Physics-informed super-resolution and forecasting method based on inaccurate partial differential equations and partial observation

Rapid prediction of cellulose, hemicellulose, and lignin content in biomass using FTIR based on transfer learning

The Bayesian approach to inverse problems, in which the posterior probability distribution on an unknown field is sampled for the purposes of computing posterior expectations of quantities of interest, is starting to become computationally feasible for partial differential equation (PDE) inverse problems. Balancing the sources of error arising from finite-dimensional approximation of the unknown field, the PDE forward solution map and the sampling of the probability space under the posterior distribution are essential for the design of efficient computational Bayesian methods for PDE inverse problems. We study Bayesian inversion for a model elliptic PDE with an unknown diffusion coefficient. We provide complexity analyses of several Markov chain Monte Carlo (MCMC) methods for the efficient numerical evaluation of expectations under the Bayesian posterior distribution, given data δ. Particular attention is given to bounds on the overall work required to achieve a prescribed error level ε. Specifically, we first bound the computational complexity of ‘plain’ MCMC, based on combining MCMC sampling with linear complexity multi-level solvers for elliptic PDE. Our (new) work versus accuracy bounds show that the complexity of this approach can be quite prohibitive. Two strategies for reducing the computational complexity are then proposed and analyzed: first, a sparse, parametric and deterministic generalized polynomial chaos (gpc) ‘surrogate’ representation of the forward response map of the PDE over the entire parameter space, and, second, a novel multi-level Markov chain Monte Carlo strategy which utilizes sampling from a multi-level discretization of the posterior and the forward PDE. For both of these strategies, we derive asymptotic bounds on work versus accuracy, and hence asymptotic bounds on the computational complexity of the algorithms. In particular, we provide sufficient conditions on the regularity of the unknown coefficients of the PDE and on the approximation methods used, in order for the accelerations of MCMC resulting from these strategies to lead to complexity reductions over ‘plain’ MCMC algorithms for the Bayesian inversion of PDEs.

Machine learning has demonstrated significant application potential in rolling bearing fault detection. However, traditional deep learning approaches typically depend on large-scale labeled datasets and are limited to identifying a single fault type, which poses challenges in meeting the complex fault diagnosis in real-world industrial scenarios, particularly under small sample conditions. To address these issues, this study proposes a multi-task attention fault diagnosis framework, convolutional attention neural network by neural discriminant dimension reduction (NDDR-CANN). The model employs multiple task-specific neural networks to extract distinct features such as fault type and severity, respectively, and achieves adaptive feature sharing across tasks by NDDR, thereby facilitating the transfer and complementarity of task-related knowledge and enhancing the model's generalization capability and predictive accuracy. Furthermore, by integrating a convolutional block attention module, the model can focus on salient features across channel and spatial dimensions, thereby improving feature discrimination. Experimental validation on the CWRU bearing dataset demonstrates that the proposed model exhibits robust effectiveness and adaptability under various fault conditions and small sample scenarios. Comparative experimental results further confirm that NDDR-CANN outperforms current mainstream few-shot fault diagnosis methodologies.

Scene flow estimation aims to predict 3D motion from consecutive point cloud frames, which is of great interest in autonomous driving field. Existing methods face challenges such as insufficient spatio-temporal modeling and inherent loss of fine-grained feature during voxelization. However, the success of Mamba, a representative state space model (SSM) that enables global modeling with linear complexity, provides a promising solution. In this paper, we propose MambaFlow, a novel scene flow estimation network with a mamba-based decoder. It enables deep interaction and coupling of spatio-temporal features using a well-designed backbone. Innovatively, we steer the global attention modeling of voxel-based features with point offset information using an efficient Mamba-based decoder, learning voxel-to-point patterns that are used to devoxelize shared voxel representations into point-wise features. To further enhance the model's generalization capabilities across diverse scenarios, we propose a novel scene-adaptive loss function that automatically adapts to different motion patterns. Extensive experiments on the Argoverse 2 benchmark demonstrate that MambaFlow achieves state-of-the-art performance with real-time inference speed among existing works, enabling accurate flow estimation in real-world urban scenarios. The code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/SCNU-RISLAB/MambaFlow</uri>.

Reconstructing as‐built building information modeling from point clouds in underground garages holds great potential for enhancing facility management. However, this task is particularly challenging due to the complex and diverse architectural and mechanical, electrical, and plumbing (MEP) components present in such environments. Moreover, there is no publicly available dataset and no dedicated semantic segmentation algorithm for underground garages environments. To address this gap, this paper first builds an expert‐labeled underground garage dataset, which includes 10 categories of components. Subsequently, this paper introduces GarageNet, a deep learning (DL) network designed for semantic segmentation of point clouds for scenes including both building and MEP components. GarageNet integrates a residual squeeze‐and‐excitation module to enhance layer and channel connection and a multi‐head attention feature aggregation module to capture local geometric structures. The results indicate that the GarageNet achieved a high overall accuracy of 95.09% and a mean intersection over union of 87.15%, surpassing other DL algorithms such as PointNext. Ablation studies and cross‐validation further demonstrate the model's reliability and generalization capability.

