformer+TCN. The Transformer and TCN networks are superimposed to improve the ability to capture complex dependencies and improve the generalization and reliability of step length estimation. Finally, we propose factor graph optimization (FGO) models based on sliding windows (SW-FGO) to provide accurate posture, which use accelerometer (ACC)/gyroscope/magnetometer (MAG) data to establish factors. We designed a fusion positioning estimation test and a comparison test on step length estimation algorithm. The results show that the fusion method based on SW-FGO proposed by us improves the positioning accuracy by 29.68% compared with the traditional FGO algorithm, and the absolute position error of the step length estimation algorithm based on Transformer+TCN in pocket mode is mitigated by 42.15% compared with the LSTM algorithm. The step length estimation model error of Transformer+TCN is 1.61%, and the step length estimation accuracy is improved by 24.41%. Full article

Background: Whole-slide images (WSIs) are crucial in pathology for digitizing tissue slides, enabling pathologists and AI models to analyze cancer patterns at gigapixel scale. However, their large size incorporates artifacts and non-tissue regions that slow AI processing, consume resources, and introduce errors like false positives. Tissue detection serves as the essential first step in WSI pipelines to focus on relevant areas, but deep learning detection methods require extensive manual annotations. Methods: This study benchmarks four thumbnail-level tissue detection methods—Otsu’s thresholding, K-Means clustering, our novel annotation-free Double-Pass hybrid, and GrandQC’s UNet++ on 3322 TCGA WSIs from nine cancer cohorts, evaluating accuracy, speed, and efficiency. Results: Double-Pass achieved an mIoU of 0.826—very close to the deep learning GrandQC model’s 0.871—while processing slides on a CPU in just 0.203s per slide, markedly faster than GrandQC’s 2.431s per slide on the same hardware. As an annotation-free, CPU-optimized method, it therefore enables efficient, scalable thumbnail-level tissue detection on standard workstations. Conclusions: The scalable, annotation-free Double-Pass pipeline reduces computational bottlenecks and facilitates high-throughput WSI preprocessing, enabling faster and more cost-effective integration of AI into clinical pathology and research workflows. Comparing Double-Pass against established methods, this benchmark demonstrates its novelty as a fast, robust and annotation-free alternative to supervised methods. Full article

Explosion-proof safety evaluation is critical for coal mine equipment operating in hazardous environments. Traditional methods rely on physical explosion testing, which is time-consuming, costly, and impractical for large-scale or complex systems. We propose a real-time virtual measurement method based on an improved combined surrogate model to address these limitations. A digital twin framework is constructed by integrating internal explosion transmission data with physical models of gas deflagration and enclosure impact mechanics. A transient multi-physical reduced-order model is developed using Latin hypercube sampling and machine learning. The core prediction model, RBF-GMSE, combines a radial basis function surrogate model and a generalized mean square error model through adaptive weighting. This model is trained on dimension-reduced finite element data and used to predict explosion-induced stress, strain, and displacement in real time. A virtual measurement system is implemented using this framework, enabling accurate, dynamic safety evaluation of explosion-proof equipment. Validation against simulation data shows a maximum prediction error below 1.89% and an average correlation coefficient of 0.9779, confirming the model’s high accuracy and robustness. This approach offers an intelligent solution for efficient and precise acquisition of explosion-proof safety characteristics in coal mine equipment. Full article

Necrotizing fasciitis (NF) is a rare but aggressive soft tissue infection with high rates of mortality and amputation, making early identification of key prognostic biomarkers essential for clinical management. However, the rarity and heterogeneity of NF mean clinical datasets are often small and non-normally distributed, limiting the effectiveness of standard parametric statistical approaches. To address this, we retrospectively analyzed 66 NF patients using a robust, distribution-free framework that combines the Nonparametric Combination (NPC) methodology and bootstrap resampling. We specifically assessed glycated hemoglobin (HBA1C) and serum albumin (ALBUMINA) as potential predictors of two outcomes: mortality (MORTO) and major amputation (AMPUTAZIONE). NPC enabled exact multivariate hypothesis testing while rigorously controlling the family-wise error rate (FWER), and bootstrap resampling generated 95% confidence intervals (CI) for critical biomarkers. HBA1C was an exceptionally significant predictor compared to the 7.0% clinical threshold (p = 1.04 × 10⁻¹⁵⁴, CI: 0.0830–0.0957), while ALBUMINA showed greater biological variability but no significant association with outcomes (2.8 g/dL; p = 0.267, CI: 2.551–2.866). We also developed a global severity ranking, integrating multiple variables to improve clinical risk stratification. Our results demonstrate that permutation-based and resampling methods provide reliable, actionable insights from challenging small-sample clinical datasets. Based on a small-sample dataset from necrotizing fasciitis patients, this framework provides a replicable model for robust, nonparametric statistical analysis in similarly rare and high-risk medical conditions. This study introduces a Nonparametric Combination (NPC) framework for risk scoring in necrotizing fasciitis using bootstrap resampling and permutation tests. Key predictors like HBA1C and Albumin were assessed, achieving an AUC of 0.89 and a Youden Index of 0.71. The model offers a robust, interpretable tool for clinical risk stratification in small-sample rare disease settings. Full article

