Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (31,611)

Search Parameters:
Keywords = experimental efficiency

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 1922 KB  
Article
On the Use of Machine Learning Methods for EV Battery Pack Data Forecast Applied to Reconstructed Dynamic Profiles
by Joaquín de la Vega, Jordi-Roger Riba and Juan Antonio Ortega-Redondo
Appl. Sci. 2025, 15(20), 11291; https://doi.org/10.3390/app152011291 - 21 Oct 2025
Abstract
Lithium-ion batteries are essential to electric vehicles, so it is crucial to continuously monitor and control their health. However, since today’s battery packs consist of hundreds or thousands of cells, monitoring all of them is challenging. Additionally, the performance of the entire battery [...] Read more.
Lithium-ion batteries are essential to electric vehicles, so it is crucial to continuously monitor and control their health. However, since today’s battery packs consist of hundreds or thousands of cells, monitoring all of them is challenging. Additionally, the performance of the entire battery pack is often limited by the weakest cell. Therefore, developing effective monitoring techniques that can reliably forecast the remaining time to depletion (RTD) of lithium-ion battery cells is essential for safe and efficient battery management. However, even in robust systems, this data can be lost due to electromagnetic interference, microcontroller malfunction, failed contacts, and other issues. Gaps in voltage measurements compromise the accuracy of data-driven forecasts. This work systematically evaluates how different voltage reconstruction methods affect the performance of recurrent neural network (RNN) forecast models trained to predict RTD through quantile regression. The paper uses experimental battery pack data based on the behavior of an electric vehicle under dynamic driving conditions. Artificial gaps of 500 s were introduced at the beginning, middle, and end of each discharge phase, resulting in over 4300 reconstruction cases. Four reconstruction methods were considered: a zero-order hold (ZOH), an autoregressive integrated moving average (ARIMA) model, a gated recurrent unit (GRU) model, and a hybrid unscented Kalman filter (UKF) model. The results presented here reveal that the UKF model, followed by the GRU model, outperform alternative reconstruction methods. These models minimize signal degradation and provide forecasts similar to the original past data signal, thus achieving the highest coefficient of determination and the lowest error indicators. The reconstructed signals were fed into LSTM and GRU RNNs to estimate RTD, which produced confidence intervals and median values for decision-making purposes. Full article
(This article belongs to the Special Issue AI-Based Machinery Health Monitoring)
23 pages, 5736 KB  
Article
Enhanced Full-Section Pavement Rutting Detection via Structured Light and Texture-Aware Point-Cloud Registration
by Huayong Zhu, Yishun Li, Feng Li, Difei Wu, Yuchuan Du and Ziyue Gao
Appl. Sci. 2025, 15(20), 11283; https://doi.org/10.3390/app152011283 - 21 Oct 2025
Abstract
Rutting is a critical form of pavement distress that compromises driving safety and long-term structural integrity. Traditional detection methods predominantly rely on cross-sectional measurements and high-cost inertial navigation-assisted laser scanning, which limits their applicability for large-scale, full-section evaluation. To address these limitations, this [...] Read more.
Rutting is a critical form of pavement distress that compromises driving safety and long-term structural integrity. Traditional detection methods predominantly rely on cross-sectional measurements and high-cost inertial navigation-assisted laser scanning, which limits their applicability for large-scale, full-section evaluation. To address these limitations, this study proposes a framework for full-section rutting detection leveraging an area-array structured light camera for efficient 3D data acquisition. A multi-scale texture enhancement strategy based on 2D wavelet transform is introduced to extract latent surface features, enabling robust and accurate point-cloud registration without the need for artificial markers. Additionally, an improved Random Sample Consensus—Density-Based Spatial Clustering of Applications with Noise (RANSAC-DBSCAN) algorithm is designed to enhance the precision and robustness of rutting region segmentation under real-world pavement conditions. The proposed method is experimentally validated using 102 multi-frame pavement point clouds. Compared to Fast Point Feature Histograms (FPFH) and Deep Closest Point (DCP), the registration approach achieves a 71.31% and 80.64% reduction in point-to-plane error, respectively. For rutting segmentation, the enhanced clustering method attains an average F1-score of 90.5%, outperforming baseline methods by over 15%. The proposed workflow can be seamlessly integrated into vehicle-mounted structured-light inspection systems, offering a low-cost and scalable solution for near real-time, full-lane rutting detection in routine pavement monitoring. Full article
28 pages, 1239 KB  
Article
Research on Computing Power Resources-Based Clustering Methods for Edge Computing Terminals
