Search Results (82)

Geological hazard data exhibits high-volume and multi-type characteristics, specifically characterized by inherent complexity; measurement uncertainty; cross-source heterogeneity; underdeveloped semantic organization; and fragile inter-entity associations. Consequently, advanced modeling techniques coupled with robust extraction frameworks become imperative for effective unstructured data governance. To address this challenge, we propose a content–knowledge representation framework that decomposes and reconstructs disaster data using fine-grained content entities as base units. This approach allows for a unified description, objectification, ordering, hierarchical storage, and indexed categorization of unstructured information. Furthermore, we develop specialized text extraction algorithms tailored to document imagery and vector maps—facilitating the systematic application of information retrieval techniques while efficiently targeting specific thematic content. Our method outperforms two representative deep learning architectures (Fast CNN and FCN), demonstrating superior performance in segmenting target regions and precisely detecting textual elements, tables, and geographic features within complex datasets. By studying the modeling and extraction technology of unstructured geologic data, this paper establishes the value chain of geologic result data, which can provide strong support for digital management of geologic disaster data and improve work efficiency. Full article

In intelligent unmanned agricultural machinery research, navigation line extraction in natural field/orchard environments is critical for autonomous operation. Existing methods still face two prominent challenges: (1) Dynamic shooting perspective shifts caused by natural environmental interference lead to geometric distortion of image features, making it difficult to acquire high-precision navigation features; (2) Symmetric distribution of crop row boundaries hinders traditional algorithms from accurately extracting effective navigation trajectories, resulting in insufficient accuracy and reliability. To address these issues, this paper proposes an environment-adaptive navigation path extraction method for multi-type agricultural scenarios, consisting of two core components: an Attention-Feature-Enhanced U-Net (AFU-Net) for semantic segmentation of navigation feature regions, and a key-point constraint-based adaptive navigation line extraction algorithm. AFU-Net improves the U-Net framework by embedding Efficient Channel Attention (ECA) modules at the ends of Encoders 1–3 to enhance feature expression, and replacing Encoder 4 with a cascaded Semantic Aware Multi-scale Enhancement (SAME) module. Trained and tested on both our KVW dataset and Yu’s field dataset, our method achieves outstanding performance: On the KVW dataset, AFU-Net attains a Mean Intersection over Union (MIoU) of 97.55% and a real-time inference speed of 32.60 FPS with only 3.95 M Params, outperforming state-of-the-art models. On Yu’s field dataset, it maintains an MIoU of 95.20% and 16.30 FPS. Additionally, compared with traditional navigation line extraction algorithms, the proposed adaptive algorithm reduces the mean absolute yaw angle error (mAYAE) to 2.06° in complex scenarios. This research exhibits strong adaptability and robustness, providing reliable technical support for the precise navigation of intelligent agricultural machinery across multiple agricultural scenarios. Full article

To address the limitations of traditional lithium battery defect detection—low efficiency, high missed detection rates for minute/composite defects, and inadequate multimodal fusion—this study develops an improved YOLOv8 model based on multimodal fusion and attention enhancement for unified full-lifecycle multi-type defect detection. Integrating visible-light and X-ray modalities, the model incorporates a Squeeze-and-Excitation (SE) module to dynamically weight channel features, suppressing redundancy and highlighting cross-modal complementarity. A Multi-Scale Fusion Module (MFM) is constructed to amplify subtle defect expression by fusing multi-scale features, building on established feature fusion principles. Experimental results show that the model achieves an mAP@0.5 of 87.5%, a minute defect recall rate (MRR) of 84.1%, and overall industrial recognition accuracy of 97.49%. It operates at 35.9 FPS (server) and 25.7 FPS (edge) with end-to-end latency of 30.9–38.9 ms, meeting high-speed production line requirements. Exhibiting strong robustness, the lightweight model outperforms YOLOv5/7/8/9-S in core metrics. Large-scale verification confirms stable performance across the battery lifecycle, providing a reliable solution for industrial defect detection and reducing production costs. Full article

Existing salient object detection methods for optical remote sensing images still face certain limitations due to complex background variations, significant scale discrepancies among targets, severe background interference, and diverse topological structures. On the one hand, the feature transmission process often neglects the constraints and complementary effects of high-level features on low-level features, leading to insufficient feature interaction and weakened model representation. On the other hand, decoder architectures generally rely on simple cascaded structures, which fail to adequately exploit and utilize contextual information. To address these challenges, this study proposes a Hierarchical Semantic Interaction Module to enhance salient object detection performance in optical remote sensing scenarios. The module introduces foreground content modeling and a hierarchical semantic interaction mechanism within a multi-scale feature space, reinforcing the synergy and complementarity among features at different levels. This effectively highlights multi-scale and multi-type salient regions in complex backgrounds. Extensive experiments on multiple optical remote sensing datasets demonstrate the effectiveness of the proposed method. Specifically, on the EORSSD dataset, our full model integrating both CA and PA modules improves the max F-measure from 0.8826 to 0.9100 (↑2.74%), increases maxE from 0.9603 to 0.9727 (↑1.24%), and enhances the S-measure from 0.9026 to 0.9295 (↑2.69%) compared with the baseline. These results clearly demonstrate the effectiveness of the proposed modules and verify the robustness and strong generalization capability of our method in complex remote sensing scenarios. Full article

