Search Results (65)

Rail transit dispatch speech plays a critical role in ensuring the safety of urban rail operations. To enable automated and accurate compliance assessment of dispatch speech, this study proposes an improved deep learning model to address the limitations of conventional approaches in terms of accuracy and robustness. Building upon the baseline Whisper model, two key enhancements are introduced: (1) low-rank adaptation (LoRA) fine-tuning to better adapt the model to the specific acoustic and linguistic characteristics of rail transit dispatch speech, and (2) a novel entity-aware attention mechanism that incorporates named entity recognition (NER) embeddings into the decoder. This mechanism enables attention computation between words belonging to the same entity category across different commands and recitations, which helps highlight keywords critical for compliance assessment and achieve precise inter-sentence element alignment. Experimental results on real-world test sets demonstrate that the proposed model improves recognition accuracy by 30.5% compared to the baseline model. In terms of robustness, we evaluate the relative performance retention under severe noise conditions. While Zero-shot, Full Fine-tuning, and LoRA-only models achieve robustness scores of 72.2%, 72.4%, and 72.1%, respectively, and the NER-only variant reaches 88.1%, our proposed approach further improves to 89.6%. These results validate the model’s significant robustness and its potential to provide efficient and reliable technical support for ensuring the normative use of dispatch speech in urban rail transit operations. Full article

Knowledge Graph Reasoning (KGR) aims to deduce missing or novel knowledge by learning structured information and semantic relationships within Knowledge Graphs (KGs). Despite significant advances achieved by deep neural networks in recent years, existing models typically extract non-linear representations from explicit features in a relatively simplistic manner and fail to fully exploit semantic heterogeneity of relation types and entity co-occurrence frequencies. Consequently, these models struggle to capture critical predictive cues embedded in various entities and relations. To address these limitations, this paper proposes a relation aware spectral decoupling attention network for KGR (RASD). First, a spectral decoupling attention network module projects joint embeddings of entities and relations into the frequency domain, extracting features across different frequency bands and adaptively allocating attention at the global level to model frequency specific information. Next, a relation-aware learning module employs relation aware filters and an augmentation mechanism to preserve distinct relational properties and suppress redundant features, thereby enhancing representation of heterogeneous relations. Experimental results demonstrate that RASD achieves significant and consistent improvements over multiple leading baseline models on link prediction tasks across five public benchmark datasets. Full article

In recent years, geographic knowledge graphs (GeoKGs) have shown great promise in representing spatio-temporal and event-driven knowledge. However, existing knowledge graph embedding approaches mainly focus on structural patterns and often overlook the dynamic evolution of entities in both time and space, which limits their effectiveness in downstream reasoning tasks. To address this, we propose a spatio-temporal evolutionary knowledge embedding approach (ST-EKA) that enhances entity representations by modeling their evolution through type-aware encoding, temporal and spatial decay mechanisms, and context aggregation. ST-EKA integrates four core components, including an entity encoder constrained by relational type consistency, a temporal encoder capable of handling both time points and intervals through unified sampling and feedforward encoding, a multi-scale spatial encoder that combines geometric coordinates with semantic attributes, and an evolutionary knowledge encoder that employs attention-based spatio-temporal weighting to capture contextual dynamics. We evaluate ST-EKA on three representative GeoKG datasets—GDELT, ICEWS, and HAD. The results demonstrate that ST-EKA achieves an average improvement of 6.5774% in AUC and 5.0992% in APR on representation learning tasks. In question answering tasks, it yields a maximum average increase of 1.7907% in AUC and 0.5843% in APR. Notably, it exhibits superior performance in chain queries and complex spatio-temporal reasoning, validating its strong robustness, good interpretability, and practical application value. Full article

Text-based person search (TPS), a critical technology for security and surveillance, aims to retrieve target individuals from image galleries using textual descriptions. The existing methods face two challenges: (1) ambiguous attribute–noun association (AANA), where syntactic ambiguities lead to incorrect associations between attributes and the intended nouns; and (2) textual noise and relevance imbalance (TNRI), where irrelevant or non-discriminative tokens (e.g., ‘wearing’) reduce the saliency of critical visual attributes in the textual description. To address these aspects, we propose the dependency-aware entity–attribute alignment network (DEAAN), a novel framework that explicitly tackles AANA through dependency-guided attention and TNRI via adaptive token filtering. The DEAAN introduces two modules: (1) dependency-assisted implicit reasoning (DAIR) to resolve AANA through syntactic parsing, and (2) relevance-adaptive token selection (RATS) to suppress TNRI by learning token saliency. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate state-of-the-art performance, with the DEAAN achieving a Rank-1 accuracy of 76.71% and an mAP of 69.07% on CUHK-PEDES, surpassing RDE by 0.77% in Rank-1 and 1.51% in mAP. Ablation studies reveal that DAIR and RATS individually improve Rank-1 by 2.54% and 3.42%, while their combination elevates the performance by 6.35%, validating their synergy. This work bridges structured linguistic analysis with adaptive feature selection, demonstrating practical robustness in surveillance-oriented TPS scenarios. Full article