by Jian Wang, Jiali Li, Xianzhi Cao, Chang Lv and Liusong Yang
Appl. Sci. 2025, 15(20), 11285; https://doi.org/10.3390/app152011285 - 21 Oct 2025
Abstract
In the “cloud–edge–end” three-tier architecture of edge computing, the cloud, edge layer, and end-device layer collaborate to enable efficient data processing and task allocation. Certain computation-intensive tasks are decomposed into subtasks at the edge layer and assigned to terminal devices for execution. However, [...] Read more.
In the “cloud–edge–end” three-tier architecture of edge computing, the cloud, edge layer, and end-device layer collaborate to enable efficient data processing and task allocation. Certain computation-intensive tasks are decomposed into subtasks at the edge layer and assigned to terminal devices for execution. However, existing research has primarily focused on resource scheduling, paying insufficient attention to the specific requirements of tasks for computing and storage resources, as well as to constructing terminal clusters tailored to the needs of different subtasks.This study proposes a multi-objective optimization-based cluster construction method to address this gap, aiming to form matched clusters for each subtask. First, this study integrates the computing and storage resources of nodes into a unified concept termed the computing power resources of terminal nodes. A computing power metric model is then designed to quantitatively evaluate the heterogeneous resources of terminals, deriving a comprehensive computing power value for each node to assess its capability. Building upon this model, this study introduces an improved NSGA-III (Non-dominated Sorting Genetic Algorithm III) clustering algorithm. This algorithm incorporates simulated annealing and adaptive genetic operations to generate the initial population and employs a differential mutation strategy in place of traditional methods, thereby enhancing optimization efficiency and solution diversity. The experimental results demonstrate that the proposed algorithm consistently outperformed the optimal baseline algorithm across most scenarios, achieving average improvements of 18.07%, 7.82%, 15.25%, and 10% across the four optimization objectives, respectively. A comprehensive comparative analysis against multiple benchmark algorithms further confirms the marked competitiveness of the method in multi-objective optimization. This approach enables more efficient construction of terminal clusters adapted to subtask requirements, thereby validating its efficacy and superior performance. Full article
(This article belongs to the Section Computing and Artificial Intelligence)
28 pages, 46610 KB  
Article
DAEF-YOLO Model for Individual and Behavior Recognition of Sanhua Geese in Precision Farming Applications
by Tianyuan Sun, Shujuan Zhang, Rui Ren, Jun Li and Yimin Xia
Animals 2025, 15(20), 3058; https://doi.org/10.3390/ani15203058 - 21 Oct 2025
Abstract
The rapid expansion of the goose farming industry creates a growing need for real-time flock counting and individual-level behavior monitoring. To meet this challenge, this study proposes an improved YOLOv8-based model, termed DAEF-YOLO (DualConv-augmented C2f, ADown down-sampling, Efficient Channel Attention integrated into SPPF, [...] Read more.
The rapid expansion of the goose farming industry creates a growing need for real-time flock counting and individual-level behavior monitoring. To meet this challenge, this study proposes an improved YOLOv8-based model, termed DAEF-YOLO (DualConv-augmented C2f, ADown down-sampling, Efficient Channel Attention integrated into SPPF, and FocalerIoU regression loss), designed for simultaneous recognition of Sanhua goose individuals and their diverse behaviors. The model incorporates three targeted architectural improvements: (1) a C2f-Dual module that enhances multi-scale feature extraction and fusion, (2) ECA embedded in the SPPF module to refine channel interaction with minimal parameter cost and (3) an ADown down-sampling module that preserves cross-channel information continuity while reducing information loss. Additionally, the adoption of the FocalerIoU loss function enhances bounding-box regression accuracy in complex detection scenarios. Experimental results demonstrate that DAEF-YOLO surpasses YOLOv5s, YOLOv7-Tiny, YOLOv7, YOLOv9s, and YOLOv10s in both accuracy and computational efficiency. Compared with YOLOv8s, DAEF-YOLO achieved a 4.56% increase in precision, 6.37% in recall, 5.50% in F1-score, and 4.59% in mAP@0.5, reaching 94.65%, 92.17%, 93.39%, and 96.10%, respectively. A generalizable classification strategy is further introduced by adding a complementary “Other” category to include behaviors beyond predefined classes. This approach ensures complete recognition coverage and demonstrates strong transferability for multi-task detection across species and environments. Ablation studies indicated that mAP@0.5 remained consistent (~96.1%), while mAP@0.5:0.95 improved in the absence of the “Other” class (75.68% vs. 69.82%). Despite this trade-off, incorporating the “Other” category ensures annotation completeness and more robust multi-task behavior recognition under real-world variability. Full article
Show Figures

