Search Results (1,360)

Rapid urbanization and the proliferation of heterogeneous urban data have intensified the challenges of semantic interoperability and integrated urban governance. To address this, we propose the Smart City Ontology Framework (SMOF), a standards-driven ontology that unifies Building Information Modeling (BIM), Geographic Information Systems (GIS), Internet of Things (IoT), and relational data. SMOF organizes five core modules and eleven major entity categories, with universal and extensible attributes and relations to support cross-domain data integration. SMOF was developed through competency questions, authoritative knowledge sources, and explicit design principles, ensuring methodological rigor and alignment with real governance needs. Its evaluation combined three complementary approaches against baseline models: quantitative metrics demonstrated higher attribute richness and balanced hierarchy; LLM as judge assessments confirmed conceptual completeness, consistency, and scalability; and expert scoring highlighted superior scenario fitness and clarity. Together, these results indicate that SMOF achieves both structural soundness and practical adaptability. Beyond structural evaluation, SMOF was validated in two representative urban service scenarios, demonstrating its capacity to integrate heterogeneous data, support graph-based querying and enable ontology-driven reasoning. In sum, SMOF offers a robust and scalable solution for semantic data integration, advancing smart city governance and decision-making efficiency. Full article

With the rapid evolution of artificial intelligence technologies in power systems, data-driven time-series forecasting has become instrumental in enhancing the stability and reliability of power systems, allowing operators to anticipate demand fluctuations and optimize energy distribution. Despite the notable progress made by current methods, they are still hindered by two major limitations: most existing models are relatively small in architecture, failing to fully leverage the potential of large-scale models, and they are based on fixed nonlinear mapping functions that cannot adequately capture complex patterns, leading to information loss. To this end, an LLM-Empowered Kolmogorov–Arnold frequency learning (LKFL) is proposed for time series forecasting in power systems, which consists of LLM-based prompt representation learning, KAN-based frequency representation learning, and entropy-oriented cross-modal fusion. Specifically, LKFL first transforms multivariable time-series data into text prompts and leverages a pre-trained LLM to extract semantic-rich prompt representations. It then applies Fast Fourier Transform to convert the time-series data into the frequency domain and employs Kolmogorov–Arnold networks (KAN) to capture multi-scale periodic structures and complex frequency characteristics. Finally, LKFL integrates the prompt and frequency representations through an entropy-oriented cross-modal fusion strategy, which minimizes the semantic gap between different modalities and ensures full integration of complementary information. This comprehensive approach enables LKFL to achieve superior forecasting performance in power systems. Extensive evaluations on five benchmarks verify that LKFL sets a new standard for time-series forecasting in power systems compared with baseline methods. Full article

Mineral prospecting from vast geological text corpora is impeded by challenges in domain-specific semantic interpretation and knowledge synthesis. General-purpose Large Language Models (LLMs) struggle to parse the complex lexicon and relational semantics of geological texts, limiting their utility for constructing precise knowledge graphs (KGs). Our novel framework addresses this gap by integrating a domain-specific LLM, GeoGPT, with a lightweight retrieval-augmented generation architecture, LightRAG. Within this framework, GeoGPT automates the construction of a high-quality mineral-prospecting KG by performing ontology definition, entity recognition, and relation extraction. The LightRAG component then leverages this KG to power a specialized geological question-answering (Q&A) system featuring a dual-layer retrieval mechanism for enhanced precision and an incremental update capability for dynamic knowledge incorporation. The results indicate that the proposed method achieves a mean F1-score of 0.835 for entity extraction, representing a 17% to 25% performance improvement over general-purpose large models using generic prompts. Furthermore, the geological Q&A model, built upon the LightRAG framework with GeoGPT as its core, demonstrates a superior win rate against the DeepSeek-V3 and Qwen2.5-72B general-purpose large models by 8–29% in the geochemistry domain and 53–78% in the remote sensing geology domain. This study establishes an effective and scalable methodology for intelligent geological text analysis, enabling lightweight, high-performance Q&A systems that accelerate knowledge discovery in mineral exploration. Full article

