Search Results (994)

In the Yangquan coal mining region, China, muffled blasting sounds commonly occur in mine surrounding rocks resulting from instantaneous energy release following the elastic deformation of overlying brittle rock layers; they are related to fracture development. Although these events rarely cause immediate hazards, their acoustic signatures contain critical information about cumulative rock damage. Currently, conventional monitoring of muffled blasting sounds and surrounding rock stability relies on microseismic systems and on-site sampling techniques. However, these methods exhibit low identification efficiency for muffled blasting events, poor real-time performance, and strong subjectivity arising from manual signal interpretation and empirical threshold setting. This article proposes retentive depthwise gated network (RDGNet). By combining retentive network sequence modeling, depthwise separable convolution, and a gated fusion mechanism, RDGNet enables multimodal feature extraction and the fusion of acoustic emission sequences and audio Mel spectrograms, supporting real-time muffled blasting sound recognition and lithology classification. Results confirm model robustness under noisy and multisource mixed-signal conditions (overall accuracy: 92.12%, area under the curve: 0.985, and Macro F1: 0.931). This work provides an efficient approach for intelligent monitoring of coal mine rock stability and can be extended to safety assessments in underground engineering, advancing the mining industry toward preventive management. Full article

Geological interfaces are crucial elements governing deposit formation, such as silica–calcium surfaces, intrusive contact interfaces, and unconformities can serve as key symbols for mineral exploration prediction. Geological maps provide relatively detailed representations of primary geological interfaces and their interrelationships. However, in previous mineral resource predictions, the type differences in different geological interfaces were ignored, and the types of different geological interfaces vary greatly, thus affecting the validity of the mineral prediction results. Manual interpretation and analysis of geological interfaces involve substantial workloads and make it difficult to effectively apply the rich geological information depicted on geological maps to mineral exploration prediction processes. Therefore, this study proposes a model for intelligent identification of geological interface types based on deep learning. The model extracts the attribute information, such as the age and lithology of the geological bodies on both sides of the geological boundary arc, based on the digital geological map of the Gouli gold mining area in Dulan County, Qinghai Province, China. The learning dataset comprising 5900 sets of geological interface types was constructed through manual annotation of geological interfaces. The arc segment is taken as the basic element; the model adopts natural language processing technology to conduct word vector embedding processing on the text attribute information of geological bodies on both sides of the geological interface. The processed embedding vectors are fed into the convolutional neural network (CNN) for training to generate the geological interface type recognition model. This method can effectively identify the type of geological interface, and the identification accuracy can reach 96.52%. Through quantitative analysis of the spatial relationship between different types of geological interfaces and ore points, it is known that they have a good correlation in spatial distribution. Experimental results show that the proposed method can effectively improve the accuracy and efficiency of geological interface recognition, and the accuracy of mineral prediction can be improved to some extent by adding geological interface type information in the process of mineral prediction. Full article

The proliferation of disinformation on social media platforms poses a significant challenge to the reliability of online information ecosystems and the protection of public discourse. This study investigates the role of emotional sequences in detecting intentionally misleading messages disseminated on social networks. To this end, we apply a methodological pipeline that combines semantic segmentation, automatic emotion recognition, and sequential pattern mining. Emotional sequences are extracted at the subsentence level, preserving each message’s temporal order of emotional cues. Comparative analyses reveal that disinformation messages exhibit a higher prevalence of negative emotions, particularly fear, anger, and sadness, interspersed with neutral segments. Moreover, false messages frequently employ complex emotional progressions—alternating between high-intensity negative emotions and emotionally neutral passages—designed to capture attention and maximize engagement. In contrast, messages from reliable sources tend to follow simpler, more linear emotional trajectories, with a greater prevalence of positive emotions such as joy. Our dataset encompasses multiple categories of disinformation, enabling a fine-grained analysis of how emotional sequencing varies across different types of misleading content. Furthermore, we validate our approach by comparing it against a publicly available disinformation dataset, demonstrating the generalizability of our findings. The results highlight the importance of analyzing temporal emotional patterns to distinguish disinformation from verified content, reinforcing the value of integrating emotional sequences into machine learning pipelines to enhance disinformation detection. This work contributes to the growing body of research emphasizing the relationship between emotional manipulation and the virality of misleading content online. Full article