Figure 1

22 pages, 2683 KB  
Article
Enhanced SWAP Model for Simulating Evapotranspiration and Cotton Growth Under Mulched Drip Irrigation in the Manas River Basin
by Shuo Zhang, Tian Gao, Rui Sun, Muhammad Arsalan Farid, Chunxia Wang, Ping Gong, Yongli Gao, Xinlin He, Fadong Li, Yi Li, Lianqing Xue and Guang Yang
Agriculture 2025, 15(20), 2178; https://doi.org/10.3390/agriculture15202178 - 21 Oct 2025
Abstract
Model-based simulation of farmland evapotranspiration and crop growth facilitates precise monitoring of crop and farmland dynamics with high efficiency, real-time responsiveness, and continuity. However, there are still significant limitations in using crop models to simulate the dynamic process of evapotranspiration and cotton growth [...] Read more.
Model-based simulation of farmland evapotranspiration and crop growth facilitates precise monitoring of crop and farmland dynamics with high efficiency, real-time responsiveness, and continuity. However, there are still significant limitations in using crop models to simulate the dynamic process of evapotranspiration and cotton growth in mulched drip-irrigated cotton fields under different irrigation gradients. The SWAP crop growth model effectively simulates crop growth. However, the original SWAP model lacks a dedicated module to consider the impact of mulching on cotton field evapotranspiration and cotton dry matter mass. Therefore, in this study, the source codes of the soil moisture, evapotranspiration, and crop growth modules of the SWAP model were improved. The evapotranspiration and cotton growth data of the mulched drip-irrigated cotton fields under three irrigation treatments (W1 = 3360 m3·hm−2, W2 = 4200 m3·hm−2, and W3 = 5040 m3·hm−2) in 2023 and 2024 at the Xinjiang Modern Water-saving Irrigation Key Experimental Station of the Corps were used to verify the simulation accuracy of the improved SWAP model. Research shows the following: (1) The average relative errors of the simulated evapotranspiration, leaf area index, and dry matter weight of cotton in the improved SWAP crop growth model are all <20% compared with the measured values. The root means square errors of the three treatments (W1, W2, and W3) ranged from 0.85 to 1.38 mm, from 0.03 to 0.18 kg·hm−2, and 55.01 to 69 kg·hm−2, respectively. The accuracy of the improved model in simulating evapotranspiration and cotton growth in the mulched cotton field increased by 37.49% and 68.25%, respectively. (2) The evapotranspiration rate of cotton fields is positively correlated with the irrigation water volume and is most influenced by meteorological factors such as temperature and solar radiation. During the flowering stage, evapotranspiration accounted for 62.83%, 62.09%, 61.21%, 26.46%, 40.01%, and 38.8% of the total evapotranspiration. Therefore, the improved SWAP model can effectively simulate the evaporation and transpiration of the mulched drip-irrigated cotton fields in the Manas River Basin. This study provides a scientific basis for the digital simulation of mulched farmland in the arid regions of Northwest China. Full article
20 pages, 1492 KB  
Article
Interpretable Diagnostics with SHAP-Rule: Fuzzy Linguistic Explanations from SHAP Values
by Alexandra I. Khalyasmaa, Pavel V. Matrenin and Stanislav A. Eroshenko
Mathematics 2025, 13(20), 3355; https://doi.org/10.3390/math13203355 - 21 Oct 2025
Abstract
This study introduces SHAP-Rule, a novel explainable artificial intelligence method that integrates Shapley additive explanations with fuzzy logic to automatically generate interpretable linguistic IF-THEN rules for diagnostic tasks. Unlike purely numeric SHAP vectors, which are difficult for decision-makers to interpret, SHAP-Rule translates feature [...] Read more.
This study introduces SHAP-Rule, a novel explainable artificial intelligence method that integrates Shapley additive explanations with fuzzy logic to automatically generate interpretable linguistic IF-THEN rules for diagnostic tasks. Unlike purely numeric SHAP vectors, which are difficult for decision-makers to interpret, SHAP-Rule translates feature attributions into concise explanations that humans can understand. The method was rigorously evaluated and compared with baseline SHAP and AnchorTabular explanations across three distinct and representative datasets: the CWRU Bearing dataset for industrial predictive maintenance, a dataset for failure analysis in power transformers, and the medical Pima Indians Diabetes dataset. Experimental results demonstrated that SHAP-Rule consistently provided clearer and more easily comprehensible explanations, achieving high expert ratings for simplicity and understanding. Additionally, SHAP-Rule exhibited superior computational efficiency and robust consistency compared to alternative methods, making it particularly suitable for real-time diagnostic applications. Although SHAP-Rule showed minor trade-offs in coverage, it maintained high global fidelity, often approaching 100%. These findings highlight the significant practical advantages of linguistic fuzzy explanations generated by SHAP-Rule, emphasizing its strong potential for enhancing interpretability, efficiency, and reliability in diagnostic decision-support systems. Full article
Show Figures

