Search Results (104)

This study proposes a hybrid machine learning framework that integrates structured financial indicators and unstructured textual strategy disclosures to improve firm-level management performance prediction. Using corporate business reports from South Korean listed firms, strategic text was extracted and categorized under the Balanced Scorecard (BSC) framework into financial, customer, internal process, and learning and growth dimensions. Various machine learning and deep learning models—including k-nearest neighbors (KNNs), support vector machine (SVM), light gradient boosting machine (LightGBM), convolutional neural network (CNN), long short-term memory (LSTM), autoencoder, and transformer—were evaluated, with results showing that the inclusion of strategic textual data significantly enhanced prediction accuracy, precision, recall, area under the curve (AUC), and F1-score. Among individual models, the transformer architecture demonstrated superior performance in extracting context-rich semantic features. A soft-voting ensemble model combining autoencoder, LSTM, and transformer achieved the best overall performance, leading in accuracy and AUC, while the best single deep learning model (transformer) obtained a marginally higher F1 score, confirming the value of hybrid learning. Furthermore, analysis revealed that customer-oriented strategy disclosures were the most predictive among BSC dimensions. These findings highlight the value of integrating financial and narrative data using advanced NLP and artificial intelligence (AI) techniques to develop interpretable and robust corporate performance forecasting models. In addition, we operationalize information security narratives using a reproducible cybersecurity lexicon and derive security disclosure intensity and weight share features that are jointly evaluated with BSC-based strategic vectors. Full article

Building height is an important indicator for describing the three-dimensional structure of cities. However, monitoring its changes is still difficult due to high labor costs, low efficiency, and the limited resolution and viewing angles of remote sensing images. This study proposes an automatic framework for estimating building height changes using multi-temporal street view images. First, buildings are detected by the YOLO-v5 model, and their contours are extracted through edge detection and hole filling. To reduce false detections, greenness and depth information are combined to filter out pseudo changes. Then, a neighboring region resampling strategy is used to select visually similar images for better alignment, which helps to reduce the influence of sampling errors. In addition, the framework applies cylindrical projection correction and introduces a triangulation-based method (HCAOT) for building height estimation. Experimental results show that the proposed framework achieves an accuracy of 85.11% in detecting real changes and 91.23% in identifying unchanged areas. For height estimation, the HCAOT method reaches an RMSE of 0.65 m and an NRMSE of 0.04, which performs better than several comparison methods. Overall, the proposed framework provides an efficient and reliable approach for dynamically updating 3D urban information and supporting spatial monitoring in smart cities. Full article

Protein function emerges from dynamic conformational changes, yet structure prediction methods provide only static snapshots. While AlphaFold3 (AF3) predicts protein structures, the potential for extracting dynamic information from its ensemble predictions has remained underexplored. Here, we demonstrate that AF3 structural ensembles contain substantial dynamic information that correlates remarkably well with molecular dynamics simulations (MD). We developed ChronoSort, a novel algorithm that organizes static structure predictions into temporally coherent trajectories by minimizing structural differences between neighboring frames. Through systematic analysis of four diverse protein targets, we show that root-mean-square fluctuations derived from AF3 ensembles can correlate strongly with those from MD (r = 0.53 to 0.84). Principal component analysis reveals that AF3 predictions capture the same collective motion patterns observed in molecular dynamics trajectories, with eigenvector similarities significantly exceeding random distributions. ChronoSort trajectories exhibit structural evolution profiles comparable to MD. These findings suggest that modern AI-based structure prediction tools encode conformational flexibility information that can be systematically extracted without expensive MD. We provide ChronoSort as open-source software to enable broad community adoption. This work offers a novel approach to extracting functional insights from structure prediction tools in minutes, with significant implications for synthetic biology, protein engineering, drug discovery, and structure–function studies. Full article

