Applications of Machine Learning in Large-Scale Optimization and High-Dimensional Learning

Guanzhong traditional vernacular dwellings are an important component of traditional architectural heritage. Their architectural decorative motifs are often attached to components such as screen walls, gable end piers, doors and windows, door pillow stones, column bases, tile ends, and roof ridges, making them important visual objects for image based documentation, typological organization, and conservation management of architectural heritage. Since the relevant images are mainly obtained through field photography, field images often contain multiple sources of interference, including weathering, spalling, occlusion, contamination, illumination variation, wall joints, brick joints, shadows, component edges, and damaged textures. These factors lead to blurred motif boundaries, strong background interference, and a high risk of misrecognition. Existing motif recognition methods mainly focus on clear samples and pay insufficient attention to candidate region generation, invalid texture filtering, and the exclusion of low confidence results in complex field scenarios. To address these problems, this study proposes a recognition method for architectural decorative motifs in complex scenarios. Based on field collected images of Guanzhong traditional vernacular dwellings, the method takes architectural decorative motifs and non-motif candidate regions as training objects. SAM is first used to generate potential motif candidate regions. Spatial-prior filtering based on candidate size, aspect ratio, and SAM stability is then introduced to reduce invalid region proposals, while semantic aggregation is used to retain large candidate regions supported by high-confidence local motif evidence. Swin Transformer is further adopted as the classification backbone to extract local texture features and overall structural relationships from candidate regions. A maximum confidence based rejection mechanism is also introduced to enhance the model’s ability to exclude low confidence predictions and regions without motifs. Component-level test-set evaluation and expert-verified complete-field-image evaluation show that the proposed method can reduce the interference of complex backgrounds and invalid textures, and improve the recognition stability of architectural decorative regions in field images. This study provides technical support for image organization, digital documentation, typological indexing, and conservation management of architectural decorative motifs in traditional vernacular dwellings. Full article

The multi-valued dependency matrix (MVD matrix) is an important testability modeling approach, which can deliver more comprehensive testability information than the traditional dependency matrix (D-matrix). However, existing testability strategy optimization algorithms perform poorly in handling the MVD matrix, and the high-dimensional MVD matrix further aggravates these limitations as system complexity increases. To address these problems, a novel testability strategy optimization method under multi-valued dependency conditions based on deep reinforcement learning (DRL) is proposed. Firstly, the sets of elements and two reward functions to minimize test sequence length and test cost are established from the MVD matrix. Subsequently, the algorithm for selecting test points based on Deep Q-Network (DQN) is proposed. The DQN parameters are updated to fit the Q-value of test points. Thirdly, Double DQN (DDQN) and the prioritized experience replay (PER) mechanism are introduced to address the overestimation problem and sample redundancy problem, respectively, in high-dimensional matrix environments. The experimental results show that the testability strategy generated by this method can isolate all faults with fewer steps or at a lower cost. In a high-dimensional matrix environment, it can reduce test costs compared with the other heuristic algorithms while maintaining a good level of stability. Full article

Hypergraph neural networks have shown strong potential for node classification due to their ability to capture high-order relationships and multi-granularity structural patterns. However, real-world hypergraphs are often sparse, which limits interaction modeling through node–hyperedge incidence and, in turn, weakens reliable attribute propagation and global dependency capture. To address this issue, we propose DDEC, a Dual Dependency-Enhanced Contrastive learning framework for sparse hypergraph node classification. To compensate for relational information lost under sparse structures, DDEC introduces an attribute view to complement the structural view. Since attribute information can be noisy and unreliable, we first design an entropy-guided feature recalibration mechanism to estimate node uncertainty and emphasize trustworthy attribute interactions. Building upon this, DDEC performs dual dependency enhancement from both structural and attribute perspectives. Specifically, we exploit the duality between a hypergraph and its line graph to perform line-graph transformation in both views, thereby constructing a shared dual relational space for interaction enhancement under sparse topologies. Within this dual space, we perform attention-based dependency enhancement in both views, so that the structural view captures explicit topological dependencies among hyperedges, while the attribute view uncovers latent semantic correlations beyond sparse incidence relations. The resulting representations from the two views are then adaptively fused, and collaborative contrastive learning is further performed at both the node and hyperedge levels to enforce multi-granularity semantic consistency. Experiments on eight public datasets demonstrate that DDEC consistently outperforms competitive baselines, validating its effectiveness and robustness. Full article