Figure 1

27 pages, 12490 KB  
Article
Fast CU Division Algorithm for Different Occupancy Types of CUs in Geometric Videos
by Nana Li, Tiantian Zhang, Jinchao Zhao and Qiuwen Zhang
Electronics 2025, 14(20), 4124; https://doi.org/10.3390/electronics14204124 - 21 Oct 2025
Abstract
Video-based point cloud compression (V-PCC) is a 3D point cloud compression standard that first projects the point cloud from 3D space onto 2D space, thereby generating geometric and attribute videos, and then encodes the geometric and attribute videos using high-efficiency video coding (HEVC). [...] Read more.
Video-based point cloud compression (V-PCC) is a 3D point cloud compression standard that first projects the point cloud from 3D space onto 2D space, thereby generating geometric and attribute videos, and then encodes the geometric and attribute videos using high-efficiency video coding (HEVC). In the whole coding process, the coding of geometric videos is extremely time-consuming, mainly because the division of geometric video coding units has high computational complexity. In order to effectively reduce the coding complexity of geometric videos in video-based point cloud compression, we propose a fast segmentation algorithm based on the occupancy type of coding units. First, the CUs are divided into three categories—unoccupied, partially occupied, and fully occupied—based on the occupancy graph. For unoccupied CUs, the segmentation is terminated immediately; for partially occupied CUs, a geometric visual perception factor is designed based on their spatial depth variation characteristics, thus realizing early depth range skipping based on visual sensitivity; and, for fully occupied CUs, a lightweight fully connected network is used to make the fast segmentation decision. The experimental results show that, under the full intra-frame configuration, this algorithm significantly reduces the coding time complexity while almost maintaining the coding quality; i.e., the BD rate of D1 and D2 only increases by an average of 0.11% and 0.28% under the total coding rate, where the geometric video coding time saving reaches up to 58.71% and the overall V-PCC coding time saving reaches up to 53.96%. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Figure 1

