Search Results (6,569)

This paper analyzes the availability of lithium resources required to support a global decarbonized energy system featuring electrical energy storage based on lithium iron phosphate (LFP) batteries. A net-zero carbon grid consisting of existing nuclear and hydro capacity, with the balance being a 50/50 mix of wind and solar power generation, is assumed to satisfy projected world electrical demand in 2050, incorporating the electrification of transportation. The battery electrical storage capacity needed to support this grid is estimated and translated into the required number of nominal 10 MWh LFP storage plants similar to the ones currently in operation. The total lithium required for the global storage system is determined from the number of nominal plants and the inventory of lithium in each plant. The energy required to refine this amount of lithium is accounted for in the estimation of the total lithium requirement. Comparison of the estimated lithium requirements with known global lithium resources indicates that a global storage system consisting only of LFP plants would require only around 12.3% of currently known lithium reserves in a high-economic-growth scenario. The overall cost for a global LFP-based grid-scale energy storage system is estimated to be approximately USD 17 trillion. Full article

Timely and accurate identification of surface damage in hydraulic structures is essential for maintaining structural integrity and ensuring operational safety. Traditional manual inspections are time-consuming, labor-intensive, and prone to subjectivity, especially for large-scale or inaccessible infrastructure. Leveraging advancements in aerial imaging, unmanned aerial vehicles (UAVs) enable efficient acquisition of high-resolution visual data across expansive hydraulic environments. However, existing deep learning (DL) models often lack architectural adaptations for the visual complexities of UAV imagery, including low-texture contrast, noise interference, and irregular crack patterns. To address these challenges, this study proposes a lightweight, robust, and high-precision segmentation framework, called LFPA-EAM-Fast-SCNN, specifically designed for pixel-level damage detection in UAV-captured images of hydraulic concrete surfaces. The developed DL-based model integrates an enhanced Fast-SCNN backbone for efficient feature extraction, a Lightweight Feature Pyramid Attention (LFPA) module for multi-scale context enhancement, and an Edge Attention Module (EAM) for refined boundary localization. The experimental results on a custom UAV-based dataset show that the proposed damage detection method achieves superior performance, with a precision of 0.949, a recall of 0.892, an F1 score of 0.906, and an IoU of 87.92%, outperforming U-Net, Attention U-Net, SegNet, DeepLab v3+, I-ST-UNet, and SegFormer. Additionally, it reaches a real-time inference speed of 56.31 FPS, significantly surpassing other models. The experimental results demonstrate the proposed framework’s strong generalization capability and robustness under varying noise levels and damage scenarios, underscoring its suitability for scalable, automated surface damage assessment in UAV-based remote sensing of civil infrastructure. Full article

Multimodal sentiment analysis (MSA) faces key challenges such as incomplete modality inputs, long-range temporal dependencies, and suboptimal fusion strategies. To address these, we propose MGMR-Net, a Mamba-guided multimodal reconstruction and fusion network that integrates modality-aware reconstruction with text-centric fusion within an efficient state-space modeling framework. MGMR-Net consists of two core components: the Mamba-collaborative fusion module, which utilizes a two-stage selective state-space mechanism for fine-grained cross-modal alignment and hierarchical temporal integration, and the Mamba-enhanced reconstruction module, which employs continuous-time recurrence and dynamic gating to accurately recover corrupted or missing modality features. The entire network is jointly optimized via a unified multi-task loss, enabling simultaneous learning of discriminative features for sentiment prediction and reconstructive features for modality recovery. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that MGMR-Net consistently outperforms several baseline methods under both complete and missing modality settings, achieving superior accuracy, robustness, and generalization. Full article

