Search Results (10,710)

This study aimed to implement an effective power prediction method to support the optimal management of the 30 MW Nagréongo solar photovoltaic (PV) plant in Burkina Faso. Initially, the performance of the PV plant was assessed by an external consultant based on data recorded in 2023 and 2024, revealing efficiency with a performance ratio (PR) of 73.73% in 2023, which improved to 77.43% in 2024. To forecast the plant’s power output, several deep learning models—namely LSTM, a GRU, LSTM-GRU, and an RNN—were applied using historical power data recorded at five-minute intervals during the 2024 periods of January–February; March–April; and July–August. All the deep learning models achieved accurate short-term forecasting for the 30 MW Nagréongo PV plant, with the seasonal performance shaped by the Sahelian weather regimes. The GRU performed best during the dry season (nRMSE ≈ 4%) and LSTM excelled in the hot months (nRMSE ≈ 2%), while the hybrid LSTM-GRU model proved most robust under rainy-season variability. Overall, the forecasting errors remained within 2–5% of plant capacity, demonstrating the suitability of these architectures for grid integration and operational planning in Sahel PV systems. Full article

Autoimmune diseases constitute a broadly prevalent category of disorders. Conventional computer-aided diagnostic (CAD) techniques rely on large volumes of data paired with reliable annotations. However, the diverse symptomatology and diagnostic complexity of autoimmune diseases result in a scarcity of reliably labeled biological samples. In this study, we propose a pseudo-label-based conditional domain adversarial network (CDAN-PL) framework by integrating Raman spectroscopy with domain adaptation technology, enabling label-free unsupervised transfer diagnosis of diseases. Compared to traditional unsupervised domain adaptation techniques, our CDAN-PL framework generates reliable pseudo-labels to ensure the robust implementation of conditional adversarial methods. Additionally, its spectral data-adaptive feature extraction techniques further solidify the model’s superiority in Raman spectroscopy-based disease diagnosis. CDAN-PL exhibits excellent performance in homologous transfer tasks, achieving an average accuracy of 92.3%—surpassing the baseline models’ 80.81% and 86.4%. Moreover, it attains an average accuracy of 90.05% in non-homologous transfer tasks, further validating its generalization capability. Full article

Short-term passenger flow prediction provides critical data-driven support for optimizing resource allocation, guiding passenger mobility, and enhancing risk response capabilities in urban rail transit systems. To further improve prediction accuracy, this study proposes a hybrid SMA-VMD-Informer-BiLSTM prediction model. Addressing the challenge of error propagation caused by non-stationary components (e.g., noise and abrupt fluctuations) in conventional passenger flow signals, the Variational Mode Decomposition (VMD) method is introduced to decompose raw flow data into multiple intrinsic mode functions (IMFs). A Slime Mould Algorithm (SMA)-based optimization mechanism is designed to adaptively tune VMD parameters, effectively mitigating mode redundancy and information loss. Furthermore, to circumvent error accumulation inherent in serial modeling frameworks, a parallel prediction architecture is developed: the Informer branch captures long-term dependencies through its ProbSparse self-attention mechanism, while the Bidirectional Long Short-Term Memory (BiLSTM) network extracts localized short-term temporal patterns. The outputs of both branches are fused via a fully connected layer, balancing global trend adherence and local fluctuation characterization. Experimental validation using historical entry flow data from Weihouzhuang Station on Xi’an Metro demonstrated the superior performance of the SMA-VMD-Informer-BiLSTM model. Compared to benchmark models (CNN-BiLSTM, CNN-BiGRU, Transformer-LSTM, ARIMA-LSTM), the proposed model achieved reductions of 7.14–53.33% in $f_{mse}$, 3.81–31.14% in $f_{rmse}$, and 8.87–38.08% in $f_{mae}$, alongside a 4.11–5.48% improvement in $R^2$. Cross-station validation across multiple Xi’an Metro hubs further confirmed robust spatial generalizability, with prediction errors bounded within $f_{mse}$: 0.0009–0.01, $f_{rmse}$: 0.0303–0.1, $f_{mae}$: 0.0196–0.0697, and $R^2$: 0.9011–0.9971. Furthermore, the model demonstrated favorable predictive performance when applied to forecasting passenger inflows at multiple stations in Nanjing and Zhengzhou, showcasing its excellent spatial transferability. By integrating multi-level, multi-scale data processing and adaptive feature extraction mechanisms, the proposed model significantly mitigates error accumulation observed in traditional approaches. These findings collectively indicate its potential as a scientific foundation for refined operational decision-making in urban rail transit management, thereby significantly promoting the sustainable development and long-term stable operation of urban rail transit systems. Full article