17 pages, 2360 KB  
Article
Gas–Water Two-Phase Flow Mechanisms in Deep Tight Gas Reservoirs: Insights from Nanofluidics
by Xuehao Pei, Li Dai, Cuili Wang, Junjie Zhong, Xingnan Ren, Zengding Wang, Chaofu Peng, Qihui Zhang and Ningtao Zhang
Nanomaterials 2025, 15(20), 1601; https://doi.org/10.3390/nano15201601 - 21 Oct 2025
Abstract
Understanding gas–water two-phase flow mechanisms in deep tight gas reservoirs is critical for improving production performance and mitigating water invasion. However, the effects of pore-throat-fracture multiscale structures on gas–water flow remain inadequately understood, particularly under high-temperature and high-pressure conditions (HT/HP). In this study, [...] Read more.
Understanding gas–water two-phase flow mechanisms in deep tight gas reservoirs is critical for improving production performance and mitigating water invasion. However, the effects of pore-throat-fracture multiscale structures on gas–water flow remain inadequately understood, particularly under high-temperature and high-pressure conditions (HT/HP). In this study, we developed visualizable multiscale throat-pore and throat-pore-fracture physical nanofluidic chip models (feature sizes 500 nm–100 μm) parameterized with Keshen block geological data in the Tarim Basin. We then established an HT/HP nanofluidic platform (rated to 240 °C, 120 MPa; operated at 100 °C, 100 MPa) and, using optical microscopy, directly visualized spontaneous water imbibition and gas–water displacement in the throat-pore and throat-pore-fracture nanofluidic chips and quantified fluid saturation, front velocity, and threshold pressure gradients. The results revealed that the spontaneous imbibition process follows a three-stage evolution controlled by capillarity, gas compression, and pore-scale heterogeneity. Nanoscale throats and microscale pores exhibit good connectivity, facilitating rapid imbibition without significant scale-induced resistance. In contrast, 100 μm fractures create preferential flow paths, leading to enhanced micro-scale water locking and faster gas–water equilibrium. The matrix gas displacement threshold gradient remains below 0.3 MPa/cm, with the cross-scale Jamin effect—rather than capillarity—dominating displacement resistance. At higher pressure gradients (~1 MPa/cm), water is efficiently expelled to low saturations via nanoscale throat networks. This work provides an experimental platform for visualizing gas–water flow in multiscale porous media under ultra-high temperature and pressure conditions and offers mechanistic insights to guide gas injection strategies and water management in deep tight gas reservoirs. Full article
(This article belongs to the Special Issue Nanomaterials and Nanotechnology for the Oil and Gas Industry)
Show Figures

Figure 1

20 pages, 2817 KB  
Article
Wildfire Detection from a Drone Perspective Based on Dynamic Frequency Domain Enhancement
by Xiaohui Ma, Yueshun He, Ping Du, Wei Lv and Yuankun Yang
Forests 2025, 16(10), 1613; https://doi.org/10.3390/f16101613 - 21 Oct 2025
Abstract
In recent years, drone-based wildfire detection technology has advanced rapidly, yet existing methods still encounter numerous challenges. For instance, high background complexity leads to frequent false positives and false negatives in models, which struggle to accurately identify both small-scale fire points and large-scale [...] Read more.
In recent years, drone-based wildfire detection technology has advanced rapidly, yet existing methods still encounter numerous challenges. For instance, high background complexity leads to frequent false positives and false negatives in models, which struggle to accurately identify both small-scale fire points and large-scale wildfires simultaneously. Furthermore, the complex model architecture and substantial parameter count hinder lightweight deployment requirements for drone platforms. To this end, this paper presents a lightweight drone-based wildfire detection model, DFE-YOLO. This model utilizes dynamic frequency domain enhancement technology to resolve the aforementioned challenges. Specifically, this study enhances small object detection capabilities through a four-tier detection mechanism; improves feature representation and robustness against interference by incorporating a Dynamic Frequency Domain Enhancement Module (DFDEM) and a Target Feature Enhancement Module (C2f_CBAM); and significantly reduces parameter count via a multi-scale sparse sampling module (MS3) to address resource constraints on drones. Experimental results demonstrate that DFE-YOLO achieves mAP50 scores of 88.4% and 88.0% on the Multiple lighting levels and Multiple wildfire objects Synthetic Forest Wildfire Dataset (M4SFWD) and Fire-detection datasets, respectively, whilst reducing parameters by 23.1%. Concurrently, mAP50-95 reaches 50.6% and 63.7%. Comprehensive results demonstrate that DFE-YOLO surpasses existing mainstream detection models in both accuracy and efficiency, providing a reliable solution for wildfire monitoring via unmanned aerial vehicles. Full article
(This article belongs to the Section Natural Hazards and Risk Management)
Show Figures