Prolonged inundations are altering coastal forest ecosystems of the southeastern US, causing extensive tree die-offs and the development of ghost forests. This hydrological stressor also alters carbon fluxes, threatening the stability of coastal carbon sinks. This study was conducted to investigate the interactions between hydrological drivers and ecosystem responses by analyzing daily eddy covariance flux data from a wetland forest in North Carolina, USA, spanning 2009–2019. We analyzed temporal patterns of net ecosystem exchange (NEE), gross primary productivity (GPP), and ecosystem respiration (RE) under both flooded and non-flooded conditions and evaluated their relationships with observed tree mortality. Generalized Additive Modeling (GAM) revealed that groundwater table depth (GWT), leaf area index (LAI), NEE, and net radiation (Rn) were key predictors of mortality transitions (R² = 0.98). Elevated GWT induces root anoxia; declining LAI reduces productivity; elevated NEE signals physiological breakdown; and higher Rn may amplify evapotranspiration stress. Receiver Operating Characteristic (ROC) analysis revealed critical early warning thresholds for tree mortality: GWT = 2.23 cm, LAI = 2.99, NEE = 1.27 g C m⁻² d⁻¹, and Rn = 167.54 W m⁻². These values offer a basis for forecasting forest mortality risk and guiding early warning systems. Our findings highlight the dominant role of hydrological variability in ecosystem degradation and offer a threshold-based framework for early detection of mortality risks. This approach provides insights into managing coastal forest resilience amid accelerating sea level rise. Full article

In response to the problem of complex and variable loads on wind turbine gearbox bearing in working conditions, as well as the limited amount of sound data making fault identification difficult, this study focuses on sound signals and proposes an intelligent diagnostic method using deep learning. By adding the CBAM module in ResNeXt to enhance the model’s attention to important features and combining it with the Arcloss loss function to make the model learn more discriminative features, the generalization ability of the model is strengthened. We used a fine-tuning transfer learning strategy, transferring pre-trained model parameters to the CBAM-ResNeXt50-ArcLoss model and training with an extracted Mel spectrogram of sound signals to extract and classify audio features of the wind turbine gearbox. Experimental validation of the proposed method on collected sound signals showed its effectiveness and superiority. Compared to CNN, ResNet50, ResNeXt50, and CBAM-ResNet50 methods, the CBAM-ResNeXt50-ArcLoss model achieved improvements of 13.3, 3.6, 2.4, and 1.3, respectively. Through comparison with classical algorithms, we demonstrated that the research method proposed in this study exhibits better diagnostic capability in classifying wind turbine gearbox sound signals. Full article

The cross-sectional dimensions of structural elements in a structure are design elements that need to be carefully designed and are related to the stiffness of the structure. Various optimization processes are applied to determine the optimum cross-sectional dimensions of beams or columns in structures. By repeating the optimization processes for multiple load scenarios, it is possible to create a data set that shows the optimum design section properties. However, this step means repeating the same processes to produce the optimum cross-sectional dimensions. Artificial intelligence technology offers a short-cut solution to this by providing the opportunity to train itself with previously generated optimum cross-sectional dimensions and infer new cross-sectional dimensions. By processing the data, the artificial neural network can generate models that predict the cross-section for a new structural element. In this study, an optimization process is applied to a simple tubular column and an I-section beam, and the results are compiled to create a data set that presents the optimum section dimensions as a class. The harmony search (HS) algorithm, which is a metaheuristic method, was used in optimization. An artificial neural network (ANN) was created to predict the cross-sectional dimensions of the sample structural elements. The neural architecture search (NAS) method, which incorporates many metaheuristic algorithms designed to search for the best artificial neural network architecture, was applied. In this method, the best values of various parameters of the neural network, such as activation function, number of layers, and neurons, are searched for in the model with a tool called HyperNetExplorer. Model metrics were calculated to evaluate the prediction success of the developed model. An effective neural network architecture for column and beam elements is obtained. Full article

