Search Results (56,141)

Increasing energy demand, decarbonization commitments, and growing expectations for thermal comfort are driving the need for more adaptive and efficient climate control in residential buildings. This review synthesizes contemporary intelligent HVAC control strategies, including model-predictive control (MPC), deep reinforcement learning (DRL), data-driven forecasting, and hybrid approaches. Following PRISMA guidelines, a set of studies published between 2010 and 2025 was systematically screened and analyzed to identify the dominant methodological trends, data requirements, implementation architectures, and evaluation practices reported in the literature. This review highlights how these methods differ in modeling assumptions, computational complexity, robustness to uncertainty, and suitability for residential environments characterized by stochastic occupancy and heterogeneous building stock. In addition, we examine enabling technologies such as sensing infrastructures, pricing signals, and embedded computation, as well as barriers to real-world deployment, including data availability, interpretability, and integration with existing building systems. The findings provide a consolidated framework for understanding the capabilities and limitations of intelligent HVAC control and outline research gaps that remain for achieving scalable, user-centered, and energy-efficient operation in residential buildings. Full article

This paper presents the design of a hardware–software system for non-invasive automated monitoring of feeding behavior in livestock with biometric identification of individual animals. Neural network models for animal identification from images and individual recognition have been developed and trained. A solution is proposed to address the challenge of acquiring a sufficient number of personalized animal images for training the identification neural network. A transfer learning approach is introduced for pig identification, where the network is first trained on a large-scale dataset of more than three million human face images obtained from open sources and subsequently fine-tuned by training the upper layers on a significantly smaller dataset consisting of 5610 pig face images. Experimental results demonstrated the high effectiveness of the system: the Top-1 identification accuracy reached 95.1%, while the ROC AUC in open-set recognition tasks achieved 0.95. The processing time per frame on an NVIDIA RTX 4090 GPU was 1.4 ms (724 FPS). Full article

Reliable maximum power point tracking (MPPT) methods are essential in dynamic wind conditions to obtain maximum efficiency in wind energy conversion systems (WECSs). Conventional methods like incremental conductance (INC) and perturb and observe (P&O) are simple and robust but have drawbacks in terms of convergence and oscillations around the maximum power point (MPP) under dynamic conditions. In contrast, intelligent control methods such as artificial neural networks (ANNs) adapt more effectively. This paper presents a comparative analysis of ANN, P&O, and INC methods to obtain MPP for a WECS. A permanent magnet synchronous generator (PMSG) was coupled with a DC–DC boost converter to study the performance of the three MPPT methods under two different wind profiles. The ANN was trained with Bayesian regularization (BR) to estimate wind speed using rotor speed and computed mechanical power as inputs. The INC method achieved MPP using real-time power–voltage curves, while the P&O method perturbs the control variable, observes its results in output power, and adjusts the control variable accordingly. The three MPPT methods were compared in terms of power extraction, voltage stability, robustness, and dynamic response. The ANN achieved faster response, smoother output power and voltage, and reduced oscillation to dynamic conditions with higher output power compared to P&O and INC. On the other hand, the P&O and INC methods are less computationally intensive and do not require offline training. Full article

Digitally configurable DC/DC converters provide built-in telemetry signals that offer new opportunities for operational data-driven monitoring in embedded energy systems. However, exploiting these signals for intelligent condition monitoring remains challenging due to limited computational resources and the need to preserve the safety and determinism of power supply control. This work investigates the combination of digitally configurable DC/DC converters and embedded artificial intelligence for resource-efficient load and condition monitoring based exclusively on converter-side power telemetry. A lightweight, feature-based current analysis pipeline is proposed, incorporating domain-informed temporal and electric features. Three representative machine learning model classes, Random Forest, Support Vector Machine, and a Neural Network, are evaluated. The approach is implemented on an ESP32-class microcontroller operating as a dedicated monitoring unit, fully separated from the safety-critical power supply control. Experimental validation on a laboratory demonstrator shows that classification accuracies of up to 99% can be achieved for four system states using only five features at a 100 Hz telemetry sampling rate, while remaining within typical embedded memory constraints. The results demonstrate that converter-internal telemetry enables effective and scalable condition monitoring without additional sensors, supporting the combination of embedded intelligence and digitally configurable power supplies for industrial applications. Full article