Figure 1

17 pages, 3194 KB  
Article
Improved Real-Time Detection Transformer with Low-Frequency Feature Integrator and Token Statistics Self-Attention for Automated Grading of Stropharia rugoso-annulata Mushroom
by Yu-Hang He, Shi-Yun Duan and Wen-Hao Su
Foods 2025, 14(20), 3581; https://doi.org/10.3390/foods14203581 - 21 Oct 2025
Abstract
Manual grading of Stropharia rugoso-annulata mushroom is plagued by inefficiency and subjectivity, while existing detection models face inherent trade-offs between accuracy, real-time performance, and deployability on resource-constrained edge devices. To address these challenges, this study presents an Improved Real-Time Detection Transformer (RT-DETR) tailored [...] Read more.
Manual grading of Stropharia rugoso-annulata mushroom is plagued by inefficiency and subjectivity, while existing detection models face inherent trade-offs between accuracy, real-time performance, and deployability on resource-constrained edge devices. To address these challenges, this study presents an Improved Real-Time Detection Transformer (RT-DETR) tailored for automated grading of Stropharia rugoso-annulata. Two innovative modules underpin the model: (1) the low-frequency feature integrator (LFFI), which leverages wavelet decomposition to preserve critical low-frequency global structural information, thereby enhancing the capture of large mushroom morphology; (2) the Token Statistics Self-Attention (TSSA) mechanism, which replaces traditional self-attention with second-moment statistical computations. This reduces complexity from O(n2) to O(n) and inherently generates interpretable attention patterns, augmenting model explainability. Experimental results demonstrate that the improved model achieves 95.2% mAP@0.5:0.95 at 262 FPS, with a substantial reduction in computational overhead compared to the original RT-DETR. It outperforms APHS-YOLO in both accuracy and efficiency, eliminates the need for non-maximum suppression (NMS) post-processing, and balances global structural awareness with local detail sensitivity. These attributes render it highly suitable for industrial edge deployment. This work offers an efficient framework for the automated grading of large-target crop detection. Full article
(This article belongs to the Section Food Engineering and Technology)
Show Figures

Figure 1

33 pages, 2631 KB  
Systematic Review
Battery Sizing and Composition in Energy Storage Systems for Domestic Renewable Energy Applications: A Systematic Review
by Ludovica Apa, Livio D’Alvia, Zaccaria Del Prete and Emanuele Rizzuto
Energies 2025, 18(20), 5536; https://doi.org/10.3390/en18205536 - 21 Oct 2025
Abstract
Renewable energy sources, such as photovoltaic panels and wind turbines, are increasingly integrated into domestic systems to address energy scarcity, rising demand, and climate change. However, their intermittent nature requires efficient energy storage systems (ESS) for stability and reliability. This systematic review, conducted [...] Read more.
Renewable energy sources, such as photovoltaic panels and wind turbines, are increasingly integrated into domestic systems to address energy scarcity, rising demand, and climate change. However, their intermittent nature requires efficient energy storage systems (ESS) for stability and reliability. This systematic review, conducted in accordance with PRISMA guidelines, aimed to evaluate the size and chemical composition of battery energy storage systems (BESS) in household renewable energy applications. A literature search was conducted in Scopus in August 2025 using predefined keywords, and studies published in English from 2015 onward were included. Exclusion criteria included book chapters, duplicate conference proceedings, geographically restricted case studies, systems without chemistry or size details, and those focusing solely on electric vehicle batteries. Of 308 initially retrieved records, 83 met the eligibility criteria and were included in the analysis. The majority (92%) employed simulation-based approaches, while 8% reported experimental setups. No formal risk-of-bias tool was applied, but a methodological quality check was conducted. Data were synthesized narratively and tabulated by chemistry, nominal voltage, capacity, and power. Lithium-ion batteries were the most prevalent (49%), followed by lead–acid (13%), vanadium redox flow (3.6%), and nickel–metal hydride (1.2%), with the remainder unspecified. Lithium-ion dominated due to high energy density, long cycle life, and efficiency. Limitations of the evidence include reliance on simulation studies, heterogeneity in reporting, and limited experimental validation. Overall, this review provides a framework for selecting and integrating appropriately sized and composed BESS into domestic renewable systems, offering implications for stability, efficiency, and household-level sustainability. The study was funded by the PNRR NEST project and Sapienza University of Rome Grant. Full article
Show Figures