Cross-document relation extraction (CodRE) aims to predict the semantic relationships between target entities located in different documents, a critical capability for comprehensive knowledge graph construction and multi-source intelligence analysis. Existing approaches primarily rely on bridge entities to capture interdependencies between target entities across documents. However, these models face two potential limitations: they employ entity-centered context filters that overlook relation-specific information, and they fail to account for varying semantic distances between document paths. To address these challenges, we propose CLEAR (Cross-document Link-Enhanced Attention for Relations), a novel framework integrating three key components: (1) the Relation-aware Context Filter that incorporates relation type descriptions to preserve critical relation-specific evidence; (2) the Path Distance-Weighted Attention mechanism that dynamically adjusts attention weights based on semantic distances between document paths; and (3) a cross-path entity matrix that leverages inner- and inter-path relations to enrich target entity representations. Experimental results on the CodRED benchmark demonstrate that CLEAR outperforms all competitive baselines, achieving state-of-the-art performance, with 68.78% AUC and 68.42% F1 scores, confirming the effectiveness of our framework. Full article

As Advanced Persistent Threats (APTs) continue to evolve, constructing a dynamic cybersecurity knowledge graph requires precise extraction of entity–relationship triples from unstructured threat intelligence. Existing approaches, however, face significant challenges in modeling low-frequency threat associations, extracting multi-relational entities, and resolving overlapping entity scenarios. To overcome these limitations, we propose the Symmetry-Aware Prototype Contrastive Learning (SAPCL) framework for joint entity and relation extraction. By explicitly modeling syntactic symmetry in attack-chain dependency structures and its interaction with asymmetric adversarial semantics, SAPCL integrates dependency relation types with contextual features using a type-enhanced Graph Attention Network. This symmetry–asymmetry fusion facilitates a more effective extraction of multi-relational triples. Furthermore, we introduce a triple prototype contrastive learning mechanism that enhances the robustness of low-frequency relations through hierarchical semantic alignment and adaptive prototype updates. A non-autoregressive decoding architecture is also employed to globally generate multi-relational triples while mitigating semantic ambiguities. SAPCL was evaluated on three publicly available CTI datasets: HACKER, ACTI, and LADDER. It achieved F1-scores of 56.63%, 60.21%, and 53.65%, respectively. Notably, SAPCL demonstrated a substantial improvement of 14.5 percentage points on the HACKER dataset, validating its effectiveness in real-world cyber threat extraction scenarios. By synergizing syntactic–semantic multi-feature fusion with symmetry-driven dynamic representation learning, SAPCL establishes a symmetry–asymmetry adaptive paradigm for cybersecurity knowledge graph construction, thus enhancing APT attack tracing, threat hunting, and proactive cyber defense. Full article

With the advancement of information technology, artificial intelligence (AI) has demonstrated significant potential in clinical prediction, helping to improve the level of intelligent medical care. Current clinical practice primarily relies on patients’ time series data and clinical notes to predict health status and makes predictions by simply concatenating cross-modal features. However, they not only ignore the inherent correlation between cross-modal features, but also fail to analyze the collaborative representation of multi-granularity features from diverse perspectives. To address these challenges, we propose a deep dynamic memory-driven cross-modal feature representation network for clinical outcome prediction. Specifically, we use a Bi-directional Gated Recurrent Unit (BiGRU) network to capture dynamic features in time series data and a dual-view feature encoding model with sentence-aware and entity-aware capabilities to extract clinical text features from global semantic and local concept perspectives, respectively. Furthermore, we introduce a memory-driven cross-modal attention mechanism, which dynamically establishes deep correlations between clinical text and time series features through learnable memory matrices. In addition, we also introduce a memory-aware constrained layer normalization to alleviate the challenges of multi-modal feature heterogeneity. Besides, we use gating mechanisms and dynamic memory components to enable the model to learn feature information of different historical-current patterns, further improving the model’s performance. Lastly, we combine the integrated gradients for feature attribution analysis to enhance the model’s interpretability. Finally, we evaluate the model’s performance on the MIMIC-III dataset, and the experimental results demonstrate that the model outperforms current advanced baselines in clinical outcome prediction tasks. Notably, our model maintains high predictive accuracy and robustness even when faced with imbalanced data. It can also provide a new perspective for researchers in the field of AI medicine. Full article