Identifying abnormal group behavior formed by multi-type participants from large-scale historical industry and tax data is important for regulators to prevent potential criminal activity. We propose an Abnormal Alliance detection framework comprising two methods. For detecting joint behavior among multi-type participants, we present DyCIAComDet, a dynamic community identification and tracking method for large-scale, time-varying bipartite multi-type participant networks, and introduce three community-splitting measurement indicators—cohesion, integration, and leadership—to improve community division. To verify whether joint behavior is abnormal, termed an Abnormal Alliance, we propose BMPS, a frequent-sequence identification algorithm that mines key features along community evolution paths based on bitmap matrices, sequence matrices, prefix-projection matrices, and repeated-projection matrices. The framework is designed to address sampling limitations, temporal issues, and subjectivity that hinder traditional analyses and to remain scalable to large datasets. Experiments on the Southern Women benchmark and a real tax dataset show DyCIAComDet yields a mean modularity Q improvement of 24.6% over traditional community detection algorithms. Compared with PrefixSpan, BMPS improves mean time and space efficiency by up to 34.8% and 35.3%, respectively. Together, DyCIAComDet and BMPS constitute an effective, scalable detection pipeline for identifying abnormal alliances in tax datasets and supporting regulatory analysis. Full article

Spatial distribution similarity analysis has extensive application value in multiple domains including geographic information science, urban planning, and engineering site selection. However, traditional regional similarity analysis methods face three key challenges: high sensitivity to directional changes, limitations in feature interpretability, and insufficient adaptability to multi-type data. Addressing these issues, this paper proposes a rotation-invariant spatial distribution similarity analysis method based on ring vectors. This method comprises three stages. First, the traversal starting point of the ring vector is dynamically selected based on the maximum value point of the regional feature matrix. Next, concentric ring features are extracted according to this starting point to achieve multi-scale characterization. Finally, the bidirectional weighted comprehensive distance of ring vectors between regions is calculated to measure the similarity between regions. Three experimental sets verified the method’s effectiveness in terrain matching, engineering site selection, and urban functional area identification. These results confirm its rotational invariance, feature interpretability, and adaptability to multi-type data. This research provides a new technical approach for spatial distribution similarity analysis, with significant theoretical and practical implications for geographic information science, urban planning, and engineering site selection. Full article

The construction of zero-carbon parks has become an urgent priority. Electric load forecasting plays a decisive role in enabling the efficient operation of industrial parks; however, the complexity of electric load features within the parks has limited the accuracy of electric load forecasting. A novel electric load forecasting framework with feature extraction (TPE-AVMD-BiLSTM with feature extraction) is proposed to improve the forecasting accuracy. This framework combines feature extraction, decomposition with TPE optimization, and BiLSTM prediction. Together, these components work to remove the influence of irrelevant or redundant features. To verify the superiority of the proposed model, ablation experiments were carried out. The annual hourly electric load (8760 h) of typical industries was predicted within the park, including a data center, chemical manufacturing company, residence, shopping mall, cement manufacturing plant, and hospital. The results showed that the proposed model achieved high accuracy for all typical industries (R² > 0.9891, E_MAE < 0.3714, E_RMSE < 0.4694), indicating that the forecasting has excellent coverage performance. The performance of the proposed model over the feature-free baseline confirms that incorporating more correlated features enhances prediction stability. The framework presents a viable solution for achieving accurate electric load forecasting within zero-carbon parks. Full article

Image enhancement in complex scenes is challenging due to the frequent coexistence of multiple degradations caused by adverse weather, imaging hardware, and transmission environments. Existing datasets remain limited to single or weather-specific degradation types, failing to capture real-world complexity. To address this gap, we introduce the Robust Multi-Type Degradation (RMTD) dataset, which synthesizes a wide range of degradations from meteorological, capture, and transmission sources to support model training and evaluation under realistic conditions. Furthermore, the superposition of multiple degradations often results in feature maps dominated by noise, obscuring underlying clean content. To tackle this, we propose the Feature Filter Transformer (FFformer), which includes: (1) a Gaussian-Filtered Self-Attention (GFSA) module that suppresses degradation-related activations by integrating Gaussian filtering into self-attention; and (2) a Feature-Shrinkage Feed-forward Network (FSFN) that applies soft-thresholding to aggressively reduce noise. Additionally, a Feature Enhancement Block (FEB) embedded in skip connections further reinforces clean background features to ensure high-fidelity restoration. Extensive experiments on RMTD and public benchmarks confirm that the proposed dataset and FFformer together bring substantial improvements to the task of complex-scene image enhancement. Full article