Deep neural network (DNN) hardware (HW) accelerators have achieved great success in improving DNNs’ performance and efficiency. One key reason is the dataflow in executing a DNN layer, including on-chip data partitioning, computation parallelism, and scheduling policy, which have large impacts on latency and energy consumption. Unlike prior works that required considerable efforts from HW engineers to design suitable dataflows for different DNNs, this work proposes an efficient data-centric approach, named Dataflow Code Propagation (DCP), to automatically find the optimal dataflow for DNN layers in seconds without human effort. It has several attractive benefits that prior studies lack, including the following: (i) We translate the HW dataflow configuration into a code representation in a unified dataflow coding space, which can be optimized by back-propagating gradients given a DNN layer or network. (ii) DCP learns a neural predictor to efficiently update the dataflow codes towards the desired gradient directions to minimize various optimization objectives, e.g., latency and energy. (iii) It can be easily generalized to unseen HW configurations in a zero-shot or few-shot learning manner. For example, without using additional training data, Extensive experiments on several representative models such as MobileNet, ResNet, and ViT show that DCP outperforms its counterparts in various settings. Full article

As Android malware grows increasingly sophisticated, traditional detection methods struggle to keep pace, creating an urgent need for robust, interpretable, and real-time solutions to safeguard mobile ecosystems. This study introduces YoloMal-XAI, a novel deep learning framework that transforms Android application files into RGB image representations by mapping DEX (Dalvik Executable), Manifest.xml, and Resources.arsc files to distinct color channels. Evaluated on the CICMalDroid2020 dataset using YOLO11 pretrained classification models, YoloMal-XAI achieves 99.87% accuracy in binary classification and 99.56% in multi-class classification (Adware, Banking, Riskware, SMS, and Benign). Compared to ResNet-50, GoogLeNet, and MobileNetV2, YOLO11 offers competitive accuracy with at least 7× faster training over 100 epochs. Against YOLOv8, YOLO11 achieves comparable or superior accuracy while reducing training time by up to 3.5×. Cross-corpus validation using Drebin and CICAndMal2017 further confirms the model’s generalization capability on previously unseen malware. An ablation study highlights the value of integrating DEX, Manifest, and Resources components, with the full RGB configuration consistently delivering the best performance. Explainable AI (XAI) techniques—Grad-CAM, Grad-CAM++, Eigen-CAM, and HiRes-CAM—are employed to interpret model decisions, revealing the DEX segment as the most influential component. These results establish YoloMal-XAI as a scalable, efficient, and interpretable framework for Android malware detection, with strong potential for future deployment on resource-constrained mobile devices. Full article

Research on raw materials for Al₂O₃-SiC-C refractory castables used in blast furnace troughs is relatively well established. However, gaps remain in both laboratory and industrial trials concerning the performance of castables incorporating SiC-modified flake graphite and alternative carbon sources. This study investigated the sintering behavior, mechanical properties, and service performance of Al₂O₃-SiC-C castables utilizing varying contents of modified flake graphite, pitch, and carbon black as carbon sources. Samples were characterized using SEM, XRD, and EDS for phase composition and microstructural morphology analysis. Key findings revealed that the thermal expansion mismatch between the SiC coating and flake graphite in SiC-modified graphite generated a microcrack-toughening effect. This effect, combined with the synergistic reinforcement from both components, enhanced the mechanical properties. The SiC modification layer improved the wettability and oxidation resistance of the flake graphite. This modified graphite further contributed to enhanced erosion resistance through mechanisms of matrix pinning and crack deflection within the microstructure. However, the microcracks induced by thermal mismatch concurrently reduced erosion resistance, resulting in an overall limited net improvement in erosion resistance attributable to the modified graphite. Specimens containing 1 wt.% modified flake graphite exhibited the optimal overall performance. During industrial trials, this formulation unexpectedly demonstrated a water reduction mechanism requiring further investigation. Full article