Event extraction aims to identify and structure event information from unstructured text, playing a critical role in real-world applications such as news analysis, public opinion discovery, and intelligence gathering. Traditional approaches, however, struggle with event co-occurrence and long-distance dependencies. To address these challenges, we introduce the Semantic-aware Prompt-based Argument Extractor (SPARE) model, which integrates entity extraction, heterogeneous graph construction, event type detection, and argument filling. By constructing a document–sentence–entity heterogeneous graph and employing graph convolutional networks (GCNs), the model effectively captures global semantic associations and interactions between cross-sentence triggers and arguments. Additionally, a position-aware semantic role (SRL) attention mechanism is proposed to enhance the association between semantic and positional information, improving argument extraction accuracy in the context of event co-occurrence. The experimental outcomes on the Richly Annotated Multilingual Schema-guided Event Structure (RAMS) and WikiEvents datasets display considerable F1 score improvements, which confirms the model’s effectiveness. Full article

The emergence of short video applications (“apps”) has facilitated the dissemination, inheritance, and protection of traditional sports and games (TSGs). However, the effectiveness of these apps in raising public awareness and responsibility toward the preservation and heritage of TSGs has received insufficient research attention. This study constructs a theoretical model based on value-belief-norm theory and the theory of planned behavior, employing both PLS-SEM and fsQCA methods to empirically analyze 417 questionnaires. The results indicate that the PLS-SEM method identifies key factors influencing users’ responsible behaviors toward TSGs on short video apps, along with the complex and interdependent relationships among these factors. The fsQCA method reveals the intricate interactions and nonlinear effects of the antecedents on users’ responsible behaviors and identifies six configurations that drive high-level TSG responsible behaviors among users. This paper extends research on public responsible behaviors concerning TSGs and provides important practical guidance for government managers, inheritors, and conservation entities in the protection and heritage of TSGs. Full article

Within the phenotypic spectrum of Alzheimer’s disease (AD), Creutzfeldt–Jakob disease (CJD) and cerebral amyloid angiopathy (CAA), dementia that is attributed to iatrogenic transmission has increasingly gained scientific attention recently. Newly recognized, this treatment-induced form of dementia may result from exposure to certain medical or surgical procedures. The present review aims to explore the distinct features of acquired dementia encompassing a history of potential exposure and relatively early age of onset, highlighting transmission potential with a rather prion-like pattern. Having reviewed all available relevant literature, dementia of iatrogenic etiology represents a new disease entity that requires an individualized investigation process and poses a great clinical challenge as far as patients with AD, CJD and CAA are concerned. Understanding the underlying pathophysiology of these rare forms of dementia may significantly enhance awareness within clinical field of neurodegenerative diseases and facilitate their prompt management. Full article

Power equipment maintenance work orders are vital in power equipment management because they contain detailed information such as equipment specifications, defect reports, and specific maintenance activities. However, due to limited research into automated information extraction, valuable operational and maintenance data remain underutilized. A key challenge is recognizing unstructured Chinese maintenance texts filled with specialized and abbreviated terms unique to the power sector. Existing named entity recognition (NER) solutions often fail to effectively manage these complexities. To tackle this, this paper proposes a NER model tailored to power equipment maintenance work orders. First, a dataset called power equipment maintenance work orders (PE-MWO) is constructed, which covers seven entity categories. Next, a novel position- and similarity-aware attention module is proposed, where an innovative position embedding method and attention score calculation are designed to improve the model’s contextual understanding while keeping computational costs low. Further, with this module as the main body, combined with the BERT-wwm-ext and conditional random field (CRF) modules, an efficient NER model is jointly constructed. Finally, validated on the PE-MWO and five public datasets, our model shows high accuracy in recognizing power sector entities, outperforming comparative models on public datasets. Full article

To address the issues of fragmented species information, low knowledge extraction efficiency, and insufficient utilization in the aquaculture domain, the main objective of this study is to construct the first knowledge graph for the Golden Pomfret aquaculture field and optimize the named entity recognition (NER) methods used in the construction process. The dataset contains challenges such as long text processing, strong local context dependencies, and entity sample imbalance, which result in low information extraction efficiency, recognition errors or omissions, and weak model generalization. This paper proposes a novel named entity recognition model, LA-CANER (Local Attention-Category Awareness NER), which combines local attention mechanisms with category awareness to improve both the accuracy and speed of NER. The constructed knowledge graph provides significant scientific knowledge support to Golden Pomfret aquaculture workers. First, by integrating and standardizing multi-source information, the knowledge graph offers comprehensive and accurate data, supporting decision-making for aquaculture management. The graph enables precise reasoning based on disease symptoms, environmental factors, and historical production data, helping workers identify potential risks early and take preventive actions. Furthermore, the knowledge graph can be integrated with large models like GPT-4 and DeepSeek-R1. By providing structured knowledge and rules, the graph enhances the reasoning and decision-making capabilities of these models. This promotes the application of smart aquaculture technologies and enables precision farming, ultimately increasing overall industry efficiency. Full article