Emotion recognition plays a crucial role in human–computer interaction, health monitoring, and affective computing by analysing physiological signals. Despite recent advancements, current research still faces challenges, including the lack of effective fusion strategies for diverse physiological modalities, difficulties in handling high-dimensional feature representations, and limited use of efficient temporal modelling techniques to capture complex emotional patterns. This study proposes a deep learning-based approach that fuses multiple physiological modalities, including Electroencephalography (EEG), Electrooculography (EOG), Electromyography (EMG), Galvanic Skin Response (GSR), Respiratory Rate (RR), Skin Temperature (SKT), and Photoplethysmography (PPG), to improve emotion recognition. Arousal and valence ratings were binarized into two classes (low/high) using a threshold of 4.5, formulating a binary classification problem. In addition to utilising Bidirectional Long Short-Term Memory (Bi-LSTM), the study employs Temporal Convolutional Networks (TCN), a widely used approach for time-series analysis, to efficiently capture temporal dependencies. The proposed model optimises feature selection through channel-wise strategies, incorporates advanced learning rate scheduling, and reduces computational overhead. Furthermore, window-wise, block-wise, and trial-wise evaluation protocols were investigated to assess the impact of temporal information leakage on emotion recognition performance. Using the DEAP dataset for validation, the proposed TCN-based approach achieved classification accuracies of 88.42% for valence and 86.35% for arousal under an overlapping block-wise evaluation protocol, demonstrating improved performance in binary emotion recognition and highlighting the importance of leakage-aware model assessment. Full article

When trained on long-tailed distributions, deep neural networks often suffer performance degradation and model bias due to the dominance of head classes. Existing reweighting and sampling strategies have significant limitations, such as reliance on fixed heuristics and inability to adapt to dynamic sample difficulty and class imbalance. Additionally, they fail to integrate sample-level granularity with class-level balance, further inadequately addressing the global imbalance issue. Motivated by these challenges, we introduce the Progressive Hierarchical Adaptation for Sample-Efficient rebalancing (PHASE) training framework, which employs a double-layer tuning paradigm to optimize performance under long-tailed distributions. Specifically, the double-layer tuning paradigm adopted by PHASE runs as follows: (1) an early-stage difficulty-aware mechanism targets those difficult-to-classify samples to guide representation learning; and (2) a later-stage multi-scale reweighting strategy integrates class distribution statistics with sample characteristics. This method ensures fine-grained adaptability and global balance, and thus outperforming those static or localized techniques. Extensive experiments on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT datasets demonstrate that PHASE can significantly improve the accuracy of tail classes without degenerating head class performance, and acquire state-of-the-art classification results. PHASE provides a novel paradigm for long-tailed image recognition. Full article

In this paper, the concept of symmetry is utilized to evaluate the distribution characteristics of flow fields—that is, flow fields with balanced displacement generally exhibit good spatial symmetry. In the late stage of water-flooding reservoir development, identifying flow field distribution and implementing targeted adjustments are crucial for improving development efficiency and enhancing oil recovery. This study establishes a quantitative evaluation index system integrating both static geological and dynamic production factors to comprehensively characterize flow field distribution in ultra-high water-cut reservoirs. The system incorporates residual oil potential abundance, water-flooding ratio, and water influx intensity as key indicators. A flow field classification method based on the K-Means clustering algorithm was proposed, with the Davies–Bouldin index applied to evaluate clustering validity. The approach was validated using the Egg model, where the flow field was effectively classified into four types: inefficient retention field, effective displacement field, dominant displacement field, and extreme displacement field. Adjustment measures were then applied based on classification results. The findings demonstrate that the proposed method weakens dominant displacement areas while expanding effective and inefficient displacement zones, leading to a 1.1 percentage point increase in recovery factor. This research provides a practical and quantitative tool for flow field diagnosis and adjustment, offering valuable technical guidance for managing ultra-high water-cut reservoirs. Full article

The deep learning-based gravity anomaly inversion method addresses the complex challenge of deriving subsurface density variation models from surface gravity anomaly data. In order to generate various geological environments and their corresponding surface gravity anomaly datasets, three-dimensional density models considering different spatial locations and density variations are created in this paper. At the same time, the residual module and spatial attention mechanism are introduced into the U-Net architecture to improve the learning ability and inversion accuracy of complex geological structures. Experimental results demonstrate that the proposed method achieves the high-precision reconstruction of density variation models in complex anomaly environments, with a model residual error lower than 3%. Additionally, the inversion results of the density change and the gravity change in the Longshoushan fault zone show that the 2022 Menyuan MS6.9 earthquake is in the middle of the positive and negative density changes, which verifies the applicability of the U-Net network in the field of gravity change data, highlighting the method’s value in the real-world environment. Full article

In the design of fluid systems, rapid iteration and simulation verification are essential, and reduced-order modeling techniques can significantly improve computational efficiency and accuracy. However, traditional Physics-Informed Neural Networks (PINNs) often face challenges such as vanishing or exploding gradients when learning flow field characteristics, limiting their ability to capture complex fluid dynamics. This study presents an enhanced reduced-order model (ROM): Physics-Informed Neural Networks based on Residual Networks (Res-PINNs). By integrating a Residual Network (ResNet) module into the PINN architecture, the proposed model improves training stability while preserving physical constraints. Additionally, the model’s ability to capture and learn flow field states is further enhanced by the design of a symmetric parallel neural network structure. To evaluate the effectiveness of the Res-PINNs model, two classic fluid dynamics problems—flow around a cylinder and Vortex-Induced Vibration (VIV)—were selected for comparative testing. The results demonstrate that the Res-PINNs model not only reconstructs flow field states with higher accuracy but also effectively addresses limitations of traditional PINN methods, such as vanishing gradients, exploding gradients, and insufficient learning capacity. Compared to existing approaches, the proposed Res-PINNs provide a more stable and efficient solution for deep learning-based reduced-order modeling in fluid system design. Full article

