Search Results (4,391)

Precise temperature control is crucial for maintaining product quality and optimizing energy efficiency in multi-zone continuous crystallizers. However, such industrial processes typically exhibit complex nonlinear dynamics and strong coupling effects. More critically, physical constraints often prevent sensor installation, rendering temperatures in key regions unobservable and challenging traditional closed-loop control strategies. To address partial observability and model uncertainty, this paper proposes a Model-Based Reinforcement Learning (MBRL) framework utilizing solely offline historical data. The core innovation lies in developing a Recursive State Space Model (RSSM) that serves not only as a high-fidelity digital twin but, more critically, is deployed as a real-time “virtual sensor” to infer unobservable system states. This virtual sensing capability provides precise state estimates for downstream policy optimization. Additionally, a multi-objective reward function is designed to balance tracking error, stability, and control cost. Experimental results demonstrate that the proposed virtual sensor exhibits exceptional long-term stability, maintaining high fidelity and effectively suppressing error accumulation during long-term multi-step autoregressive predictions. Consequently, the trained agent outperforms traditional Proportional-Integral-Derivative (PID) and Model Predictive Control (MPC) controllers, achieving over 67% improvement in temperature tracking accuracy while reducing control action costs by more than 93%, indicating smoother system operation and enhanced energy efficiency. Full article

Sentiment classification plays a crucial role in analyzing customer feedback to identify market trends, enhance product recommendations, and improve customer satisfaction. This study focuses on sentiment analysis of Amazon reviews using two major datasets—Fine Food Reviews and Unlocked Mobile Reviews—which exhibit label imbalance. To address this challenge, both oversampling and undersampling techniques were applied to balance the datasets. Various machine learning (ML) algorithms, including Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Naïve Bayes (NB), and Gradient Boosting Machine (GBM), as well as deep learning (DL) models such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and transformer-based models like RoBERTa, were implemented. After data cleaning and preprocessing, models were trained, and performance was evaluated. The results indicate that oversampling significantly enhances classification accuracy, particularly for the Fine Food dataset. Among ML models, Random Forest achieved the highest accuracy due to its ensemble approach and robustness in handling high-dimensional data. DL models, particularly RoBERTa, also demonstrated superior performance owing to their capacity to capture contextual dependencies. The findings emphasize the importance of data balancing for optimal sentiment analysis and contribute valuable insights toward advancing automated opinion classification in e-commerce applications. Full article

Aiming at the complex hybrid scenario where Low Earth Orbit (LEO) satellite communication systems simultaneously serve unmanned terminals and terrestrial mobile users, this study proposes a two-stage resource allocation strategy based on the Deep Deterministic Policy Gradient (DDPG) algorithm. The strategy is designed to tackle the problems of uneven traffic distribution and large discrepancies in users’ real-time requirements. First, load balancing is achieved by flexibly adjusting the mapping relationship between users and satellite beams. Then, the Time-Frequency Deep Deterministic Policy Gradient (TF-DDPG) deep reinforcement learning algorithm is adopted, through which the agent autonomously learns via training and dynamically allocates time-frequency resources within a short period, giving priority to guaranteeing the communication demands of unmanned terminals. Simulation results demonstrate that, compared with heuristic algorithms, the proposed strategy realizes millisecond-level response in resource allocation decisions and improves system resource utilization, with an average user satisfaction rate of 73.41%. This method effectively resolves the issue of satellite time-frequency resource allocation in complex hybrid scenarios and provides a practical solution for the efficient resource management of future LEO satellite internet systems. Full article

Predictive maintenance (PdM) and predictive quality monitoring (PQM) increasingly rely on data-driven condition monitoring using vibration and related signals. However, real-world deployment often faces domain drift across machines, operating regimes, and sensing conditions, while only a few labeled target samples are available. This combination of distribution shift and label scarcity creates a substantial deployment gap for models trained in a single setting. This paper proposes a physics-informed few-shot learning (PI-FSL) domain adaptation framework that is among the first to combine episodic metric learning with soft physics-consistency regularization to improve cross-domain generalization. The framework integrates CWT-based time–frequency encoding, relation-based episodic classification, physics-consistency constraints at representation and signal levels, and PSD-guided episodic sampling within a unified adaptation pipeline. We evaluated PI-FSL under explicit few-shot transfer scenarios on tool-wear and bearing-condition-monitoring datasets. On the Bosch benchmark, PI-FSL achieved an F1 = 0.960 (balanced accuracy = 0.961) for cross-machine transfer and an F1 = 0.907 (balanced accuracy = 0.901) under a combined machine-operation shift. A cross-dataset evaluation across tool-wear and multiple bearing-fault benchmarks under a unified two-way five-shot protocol further demonstrated a competitive and transferable performance. PI-FSL achieved the best average macro-F1 and a balanced accuracy, with the largest margin on PU bearing transfer (macro-F1, 0.663 vs. 0.590; balanced accuracy, 0.710 vs. 0.634). The ablation results showed that few-shot fine-tuning is the main contributor, while physics regularization provides an additional stabilizing gain under transfer. These findings support PI-FSL as a practical episodic framework for robust cross-domain condition monitoring across heterogeneous industrial datasets under realistic drift and limited labels. Full article