Crack detection and analysis are essential for maintaining the stability and longevity of infrastructure; however, traditional manual inspections or simple image processing techniques are inefficient. To address this, automated crack segmentation using deep learning is being actively researched. This study proposes a hybrid model combining U-Net and a Vision Transformer to enhance the accuracy of crack segmentation. The proposed model is based on U-Net’s encoder–decoder architecture and integrates a Convolutional Neural Network (CNN), which is strong in local feature extraction, with a Vision Transformer, which excels at capturing global features and long-range dependencies, to effectively learn complex crack patterns. Experimental results on the CrackSeg9k dataset show that the proposed model achieves a mean Intersection over Union (mIoU) of 0.7184, demonstrating superior segmentation performance compared to other models like the conventional U-Net and Attention U-Net. This indicates that the proposed hybrid approach successfully leverages both local and global features, proving its effectiveness in segmenting complex and irregular crack patterns. Full article

Currently, the customs inspection of wood-boring pests in timber still primarily relies on manual visual inspection, which involves observing insect holes on the timber surface and splitting the timber for confirmation. However, this method has significant drawbacks such as long detection time, high labor cost, and accuracy relying on human experience, making it difficult to meet the practical needs of efficient and intelligent customs quarantine. To address this issue, this paper develops a rapid identification system based on the peristaltic signals of wood-boring pests through the PyQt framework. The system employs a deep learning model with multi-attention mechanisms, namely the Residual Denoising Vision Network (RDVNet). Firstly, a LabVIEW-based hardware–software system is used to collect pest peristaltic signals in an environment free of vibration interference. Subsequently, the original signals are clipped, converted to audio format, and mixed with external noise. Then signal features are extracted through three cepstral feature extraction methods Mel-Frequency Cepstral Coefficients (MFCC), Power-Normalized Cepstral Coefficients (PNCC), and RelAtive SpecTrAl-Perceptual Linear Prediction (RASTA-PLP) and input into the model. In the experimental stage, this paper compares the denoising module of RDVNet (de-RDVNet) with four classic denoising models under five noise intensity conditions. Finally, it evaluates the performance of RDVNet and four other noise reduction classification models in classification tasks. The results show that PNCC has the most comprehensive feature extraction capability. When PNCC is used as the model input, de-RDVNet achieves an average peak signal-to-noise ratio (PSNR) of 29.8 and a Structural Similarity Index Measure (SSIM) of 0.820 in denoising experiments, both being the best among the comparative models. In classification experiments, RDVNet has an average F1 score of 0.878 and an accuracy of 92.8%, demonstrating the most excellent performance. Overall, the application of this system in customs timber quarantine can effectively improve detection efficiency and reduce labor costs and has significant practical value and promotion prospects. Full article