Figure 1

23 pages, 11025 KB  
Article
HybriDet: A Hybrid Neural Network Combining CNN and Transformer for Wildfire Detection in Remote Sensing Imagery
by Fengming Dong and Ming Wang
Remote Sens. 2025, 17(20), 3497; https://doi.org/10.3390/rs17203497 - 21 Oct 2025
Abstract
Early warning systems on edge devices such as satellites and unmanned aerial vehicles (UAVs) are essential for effective forest fire prevention. Edge Intelligence (EI) enables deploying deep learning models on edge devices; however, traditional convolutional neural networks (CNNs)/Transformer-based models struggle to balance local-global [...] Read more.
Early warning systems on edge devices such as satellites and unmanned aerial vehicles (UAVs) are essential for effective forest fire prevention. Edge Intelligence (EI) enables deploying deep learning models on edge devices; however, traditional convolutional neural networks (CNNs)/Transformer-based models struggle to balance local-global context integration and computational efficiency in such constrained environments. To address these challenges, this paper proposes HybriDet, a novel hybrid-architecture neural network for wildfire detection. This architecture integrates the strengths of both CNNs and Transformers to effectively capture both local and global contextual information. Furthermore, we introduce efficient attention mechanisms—Windowed Attention and Coordinate-Spatial (CS) Attention—to simultaneously enhance channel-wise and spatial-wise features in high-resolution imagery, enabling long-range dependency modeling and discriminative feature extraction. Additionally, to optimize deployment efficiency, we also apply model pruning techniques to improve generalization performance and inference speed. Extensive experimental evaluations demonstrate that HybriDet achieves superior feature extraction capabilities while maintaining high computational efficiency. The optimized lightweight variant of HybriDet has a compact model size of merely 6.45 M parameters, facilitating seamless deployment on resource-constrained edge devices. Comparative evaluations on the FASDD-UAV, FASDD-RS, and VOC datasets demonstrate that HybriDet achieves superior performance over state-of-the-art models, particularly in processing highly heterogeneous remote sensing (RS) imagery. When benchmarked against YOLOv8, HybriDet demonstrates a 6.4% enhancement in mAP50 on the FASDD-RS dataset while maintaining comparable computational complexity. Meanwhile, on the VOC dataset and the FASDD-UAV dataset, our model improved by 3.6% and 0.2%, respectively, compared to the baseline model YOLOv8. These advancements highlight HybriDet’s theoretical significance as a novel hybrid EI framework for wildfire detection, with practical implications for disaster emergency response, socioeconomic security, and ecological conservation. Full article
(This article belongs to the Section Earth Observation for Emergency Management)
Show Figures

Figure 1

22 pages, 1585 KB  
Article
Sustainable Control of Large-Scale Industrial Systems via Approximate Optimal Switching with Standard Regulators
by Alexander Chupin, Zhanna Chupina, Oksana Ovchinnikova, Marina Bolsunovskaya, Alexander Leksashov and Svetlana Shirokova
Sustainability 2025, 17(20), 9337; https://doi.org/10.3390/su17209337 - 21 Oct 2025
Abstract
Large-scale production systems (LSPS) operate under growing complexity driven by digital transformation, tighter environmental regulations, and the demand for resilient and resource-efficient operation. Conventional control strategies, particularly PID and isodromic regulators, remain dominant in industrial automation due to their simplicity and robustness; however, [...] Read more.
Large-scale production systems (LSPS) operate under growing complexity driven by digital transformation, tighter environmental regulations, and the demand for resilient and resource-efficient operation. Conventional control strategies, particularly PID and isodromic regulators, remain dominant in industrial automation due to their simplicity and robustness; however, their capability to achieve near-optimal performance is limited under constraints on control amplitude, rate, and energy consumption. This study develops an analytical–computational approach for the approximate realization of optimal nonlinear control using standard regulator architectures. The method determines switching moments analytically and incorporates practical feasibility conditions that account for nonlinearities, measurement noise, and actuator limitations. A comprehensive robustness analysis and simulation-based validation were conducted across four representative industrial scenarios—energy, chemical, logistics, and metallurgy. The results show that the proposed control strategy reduces transient duration by up to 20%, decreases overshoot by a factor of three, and lowers transient energy losses by 5–8% compared with baseline configurations, while maintaining bounded-input–bounded-output (BIBO) stability under parameter uncertainty and external disturbances. The framework provides a clear implementation pathway combining analytical tuning with observer-based derivative estimation, ensuring applicability in real industrial environments without requiring complex computational infrastructure. From a broader sustainability perspective, the proposed method contributes to the reliability, energy efficiency, and longevity of industrial systems. By reducing transient energy demand and mechanical wear, it supports sustainable production practices consistent with the following United Nations Sustainable Development Goals—SDG 7 (Affordable and Clean Energy), SDG 9 (Industry, Innovation and Infrastructure), and SDG 12 (Responsible Consumption and Production). The presented results confirm both the theoretical soundness and practical feasibility of the approach, while experimental validation on physical setups is identified as a promising direction for future research. Full article
(This article belongs to the Special Issue Large-Scale Production Systems: Sustainable Manufacturing and Service)
Show Figures