Recent computing technologies and modern information systems require an access control model that provides flexibility, granularity, and dynamism. The Attribute-Based Access Control (ABAC) model was developed to address the new challenges of emerging applications. Designing and implementing an ABAC policy manually is usually a complex and costly task; therefore, many organizations prefer to keep their access control mechanisms in operation rather than incur the costs associated with the migration process. A solution to the above is to automate the process of creating access control policies. This action is known as policy mining. In this paper, we present a novel approach, based on complex network analysis, for mining an ABAC policy from an access control log. The proposed approach is based on the data and the relationships that can be generated from them. The proposed methodology is divided into five phases: (1) data preprocessing, (2) network model, (3) community detection, (4) policy rule extraction, and (5) policy refinement. The results show that it is possible to obtain an ABAC policy using the approach based on complex networks. In addition, our proposed methodology outperforms existing ABAC mining algorithms regarding quality. Finally, we present a novel access decision process that reduces the number of rules to evaluate based on a rule network. Full article

Current coal mine fire risk assessments often rely on static models and isolated factors, failing to capture the complex, dynamic interactions that lead to fires. To address this gap, we propose a comprehensive framework—termed INK-FBSD—integrating Interpretive Structural Modeling (ISM), the NK model, fuzzy Bayesian network analysis, and System Dynamics (SD) simulation. Using ISM, we identified and hierarchically structured 31 risk factors across human, equipment, environment, management, and fire protection domains, revealing that a robust mine safety accountability system is a pivotal root factor. The NK model quantifies how accident likelihood escalates as more factors interact—for example, four-factor couplings (e.g., equipment–environment–management–fire protection) yield significantly higher risk indices (T ≈ 0.34) than two-factor scenarios. The fuzzy Bayesian analysis estimates an overall 46% probability of a fire accident under current conditions, and diagnostic inference pinpoints excessive coal dust accumulation and neglected fire prevention as top contributors when an incident occurs (posterior probabilities 83% and 78%, respectively). Finally, SD simulations show how key risk factors (such as equipment failure and maintenance delays) can rapidly elevate to severe risk levels within 9–15 months without intervention, underscoring the need for continuous monitoring and proactive control. In summary, the INK-FBSD approach provides a multidimensional understanding of coal mine fire mechanisms and delivers practical guidance for safety management by prioritizing critical risk factors, anticipating high-risk coupling pathways, and informing more effective fire prevention and emergency response strategies. Full article

Accurate prediction of toxic gas concentrations during conveyor-belt fires is essential for ensuring mine safety, yet the nonlinear, time-varying, and turbulent characteristics of underground environments pose significant challenges for real-time forecasting. This study proposes a Physics-Informed Neural Network–Long Short-Term Memory (PINN-LSTM) hybrid model that integrates the one-dimensional convection–diffusion equation as a physical constraint with the sequential learning capability of an LSTM. Full-scale mine tunnel combustion experiments and Fire Dynamics Simulator (FDS) numerical simulations under multiple wind speeds and distances were conducted for model training and validation. The results indicate that the proposed PINN-LSTM achieves the lowest error metrics under all test conditions. The model reduced MSE and RMSE by 70–78% and 65–73%, respectively, compared with traditional LSTM models, and by 8–12% compared with the PINN-TCN variant. The proposed PINN-LSTM achieves the lowest error under all conditions. The PINN-LSTM model has strong prediction accuracy, physical interpretability, and real-time reasoning ability, providing a reliable and physically consistent solution for intelligent gas monitoring and early warning systems in underground fire scenarios. Full article