Predicting favorable reservoirs controlled by source-to-sink systems in rift basins is a current research focus. Using seismic, core, drilling, logging, and thin-section data, this paper systematically identifies fan types and their reservoir characteristics controlled by two boundary faults in the southern steep-slope zone of Wushi Sag, Beibuwan Basin, South China Sea. The analysis compares differences in (1) source–channel–margin–sink systems and (2) diagenetic facies, dividing the sink area into migratory and progradational fans. Results show that migratory fans are associated with denudation. Sediments migrate through wide, deep “V”-shaped valleys, forming fan deltas that are large in area but short in progradation. Lithology is dominated by fine sandstone with siltstone interbeds, reservoirs’ diagenetic evolution is weak, pores are mainly primary, and Type I-II reservoirs are developed. In contrast, progradational fans reflect weaker source area denudation, with sediments prograding through narrow, shallow “U”-shaped valleys. These form broom-shaped fan deltas that are small in area but long in progradation, with lithology dominated by fine sandstone interbedded with mudstone. Reservoirs show strong diagenetic evolution, well-developed secondary porosity, and Type II-III reservoirs. Reservoir prediction models indicate that high-quality migratory reservoirs are large, with excellent physical properties and oil-bearing capacity, mainly in fan stacking zones. High-quality progradational reservoirs are concentrated in the fan midsections, with strong cementation and secondary porosity. These findings provide a theoretical basis for reservoir prediction and oil and gas exploration in the southern steep-slope zone of Wushi Sag. Full article

Short-term building cooling load prediction is crucial for optimizing building energy management and promoting sustainability. While data-driven models excel in this task, their performance heavily depends on the input feature set. Feature selection must balance predictive accuracy (relevance) and model simplicity (minimal redundancy), a challenge that existing methods often address incompletely. This study proposes a novel feature optimization framework that integrates the Maximum Information Coefficient (MIC) to measure non-linear relevance and the Maximum Relevance Minimum Redundancy (MRMR) principle to control redundancy. The proposed MRMR-MIC method was evaluated against four benchmark feature selection methods using three predictive models in a simulated office building case study. The results demonstrate that MRMR-MIC significantly outperforms other methods: it reduces the feature dimensionality from over 170 to merely 40 variables while maintaining a prediction error below 5%. This represents a substantial reduction in model complexity without sacrificing accuracy. Furthermore, the selected features cover a more comprehensive and physically meaningful set of attributes compared to other redundancy-control methods. The study concludes that the MRMR-MIC framework provides a robust, systematic methodology for identifying essential feature variables, which can not only enhance the performance of prediction models, but also offer practical guidance for designing cost-effective data acquisition systems in real-building applications. Full article

Customer experience is central to omnichannel marketing and is increasingly the focus of research attention. However, few studies have focused on the development of excellent omnichannel customer experiences. To fill this research gap, we examined the drivers of these experiences from a customer journey design perspective. Partial least squares structural equation modeling (PLS-SEM) and partial least squares multigroup analysis (PLS-MGA) were employed to analyze 775 valid omnichannel customers’ data, which were collected through an online survey. The findings suggest that the thematic cohesion, consistency, context sensitivity, and connectivity of touchpoints play an important role in improving omnichannel customer experience. Value co-creation behavior can be significantly increased by affective, cognitive, physical, relational, and symbolic experiences, but not by sensorial omnichannel customer experiences. These results not only contribute to the knowledge of omnichannel customer experiences, customer journeys, and value co-creation behavior, but also offer useful advice for omnichannel marketers. Full article

This paper proposes a multi-sensor data-fusion-based method for real-scene 3D reconstruction and digital twin visualization of coal mine tunnels, aiming to address issues such as low accuracy in non-photorealistic modeling and difficulties in feature object recognition during traditional coal mine digitization processes. The research employs cubemap-based mapping technology to project acquired real-time tunnel images onto six faces of a cube, combined with navigation information, pose data, and synchronously acquired point cloud data to achieve spatial alignment and data fusion. On this basis, inner/outer corner detection algorithms are utilized for precise image segmentation, and a point cloud region growing algorithm integrated with information entropy optimization is proposed to realize complete recognition and segmentation of tunnel planes (e.g., roof, floor, left/right sidewalls) and high-curvature feature objects (e.g., ventilation ducts). Furthermore, geometric dimensions extracted from segmentation results are used to construct 3D models, and real-scene images are mapped onto model surfaces via UV (U and V axes of texture coordinate) texture mapping technology, generating digital twin models with authentic texture details. Experimental validation demonstrates that the method performs excellently in both simulated and real coal mine environments, with models capable of faithfully reproducing tunnel spatial layouts and detailed features while supporting multi-view visualization (e.g., bottom view, left/right rotated views, front view). This approach provides efficient and precise technical support for digital twin construction, fine-grained structural modeling, and safety monitoring of coal mine tunnels, significantly enhancing the accuracy and practicality of photorealistic 3D modeling in intelligent mining applications. Full article