With the rapid development of big data and artificial intelligence, agricultural product price forecasting is evolving toward more intelligent and accurate approaches. However, such prices are affected by complex factors including natural conditions, market dynamics, and policy changes, resulting in strong nonlinearity and noise. To address the above challenges and achieve accurate agricultural price forecasts, this study proposes a hybrid framework that integrates a secondary decomposition algorithm with an improved Human Evolutionary Optimization Algorithm specifically tailored for the agricultural domain. The original price series is first decomposed using complete ensemble empirical mode decomposition with adaptive noise, and the high-frequency component is further processed using variational mode decomposition to enhance feature extraction. The improved optimization algorithm introduces Gaussian mutation and adaptive weights to optimize neural network parameters. Experiments on wheat, Chinese cabbage, and broiler chicken demonstrate that the proposed model significantly improves prediction accuracy, with determination coefficients increasing by 6.69, 8.87, and 6.43 percentage points, respectively. The results confirm the model’s effectiveness in reducing noise, capturing multi-scale features, and improving forecasting performance. Full article

Handling class imbalance remains a central challenge in machine learning, particularly in pattern recognition tasks where identifying rare but critical anomalies is of paramount importance. Traditional generative models often decouple data synthesis from classification, leading to a distribution mismatch that limits their practical benefit. To address these shortcomings, we introduce Causal Cooperative Networks (CCNETS), a modular framework that establishes a functional causal link between generation, inference, and reconstruction. CCNETS is composed of three specialized cooperative modules: an Explainer for latent feature abstraction, a Reasoner for probabilistic label prediction, and a Producer for context-aware data synthesis. These components interact through a dynamic causal feedback loop, where classification outcomes directly guide targeted sample synthesis to adaptively reinforce vulnerable decision boundaries. A key innovation, our proposed Zoint mechanism, enables the adaptive fusion of latent and observable features, enhancing semantic richness and decision-making robustness under uncertainty. We evaluated CCNETS on two distinct real-world datasets: Credit Card Fraud Detection dataset, characterized by extreme imbalance (fraud rate < 0.2%), and the AI4I 2020 Predictive Maintenance dataset (failure rate < 4%). Across comprehensive experimental setups, CCNETS consistently outperformed baseline methods, achieving superior F1-scores, and AUPRC. Furthermore, data synthesized by CCNETS demonstrated enhanced generalization and learning stability under limited data conditions. These results establish CCNETS as a scalable, interpretable, and hybrid soft computing framework that effectively aligns synthetic data with classifier objectives, advancing robust imbalanced learning. Full article

Background/Objectives: The incidence of dementia and the concurrent burden on healthcare will increase with a population that continues to age. Pharmaceutical interventions for dementia carry negative side effects, ineffectively treat underlying causes, and fail to prevent disease onset. Therefore, non-pharmaceutical interventions such as music therapy should to be explored as a standalone or co-therapy for dementia. Music therapy improves cognitive symptoms of dementia; however, the neural mechanisms underpinning these improvements are not fully understood. Methods: To investigate potential neural mechanisms, six participants with dementia completed the Standardised Mini Mental State Examination, an n-back task, and magnetoencephalography (MEG) scanning before and after a music therapy program structured around improving executive functioning. Results: After music therapy, scores on an n-back task improved, and the MEG data revealed increased connectivity in neural networks and areas associated with compensation during executive functioning tasks. Connectivity results suggest there is preliminary evidence that music therapy improves cognitive symptoms of dementia by activating compensatory neural networks and areas; however, given the small sample size, these results should be interpreted with caution. Conclusions: The results of this hypotheses study present music therapy as a potentially viable short-term intervention which may operate by targeting compensatory neural networks and could be a long-term intervention that incorporates positive modifiable lifestyle factors, protecting the brain from dementia. Full article

The use of Silicon Carbide (SiC) MOSFETs significantly improves converter performance by increasing efficiency and reducing costs, to the detriment of electro-magnetic emission and reliability. Implementing a predictive maintenance strategy based on a prognosis tool can mitigate this limitation. This literature review offers a methodological synthesis of prognosis design tools for SiC MOSFETs, while also encompassing studies on IGBTs and silicon-based power MOSFETs where these approaches are transferable. The analysis focuses on wear-out prognosis under nominal operating conditions of standard package device, excluding environmental constraints. Articles published up to 2025 were identified in the OpenAlex database using a keyword-based search and manually filtered according to the study scope. Most reviewed works rely on Data-Based prognosis methods, mostly based on neural networks, though out-of-sample validation remains uncommon. Our study also highlights the dependence of Data-Based prognosis performance on the shape of degradation indicator trends. Moreover, the estimation of prediction uncertainty is rarely addressed in the reviewed literature. Despite notable methodological advances, ensuring the reliability of prognosis tools for SiC MOSFETs remains an ongoing research challenge. Full article