Due to hardware limitations of Thermal InfraRed (TIR) cameras, TIR images captured by Unmanned Aerial Vehicles (UAVs) suffer from Low Resolutions (LRs) and blurred textures. Improving the spatial resolution of TIR images is of great significance for subsequent applications. Existing image Super-Resolution (SR) methods rely on High-Resolution (HR) ground truth for supervised training, resulting in limited generalization and a lack of mechanisms to preserve the physical consistency of thermal radiation. To address these two issues, this paper proposes an unsupervised super-resolution framework for UAV TIR imagery that integrates diffusion modeling with cross-modal texture transfer. The diffusion model enables stable reconstruction of the fundamental TIR structure without requiring high-resolution supervision, while multi-scale textures extracted from visible (VIS) imagery via Multi-Stage Decomposition based on Latent Low-Rank Representation (MS-DLatLRR) compensate for missing details. To suppress temperature distortions introduced by cross-modal texture transfer, a physics-guided constraint termed Prior-Informed Emissivity-Guided Coefficient Mapping (PI-EGCM) is incorporated. Emissivity-aware guidance maps constructed via semantic classification regulate texture transfer and preserve thermal radiation consistency. Experimental results demonstrate that the proposed method improves spatial resolution and perceptual quality while effectively maintaining temperature fidelity, achieving a balanced enhancement of structural detail and physical consistency. Full article

Road safety depends heavily on the timely identification and repair of potholes; however, detecting potholes is challenging due to various lighting and weather conditions. This work presents an attention-enhanced object detection framework for aerial pothole detection design that relies on a pre-trained backbone, YOLOv8, and a custom feature-extraction network, the Feature Pyramid Network (FPN). An enhanced detection head is used to make the model aware of discriminative areas in space to get accurate localization of a pothole to overcome the major limitations of the standard YOLOv8 used in aerial road inspection, irrespective of the road surface. The underlying architecture incorporates a purpose-built data layer and a preprocessing engine that can accommodate scenarios such as seasonal changes and bad weather. To further enhance learning dynamics, a customized loss function and a new optimizer framework are incorporated to improve convergence towards overall detection reliability. Specifically, a custom differential optimizer that uses layer-wise adaptive learning rates and momentum-based gradient updates to help suppress false positives and accelerate convergence. Conversely, the IoU-based personal loss function, combined with real-time validation, stabilizes training across a range of road conditions. A major feature of the proposed system is its ability to process aerial imagery from unmanned drone platforms. Empirical analysis proves a good result: an average precision of 0.980 with the IoU of 0.5 and an F1-score of 0.97 with a confidence threshold of 0.30. Precision is high (0.97 at the 90-percent confidence level). These metrics show how well the model will be able to balance false positives and false negatives—a critical need in a safety-critical deployment. The results make the framework a potential, scalable, and reliable candidate for integrating smart transportation systems and autonomous vehicle navigation. Full article