Entity alignment in knowledge graphs plays a crucial role in ensuring the consistency and integration of data across different domains. For example, in power topology, accurate entity matching is essential for optimizing system design and control. However, traditional approaches to entity alignment often rely heavily on language models to extract general features, which can overlook important logical aspects such as temporal and event-centric relationships that are crucial for precise alignment.To address this issue, we propose EAL (Entity Alignment with Logical Capturing), a novel and lightweight RNN-based framework designed to enhance logical feature learning in entity alignment tasks. EAL introduces a logical paradigm learning module that effectively models complex-event relationships, capturing structured and context-aware logical patterns that are essential for alignment. This module encodes logical dependencies between entities to dynamically capture both local and global temporal-event interactions. Additionally, we integrate an adaptive logical attention mechanism that prioritizes influential logical features based on task-specific contexts, ensuring the extracted features are both relevant and discriminative. EAL also incorporates a key feature alignment framework that emphasizes critical event-centric logical structures. This framework employs a hierarchical feature aggregation strategy combining low-level information on temporal events with high-level semantic patterns, enabling robust entity matching while maintaining computational efficiency. By leveraging a multi-stage alignment process, EAL iteratively refines alignment predictions, optimizing both precision and recall. Experimental results on benchmark datasets demonstrate the effectiveness and robustness of EAL, which not only achieves superior performance in entity alignment tasks but also provides a lightweight yet powerful solution that reduces reliance on large language models. Full article

Knowledge graphs have shown great potential in alleviating the data sparsity problem in recommendation systems. However, existing graph-attention-based recommendation methods primarily focus on user–item–entity interactions, overlooking potential relationships between users while introducing noisy entities and redundant high-order information. To address these challenges, this paper proposes a graph-attention-based recommendation method that enhances user features using knowledge graphs (KGAEUF). This method models user relationships through collaborative propagation, links entities via similar user entities, and filters highly relevant entities from both user–entity and user–relation perspectives to reduce noise interference. In multi-layer propagation, a distance-aware weight allocation mechanism is introduced to optimize high-order information aggregation. Experimental results demonstrate that KGAEUF outperforms existing methods on AUC and F1 metrics on the Last.FM and Book-Crossing datasets, validating the model’s effectiveness. Full article

Background/Objectives: Gastrointestinal diseases are a major cause of morbidity in common variable immunodeficiency disorder (CVID), clinically often mimicking other conditions including celiac disease and inflammatory bowel disease (IBD). Hence, diagnosis of CVID remains challenging. This study aims to raise awareness and highlight histopathological clues for CVID in intestinal biopsies, emphasizing diagnostic pitfalls for the pathologist/gastroenterologist. Methods: We reviewed 63 (18 duodenal, 23 ileal, 22 colonic) biopsies and case histories from seven CVID patients, obtained over a 31-year period, with attention to active inflammation, intraepithelial lymphocytes, plasma cells, lymphoid hyperplasia, crypt/villous architecture, subepithelial collagen, apoptosis, granulomas, and infections. Clinical information of 41 pathology requests was reviewed. Results: Gastrointestinal symptoms were variable. Histological features included IBD-like (3/7), celiac disease-like (2/7), graft-versus-host disease (GVHD)-like (2/7), lymphocytic sprue/colitis-like (3/7), collagenous colitis-like (2/7), and acute colitis-like (4/7) patterns, often overlapping (2/7) and/or changing over time (3/7). Lymphoid hyperplasia was seen in 3/7 patients; 1/7 had giardiasis; and 5/7 had few plasma cells, usually only in part of the gut (3/5). Clinical information of 12/41 (29%) pathology requests mentioned known/suspected CVID, despite being known in 33/41 (80%). Conclusions: Clinical/histological features of CVID in the gut are diverse, often mimicking IBD, microscopic colitis, celiac disease and/or GVHD, hence the importance of adequate clinical information. Some histological features are atypical of these established entities and may indicate CVID, as may overlapping/changing histological patterns and/or few plasma cells in part of the gut. Awareness of the heterogenous clinical presentation and histopathological indicators of CVID may improve diagnosis. Full article