The Automatic Dependent Surveillance-Broadcast (ADS-B) is a key component of the new-generation air traffic surveillance system. However, it is vulnerable to security threats due to its plaintext transmission and lack of authentication mechanisms. Existing ADS-B anomaly detection methods still suffer from significant limitations, including low anomaly detection rates and limited adaptability. To address these issues, this paper proposes a novel ADS-B anomaly detection framework driven by large language models (LLMs). The approach utilizes pre-trained LLMs and a self-iterative prompt optimization loop, which integrates historical trajectories and multimodal features to refine expert-initialized prompts. The optimized prompts guide the LLM in identifying ADS-B anomalies. The advantage of the proposed ADS-B anomaly detection framework lies in overcoming the limitation of traditional model adaptation. Experimental results show that the proposed method achieves excellent performance on key metrics: the anomaly detection rate of 98.55%, the false alarm rate controlled at 3.61%, the miss detection rate reduced to 1.45%, and a recall of 96.39%. Compared to traditional detection methods, this method improves detection accuracy by an average of more than 12%. Furthermore, experiments on multi-type anomaly detection tasks validate that the framework exhibits strong adaptability and good generalization, providing effective technical support for the development of aviation data security protection systems. Full article

Concrete compressive strength is a critical property for structural performance and construction scheduling. Traditional non-destructive testing (NDT) methods, such as rebound hammer and ultrasonic pulse velocity, offer limited reliability and resolution, particularly at early ages. This study presents an AI-powered structural health monitoring (SHM) framework that integrates multi-type and multi-position piezoelectric (PZT) sensor networks with machine learning for in situ prediction of concrete compressive strength. Signals were collected from various PZT types positioned on the top, middle, bottom, and surface sides of concrete cubes during curing. A series of machine learning models were trained and evaluated using both the full and selected feature sets. Results showed that combining multiple PZT types and locations significantly improved prediction accuracy, with the best models achieving up to 95% classification accuracy using only the top 200 features. Feature importance and PCA analyses confirmed the added value of sensor heterogeneity. This study demonstrates that multi-sensor AI-enhanced SHM systems can offer a practical, non-destructive solution for real-time strength estimation, enabling earlier and more reliable construction decisions in line with industry standards. Full article

Semi-rigid base asphalt pavements, a common highway structure in China, often suffer from debonding defects which reduce road stability and shorten service life. In this study, a new method of road debonding detection based on the acoustic vibration method is proposed to address the needs of hidden debonding defects which are difficult to detect. The approach combines the Transformer model and the Transformer-based Parallel Cross-Gated Convolutional Neural Network (T-PCG-CNN) to classify and recognize semi-rigid base asphalt pavement acoustic data. Firstly, over a span of several years, an excitation device was designed and employed to collect acoustic data from different road types, creating a dedicated multi-sample dataset specifically for semi-rigid base asphalt pavements. Secondly, the improved Mel frequency cepstral coefficient (MFCC) feature and its first-order differential features (ΔMFCC) and second-order differential features (Δ₂MFCC) are adopted as the input data of the network for different sample acoustic signal characteristics. Then, the proposed T-PCG-CNN model fuses the multi-frequency feature extraction advantage of a parallel cross-gate convolutional network and the long-time dependency capture ability of the Transformer model to improve the classification performance of different road acoustic features. Comprehensive experiments were conducted to analyze parameter sensitivity, feature combination strategies, and comparisons with existing classification algorithms. The results demonstrate that the proposed model achieves high accuracy and weighted F1 score. The confusion matrix indicates high per-class recall (including debonding), and the one-vs-rest ROC curves (AUC ≥ 0.95 for all classes) confirm strong class separability with low false-alarm trade-offs across operating thresholds. Moreover, the use of blockwise self-attention with global tokens and shared weight matrices significantly reduces model complexity and size. In the multi-type road data classification test, the classification accuracy reaches 0.9208 and the weighted F1 value reaches 0.9315, which is significantly better than the existing methods, demonstrating its generalizability in the identification of multiple road defect types. Full article