Background: Upper-limb performance in handball depends on accurate shoulder sensorimotor control under high loads and fatigue. This study examined between-cohort differences associated with concentric versus eccentric exercise-induced fatigue in shoulder proprioception, kinesthesia, functional stability, and isometric force output in professional male handball players. Methods: This was a retrospective, quasi-experimental (non-randomized) between-cohort comparison of two previously collected cohorts who completed either a concentric (n = 46) or eccentric (n = 33) fatigue protocol, with pre- and post-fatigue assessments of joint repositioning sense (absolute angular error, AAE), threshold to detection of passive movement (TTDPM), Y Balance Test Upper Quarter (YBT-UQ), and the Athletic Shoulder (ASH) test. Results: Fatigue significantly increased AAE across all tested angles (Time: all p < 0.001), with a contraction-specific effect at end-range internal rotation (IR45°), where AAE increased more after concentric than eccentric fatigue (Time × Fatigue Type: p = 0.017; Δ = +1.34° (+61.8%) vs. +0.20° (+7.4%)). TTDPM increased after fatigue (p = 0.001) with no interaction (p = 0.968). YBT-UQ performance decreased after fatigue for all dominant-limb outcomes and for non-dominant inferolateral, superolateral, and composite scores (all p ≤ 0.018), but not for non-dominant anteromedial reach (p = 0.986); no Time × Fatigue Type interactions were detected for YBT-UQ outcomes (all p > 0.05). ASH force output decreased across all positions and both limbs (all p ≤ 0.002), with the dominant-limb Y position showing a greater decline following eccentric fatigue (Time × Fatigue Type: p = 0.030; e.g., ASH Y dominant Δ = −0.49 (−4.6%) vs. −1.43 N·kg⁻¹ (−13.3%)). Conclusions: Exercise-induced fatigue impairs shoulder sensorimotor function and upper-limb performance in handball. Contraction-mode differences were small and task-specific in this between-cohort comparison, emerging primarily at end-range proprioception and selected isometric strength positions. These findings may inform the design of training programs that emphasize fatigue-resistant sensorimotor control and end-range strength, while causal inferences regarding contraction mode are not warranted given the non-randomized design. Full article

Background and Objectives: Post-traumatic lower limb injuries are frequently associated with gait impairment, reduced functional independence, and delayed recovery due to weight-bearing restrictions. Dynamic body weight support (DBWS) refers to rehabilitation technologies that provide real-time, adaptive unloading of body weight during functional tasks such as walking, enabling safer and more effective gait training. Although these robotic systems have been extensively investigated in neurological pathologies, there is a lack of evidence regarding their use in post-traumatic lower limb injuries. Therefore, this systematic review aimed to evaluate the clinical effectiveness of robotic systems incorporating DBWS in the rehabilitation of post-traumatic lower limb pathologies. Materials and Methods: This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, and the protocol was registered in PROSPERO (CRD420261294273). Seven major databases (PubMed, Scopus, ScienceDirect, Cochrane, Web of Science, Springer, and Wiley) were searched from inception to October 2025. Studies that were considered included patients with recent post-traumatic pathologies in the lower limbs. The methodological quality and risk of bias of the included studies were evaluated using the PEDro scale and the RoB 2 tool. Results: Seven studies involving 265 participants with recent post-traumatic lower limb injuries were included. The rehabilitation systems reviewed enabled early, intensive gait and balance training by reducing lower limb loading and facilitating safe performance of functional walking tasks. However, substantial heterogeneity in intervention protocols and outcome measures limited direct comparisons across studies. Conclusions: The findings of this systematic review suggest that DBWS interventions may enhance gait and balance recovery in individuals with post-traumatic lower limb injuries. Despite the small number of participants included, the available evidence indicates that these technologies can facilitate functional improvements during the early stages of rehabilitation and may represent a valuable adjunct to conventional therapeutic approaches. Nevertheless, further well-designed studies with larger sample sizes, standardized intervention protocols, and long-term follow-up are required to establish optimal clinical implementation strategies and to confirm the durability of treatment effects. Full article

Machine learning has enhanced rice grain classification by enabling accurate, automated, and objective morphological analysis, supporting quality control and varietal selection. This study compared the performance of several algorithms in identifying three Ecuadorian rice varieties (INIAP-11, INIAP-12, and INIAP-20) using a balanced dataset of morphological features. Five models were trained with cross-validation and evaluated using multi-class metrics. Significant differences among varieties particularly in area, length, and eccentricity confirmed their discriminative potential. Initially, models were trained using all morphological variables. However, to optimize training time and computational cost, the study also evaluated model performance after applying dimensionality reduction through Principal Component Analysis (PCA). This approach enabled assessing whether reduced feature spaces could maintain competitive predictive performance while improving efficiency. Overall, all algorithms performed well, but only the Artificial Neural Network (ANN) and Support Vector Classifier (SVC) demonstrated strong generalization without overfitting. In contrast, Random Forest achieved perfect accuracy in training but decreased performance in testing. In conclusion, ANN and SVC emerged as the most robust alternatives for rice grain morphological classification, while the PCA results highlight the value of dimensionality reduction as a strategy to enhance computational scalability without substantially compromising accuracy. The objective of the present study is to train, evaluate, and compare different machine learning algorithms for the classification of three types of rice grains, in order to determine the best model for this task based on seven morphological characteristics of the grains applying machine learning algorithms with and without dimensional reduction. Full article