Mine rescue robots operate in extremely adverse subterranean environments, where the acquired video data are frequently affected by severe jitter and motion distortion. Such instability leads to the loss of critical visual information, thereby reducing the reliability of rescue decision-making. To address this issue, a dual-channel visual stabilization framework based on the SuperPoint network is proposed, extending the traditional ORB descriptor framework. Here, dual-channel refers to two configurable and mutually exclusive feature extraction paths—an ORB-based path and a SuperPoint-based path—that can be flexibly switched according to scene conditions and computational requirements, rather than operating simultaneously on the same frame. The subsequent stabilization pipeline remains unified and consistent across both modes. The method employs an optimized detector head that integrates deep feature extraction, non-maximum suppression, and boundary filtering to enable precise estimation of inter-frame motion. When combined with smoothing filters, the approach effectively attenuates vibrations induced by irregular terrain and dynamic operational conditions. Experimental evaluations conducted across diverse scenarios demonstrate that the proposed algorithm achieves an average improvement of 27.91% in Peak Signal-to-Noise Ratio (PSNR), a 55.04% reduction in Mean Squared Error (MSE), and more than a twofold increase in the Structural Similarity Index (SSIM) relative to pre-stabilized sequences. Moreover, runtime analysis indicates that the algorithm can operate in near-real-time, supporting its practical deployment on embedded mine rescue robot platforms.These results verify the algorithm’s robustness and applicability in environments requiring high visual stability and image fidelity, providing a reliable foundation for enhanced visual perception and autonomous decision-making in complex disaster scenarios. Full article

Honey production is influenced by multiple factors, including climatic conditions, hive management practices, and harvest scheduling. This study evaluated the predictive capacity of statistical modeling techniques using data mining algorithms (MARS, CHAID, CART, and Exhaustive) and artificial neural network algorithms (Multilayer Perceptron, MLP) to estimate honey yields in apiaries located in northeastern Peru. A structured survey was conducted with sixty-nine beekeepers across nineteen districts in the Chachapoyas province. Variables included beekeeper experience, instruction, hive count, visit frequency, harvest frequency, additional income-generating activities, and geographic location. Descriptive statistics, non-parametric tests, Spearman correlations, and exploratory factor analysis were applied to identify latent structures. A linear mixed-effects model was used to assess the combined influence of predictors on honey production, with district included as a random effect. Results indicated that hive number, beekeeping experience, harvest frequency, and exclusive engagement in apiculture were statistically associated with increased honey yields. The model explained a substantial proportion of variance, supporting the integration of technical and socio-demographic variables in production forecasting. These findings demonstrate the utility of predictive modeling for informing hive management strategies and improving the operational efficiency of small-scale beekeeping systems in Andean regions. Full article

Accurate prediction of blast-induced air overpressure (AOp) is vital for environmental management and safety in mining and construction. Traditional empirical models are simple but fail to capture complex meteorological effects, while accurate black-box machine learning models lack interpretability, creating a significant dilemma for practical engineering. This study resolves this by applying explainable AI (XAI) to develop a transparent, “white-box” model that explicitly quantifies how meteorological parameters, wind speed, direction, and air temperature influence AOp. Using a dataset from an urban excavation site, the methodology involved comparing a standard USBM empirical model and a Multivariate Non-linear Regression (MNLR) model against a Symbolic Regression (SR) model implemented with the PySR tool. The SR model demonstrated superior performance on an independent test set, achieving an R² of 0.771, outperforming both the USBM (R² = 0.665) and MNLR (R² = 0.698) models, with accuracy rivaling a previous “black-box” neural network. The key innovation is SR’s ability to autonomously generate an explicit, interpretable equation, revealing complex, non-linear relationships between AOp and meteorological factors. This provides a significant engineering contribution: a trustworthy, transparent tool that enables engineers to perform reliable, meteorologically informed risk assessments for safer blasting operations in sensitive environments like urban areas. Full article