Autonomous navigation in mobile robots operating in dynamic and partially known environments demands the coordinated integration of perception, decision-making, and control while ensuring stability, safety, and energy efficiency. This paper presents an integrated navigation framework for differential-drive mobile robots that combines deep learning-based visual perception, reinforcement learning (RL) for high-level decision-making, and a Lyapunov-based trajectory reference generator for low-level motion execution. A convolutional neural network processes RGB-D images to classify obstacle configurations in real time, enabling navigation without prior map information. Based on this perception layer, an RL policy generates adaptive navigation subgoals in response to environmental changes. To ensure stable motion execution, a Lyapunov-based control strategy is formulated at the kinematic level to generate smooth velocity references, which are subsequently tracked by embedded PID controllers, explicitly decoupling learning-based decision-making from stability-critical control tasks. The local stability of the trajectory-tracking error is analyzed using a quadratic Lyapunov candidate function, ensuring asymptotic convergence under ideal kinematic assumptions. Experimental results demonstrate that while higher control gains provide faster convergence in simulation, an intermediate gain value (K = 0.5I) achieves a favorable trade-off between responsiveness and robustness in real-world conditions, mitigating oscillations caused by actuator dynamics, delays, and sensor noise. Validation across multiple navigation scenarios shows average tracking errors below 1.2 cm, obstacle detection accuracies above 95% for human obstacles, and a significant reduction in energy consumption compared to classical A* planners, highlighting the effectiveness of integrating learning-based navigation with analytically grounded control. Full article

Ionizing radiation is a non-thermal sanitization technique used in the food field to eliminate bacteria, molds, insects and other microbes, resulting in delayed spoilage and extended shelf life. In this work, mozzarella cheese was irradiated with X-rays at a dose of 3.0 kGy, and irradiation-induced lipid modifications were evaluated through a comprehensive analysis of the mozzarella lipid fingerprint. To this aim, an optimized microwave-assisted extraction method associated with UHPLC-Q-Orbitrap-MS analysis was used for reliable and accurate lipid identification in the controls and in irradiated samples. The outcomes demonstrated that the X-ray dose employed in this investigation did not cause the formation of new lipid molecules. However, lipidomic chemometric modeling, including partial least squares-discriminant analysis, enabled the discrimination of irradiated versus non-irradiated samples and the selection of five ceramides, eight hexosyl ceramides, four sphingomyelins, one phosphatidylethanolamine, one cholesterol ester, ten oxidized triacylglycerols, and one oxidized diacylglycerol as potential markers of treatment. Finally, an artificial neural network was developed to accurately model the entire pattern in omics data in relation to the treatment. This developed analytical workflow allows for expanding knowledge on the effects of this technology and could have interesting applications in food safety traceability and control plans. Full article

Polymer additive manufacturing (AM) has grown rapidly in the past decade, with material extrusion, vat photopolymerization, powder bed fusion and jetting now widely used for functional polymer parts. The mechanical performance of these parts depends strongly on process parameters such as layer height, build orientation, energy input and post-processing conditions, which motivate the development of predictive models for process–property relationships. Classical approaches based on Taguchi designs, ANOVA and response surface methodology have provided valuable insight, but the potential of modern machine learning (ML) techniques is not yet fully exploited. This review surveys recent work on ML-based prediction of mechanical properties of polymer AM parts using process parameters as inputs. Across the literature, well-tuned artificial neural networks, tree-based ensembles and support vector regression typically achieve prediction errors below about 5–10% for strength and modulus, showing that data-driven surrogates can substantially reduce experimental trial-and-error in process optimization. Ongoing challenges include small datasets, missing standardized error metrics, and limited coverage of non-quasi-static phenomena like fatigue, impact, and environmental degradation. Full article

A wearable elbow exosuit system has been proposed in this work, including the origami-inspired exosuit structure along with a portable air source and electromyography (EMG)-based active rehabilitation control method. The elbow exosuit is designed using an origami-inspired pneumatic actuator to meet the biomechanic requirements for elbow assistance. And a portable pneumatic source attached to the waist is also proposed to drive the elbow exosuit. On the basis of exosuit structure design, the active control with cascaded frame is then developed. For the active perspective, the EMG-based motion prediction is accomplished for the input of controller. To achieve real-time and accurate prediction, a simple feedforward neural network is utilized for a motion prediction model based on its fast training. To further reduce the size of the network, the features are extracted from the EMG and angle for the inputs, replacing the end-to-end method. Based on intention prediction, the cascaded controller subsequently completes position control, torque control and pressure servo control. Finally, through preliminary experiments on healthy participants, the elbow can be accurately predicted for the EMG-based method, and the assistance efficiency is verified through task scores and reduction in muscle activation. In summary, the proposed wearable exosuit can provide a reference for the design of wearable devices. Full article