Combining Organic Rankine Cycles (ORC) with cooling cycles offers a promising approach to achieving greater outputs within a single system. In this study, a novel directly combined ORC-VCC system has been designed to not only meet the cooling demand using a geothermal heat source but also generate power. The proposed novel ORC-VCC system has been analyzed for its energetic performance using four selected fluids: R290, R600a, R601, and R1234ze(E). Parametric analysis has been conducted to investigate the effects of parameters of heat source temperature, heat source mass flow rate, cooling capacities, condenser temperature, ORC evaporator temperature, pinch point temperature difference and isentropic efficiencies on net power production. Among the working fluids, R290 has provided the highest net power production under all conditions in which it was available to operate. Additionally, the results have been analyzed concerning a reference cycle for comparative evaluation. The proposed novel cycle has outperformed the reference cycle in all investigated cases in terms of net power production such as demonstrating an improvement of approximately from 8.7% to 57.8% in geothermal heat source temperature investigations. Similar improvements have been observed over the reference cycle at lower heat source mass flow rates, where net power increases by up to 50.8%. Full article

This study presents a comparative analysis of the annual performances of stationary and dual-axis sun-tracked photovoltaic–thermal (PVT) systems. The experimental research was conducted at a demonstration site in Oświęcim, Poland, where both systems were evaluated in terms of electricity and heat production. The test installation consisted of thirty stationary PVT modules and five dual-axis sun-tracking systems, each equipped with six PV modules. An innovative cooling system was developed for the PVT modules, consisting of a surface-mounted heat sink installed on the rear side of each panel. The system includes embedded tubes through which a cooling fluid circulates, enabling efficient heat recovery. The results indicated that the stationary PVT system outperformed a conventional fixed PV installation, whose expected output was estimated using PVGIS data. Specifically, the stationary PVT system generated 26.1 kWh/m² more electricity annually, representing a 14.8% increase. The sun-tracked PVT modules yielded even higher gains, producing 42% more electricity than the stationary system, with particularly notable improvements during the autumn and winter seasons. After accounting for the electricity consumed by the tracking mechanisms, the sun-tracked PVT system still delivered a 34% higher net electricity output. Moreover, it enhanced the thermal energy output by 85%. The findings contribute to the ongoing development of high-performance PVT systems and provide valuable insights for their optimal deployment in various climatic conditions, supporting the broader integration of renewable energy technologies in building energy systems. Full article

Background/Objectives: Melanoma is an aggressive type of skin cancer that poses serious health risks if not detected in its early stages. Although early diagnosis enables effective treatment, delays can result in life-threatening consequences. Traditional diagnostic processes predominantly rely on the subjective expertise of dermatologists, which can lead to variability and time inefficiencies. Consequently, there is an increasing demand for automated systems that can accurately classify melanoma lesions and retrieve visually similar cases to support clinical decision-making. Methods: This study proposes a transfer learning (TL)-based deep learning (DL) framework for the classification of melanoma images and the enhancement of content-based image retrieval (CBIR) systems. Pre-trained models including DenseNet121, InceptionV3, Vision Transformer (ViT), and Xception were employed to extract deep feature representations. These features were integrated using a weighted fusion strategy and classified through an Ensemble learning approach designed to capitalize on the complementary strengths of the individual models. The performance of the proposed system was evaluated using classification accuracy and mean Average Precision (mAP) metrics. Results: Experimental evaluations demonstrated that the proposed Ensemble model significantly outperformed each standalone model in both classification and retrieval tasks. The Ensemble approach achieved a classification accuracy of 95.25%. In the CBIR task, the system attained a mean Average Precision (mAP) score of 0.9538, indicating high retrieval effectiveness. The performance gains were attributed to the synergistic integration of features from diverse model architectures through the ensemble and fusion strategies. Conclusions: The findings underscore the effectiveness of TL-based DL models in automating melanoma image classification and enhancing CBIR systems. The integration of deep features from multiple pre-trained models using an Ensemble approach not only improved accuracy but also demonstrated robustness in feature generalization. This approach holds promise for integration into clinical workflows, offering improved diagnostic accuracy and efficiency in the early detection of melanoma. Full article