In recent years, research in sequential recommendation has primarily refined user intent by constructing sequence-level contrastive learning tasks through data augmentation or by extracting preference information from the latent space of user behavior sequences. However, existing methods suffer from two critical limitations. Firstly, they fail to account for how random data augmentation may introduce unreasonable item associations in contrastive learning samples, thereby perturbing sequential semantic relationships. Secondly, the neglect of temporal dependencies may prevent models from effectively distinguishing between incidental behaviors and stable intentions, ultimately impairing the learning of user intent representations. To address these limitations, we propose TCLRec, a novel temporal-aware and intent contrastive learning framework for sequential recommendation, incorporating symmetry into its architecture. During the data augmentation phase, the model employs a symmetrical contrastive learning architecture and incorporates semantic enhancement operators to integrate user preferences. By introducing user rating information into both branches of the contrastive learning framework, this approach effectively enhances the semantic relevance between positive sample pairs. Furthermore, in the intent contrastive learning phase, TCLRec adaptively attenuates noise information in the frequency domain through learnable filters, while in the pre-training phase of sequence-level contrastive learning, it introduces a temporal-aware network that utilizes additional self-supervised signals to assist the model in capturing both long-term dependencies and short-term interests from user behavior sequences. The model employs a multi-task training strategy that alternately performs intent contrastive learning and sequential recommendation tasks to jointly optimize user intent representations. Comprehensive experiments conducted on the Beauty, Sports, and LastFM datasets demonstrate the soundness and effectiveness of TCLRec, where the incorporation of symmetry enhances the model’s capability to represent user intentions. Full article

Manual pixel-level annotation remains a major bottleneck in deploying deep learning models for dense prediction and semantic segmentation tasks across domains. This challenge is especially pronounced in applications involving fine-scale structures, such as cracks in infrastructure or lesions in medical imaging, where annotations are time-consuming, expensive, and subject to inter-observer variability. To address these challenges, this work proposes a weakly supervised and annotation-efficient segmentation framework that integrates sparse bounding-box annotations with a limited subset of strong (pixel-level) labels to train robust segmentation models. The fundamental element of the framework is a lightweight Bounding Box Encoder that converts weak annotations into multi-scale attention maps. These maps guide a ConvNeXt-Base encoder, and a lightweight U-Net–style convolutional neural network (CNN) decoder—using nearest-neighbor upsampling and skip connections—reconstructs the final segmentation mask. This design enables the model to focus on semantically relevant regions without relying on full supervision, drastically reducing annotation cost while maintaining high accuracy. We validate our framework on two distinct domains, road crack detection and skin cancer segmentation, demonstrating that it achieves performance comparable to fully supervised segmentation models using only 10–20% of strong annotations. Given the ability of the proposed framework to generalize across varied visual contexts, it has strong potential as a general annotation-efficient segmentation tool for domains where strong labeling is costly or infeasible. Full article

Synthetic aperture radar (SAR) exhibits all-day and all-weather capabilities, granting it significant application in remote sensing. However, interpreting SAR images requires extensive expertise, making SAR-to-optical remote sensing image translation a crucial research direction. While conditional generative adversarial networks (CGANs) have demonstrated exceptional performance in image translation tasks, their massive number of parameters pose substantial challenges. Therefore, this paper proposes ILF-BDSNet, a compressed network for SAR-to-optical image translation. Specifically, first, standard convolutions in the feature-transformation module of the teacher network are replaced with depthwise separable convolutions to construct the student network, and a dual-resolution collaborative discriminator based on PatchGAN is proposed. Next, knowledge distillation based on intermediate-layer features and channel pruning via weight sharing are designed to train the student network. Then, the bio-inspired dynamic search of channel configuration (BDSCC) algorithm is proposed to efficiently select the optimal subnet. Meanwhile, the pixel-semantic dual-domain alignment loss function is designed. The feature-matching loss within this function establishes an alignment mechanism based on intermediate-layer features from the discriminator. Extensive experiments demonstrate the superiority of ILF-BDSNet, which significantly reduces number of parameters and computational complexity while still generating high-quality optical images, providing an efficient solution for SAR image translation in resource-constrained environments. Full article

Objectives: The process of social rehabilitation involves several stages, from assessing an individual’s condition and determining their potential for rehabilitation to implementing a personalized plan with continuous monitoring of progress. Advances in information technology, including artificial intelligence, enable the use of software-assisted solutions for objective assessments and personalized rehabilitation strategies. The research aims to present interconnected semantic models that represent expandable knowledge in the field of rehabilitation, as well as an integrated framework and methodology for constructing virtual assistants and personalized decision support systems based on these models. Materials and Methods: The knowledge and data accumulated in these areas require special tools for their representation, access, and use. To develop a set of models that form the basis of decision support systems in rehabilitation, it is necessary to (1) analyze the domain, identify concepts and group them by type, and establish a set of resources that should contain knowledge for intellectual support; (2) create a set of semantic models to represent knowledge for the rehabilitation of patients. The ontological approach, combined with the cloud cover of the IACPaaS platform, has been proposed. Results: This paper presents a suite of semantic models and a methodology for implementing decision support systems capable of expanding rehabilitation knowledge through updated regulatory frameworks and empirical data. Conclusions: The potential advantage of such systems is the combination of the most relevant knowledge with a high degree of personalization in rehabilitation planning. Full article