The accurate and timely extraction of water bodies from high-resolution remote sensing imagery is vital for environmental monitoring, yet segmenting small, scattered, and irregularly shaped water bodies in complex rural landscapes remains a persistent challenge. While state-of-the-art deep learning models have advanced segmentation accuracy, they often achieve this at the cost of substantial computational overhead, limiting their practical application for large-scale monitoring. To address this trade-off between precision and efficiency, this paper introduces HWBENet, a novel hybrid network for water body extraction. HWBENet is built upon a lightweight MobileNetV3 encoder to ensure computational efficiency while preserving strong feature extraction capabilities. Its core innovation lies in two specifically designed modules. First, the Contextual Information Mining Module (CIMM) is proposed to enhance the network’s ability to learn and fuse both global scene-level context and fine-grained local details, which is crucial for identifying fragmented water bodies. Second, an Edge Refinement Module (ERM) is integrated into the decoder, which uniquely leverages transformer mechanisms to sharpen boundary details by effectively fusing prior feature information with up-sampled features. Extensive experiments on challenging rural water body datasets demonstrate that HWBENet strikes a superior balance between accuracy and computational cost. The experimental results validate the finding that HWBENet is an efficient, accurate, and scalable solution, offering significant practical value for large-scale hydrological mapping in complex rural environments. Full article

Steganalysis is a critical research direction in the field of information security. Traditional approaches typically employ convolution operations for feature extraction, followed by classification on noise residuals. However, since steganographic signals are inherently weak, convolution alone cannot fully capture their characteristics. To address this limitation, we propose a steganalysis method based on relationship mining, termed RMNet, which leverages positional relationships of steganographic signals for detection. Specifically, features are modeled as graph nodes, where both locally focused and globally adaptive dynamic adjacency matrices guide the propagation paths of these nodes. Meanwhile, the results are further constrained in the feature space, encouraging intra-class compactness and inter-class separability, thereby increasing inter-class separability of positional features and yielding a more discriminative decision boundary. Additionally, to counter signal attenuation during network propagation, we introduce a multi-scale perception module with cross-attention fusion. Experimental results demonstrate that RMNet achieves performance comparable to state-of-the-art models on the BOSSbase and BOWS2 datasets, while offering superior generalization capability. Full article

Cross-scene classification of hyperspectral images poses significant challenges due to the lack of a priori knowledge and the differences in data distribution across scenes. While traditional studies have had limited use of a priori knowledge from other modalities, recent advancements in pre-trained large-scale language-vision models have shown strong performance on various downstream tasks, highlighting the potential of cross-modal assisted learning. In this paper, we propose a Semantic-aware Collaborative Parallel Network (SCPNet) to mitigate the impact of data distribution differences by incorporating linguistic modalities to assist in learning cross-domain invariant representations of hyperspectral images. SCPNet uses a parallel architecture consisting of a spatial–spectral feature extraction module and a multiscale feature extraction module, designed to capture rich image information during the feature extraction phase. The extracted features are then mapped into an optimized semantic space, where improved supervised contrastive learning clusters image features from the same category together while separating those from different categories. Semantic space bridges the gap between visual and linguistic modalities, enabling the model to mine cross-domain invariant representations from the linguistic modality. Experimental results demonstrate that SCPNet significantly outperforms existing methods on three publicly available datasets, confirming its effectiveness for cross-scene hyperspectral image classification tasks. Full article