Figure 1

12 pages, 6063 KB  
Article
Prex-NetII: Attention-Based Back-Projection Network for Light Field Reconstruction
by Dong-Myung Kim and Jae-Won Suh
Electronics 2025, 14(20), 4117; https://doi.org/10.3390/electronics14204117 - 21 Oct 2025
Abstract
We propose an attention-based back-projection network that enhances light field reconstruction quality by modeling inter-view dependencies. The network uses pixel shuffle to efficiently extract initial features. Spatial attention focuses on important regions while capturing inter-view dependencies. Skip connections in the refinement network improve [...] Read more.
We propose an attention-based back-projection network that enhances light field reconstruction quality by modeling inter-view dependencies. The network uses pixel shuffle to efficiently extract initial features. Spatial attention focuses on important regions while capturing inter-view dependencies. Skip connections in the refinement network improve stability and reconstruction performance. In addition, channel attention within the projection blocks enhances structural representation across views. The proposed method reconstructs high-quality light field images not only in general scenes but also in complex scenes containing occlusions and reflections. The experimental results show that the proposed method outperforms existing approaches. Full article
(This article belongs to the Special Issue Image Processing Based on Convolution Neural Network: 2nd Edition)
Show Figures

Figure 1

25 pages, 5190 KB  
Article
An Automated System for Underground Pipeline Parameter Estimation from GPR Recordings
by Daniel Štifanić, Jelena Štifanić, Nikola Anđelić and Zlatan Car
Remote Sens. 2025, 17(20), 3493; https://doi.org/10.3390/rs17203493 - 21 Oct 2025
Abstract
Underground pipelines form a critical part of urban infrastructure, yet their complex configurations and fragmented documentation hinder efficient maintenance and risk management. Ground-penetrating radar provides a non-invasive method for subsurface inspection; however, traditional interpretation of B-scan data relies heavily on manual analysis, which [...] Read more.
Underground pipelines form a critical part of urban infrastructure, yet their complex configurations and fragmented documentation hinder efficient maintenance and risk management. Ground-penetrating radar provides a non-invasive method for subsurface inspection; however, traditional interpretation of B-scan data relies heavily on manual analysis, which is time-consuming and prone to error. This research proposes a two-step automated system for the detection and quantitative characterization of underground pipelines from GPR B-scans. In the first step, hyperbolic reflections are automatically detected and localized using state-of-the-art object detection algorithms, where YOLOv11x achieved superior stability compared to RT-DETR-X. In the second step, detected hyperbolic reflections are processed in order to estimate key parameters, including two-way travel time, burial depth, pipeline diameter, and the angle between GPR survey line and pipeline. Experimental results from 5-fold cross-validation demonstrate that TWTT and burial depth can be estimated with high performance, while pipeline diameter and angle exhibit moderate performance, reflecting their higher complexity and sensitivity to noise. According to the experimental results, EfficientNetV2L consistently produced the best overall performance. The proposed automated system reduces reliance on manual inspection, improves efficiency, and establishes a foundation for real-time, autonomous GPR-based underground infrastructure assessment. Full article
Show Figures

Figure 1

Back to TopTop