We present a comparative analysis of three hybrid methodologies for transforming 3D kidney tumor segmentations of volumetric NIfTI data into highly accurate network representations. Exploiting the KiTS23 dataset, we evaluate edge-preserving reconstruction pipelines integrating anisotropic diffusion, multiscale Gaussian filtering and KNN-based network optimisation. Model 1 uses Gaussian smoothing with Marching Cubes, while Model 2 uses spline interpolation and Perona-Malik filtering for improved resolution. Model 3 extends this structure with normal sensitive vertex smoothing to preserve critical anatomical interfaces. Quantitative metrics (Dice score, HD₉₅) demonstrated the advantage of Model 3, which achieved a 22% reduction in the Hausdorff distance error rate compared to conventional methods while maintaining segmentation accuracy (Dice > 0.92). The proposed unsupervised pipeline bridges the gap between clinical interpretability and computational accuracy, providing a robust infrastructure for further applications in surgical planning and deep learning-based classification. Full article

Tool structure design methodologies predominantly rely on trial-and-error approaches or single-objective optimization but fail to achieve coordinated enhancement of multiple performance metrics while lacking thorough investigation into complex cutting coupling mechanisms. This study proposes a multi-objective optimization framework integrating joint simulation approaches. First, a finite element model for orthogonal turning was developed, incorporating the hyperbolic tangent (TANH) constitutive model and variable coefficient friction model. The cutting performance of four micro-groove configurations is comparatively analyzed. Subsequently, parametric modeling coupled with simulation–data interaction enables multi-objective optimization targeting minimized cutting force, reduced cutting temperature, and decreased wear rate. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) explores Pareto-optimized solutions for arc micro-groove geometric parameters. Finally, optimized tools manufactured via powder metallurgy undergo experimental validation. The results demonstrate that the optimized tool achieves significant improvements: a 19.3% reduction in cutting force, a 14.2% decrease in cutting temperature, and tool life extended by 33.3% compared to baseline tools. Enhanced chip control is evidenced by an 11.4% reduction in chip curl radius, accompanied by diminished oxidation/adhesive wear and superior surface finish. This multi-objective optimization methodology effectively overcomes the constraints of conventional single-parameter optimization, substantially improving comprehensive tool performance while establishing a reference paradigm for cutting tool design under complex operational conditions. Full article

A Universal Numerical Integrator (UNI) is a computational framework that combines a classical numerical integration method, such as Euler, Runge–Kutta, or Adams–Bashforth, with a universal approximator of functions, such as a feed-forward neural network (including MLP, SVM, RBF, among others) or a fuzzy inference system. The Euler-Type Universal Numerical Integrator (E–TUNI) is a particular case of UNI based on the first-order Euler integrator and is designed to model non-linear dynamic systems observed in real-world scenarios accurately. The UNI framework can be organized into three primary methodologies: the NARMAX model (Non-linear AutoRegressive Moving Average with eXogenous input), the mean derivatives approach (which characterizes E–TUNI), and the instantaneous derivatives approach. The E–TUNI methodology relies exclusively on mean derivative functions, distinguishing it from techniques that employ instantaneous derivatives. Although it is based on a first-order scheme, the E–TUNI achieves an accuracy level comparable to that of higher-order integrators. This performance is made possible by the incorporation of a neural network acting as a universal approximator, which significantly reduces the approximation error. This article provides a comprehensive overview of the E–TUNI methodology, focusing on its application to the modeling of non-linear autonomous dynamic systems and its use in predictive control. Several computational experiments are presented to illustrate and validate the effectiveness of the proposed method. Full article

Local variations in mechanical properties are commonly observed in engineering structures, driven by complex manufacturing histories and harsh service environments. The evaluation of mechanical properties accurately constitutes a fundamental requirement for structural integrity assessment. The Instrumented Indentation Technique (IIT) can play a critical role in the in-site testing of local properties. However, it could be often a challenge to correlate indentation characteristics with uniaxial stress–strain relationships. In this study, we investigated quantitatively the connection between the indentation responses of commonly used metals and their plastic properties using the finite element inversion method. Materials typically exhibit plastic deformation mechanisms characterized by either linear or power-law hardening behaviors. Consequently, conventional prediction methods based on a single constitutive model may no longer be universally applicable. Hence, this study developed methods for acquiring mechanical properties suitable for either the power-law and linear hardening model, or combined, respectively, based on analyses of microstructures of materials exhibiting different hardening behaviors. We proposed a novel integrated IIT incorporating microstructures and material-specific constitutive models. Moreover, the inter-dependency between microstructural evolution and hardening behaviors was systematically investigated. The proposed method was validated on representative engineering steels, including austenitic stainless steel, structural steel, and low-alloy steel. The predicted deviations in yield strength and strain hardening exponent are broadly within 10%, with the maximum error at 12%. This study is expected to provide a fundamental framework for the advancement of IIT and structural integrity assessment. Full article