Multi-modal sensor fusion has become a cornerstone of robust autonomous driving systems, enabling perception models to integrate complementary cues from cameras, LiDARs, radars, and other modalities. This survey provides a structured overview of recent advances in deep learning-based fusion methods, categorizing them by architectural paradigms (e.g., BEV-centric fusion and cross-modal attention), learning strategies, and task adaptations. We highlight two dominant architectural trends: unified BEV representation and token-level cross-modal alignment, analyzing their design trade-offs and integration challenges. Furthermore, we review a wide range of applications, from object detection and semantic segmentation to behavior prediction and planning. Despite considerable progress, real-world deployment is hindered by issues such as spatio-temporal misalignment, domain shifts, and limited interpretability. We discuss how recent developments, such as diffusion models for generative fusion, Mamba-style recurrent architectures, and large vision–language models, may unlock future directions for scalable and trustworthy perception systems. Extensive comparisons, benchmark analyses, and design insights are provided to guide future research in this rapidly evolving field. Full article

Older adults often face significant challenges in understanding medical information due to cognitive aging and limited health literacy. Existing simplification models, while effective in general domains, cannot adapt content for elderly users, frequently overlooking narrative tone, readability constraints, and semantic fidelity. In this work, we propose GENSIM—a Generative Expert-Narrated Simplification Model tailored for age-adapted medical text simplification. GENSIM introduces a modular architecture that integrates a Dual-Stream Encoder, which fuses biomedical semantics with elder-friendly linguistic patterns; a Persona-Tuned Narrative Decoder, which controls tone, clarity, and empathy; and a Reinforcement Learning with Human Feedback (RLHF) framework guided by dual discriminators for factual alignment and age-specific readability. Trained on a triad of corpora—SimpleDC, PLABA, and a custom NIH-SeniorHealth corpus—GENSIM achieves state-of-the-art performance on SARI, FKGL, BERTScore, and BLEU across multiple test sets. Ablation studies confirm the individual and synergistic value of each component, while structured human evaluations demonstrate that GENSIM produces outputs rated significantly higher in faithfulness, simplicity, and demographic suitability. This work represents the first unified framework for elderly-centered medical text simplification and marks a paradigm shift toward inclusive, user-aligned generation for health communication. Full article

Universities face growing pressure to deliver personalized learning that prepares students with adaptable, future-ready competencies. Traditional static curricula are often unable to meet these demands. This paper introduces a novel framework based on AI-enhanced digital twins of students (DTS) as dynamic virtual representations integrating academic performance, competency attainment, learning preferences, career objectives, and engagement patterns. The DTS framework employs artificial intelligence algorithms, semantic ontologies spanning educational and career domains, and real-time feedback mechanisms for personalized learning pathway orchestration. To demonstrate the framework’s potential, a simulation study was conducted using synthetic student data. Results compared DTS-guided adaptive pathways with traditional static approaches and showed improvements in competency attainment, engagement, learning efficiency, and reduced dropout risk. Full article

With the rapid development of social media, short-text data have become increasingly important in fields such as public opinion monitoring, user feedback analysis, and intelligent recommendation systems. However, existing short-text sentiment analysis models often suffer from limited cross-domain adaptability and poor generalization performance. To address these challenges, this study proposes a novel short-text sentiment classification model based on the Bidirectional Encoder Representations from Transformers (BERTs) and a dual-stream Transformer gated attention mechanism. This model first employs Bidirectional Encoder Representations from Transformers (BERTs) and the Chinese Robustly Optimized BERT Pretraining Approach (Chinese-RoBERTa) to achieve data augmentation and multilevel semantic mining, thereby expanding the training corpus and enhancing minority class coverage. Second, a dual-stream Transformer gated attention mechanism was developed to dynamically adjust feature fusion weights, enhancing adaptability to heterogeneous texts. Finally, the model integrates a Bidirectional Gated Recurrent Unit (BiGRU) with Multi-Head Self-Attention (MHSA) to strengthen sequence information modeling and global context capture, enabling the precise identification of key sentiment dependencies. The model’s superior performance in handling data imbalance and complex textual sentiment logic scenarios is demonstrated by the experimental results, achieving significant improvements in accuracy and F1 score. The F1 score reached 92.4%, representing an average increase of 8.7% over the baseline models. This provides an effective solution for enhancing the performance and expanding the application scenarios of short-text sentiment analysis models. Full article