This paper pioneers a novel approach in electromagnetic (EM) system analysis by synergistically combining Bayesian Neural Networks (BNNs) informed by Latin Hypercube Sampling (LHS) with advanced thermal-mechanical surrogate modeling within COMSOL simulations for high-frequency low-pass filter modeling. Our methodology transcends traditional EM characterization by integrating physical dimension variability, thermal effects, mechanical deformation, and real-world operational conditions, thereby achieving a significant leap in predictive modeling fidelity. Through rigorous evaluation using Mean Squared Error (MSE), Maximum Learning Error (MLE), and Maximum Test Error (MTE) metrics, as well as comprehensive validation on unseen data, the model's robustness and generalization capability is demonstrated. This research challenges conventional methods, offering a nuanced understanding of multiphysical phenomena to enhance reliability and resilience in electronic component design and optimization. The integration of thermal variables alongside dimensional parameters marks a novel paradigm in filter performance analysis, significantly improving simulation accuracy. Our findings not only contribute to the body of knowledge in EM diagnostics and complex-environment analysis but also pave the way for future investigations into the fusion of machine learning with computational physics, promising transformative impacts across various applications, from telecommunications to medical devices.

Aiming at the problem that the boiler thermal efficiency can't be on-line calculated in the field, data collected are divided into training data and testing data by researching on the 1000MW unit of Sanbaimen Power Plant in Datang Chaozhou, and then prediction model for boiler thermal efficiency is established by applying support vector regression and particle swarm optimization. This method uses optimization function of particle swarm algorithm to optimize the parameters C and g of the prediction model, and applys test data and the randon data to test the model's accuracy and generalization capability. The simulation results show that prediction model for boiler thermal efficiency has higher pre- diction accuracy that relative error is controlled within 1% and has better generalization ability, which provides feasible scheme for online measurement of boiler thermal efficiency.

Optimizing Time-Series forecasting using stacked deep learning framework with enhanced adaptive moment estimation and error correction

This study introduces significant improvements in the construction of deep convolutional neural network models for classifying agricultural products, specifically oranges, based on their shape, size, and color. Utilizing the MobileNetV2 architecture, this research leverages its efficiency and lightweight nature, making it suitable for mobile and embedded applications. Key techniques such as depthwise separable convolutions, linear bottlenecks, and inverted residuals help reduce the number of parameters and computational load while maintaining high performance in feature extraction. Additionally, the study employs comprehensive data augmentation methods, including horizontal and vertical flips, grayscale transformations, hue adjustments, brightness adjustments, and noise addition to enhance the model's robustness and generalization capabilities. The proposed model demonstrates superior performance, achieving an overall accuracy of 99.53%∼100% with nearly perfect precision, recall of 95.7%, and F1-score of 94.6% for both “orange_good” and “orange_bad” classes, significantly outperforming previous models which typically achieved accuracies between 70% and 90%. While the classification performance was near-perfect in some aspects, there were minor errors in specific detection tasks. The confusion matrix shows that the model has high sensitivity and specificity, with very few misclassifications. Finally, this study highlights the practical applicability of the proposed model, particularly its easy deployment on resource-constrained devices and its effectiveness in agricultural product quality control processes. These findings affirm the model in this research as a reliable and highly efficient tool for agricultural product classification, surpassing the capabilities of traditional models in this field.

This study investigates the effectiveness of an Artificial Neural Network (ANN) model in enhancing the classification of dry beans varieties. The dry beans dataset, comprising 13,611 samples and 16 numerical features, was preprocessed using Z-score normalization for outlier removal and Principal Component Analysis (PCA) to remove 702 outliers and reduce dimensionality to 10 components while preserving 99.99% of the original variance. A feedforward ANN architecture was designed, constructed as a feedforward neural network with three fully connected layers namely, an input layer that receives 10 features (as reduced by PCA), a first hidden layer with 16 neurons and ReLU activation, a second hidden layer with 32 neurons and ReLU activation, and an output layer with neurons equal to the number of classes, using softmax activation for multi-class probability prediction. The model was trained over 60 epochs using TensorFlow/Keras. Evaluation on a held-out test set demonstrated that the ANN model achieved a classification accuracy of 94.50%. Performance metrics, including accuracy, precision, recall, F1-score, and confusion matrix analysis, confirmed the model's robustness and generalization capability across all dry beans’ classes. The findings affirm that ANN models, when supported by appropriate preprocessing, can serve as scalable and accurate alternatives to conventional machine learning approaches in agricultural classification tasks.