Data-driven text classification technology is crucial for understanding and managing a large number of entrepreneurial policy-related texts, yet it is hindered by two primary challenges. First, the intricate, multi-faceted nature of policy documents often leads to insufficient information extraction, as existing models struggle to synergistically leverage diverse information types, such as statistical regularities, linguistic structures, and external factual knowledge, resulting in semantic sparsity. Second, the performance of state-of-the-art deep learning models is heavily reliant on large-scale annotated data, a resource that is scarce and costly to acquire in entrepreneurial policy domains, rendering models susceptible to overfitting and poor generalization. To address these challenges, this paper proposes a Multi-granularity Invariant Structure Learning (MISL) model. Specifically, MISL first employs a multi-view feature engineering module that constructs and fuses distinct statistical, linguistic, and knowledge graphs to generate a comprehensive and rich semantic representation, thereby alleviating semantic sparsity. Furthermore, to enhance robustness and generalization from limited data, we introduce a dual invariant structure learning framework. This framework operates at two levels: (1) sample-invariant representation learning uses data augmentation and mutual information maximization to learn the essential semantic core of a text, invariant to superficial perturbations; (2) neighborhood-invariant semantic learning applies a contrastive objective on a nearest-neighbor graph to enforce intra-class compactness and inter-class separability in the feature space. Extensive experiments demonstrate that our proposed MISL model significantly outperforms state-of-the-art baselines, proving its effectiveness and robustness for classifying complex texts in entrepreneurial policy domains. Full article

As the Internet of Things (IoT) expands and spectrum resources become increasingly scarce, Automatic Modulation Classification (AMC) has become critical for enabling dynamic spectrum access, interference mitigation, and spectrum monitoring without coordination or prior signaling. Most deep learning-based AMC methods (e.g., CNNs, LSTMs, Transformers) operate in Euclidean spaces and therefore overlook the non-Euclidean relationships inherent in modulated signals. We propose KGNN, a graph-based AMC architecture that couples a KNN-driven graph representation with GraphSAGE convolutions for neighborhood aggregation. In the KNN stage, each feature vector is connected to its nearest neighbors, transforming temporal signals into structured graphs, while GraphSAGE extracts relational information across nodes and edges for classification. On the RML2016.10b dataset, KGNN attains an overall accuracy of 64.72%, outperforming strong baselines (including MCLDNN) while using only one-eighth the number of parameters used by MCLDNN and preserving fast inference. These results highlight the effectiveness of graph convolutional modeling for AMC under practical resource constraints and motivate further exploration of graph-centric designs for robust wireless intelligence. Full article

Background/Objectives: Urinary system stone disease is an important health problem both clinically and economically due to its high recurrence rates. In this study, an innovative hybrid approach based on deep learning is proposed to predict the recurrence risk of stone disease. Methods: Patient data were divided into three subsets: anthropometric measurements (Part A), derived body composition indices (Part B), and other clinical and demographic information (Part C). Each data subset was processed with autoencoder models, and low-dimensional, meaningful features were extracted. The obtained features were combined, and the classification process was performed using four different machine learning algorithms: Extreme Gradient Boosting (XGBoost), Cubic Support Vector Machines (Cubic SVM), k-Nearest Neighbor algorithm (KNN), and Decision Tree (DT). Results: According to the experimental results, the highest classification performance was obtained with the XGBoost algorithm. The suggested approach adds to the literature by offering a novel solution that makes early risk calculation for stone disease recurrence easier. It also shows how well structural feature engineering and deep representation can be integrated in clinical prediction issues. Conclusions: Prediction of the stone recurrence risk in advance is of great importance both in terms of improving the quality of life of patients and reducing the unnecessary diagnostic evaluations along with lowering treatment costs. Full article