This paper aims to find an efficient optimization algorithm to bring down the cost function without compromising the stability of the system and respect the operational constraints of the Hybrid Renewable Energy System. To accomplish this, MATLAB simulations were carried out using three optimization techniques: Grey Wolf Optimization (GWO), Teaching–Learning-Based Optimization (TLBO), and Multi-Objective Particle Swarm Optimization (MOPSO). The study compared their outcomes to identify which method yielded the most effective performance. The research included a statistical analysis to evaluate how consistently and stably each optimization method performed. The analysis revealed optimal values for the output power of photovoltaic systems (PVs), wind turbines (WTs), diesel generator capacity (DGs), and battery storage (BS). A one-year period was used to confirm the optimized configuration through the analysis of capital investment and fuel consumption. Among the three methods, GWO achieved the best fitness value of 0.24593 with an LPSP of 0.12528, indicating high system reliability. MOPSO exhibited the fastest convergence behaviour. TLBO yielded the lowest Net Present Cost (NPC) of 213,440 and a Cost of Energy (COE) of 1.91446/kW, though with a comparatively higher fitness value of 0.26628. The analysis suggests that GWO is suitable for applications requiring high reliability, TLBO is preferable for cost-sensitive solutions, and MOPSO is advantageous for obtaining quick, approximate results. Full article

Accurate identification of predator–pest relationships is essential for implementing effective and sustainable biological control in agriculture. However, existing image-based methods struggle to recognize insect co-occurrence under complex field conditions, limiting their ecological applicability. To address this challenge, we propose a hybrid deep learning framework that integrates convolutional neural networks (CNNs) and Transformer architectures for multi-label recognition of predator–pest combinations. The model leverages a novel co-occurrence attention mechanism to capture semantic relationships between insect categories and employs a pairwise label matching loss to enhance ecological pairing accuracy. Evaluated on a field-constructed dataset of 5,037 images across eight categories, the model achieved an F1-score of 86.5%, mAP50 of 85.1%, and demonstrated strong generalization to unseen predator–pest pairs with an average F1-score of 79.6%. These results outperform several strong baselines, including ResNet-50, YOLOv8, and Vision Transformer. This work contributes a robust, interpretable approach for multi-object ecological detection and offers practical potential for deployment in smart farming systems, UAV-based monitoring, and precision pest management. Full article

Channels with three standard symmetrical sections and one asymmetric section are mounted as cantilever beams with the web oriented vertically. A classical solution to the analysis of stress in each thin-walled cantilever channel is provided using the principle of wall shear flow superposition. The latter is coupled with a further superposition between axial stress arising from bending and from the constraint placed on free warping imposed at the fixed end. Closed solutions for design are tabulated for the net shear stress and the net axial stress at points around any section within the length. Stress distributions thus derived serve as a benchmark structure for alternative numerical solutions and for experimental investigations. The conversion of the transverse free end-loading applied to a thin-walled cantilever channel into the shear and axial stress that it must bear is outlined. It is shown that the point at which this loading is applied within the cross-section is crucial to this stress conversion. When a single force is applied to an arbitrary point at the free-end section, three loading effects arise generally: bending, flexural shear and torsion. The analysis of each effect requires that this force’s components are resolved to align with the section’s principal axes. These forces are then considered in reference to its centroid and to its shear centre. This shows that axial stress arises directly from bending and from the constraint imposed on free warping at the fixed end. Shear stress arises from flexural shear and also from torsion with a load offset from the shear centre. When the three actions are combined, the net stresses of each action are considered within the ability of the structure to resist collapse from plasticity and buckling. The novelty herein refers to the presentation of the shear flow calculations within a thin wall as they arise from an end load offset from the shear centre. It is shown how the principle of superposition can be applied to individual shear flow and axial stress distributions arising from flexural bending, shear and torsion. Therein, the new concept of a ‘trans-moment’ appears from the transfer in moments from their axes through centroid G to parallel axes through shear centre E. The trans-moment complements the static equilibrium condition, in which a shift in transverse force components from G to E is accompanied by torsion and bending about the flexural axis through E. Full article