Collisions between ships and sea ice pose a significant threat to maritime safety, making it essential to detect sea ice and perform safety-oriented path planning for polar navigation. This paper utilizes an optimized You Only Look Once version 5 (YOLOv5) model, designated as YOLOv5-ICE, for the detection of sea ice in satellite imagery, with the resultant detection data being employed to input obstacle coordinates into a ship path planning system. The enhancements include the Squeeze-and-Excitation (SE) attention mechanism, improved spatial pyramid pooling, and the Flexible ReLU (FReLU) activation function. The improved YOLOv5-ICE shows enhanced performance, with its mAP increasing by 3.5% compared to the baseline YOLOv5 and also by 1.3% compared to YOLOv8. YOLOv5-ICE demonstrates robust performance in detecting small sea ice targets within large-scale satellite images and excels in high ice concentration regions. For path planning, the Any-Angle Path Planning on Grids algorithm is applied to simulate routes based on detected sea ice floes. The objective function incorporates the path length, number of ship turns, and sea ice risk value, enabling path planning under varying ice concentrations. By integrating detection and path planning, this work proposes a novel method to enhance navigational safety in polar regions. Full article

In Ecuador, the transmission of dengue has steadily increased in recent decades, particularly in coastal cities like Manta, where the conditions are favorable for the proliferation of the Aedes aegypti mosquito. The objective of this study was to model the spatial distribution of dengue transmission risk in Manta, a coastal city in Ecuador with consistently high incidence rates. A total of 148 georeferenced dengue cases from 2018 to 2021 were collected, and environmental and socioeconomic variables were incorporated into a maximum entropy model (MaxEnt). Additionally, climate and social zoning were performed using a multi-criteria model in TerrSet. The MaxEnt model demonstrated excellent predictive ability (training AUC = 0.916; test AUC = 0.876) and identified population density, sewer system access, and distance to rivers as the primary predictors. Three high-risk clusters were identified in the southern, northwestern, and northeastern parts of the city, while the coastal strip showed lower suitability due to low rainfall and vegetation. These findings reveal the strong spatial heterogeneity of dengue risk at the neighborhood level and provide operational information for targeted interventions. This approach can support more efficient surveillance, resource allocation, and community action in coastal urban areas affected by vector-borne diseases. Full article

In order to tackle the issues of poor mobility and unstable traction of electric vehicles on sandy landscapes, this research develops a high-accuracy numerical model for wheel–sand interaction relying on the Discrete Element Method (DEM). An innovative parameter calibration procedure is proposed herein, which optimizes the sand contact parameters. This reduces the error between the simulated and measured angles of repose to merely 1.2% and substantially improves the model’s reliability. The model was then used to systematically compare the performance of a 205/55 R16 slick tire with a treaded tire on sand. Simulations demonstrate that at a 30% slip ratio, the treaded tire exhibited significantly higher traction and greater sinkage than the slick tire. This indicates that tread patterns enhance traction mechanically by increasing the contact area and promoting shear deformation of the sand. The trends of traction with slip ratio and the corresponding sand flow patterns showed excellent agreement with experimental observations, which validated the simulation approach. This research provides an efficient and accurate tool for evaluating tire-sand interaction, providing critical support for the design and control of electric vehicles on complex terrains. Full article