The application of efficient optical-electrical sorting technology for the automatic separation of copper mine waste rocks not only enables the recovery of valuable copper metals and promotes the resource utilization of non-ferrous mine waste, but also conserves large areas of land otherwise used for waste disposal and alleviates associated environmental issues. However, the process is challenged by the low copper content, fine dissemination of copper-bearing minerals, and complex mineral composition and associated relationships. To address these challenges, this study leverages dual-energy X-ray imaging and multimodal learning, proposing a lightweight twin-tower convolutional neural network (CNN) designed to fuse high- and low-energy spectral information for the automated sorting of copper mine waste rocks. Additionally, the study integrates an emerging Kolmogorov-Arnold network as a classifier to enhance the sorting performance. To validate the efficacy of our approach, a dataset comprising 31,057 pairs of copper mine waste rock images with corresponding high- and low-energy spectra was meticulously compiled. The experimental results demonstrate that the proposed lightweight method achieves competitive, if not superior, performance compared to contemporary mainstream deep learning networks, yet it requires merely 1.32 million parameters (only 6.2% of ResNet-34), thereby indicating extensive potential for practical deployment. Full article

Image-based geo-localization is a challenging task that aims to determine the geographic location of a ground-level query image captured by an Unmanned Ground Vehicle (UGV) by matching it to geo-tagged nadir-view (top-down) images from an Unmanned Aerial Vehicle (UAV) stored in a reference database. The challenge comes from the perspective inconsistency between matched objects. In this work, we propose a novel metric learning scheme for hard exemplar mining to improve the performance of cross-view geo-localization. Specifically, we introduce a Dynamic Online Cross-Batch (DOCB) hard exemplar mining scheme that solves the problem of the lack of hard exemplars in mini-batches in the middle and late stages of training, which leads to training stagnation. It mines cross-batch hard negative exemplars according to the current network state and reloads them into the network to make the gradient of negative exemplars participating in back-propagation. Since the feature representation of cross-batch negative examples adapts to the current network state, the triplet loss calculation becomes more accurate. Compared with methods only considering the gradient of anchors and positives, adding the gradient of negative exemplars helps us to obtain the correct gradient direction. Therefore, our DOCB scheme can better guide the network to learn valuable metric information. Moreover, we design a simple Siamese-like network called multi-scale feature aggregation (MSFA), which can generate multi-scale feature aggregation by learning and fusing multiple local spatial embeddings. The experimental results demonstrate that our DOCB scheme and MSFA network achieve an accuracy of 95.78% on the CVUSA dataset and 86.34% on the CVACT_val dataset, which outperforms those of other existing methods in the field. Full article

Collagen is a family of large, fibrous biomacromolecules common in animals, distinguished by unique molecular, structural, and functional properties. Despite the relatively low complexity of their sequences and the repetitive conformation of the triple helix, which is the defining feature of this family, unraveling sequence–stability and structure–function relationships in this group of proteins remains a challenging task. Considering the importance of the structural aspects in collagen chain recognition and selection, we reviewed our current knowledge of the heterotrimeric structures of non-collagenous (NC) regions that lack the triple helix sequence motif, Gly-X-Y, and are crucial for the correct folding of the functional states of these proteins. This study was conducted by simultaneously surveying the current literature, mining the structural database, and making predictions of the three-dimensional structure of these domains using highly reliable approaches based on machine learning techniques, such as AlphaFold. The combination of experimental structural data and predictive analyses offers some interesting clues about the structural features of heterotrimers formed by collagen NC regions. Structural studies carried out in the last decade show that for fibrillar collagens (types I, V, XI, and mixed V/XI), key factors include the formation of specific disulfide bridges and electrostatic interaction patterns. In the subgroup of collagens whose heterotrimers create supramolecular networks (types IV and VIII), available structural information provides a solid ground for the definition of the basis of the molecular and supramolecular organization. Very recent AlphaFold predictions and structural analyses of type VI collagen offer strong evidence of the specific domains in the NC region of the protein that are involved in chain selection and their staggering. Insightful crystallographic studies have also revealed some fundamental elements of the chain selection process in type IX collagen. Collectively, the data reported here indicate that, although some aspects (particularly the quantification of the relative contribution of the NC and triple helix regions to correct collagen folding) are yet to be fully understood, the available structural information provides a solid foundation for future studies aimed at precisely defining sequence–structure–function relationships in collagens. Full article