Electro-hydrostatic actuators (EHAs) are increasingly deployed in modern aircraft due to their compact size, fast response, and high power-to-weight ratio. However, existing airborne QAR and EICAS data are typically recorded as independent parameters without explicit correspondence to system health states, making degradation assessment and remaining useful life (RUL) prediction challenging. To address this issue, this paper proposes a spatiotemporal degradation modeling framework, termed PreDyn-ST, based on multivariate time series (MTS) data. The method integrates SimCLR-based contrastive pretraining and a dynamic feature fusion mechanism to capture evolving temporal dependencies and spatial sensor correlations. Specifically, graph convolutional networks (GCNs) incorporating physical connectivity priors are employed for spatial modeling, while a Transformer extracts long-range temporal patterns. A learnable dynamic weighting mechanism adaptively balances spatial and temporal features during training. The adaptive behavior is further analyzed using correlation statistical index (CSI) curves for interpretability. Experimental validation on a self-developed EHA degradation test bench and the C-MAPSS benchmark dataset demonstrates that PreDyn-ST achieves competitive and stable prediction performance. In particular, the method shows robust performance under complex operating conditions such as FD004. These results indicate the effectiveness of the proposed framework for accurate and interpretable degradation modeling in aerospace applications. Full article

Objectives: This study investigated the effects of trunk extension-based inspiratory muscle strengthening on respiratory function, balance, and gait in patients with stroke. Methods: Thirty stroke patients were randomly assigned to the study group (n = 15) or control group (n = 15). The study group performed inspiratory muscle strengthening exercises in a trunk extension posture, while the control group received conventional inspiratory muscle training. Both groups trained five times per week for six weeks. Outcome measures included maximal inspiratory pressure (MIP), maximal inspiratory flow rate (MIFR), maximal inspiratory volume (MIV), peak expiratory flow (PEF), forced expiratory volume in 1 s (FEV₁), Berg Balance Scale (BBS), weight distribution ratio (WDR), limits of stability (LOSs), Timed Up and Go (TUG), gait velocity, cadence, and stride length. Results: The study group showed significantly greater improvements in respiratory parameters (MIP, MIFR, MIV, PEF, FEV₁) and functional outcomes (WDR, LOS, BBS, TUG, gait velocity, cadence, stride length) compared to the control group. Conclusions: Trunk extension-based inspiratory muscle strengthening effectively improves respiratory function, balance, and gait in stroke patients, and may serve as a valuable addition to stroke rehabilitation programs. Full article

The demand for high-quality sulfur that is used in medicine, chemistry, and other industries is growing. The technological processes for extracting sulfur from harmful acid gases in oil refining are characterized by complex, nonlinear, and fuzzy relationships between input and output parameters, complicating the development of their models. Therefore, solving the problems of modeling and optimizing sulfur production processes under uncertainty, as they occur in sulfur recovery units (SRUs), is a highly relevant scientific and practical task. To address these issues, we propose a method for synthesizing a neuro-fuzzy model for assessing the integrated quality and volume of sulfur, enabling the development of a highly adequate model under fuzzy conditions. The developed hybrid model, based on the proposed method, is trained on historical data and adapts its fuzzy rules, enabling the modeling of complex nonlinear, fuzzy relationships between the input and output parameters of sulfur production processes. An ANFIS architecture for a neuro-fuzzy model for assessing the quality and volume of sulfur from the reactor outlet of the Atyrau refinery SRU was developed. A fuzzy Pareto optimization method was proposed, which, based on the developed neuro-fuzzy model, enables vector optimization of sulfur production processes, taking into account the constraints, and determines a Pareto-optimal solution in a fuzzy environment. The best solution selected by the decision-maker from the Pareto set, depending on the current situation, ensures a balance between the sulfur volume and its integrated quality. As a result of multi-criteria optimization of sulfur production processes at the Atyrau refinery SRU based on the proposed methods, the volume of high-quality sulfur increased by 7.39%, hydrogen by 10.71%, and energy consumption decreased by 80 kW/h, demonstrating the effectiveness of the proposed methods. Full article