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model's performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops.

In multimode fiber (MMF) imaging, neural networks typically require large datasets and extensive training times, which present substantial challenges for both data acquisition and practical deployment. To address this limitation, we propose a pre-training approach that utilizes data generated from a physical model. By incorporating physically based training data, the required training time for actual fiber data is reduced to approximately one-third. Additionally, this method demonstrates superior performance on the test set, with a 0.04 increase in the average structural similarity index measure (SSIM) and a 31.25% reduction in the average mean squared error (MSE) compared to the baseline model. This approach not only accelerates the training process but also improves the model's accuracy and generalization capabilities, offering a more efficient and effective solution for MMF imaging.

Change detection (CD) in remote sensing imagery is crucial for monitoring environmental variations over time. Recent advancements have introduced numerous effective algorithms, significantly enhancing the performance of CD tasks. However, various challenges still persist, such as complex backgrounds, small targets, and diverse change types. To address these challenges, we propose a novel Mamba-based multi-scale feature enhancement method. Our method leverages the strengths of state space models in handling long sequences by reformulating the pyramid (multi-scale) feature fusion as a sequence processing task. This approach enables our model to efficiently capture both long-range context and fine-grained local details, which are critical for effective feature learning and mitigating the aforementioned challenges. Moreover, we introduce scale-level embedding and auxiliary loss to optimize and regulate the model's training process. These enhancements not only accelerate training but also improve the model's generalization capability. Extensive experiments are conducted on four leading benchmarks: WHUCD, SYSU-CD, LEVIR-CD, and DSIFN-CD datasets. The results demonstrate that our approach consistently delivers state-of-theart performance, surpassing other cutting-edge methods by a significant margin. The source code will be made available at https://github.com/Band-127/Pyramid-Mamba-CD upon formal acceptance of the paper.

As a pivotal area of research in the field of computer vision, the technology for food identification has become indispensable across diverse domains including dietary nutrition monitoring, intelligent service provision in restaurants, and ensuring quality control within the food industry. However, recognizing food images falls within the domain of Fine-Grained Visual Classification (FGVC), which presents challenges such as inter-class similarity, intra-class variability, and the complexity of capturing intricate local features. Researchers have primarily focused on deep information in deep convolutional neural networks for fine-grained visual classification, often neglecting shallow and detailed information. Taking these factors into account, we propose a Multi-level Attention Feature Fusion Network (MAF-Net). Specifically, we use feature maps generated by the Convolutional Neural Networks (CNNs) backbone network at different stages as inputs. We apply a self-attention mechanism to identify local features on these feature maps and then stack them together. The feature vectors obtained through the attention mechanism are then integrated with the original input to enhance data augmentation. Simultaneously, to capture as many local features as possible, we encourage multi-scale features to concentrate on distinct local regions at each stage by maximizing the Kullback-Leibler Divergence (KL-divergence) between the different stages. Additionally, we present a novel approach called subclass center loss (SCloss) to implement label smoothing, minimize intra-class feature distribution differences, and enhance the model's generalization capability. Experiments conducted on three food image datasets-CETH Food-101, Vireo Food-172, and UEC Food-100-demonstrated the superiority of the proposed model. The model achieved Top-1 accuracies of 90.22%, 89.86%, and 90.61% on CETH Food-101, Vireo Food-172, and UEC Food-100, respectively. Notably, our method not only outperformed other methods in terms of the Top-5 accuracy of Vireo Food-172 but also achieved the highest performance in the Top-1 accuracies of UEC Food-100.

With the growth of multisource sensor technology, multimodal learning has become pivotal in remote sensing (RS) image segmentation. Despite its potential, current methods face challenges in acquiring large-scale paired samples. When annotated optical images are available, but synthetic aperture radar (SAR) images lack annotations, learning discriminative features for SAR images from optical images becomes difficult. Unsupervised domain adaptation (UDA) offers a potential solution to this challenge, which we refer to as unpaired cross-modality UDA. In this article, we propose unlocking pseudolabel potential and alignment (ULPA) for unpaired cross-modality adaptation in RS image segmentation, a novel one-stage adaptation framework designed to enhance cross-modality knowledge transfer. Our approach employs a prototypical multidomain alignment (PMDA) strategy, which reduces the modality gap through contrastive learning between features and prototypes of identical classes across different modalities. In addition, we introduce the unreliable-sample-guided feature contrast (UFC) loss to address the underutilization of unreliable pixels during training. This strategy separates reliable and unreliable pixels based on prediction confidence, assigning unreliable pixels to a category-wise queue of negative samples, thus ensuring all candidate pixels contribute to the training process. Extensive experiments show that the integration of PMDA and UFC loss can lead to more effective cross-modality domain alignment and substantially boost the model's generalization capability.