This paper proposes a Tibetan judicial event argument extraction method based on machine reading comprehension (MRC) to address the challenges of data scarcity and insufficient model generalization in low-resource language scenarios. Unlike traditional methods, this work models event argument extraction as an MRC task, progressively identifying and extracting various event arguments through a question-guided approach. First, a strategy for constructing event knowledge-enhanced questions tailored to the Tibetan judicial domain is designed. Specifically, interrogative words are formulated for different types of event arguments, and event semantic information is incorporated into questions to effectively disambiguate questions. Second, a deep semantic understanding architecture for Tibetan judicial events based on the CINO (Chinese Minority Pretrained Language Model) is proposed, incorporating a multi-head self-attention mechanism to enhance semantic alignment and global understanding between event sentences and questions. Finally, a two-stage training strategy is proposed for low-resource languages. Training is performed on a general Tibetan machine reading comprehension dataset, followed by task-adaptive fine-tuning on judicial domain data, effectively alleviating the data scarcity issue. Experimental results show that the proposed method achieved an F1-score of 76.59% in the Tibetan judicial event argument extraction task. This research offers new ideas for low-resource language event extraction and is of great significance for promoting intelligent information processing of minority languages. Full article

High-resolution remote sensing imagery is crucial for ship extraction in ocean-related applications. Existing object detection and semantic segmentation methods for ship extraction have limitations: the former cannot precisely obtain ship shapes, while the latter struggles with small targets and complex backgrounds. This study addresses these issues by constructing two datasets, DIOR_SHIP and LEVIR_SHIP, using the SAM model and morphological operations. A novel MambaSegNet is then designed based on the advanced Mamba architecture. It is an encoder–decoder network with MambaLayer and ResMambaBlock for effective multi-scale feature processing. The experiments conducted with seven mainstream models show that the IOU of MambaSegNet is 0.8208, the Accuracy is 0.9176, the Precision is 0.9276, the Recall is 0.9076, and the F1-score is 0.9176. Compared with other models, it acquired the best performance. This research offers a valuable dataset and a novel model for ship extraction, with potential cross-domain application prospects. Full article

The Internet of Things (IoT) has enabled a vast network of devices to communicate over the Internet. However, the fragmentation of IoT systems continues to hinder seamless data sharing and coordinated management across platforms.However, there is currently no actual search engine for IoT data. Existing IoT search engines are considered device discovery tools, providing only metadata about devices rather than enabling access to IoT application data. While efforts such as IoTCrawler have striven to support IoT application data, they have largely failed due to the fragmentation of IoT systems and the heterogeneity of IoT data.To address this, we recently introduced SensorsConnect—a unified framework designed to facilitate interoperable content and sensor data sharing among collaborative IoT systems, inspired by how the World Wide Web (WWW) enabled shared and accessible information spaces for humans. This paper presents the IoT Agentic Search Engine (IoTASE), a real-time semantic search engine tailored specifically for IoT environments. IoTASE leverages LLMs and Retrieval-Augmented Generation (RAG) techniques to address the challenges of navigating and searching vast, heterogeneous streams of real-time IoT data. This approach enables the system to process complex natural language queries and return accurate, contextually relevant results in real time. To evaluate its effectiveness, we implemented a hypothetical deployment in the Toronto region, simulating a realistic urban environment using a dataset composed of 500 services and over 37,000 IoT-like data entries. Our evaluation shows that IoT-ASE achieved 92% accuracy in retrieving intent-aligned services and consistently generated concise, relevant, and preference-aware responses, outperforming generalized outputs produced by systems such as Gemini. These results underscore the potential of IoT-ASE to make real-time IoT data both accessible and actionable, supporting intelligent decision-making across diverse application domains. Full article

Object detection in soccer scenes serves as a fundamental task for soccer video analysis and target tracking. This paper proposes WCC-YOLO, a symmetry-enhanced object detection framework based on YOLOv11n. Our approach integrates symmetry principles at multiple levels: (1) The novel C3k2-WTConv module synergistically combines conventional convolution with wavelet decomposition, leveraging the orthogonal symmetry of Haar wavelet quadrature mirror filters (QMFs) to achieve balanced frequency-domain decomposition and enhance multi-scale feature representation. (2) The Channel Prior Convolutional Attention (CPCA) mechanism incorporates symmetrical operations—using average-max pooling pairs in channel attention and multi-scale convolutional kernels in spatial attention—to automatically learn to prioritize semantically salient regions through channel-wise feature recalibration, thereby enabling balanced feature representation. Coupled with InnerShape-IoU for refined bounding box regression, WCC-YOLO achieves a 4.5% improvement in mAP@0.5:0.95 and a 5.7% gain in mAP@0.5 compared to the baseline YOLOv11n while simultaneously reducing the number of parameters and maintaining near-identical inference latency (δ < 0.1 ms). This work demonstrates the value of explicit symmetry-aware modeling for sports analytics. Full article