Non-intrusive load monitoring (NILM) can provide actionable feedback for demand response (DR) when direct measurements of device states are unavailable. We propose a reproducible, engineering-oriented pipeline for detecting ON/OFF states of end-use load groups from an aggregated active power time series. The method uses robust hysteresis-based labeling with adaptive thresholds derived from the median and median absolute deviation, followed by compact feature engineering restricted to global active power (GAP). After removing collinear features (|r| > 0.98), permutation importance is used to retain informative predictors. Probabilistic binary classifiers (LGBM, Histogram-based Gradient Boosting, XGBoost, and CatBoost) are trained for each target load, and the decision threshold is optimized via F_β to balance missed events and false alarms. A post-processing stage stabilizes predictions by smoothing probabilities and suppressing spurious triggers. Model quality is assessed with both sample-wise metrics and event-based metrics that credit the correct detection of switching intervals within a time tolerance. Experiments on the open “Individual Household Electric Power Consumption” dataset (1-min resolution, 2007–2010) demonstrate that lightweight gradient boosting models, particularly LGBM, deliver reliable and interpretable state estimates suitable for practical DR integration and edge deployment. Full article

In recent years, deep learning models have exhibited exceptional performance across several tasks. However, the substantial computational and storage demands impede implementation on edge devices with constrained resources. Online Knowledge Distillation (OKD) has arisen as an effective model compression strategy that removes the reliance on pre-trained teachers characteristic of conventional distillation approaches. Nonetheless, OKD persists in facing challenges, including substantial performance variances within student networks, insufficient learning capacity for difficult data, and network homogeneity. To address those issues, this paper proposes an Elite-Student-Enhanced Adaptive Online Knowledge Distillation (ESAKD) algorithm. ESAKD introduces a patience factor-based adaptive temperature scheduling mechanism to dynamically balance knowledge clarity and richness during knowledge transfer. This mechanism utilizes the performance benefits of elite-students, particularly during initial training phases, to offer superior supervision that successfully transcends the learning capacity limitations of current OKD approaches. This method promotes swift convergence and substantially enhances the ultimate precision of the standard-student models. Furthermore, a confidence-weighted ensemble student model is designed to improve collective decision-making. Experimental assessments indicate that ESAKD provides substantial performance improvements over supervised learning without distillation and other leading online distillation techniques. On the CIFAR-100 dataset, ESAKD improves the test accuracy of various models by 1.49–6% over the undistilled baselines, and by 0.27–2.18% compared to advanced online distillation algorithms. Moreover, it exhibits enhanced performance on the Tiny-ImageNet-200 dataset as well. Full article

Background and Objectives: This study investigated the efficacy of eccentric isokinetic muscle strengthening versus passive motion protocols on neuromuscular function and performance capacity in female swimmers with chronic lateral epicondylitis. Materials and Methods: Twenty-five swimmers (age 46.1 ± 3.1 years) with lateral epicondylitis exceeding three months’ duration completed a randomized controlled trial comparing eccentric training in Controlled Active Motion mode (experimental group (EG), n = 13) against passive motion in Continuous Passive Motion mode (control group (CG), n = 12). Both groups performed 18 supervised sessions over six weeks (60°/s angular velocity, progressive loading 1–12 sets × 5 repetitions). Bilateral concentric peak torque of elbow extensors and flexors constituted the primary outcomes. Secondary measures included push-up performance, explosive power assessed by the Seated Medicine Ball Chest Push Test, and goniometric range of motion. Linear mixed-effects models and analysis of covariance with baseline adjustment were employed. Results: Eccentric training produced side-specific strength adaptations in elbow flexors (confirmed interaction: F_1,23 = 8.56, p = 0.008, η_p² = 0.271), with the experimental group demonstrating balanced bilateral gains, whereas the control group exhibited asymmetric responses favoring the non-dominant limb. EG demonstrated superior functional gains: push-up repetitions increased 4.15 ± 1.77 versus 2.17 ± 1.27 in CG (adjusted difference = 3.21 repetitions, 95% CI [1.52, 4.90], p = 0.001, d = 1.31), while explosive power improved 0.32 ± 0.09 m versus 0.10 ± 0.06 m (adjusted difference = 0.35 m, 95% CI [0.25, 0.45], p < 0.001, d = 1.20). Range of motion remained unchanged across groups (all p > 0.65). Conclusions: Eccentric isokinetic strengthening confers substantial advantages over passive motion protocols for restoring upper-body muscular endurance and ballistic force production in swimmers with lateral epicondylitis, supporting its integration into rehabilitation frameworks for the management of tendinopathy. Full article