Generating non-standard fonts, such as running script (e.g., XingShu), poses significant challenges due to their high stroke continuity, structural flexibility, and stylistic diversity, which traditional component-based prior knowledge methods struggle to model effectively. While diffusion models excel at capturing continuous feature spaces and stroke variations through iterative denoising, they face critical limitations: (1) style leakage, where large stylistic differences lead to inconsistent outputs due to noise interference; (2) structural distortion, caused by the absence of explicit structural guidance, resulting in broken strokes or deformed glyphs; and (3) style confusion, where similar font styles are inadequately distinguished, producing ambiguous results. To address these issues, we propose a novel skeleton-guided diffusion model with three key innovations: (1) a skeleton-constrained style rendering module that enforces semantic alignment and balanced energy constraints to amplify critical skeletal features, mitigating style leakage and ensuring stylistic consistency; (2) a cross-scale skeleton preservation module that integrates multi-scale glyph skeleton information through cross-dimensional interactions, effectively modeling macro-level layouts and micro-level stroke details to prevent structural distortions; (3) a contrastive style refinement module that leverages skeleton decomposition and recombination strategies, coupled with contrastive learning on positive and negative samples, to establish robust style representations and disambiguate similar styles. Extensive experiments on diverse font datasets demonstrate that our approach significantly improves the generation quality, achieving superior style fidelity, structural integrity, and style differentiation compared to state-of-the-art diffusion-based font generation methods. Full article

Research Problem and Gap: Live streaming sales rely heavily on streamers, with both genuine and AI-generated virtual streamers gaining popularity. However, these streamer types possess contrasting capabilities. Genuine streamers are superior at building trust and reducing product valuation uncertainty but have limited reach, while virtual streamers excel at broad audience engagement but are less effective at mitigating uncertainty, often leading to higher product return rates. This trade-off creates a critical strategic gap; that is, brand firms lack clear guidance on whether to invest in genuine or virtual streamers or adopt a hybrid approach for their live channels. Objective and Methods: This study addresses this gap by developing a theoretical analytical model to determine a monopolistic brand firm’s optimal streamer strategy among three options: using only a genuine streamer, only a virtual streamer, or a combination of the two (hybrid approach). The researchers model consumer utility, factoring in uncertainty and the streamers’ differential impact on reach, to derive optimal decisions on pricing and streamer selection. Results and Findings: The analysis yields several key findings with direct managerial implications. First, while a hybrid strategy leverages the complementary strengths of both streamer types, its success depends on employing high-quality streamers; in other words, this strategy does not justify settling for inferior talent of either type. Second, employing a virtual streamer requires a moderate price reduction to compensate for higher consumer uncertainty and prevent high profit-eroding return rates. Third, a pure strategy (only genuine or only virtual) is optimal only when that streamer type has a significant cost advantage. Otherwise, the hybrid strategy tends to be the most profitable. Moreover, higher product return costs directly diminish the viability of virtual streamers, making a genuine or hybrid strategy more attractive for products with expensive return processes. Conclusions: The results provide a clear framework for brand firms—that is, the choice of streamer is a strategic decision intertwined with pricing and product return costs. Firms should pursue a hybrid strategy not as a compromise but as a premium approach, use targeted pricing to mitigate the risk of virtual streamers, and avoid virtual options altogether for products with high return costs. Full article

Sintered nano-silver paste is widely used in electronic packaging due to its excellent thermal and electrical conductivity. A phenomenological variable-order fractional constitutive model has been developed to characterize the evolution of its mechanical properties, incorporating dependencies on both temperature and strain rate. Based on the Weissenberg number and classical Arrhenius equation, a formulation for relaxation time with temperature and strain rate dependence has been proposed. A temperature- and rate-sensitive fractional order is introduced to capture the coupled influences of thermal and strain rate effects. Furthermore, the effects of temperature and the strain rate on the elastic modulus and relaxation time are quantitatively described through established coupling criteria. Simulation results demonstrate that the proposed model offers high accuracy and strong predictive capability. Comparisons with the classical Anand model highlight the effectiveness of the variable-order fractional model, particularly at lower temperatures. Full article