Instance segmentation stands as a foundational technology in real-world applications such as autonomous driving, where the inherent trade-off between accuracy and computational efficiency remains a key barrier to practical deployment. To tackle this challenge, we propose a dual-path enhanced framework based on YOLO11l. In this framework, two improved models, YOLO-SA and YOLO-SD, are developed to enable high-performance lightweight instance segmentation. The core innovation lies in balancing precision and efficiency through targeted architectural advancements. For YOLO-SA, we embed the parameter-free SimAM attention mechanism into the C3k2 module, yielding a novel C3k2SA structure. This design leverages neural inhibition principles to dynamically enhance focus on critical regions (e.g., object contours and semantic key points) without adding to model complexity. For YOLO-SD, we replace standard backbone convolutions with lightweight SPD-Conv layers (featuring spatial awareness) and adopt DySample in place of nearest-neighbor interpolation in the upsampling path. This dual modification minimizes information loss during feature propagation while accelerating feature extraction, directly optimizing computational efficiency. Experimental validation on the Cityscapes dataset demonstrates the effectiveness of our approach: YOLO-SA increases mAP from 0.401 to 0.410 with negligible overhead; YOLO-SD achieves a slight mAP improvement over the baseline while reducing parameters by approximately 5.7% and computational cost by 1.06%. These results confirm that our dual-path enhancements effectively reconcile accuracy and efficiency, offering a practical, lightweight solution tailored for resource-constrained real-world scenarios. 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

Identifying correspondences of road segments in different road networks, namely road-network matching, is an essential task for road network-centric data processing such as data integration of road networks and data quality assessment of crowd-sourced road networks. Traditional road-network matching usually relies on feature engineering and parameter selection of the geometry and topology of road networks for similarity measurement, resulting in poor performance when dealing with dense and irregular road network structures. Recent development of graph neural networks (GNNs) has demonstrated unsupervised modeling power on road network data, which learn the embedded vector representation of road networks through spatial feature induction and topology-based neighbor aggregation. However, weighting spatial information on the node feature alone fails to give full play to the expressive power of GNNs. To this end, this paper proposes a Spatial Pattern-aware Graph EMbedding learning method for road-network matching, named SP-GEM, which explores the idea of spatially-explicit modeling by identifying spatial patterns in neighbor aggregation. Firstly, a road graph is constructed from the road network data, and geometric, topological features are extracted as node features of the road graph. Then, four spatial patterns, including grid, high branching degree, irregular grid, and circuitous, are modelled in a sector-based road neighborhood for road embedding. Finally, the similarity of road embedding is used to find data correspondences between road networks. We conduct an algorithmic accuracy test to verify the effectiveness of SP-GEM on OSM and Tele Atlas data. The algorithmic accuracy experiments show that SP-GEM improves the matching accuracy and recall by at least 6.7% and 10.2% among the baselines, with high matching success rate (>70%), and improves the matching accuracy and recall by at least 17.7% and 17.0%, compared to the baseline GNNs, without spatially-explicit modeling. Further embedding analysis also verifies the effectiveness of the induction of spatial patterns. This study not only provides an effective and practical algorithm for road-network matching, but also serves as a test bed in exploring the role of spatially-explicit modeling in GNN-based road network modeling. The experimental performances of SP-GEM illuminate the path to develop GeoEmbedding services for geospatial applications. Full article

Personality is a fundamental psychological trait that exerts a long-term influence on human behavior patterns and social interactions. Automatic personality recognition (APR) has exhibited increasing importance across various domains, including Human–Robot Interaction (HRI), personalized services, and psychological assessments. In this study, we propose a multimodal personality recognition model that classifies the Big Five personality traits by extracting features from three heterogeneous sources: audio processed using Wav2Vec2, video represented as Skeleton Landmark time series, and text encoded through Bidirectional Encoder Representations from Transformers (BERT) and Doc2Vec embeddings. Each modality is handled through an independent Self-Attention block that highlights salient temporal information, and these representations are then summarized and integrated using a late fusion approach to effectively reflect both the inter-modal complementarity and cross-modal interactions. Compared to traditional recurrent neural network (RNN)-based multimodal models and unimodal classifiers, the proposed model achieves an improvement of up to 12 percent in the F1-score. It also maintains a high prediction accuracy and robustness under limited input conditions. Furthermore, a visualization based on t-distributed Stochastic Neighbor Embedding (t-SNE) demonstrates clear distributional separation across the personality classes, enhancing the interpretability of the model and providing insights into the structural characteristics of its latent representations. To support real-time deployment, a lightweight thread-based processing architecture is implemented, ensuring computational efficiency. By leveraging deep learning-based feature extraction and the Self-Attention mechanism, we present a novel personality recognition framework that balances performance with interpretability. The proposed approach establishes a strong foundation for practical applications in HRI, counseling, education, and other interactive systems that require personalized adaptation. Full article