This study investigates how cover crop management and soil tillage influence the development and yield of cucumber and cabbage crops. Three cover crop treatments—blue lupin, black oats, and their mixture—were evaluated during the autumn/winter season, while Stylosanthes capitata (Fabaceae), pearl millet (Pennisetum glaucum, Poaceae), and their mixture were assessed during the spring/summer season, under both conventional tillage and no-till (direct seeding) systems. Cover crops were established in spring/summer (October–November) and, after their management, cucumber (Cucumis sativus L.) was cultivated from December to February. Subsequently, winter cover crops were grown from May to July, followed by cabbage (Brassica oleracea var. capitata) cultivation from July to September. Drip irrigation was used, and organic practices were employed for weed, pest, and disease management. Germination, seedling survival rate, and plant growth (height, number of leaves, foliage cover, and fruit or cabbage size) were evaluated. Finally, crop yield is considered by comparing harvest weight and quality to determine which combination of soil cover and planting method maximizes crop productivity and quality. Obviously, management differences that influence yield will be associated with soil properties. To better understand the causes of these yield differences, the influence of soil chemical properties was explored using multivariate analysis techniques (discriminant analysis) and neural networks. Multivariate techniques allow for the exploration of complex relationships among multiple variables simultaneously, facilitating the identification of key patterns or factors that influence crop yield. On the other hand, neural networks, using machine learning models, allow for the prediction of outcomes based on the soil’s physicochemical properties, as well as the identification of optimal combinations of factors that maximize crop yield. Discriminant analysis and neural networks showed that soil variables such as pH, organic matter (OM), cation exchange capacity (CEC), phosphorus (P), and potassium (K) were key determinants in differentiating the yield groups. Cabbage yield was most strongly associated with pH and OM, while cucumber yield responded more strongly to potassium and CEC. Full article

Nowadays, air quality is a major issue, especially in large cities. Apart from air pollution, particulate matter (PM), especially PM2.5, poses serious health risks to individuals with respiratory conditions. Accurate forecasting of PM levels is crucial to warn vulnerable populations and reduce exposure. Machine learning models can effectively predict PM concentrations based on historical data and barometric conditions such as temperature and humidity. Such predictions can support timely public health interventions and environmental policy decisions. The selection of the optimal machine learning model for time series forecasting requires a careful balance between predictive accuracy and computational efficiency. This study evaluates a number of widely used models, such as Random Forest (RF), Long Short-Term Memory (LSTM), Convolutional Neural Network-LSTM (CNN–LSTM), Extreme Gradient Boosting (XGB/HistGradientBoosting), and hybrid approaches (LSTM embeddings + RF), in the context of time series forecasting for particulate matter (PM) concentrations. Performance is assessed using three key error metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Scaled Error (MASE). Additionally, the computational demands and development complexity of each model are analyzed. The overall results are of great interest for each application model, and in more detail, it is shown that the best compromise between accuracy and efficiency can be achieved, while a corresponding prediction model with satisfactory predictive performance can be implemented. The results show that CNN–LSTM and hybrid approaches provide high accuracy, while tree-based models are computationally efficient, offering practical options for real-time forecasting systems. Full article

Postprandial plasma amino acid (AA) kinetics serve as essential indicators of digestive efficiency and systemic metabolic status in pigs. Traditional kinetic analysis relies on Non-Linear Least Squares (NLS) regression using compartmental models, yet these methods typically demand repeated blood sampling and precise initialization to ensure convergence. In this study, we developed a Physics-Informed Neural Network (PINN) framework by integrating mechanistic Ordinary Differential Equations (ODEs) directly into the deep learning loss function. The framework was evaluated using a benchmark dataset. Specifically, we performed a retrospective analysis by downsampling the original high-frequency data to simulate dense and sparse sampling strategies. The results demonstrate that while both models exhibit high fidelity under dense sampling, PINN maintains superior robustness and predictive accuracy under data-constrained conditions. Under the sparse sampling scenario, PINN reduced the Root Mean Square Error (RMSE) compared to NLS in key metabolic profiles, such as Methionine in the FAA group (p < 0.01) and Lysine in the HYD group (p < 0.05). Unlike NLS, which is sensitive to initial guesses, PINN successfully utilized physical laws as a regularization term to robustly solve the inverse problem, demonstrating superior parameter identification stability and predictive consistency under data-constrained conditions compared to NLS. We concluded that the PINN framework provides a reliable and consistent alternative for modeling the AA dynamics. In the future, it may be possible to reconstruct highly accurate physiological trajectories under optimized sparse sampling conditions. Full article