The global community is awaiting the advent of a self-driving vehicle that is safe, reliable, and capable of navigating a diverse range of road conditions and terrains. This requires a lot of research, study, and optimization. Thus, this work focused on implementing, training, and optimizing a convolutional neural network (CNN) model, aiming to predict the steering angle during driving (one of the main issues). The considered dataset comprises images collected inside a car-driving simulator and further processed for augmentation and removal of unimportant details. In addition, an innovative data-balancing process was previously performed. A CNN model was trained with the dataset, conducting a comparison between several different standard optimizers. Moreover, evolutionary optimization was applied to optimize the model’s weights as well as the optimizers themselves. Several experiments were performed considering different approaches of genetic algorithms (GAs) along with other optimizers from the state of the art. The obtained results demonstrate that the GA is an effective optimization tool for this problem. Full article

Maximum entropy (MaxEnt) models are a class of statistical models that use the maximum entropy principle to estimate probability distributions from data. Due to the size of modern data sets, MaxEnt models need efficient optimization algorithms to scale well for big data applications. State-of-the-art algorithms for MaxEnt models, however, were not originally designed to handle big data sets; these algorithms either rely on technical devices that may yield unreliable numerical results, scale poorly, or require smoothness assumptions that many practical MaxEnt models lack. In this paper, we present novel optimization algorithms that overcome the shortcomings of state-of-the-art algorithms for training large-scale, non-smooth MaxEnt models. Our proposed first-order algorithms leverage the Kullback–Leibler divergence to train large-scale and non-smooth MaxEnt models efficiently. For MaxEnt models with discrete probability distribution of n elements built from samples, each containing m features, the stepsize parameter estimation and iterations in our algorithms scale on the order of $O\left(mn\right)$ operations and can be trivially parallelized. Moreover, the strong ${\ell }_1$ convexity of the Kullback–Leibler divergence allows for larger stepsize parameters, thereby speeding up the convergence rate of our algorithms. To illustrate the efficiency of our novel algorithms, we consider the problem of estimating probabilities of fire occurrences as a function of ecological features in the Western US MTBS-Interagency wildfire data set. Our numerical results show that our algorithms outperform the state of the art by one order of magnitude and yield results that agree with physical models of wildfire occurrence and previous statistical analyses of wildfire drivers. Full article

With the continuous growth of electricity demand, the safety and stability of transmission lines have become increasingly important. To ensure the reliability of power supply, it is essential to promptly detect and address foreign object intrusions on transmission lines, such as tree branches, kites, and balloons. Addressing the issues where foreign objects can cause power outages and severe safety accidents, as well as the inefficiency, time consumption, and labor-intensiveness of traditional manual inspection methods, especially in large-scale power transmission lines, we propose an enhanced YOLOv8-based model for detecting foreign objects. This model incorporates the Swin Transformer, AFPN (Asymptotic Feature Pyramid Network), and a novel loss function, Focal SIoU, to improve both the accuracy and real-time detection of hazards. The integration of the Swin Transformer into the YOLOv8 backbone network significantly improves feature extraction capabilities. The AFPN enhances the multi-scale feature fusion process, effectively integrating information from different levels and improving detection accuracy, especially for small and occluded objects. The introduction of the Focal SIoU loss function optimizes the model’s training process, enhancing its ability to handle hard-to-classify samples and uncertain predictions. This method achieves efficient automatic detection of foreign objects by comprehensively utilizing multi-level feature information and optimized label matching strategies. The dataset used in this study consists of images of foreign objects on power transmission lines provided by a power supply company in Jilin, China. These images were captured by drones, offering a comprehensive view of the transmission lines and enabling the collection of detailed data on various foreign objects. Experimental results show that the improved YOLOv8 network has high accuracy and recall rates in detecting foreign objects such as balloons, kites, and bird nests, while also possessing good real-time processing capabilities. Full article

As the demand for efficient and lightweight models in image classification grows, knowledge distillation has emerged as a promising technique to transfer expertise from complex teacher models to simpler student models. However, the efficacy of knowledge distillation is intricately linked to the choice of datasets used during training. Datasets are pivotal in shaping a model’s learning process, influencing its ability to generalize and discriminate between diverse patterns. While considerable research has independently explored knowledge distillation and image classification, a comprehensive understanding of how different datasets impact knowledge distillation remains a critical gap. This study systematically investigates the impact of diverse datasets on knowledge distillation in image classification. By varying dataset characteristics such as size, domain specificity, and inherent biases, we aim to unravel the nuanced relationship between datasets and the efficacy of knowledge transfer. Our experiments employ a range of datasets to comprehensively explore their impact on the performance gains achieved through knowledge distillation. This study contributes valuable guidance for researchers and practitioners seeking to optimize image classification models through kno-featured applications. By elucidating the intricate interplay between dataset characteristics and knowledge distillation outcomes, our findings empower the community to make informed decisions when selecting datasets, ultimately advancing the field toward more robust and efficient model development. Full article