Amid the accelerating pace of global urbanization, the volume of municipal solid garbage has surged dramatically, thereby demanding more efficient and precise garbage management technologies. In this paper, we introduce a novel garbage classification approach that leverages a dynamic graph neural network based on multimodal feature fusion. Specifically, the proposed method employs an enhanced Residual Network Attention Module (RNAM) network to capture deep semantic features and utilizes CIELAB color (LAB) histograms to extract color distribution characteristics, achieving a complementary integration of multimodal information. An adaptive K-nearest neighbor algorithm is utilized to construct the dynamic graph structure, while the incorporation of a multi-head attention layer within the graph neural network facilitates the efficient aggregation of both local and global features. This design significantly enhances the model’s ability to discriminate among various garbage categories. Experimental evaluations reveal that on our self-curated KRHO dataset, all performance metrics approach 1.00, and the overall classification accuracy reaches an impressive 99.33%, surpassing existing mainstream models. Moreover, on the public TrashNet dataset, the proposed method demonstrates equally outstanding classification performance and robustness, achieving an overall accuracy of 99.49%. Additionally, hyperparameter studies indicate that the model attains optimal performance with a learning rate of 2 × 10⁻⁴, a dropout rate of 0.3, an initial neighbor count of 20, and 8 attention heads. Full article

High-quality reconstruction of magnetic resonance imaging (MRI) data from undersampled k-space remains a significant challenge in medical imaging. While the integration of compressed sensing and deep learning has notably improved the performance of MRI reconstruction, existing convolutional neural network-based methods are limited by their small receptive fields, which hinders the exploration of global image features. Meanwhile, Swin-Transformer-based approaches struggle with inter-window information interaction and global feature extraction and perform poorly when dealing with complex repetitive structures and similar texture features under undersampling conditions, resulting in suboptimal reconstruction quality. To address these issues, we propose a Symmetry-based Cascaded Dual-Domain Hybrid Attention Network (SCDDHAN). Leveraging the inherent symmetry of medical images, the network combines channel and self-attention to improve global context modeling and local detail restoration. The overlapping window self-attention module is designed with symmetry in mind to improve cross-window information interaction by overlapping adjacent windows and directly linking neighboring regions. This facilitates more accurate detail recovery. The concept of symmetry is deeply embedded in the network design, guiding the model to better capture regular patterns and balanced structures within MRI images. Experimental results demonstrate that under 5× and 10× undersampling conditions, SCDDHAN outperforms existing methods in artifact suppression, achieving more natural edge transitions, clearer complex textures and superior overall performance. This study highlights the potential of integrating symmetry concepts into hybrid attention modules for accelerating MRI reconstruction and offers an efficient, innovative solution for future research in this area. Full article