Chronic respiratory diseases claim nearly four million lives annually, making them the third leading cause of death worldwide. Extracorporeal membrane oxygenation (ECMO) is often the last line of support for patients with severe lung failure. Still, its performance is limited by an incomplete understanding of gas exchange in hollow fiber membrane (HFM) oxygenators. Computational fluid dynamics (CFD) has become a robust oxygenator design and optimization tool. However, most models oversimplify O₂ and CO₂ transport by ignoring their physiological coupling, instead relying on fixed saturation curves or constant-content assumptions. For the first time, this study introduces a novel physiologically informed CFD model that integrates the Bohr and Haldane effects to capture the coupled transport of oxygen and carbon dioxide as functions of local pH, temperature, and gas partial pressures. The model is validated against in vitro experimental data from the literature and assessed against established CFD models. The proposed CFD model achieved excellent agreement with experiments across blood flow rates (100–500 $\mathrm{mL}/\min$ ), with relative errors below 5% for oxygen and 10–15% for carbon dioxide transfer. These results surpassed the accuracy of all existing CFD approaches, demonstrating that a carefully formulated single-phase model combined with physiologically informed diffusivities can outperform more complex multiphase simulations. This work provides a computationally efficient and physiologically realistic framework for oxygenator optimization, potentially accelerating device development, reducing reliance on costly in vitro testing, and enabling patient-specific simulations. Full article

The integration of artificial intelligence (AI) and machine learning (ML) technologies in energy storage systems has emerged as a transformative approach in addressing the complex challenges of modern energy infrastructure. This comprehensive review examines current state of the art AI applications in energy storage, from battery management systems to grid-scale storage optimization. We analyze various AI techniques, including supervised learning, deep learning, reinforcement learning, and neural networks, and their applications in state estimation, predictive maintenance, energy forecasting, and system optimization. The review synthesizes findings from the recent literature demonstrating quantitative improvements achieved through AI integration: distributed reinforcement learning frameworks reducing grid disruptions by 40% and operational costs by 12.2%, LSTM models achieving state of charge estimations with a mean absolute error of 0.10, multi-objective optimization reducing power losses by up to 22.8% and voltage fluctuations by up to 71%, and real options analysis showing 45–81% cost reductions compared to conventional planning approaches. Despite remarkable progress, challenges remain in terms of data quality, model interpretability, and industrial implementation. This paper provides insights into emerging technologies and future research directions that will shape the evolution of intelligent energy storage systems. Full article

This paper presents the study of integrating a deep motion model into simple online and real-time tracking for video multi-object tracking. The tracking-by-detection paradigm faces significant challenges in handling nonlinear motion and occlusions. Although conventional Kalman-filter-based methods such as the SORT are efficient, they suffer from error accumulation because of their linear motion assumption. We propose KalmanFormer, a novel framework that enhances Kalman-filter-based tracking through adaptive motion modeling for video sequences. KalmanFormer consists of three key components. First, the inner-trajectory motion corrector, built upon the transformer architecture, refines Kalman filter predictions by learning nonlinear residuals from historical trajectories, thereby improving adaptability to complex motion patterns in videos. Second, the cross-trajectory attention module captures interobject motion correlations, significantly boosting object association under occlusions. Third, a pseudo-observation generator is integrated to provide neural-based predictions when detections are missing, stabilizing the Kalman filter update process. To validate our approach, we conduct comprehensive evaluations on the video benchmarks DanceTrack, MOT17, and MOT20 to demonstrate its effectiveness in handling complex motion and occlusion. The experimental results on the DanceTrack, MOT17, and MOT20 benchmarks demonstrate that KalmanFormer achieves competitive performance, with HOTA scores of 66.6 on MOT17 and 63.2 on MOT20, and strong identity preservation, IDF1: 82.0% and 80.1%, respectively. Full article

Rock mechanical parameters are essential to design, stability analysis, and safety construction in rock underground engineering. Inverse analysis is an effective tool for determining the mechanical properties of rock masses in deep underground engineering. Given that conventional methods cannot accurately solve such problems, proxy models are widely used. This study proposes a novel inverse analysis framework integrating the CatBoost algorithm and Simplicial Homology Global Optimization (SHGO) to overcome limitations of conventional methods. CatBoost efficiently constructs a proxy model, replacing time-consuming numerical simulations. SHGO then searches for optimal rock parameters using this proxy. The method was validated in the D2 laboratory of the second phase project of the Jinping Underground Laboratory (CJPL–II) in China and applied to invert surrounding rock parameters using field displacement monitoring data and numerical simulations. Investigations examined inversion accuracy under varying excavation steps, numbers of monitoring points, and wider parameter ranges. Results show inverted parameters converge towards true values as excavation steps and monitoring points increase. Crucially, even within the most extensive parameter range, relative errors between inversion results and true values remain below 20%. This integrated CatBoost–SHGO framework provides a feasible, scientific, and promising approach for determining rock mechanical parameters. Full article