Heterogeneous information network (HIN) embedding transforms multi-type nodes into low-dimensional vectors to preserve structural and semantic information for downstream tasks. However, it struggles with multiplex networks where nodes connect via diverse semantic paths (metapaths). Information fusion mainly improves the quality of node embedding by fully exploiting the structure and hidden information within the network. Current metapath-based methods ignore information from intermediate nodes along paths, depend on manually defined metapaths, and overlook implicit relationships between nodes sharing similar attributes. Our objective is to develop an adaptive framework that overcomes limitations in existing metapath-based embedding (incomplete information aggregation, manual path dependency, and ignorance of latent semantics) to learn more discriminative embeddings. We propose an adaptive multi-hop neighbor information fusion model for heterogeneous network embedding (ANHNE), which: (1) autonomously extracts composite metapaths (weighted combinations of relations) via a multipath aggregation matrix to mine hierarchical semantics of varying lengths for task-specific scenarios; (2) projects heterogeneous nodes into a unified space and employs hierarchical attention to selectively fuse neighborhood features across metapath hierarchies; and (3) enhances semantics by identifying potential node correlations via cosine similarity to construct implicit connections, enriching network structure with latent information. Extensive experimental results on multiple datasets show that ANHNE achieves more precise embeddings than comparable baseline models. Full article

In the coal industry, miner safety is increasingly challenged by growing mining depths and complex environments. The failure to wear Personal Protective Equipment (PPE) is a frequent issue in accidents, threatening lives and reducing operational efficiency. Additionally, existing PPE datasets are inadequate for model training due to their small size, lack of diversity, and poor labeling. Current methods often struggle with the complexity of multi-scenario and multi-type PPE detection, especially under varying environmental conditions and with limited training data. In this paper, we propose a novel minersPPE dataset and an improved algorithm based on YOLOv8, enhanced with Dilated-CBAM (Dilated Convolutional Block Attention Module) and DBB (Diverse Branch Block) Detection Block (YOLOv8-DCDB), to address these challenges. The minersPPE dataset constructed in this paper includes 14 categories of protective equipment needed for various body parts of miners. To improve detection performance under complex lighting conditions and with varying PPE features, the algorithm incorporates the Dilated-CBAM module. Additionally, a multi-branch structured detection head is employed to effectively capture multi-scale features, especially enhancing the detection of small targets. To mitigate the class imbalance issue caused by the long-tail distribution in the dataset, we adopt a K-fold cross-validation strategy, optimizing the detection results. Compared to standard YOLOv8-based models, experiments on the minersPPE dataset demonstrate an 18.9% improvement in detection precision, verifying the effectiveness of the proposed YOLOv8-DCDB model in multi-scenario, multi-type PPE detection tasks. Full article

To address the issues of poor thermal performance and high energy consumption in rural dwellings in cold regions of China, this study investigates multi-type energy-efficient retrofitting strategies for rural houses in the Hebei–Tianjin region. By utilizing a two-step cluster analysis method, 458 rural dwellings from 32 villages were classified based on household demographics, architectural features, and energy consumption patterns, identifying three typical categories: pre-1980s adobe dwellings, 1980s–1990s brick–wood structures, and post-1990s brick–concrete houses. Tailored sunspace design strategies were proposed through simulation: low-cost plastic film sunspaces for adobe dwellings (dynamic payback period: 2.8 years; net present value: CNY 2343), 10 mm hollow polycarbonate (PC) panels for brick–wood structures (cost–benefit ratio: 1.72), and high-efficiency broken bridge aluminum Low-e sunspaces for brick–concrete houses (annual natural gas savings: 345.24 m³). Economic analysis confirmed the feasibility of the selected strategies, with positive net present values and cost–benefit ratios exceeding 1. The findings demonstrate that classification-based retrofitting strategies effectively balance energy-saving benefits with economic costs, providing a scientific hierarchical implementation framework for rural residential energy efficiency improvements in cold regions. Full article

The analysis and accurate identification of DC-side grounding faults in grid-connected photovoltaic (PV) inverters is a critical step in enhancing operation and maintenance capabilities and ensuring the safe operation of PV grid-connected systems. However, the characteristics of DC-side grounding faults remain unclear, and effective methods for identifying such faults are lacking. To address the need for leakage characteristic analysis and fault identification of DC-side grounding faults in grid-connected PV inverters, this paper first establishes an equivalent analysis model for DC-side grounding faults in three-phase grid-connected inverters. The formation mechanism and frequency-domain characteristics of residual current under DC-side fault conditions are analyzed, and the specific causes of different frequency components in the residual current are identified. Based on the leakage current mechanisms and statistical characteristics of grid-connected PV inverters, a multi-type DC-side grounding fault identification method is proposed using the light gradient-boosting machine (LGBM) algorithm. In the simulation case study, the proposed fault identification method, which combines mechanism characteristics and statistical characteristics, achieved an accuracy rate of 99%, which was significantly superior to traditional methods based solely on statistical characteristics and other machine learning algorithms. Real-time simulation verification shows that introducing mechanism-based features into grid-connected photovoltaic inverters can significantly improve the accuracy of identifying grounding faults on the DC side. Full article