Entity alignment is a critical technique for integrating diverse knowledge graphs. Although existing methods have achieved impressive success in traditional entity alignment, they may struggle to handle the complexities arising from interactions and dependencies in multi-modal knowledge. In this paper, a novel multi-modal entity alignment model called ERMF is proposed, which leverages distinct modal characteristics of entities to identify equivalent entities across different multi-modal knowledge graphs. The symmetry in cross-modal interactions and hierarchical feature fusion is a core design principle of our approach. Specifically, we first utilize different feature encoders to independently extract features from different modalities. Concurrently, visual features and nearest neighbor negative sampling methods are incorporated to design a vision-guided negative sample generation strategy based on contrastive learning, ensuring a symmetric balance between positive and negative samples and guiding the model to learn effective relationship embeddings. Subsequently, in the feature fusion stage, we propose a multi-layer feature fusion approach that incorporates cross-attention and cross-modal attention mechanisms with symmetric processing of intra- and inter-modal correlations, thereby obtaining multi-granularity features. Extensive experiments were conducted on two public datasets, namely FB15K-DB15K and FB15K-YAGO15K. With 20% aligned seeds, ERMF improves Hits@1 by 8.4% and 26%, and MRR by 6% and 19.2% compared to the best baseline. The symmetric architecture of our model ensures the robust and balanced utilization of multi-modal information, aligning with the principles of structural and functional symmetry in knowledge integration. Full article

Traditional villages contain rich natural and humanistic information, and exploring the spatial distribution characteristics and cultural landscape zoning of traditional villages can provide scientific support for their centralized and continuous protection and renewal and sustainable development. In this study, 326 traditional villages in the northern Henan region were taken as the research object, followed by analyzing their spatial distribution characteristics by using geostatistical methods, such as nearest-neighbor index, imbalance index, geographic concentration index, etc., combining the theory of cultural landscape to construct the traditional villages’ cultural factor index system, extracting the cultural factors of the traditional villages to form a database, and adopting the K-means clustering method to divide the region. The results show that the spatial distribution of traditional villages in northern Henan tends to be concentrated overall, with an uneven distribution throughout the region. The density is highest in the northwestern part of Hebi City and lower in the central and southern parts of Xinxiang City, Neihuang County, and Puyang City. Based on the cultural factor index system, the K-means algorithm divides the traditional villages in northern Henan into six clusters. Among them, the five cultural factors of topography and geomorphology, building materials, courtyard form, structural system, and altitude and elevation are the most significant, and they are the cultural factors that dominate the landscape of the villages. There is a significant correlation between topography, altitude, and other cultural factors, while the correlation between the street layout and other factors is the lowest. Based on the similarity between the clustering results and the landscape characteristics, the traditional villages in northern Henan can be divided into the stone masonry building culture area along the Taihang Mountains, the brick and stone mixed building culture area in the low hills of the Taihang Mountains, the brick and wood building culture area in the North China Plain, and the raw soil building culture area in the transition zone of the Loess Plateau. Full article

Anomaly detection plays a vital role in the processing of hyperspectral images and has garnered significant attention recently. Hyperspectral images are characterized by their “integration of spatial and spectral information” as well as their rich spectral content. Therefore, effectively combining the spatial and spectral information of images and thoroughly mining the latent structural features of the data to achieve high-precision detection are significant challenges in hyperspectral anomaly detection. Traditional detection methods, which rely solely on raw spectral features, often face limitations in enhancing target signals and suppressing background noise. To address these issues, we propose an innovative hyperspectral anomaly detection approach based on the fractional optimal-order Fourier transform combined with a multi-directional dual-window detector. First, a new criterion for determining the optimal order of the fractional Fourier transform is introduced. By applying the optimal fractional Fourier transform, prominent features are extracted from the hyperspectral data. Subsequently, band selection is applied to the transformed data to remove redundant information and retain critical features. Additionally, a multi-directional sliding dual-window RAD detector is designed. This detector fully utilizes the spectral information of the pixel under test along with its neighboring information in eight directions to enhance detection accuracy. Furthermore, a spatial–spectral combined saliency-weighted strategy is developed to fuse the detection results from various directions using weighted contributions, further improving the distinction between anomalies and the background. The proposed method’s experimental results on six classic datasets demonstrate that it outperforms existing detectors, achieving superior detection performance. Full article