Search Results (4,295)

This article presents a systematic bibliometric analysis on academic research into Artificial Intelligence (AI) applications in Architectural Conceptual Design (ACD). Based on a curated selection of publications indexed in the Web of Science (WoS) and Scopus databases between 2010 and 2025, this article shows a study that maps the intellectual evolution, thematic composition, and methodological trends of the field. By using the software tool VOSviewer, this study generates a series of knowledge graphs, including Keyword Co-Occurrence and International Collaboration Networks. The findings from this study reveal a rapid acceleration in AI-related research focused on the conceptual design stage, highlighting its transformative potential for architectural practice. Through a critical analysis of bibliometric results, this study identifies dominant research emphases, emerging directions, and persistent frictions between academic approaches and industry adoption. This review article contributes to the theoretical consolidation of AI applications in ACD and provides a structured foundation for future ACD-related research and practice. Full article

Partial multi-label feature selection aims to identify discriminative features from data where each instance is associated with an ambiguous candidate label set. Existing methods are typically built upon single-scale modeling assumptions and may fail to fully exploit the multi-granularity structure underlying instance–label relationships. To address this limitation, we propose a novel framework termed PML-FSMNG, which integrates entropy-weighted multi-scale neighborhood granules with label distribution learning. Specifically, multi-scale neighborhood systems are constructed to estimate label distinguishability at multiple structural scales, and Shannon entropy is employed to adaptively fuse scale-specific label distributions into a robust soft supervisory signal. Based on the learned label distribution, an embedded sparse regression model with ${\ell }_{2,1}$-norm regularization is developed for discriminative feature selection, together with an entropy-regularized adaptive graph learning mechanism to preserve intrinsic geometric structure. Extensive experiments on benchmark datasets demonstrate that the proposed method consistently outperforms several state-of-the-art approaches, validating the effectiveness of multi-scale modeling and entropy-guided adaptive learning under label ambiguity. Full article

The development of novel antiepileptic agents requires early identification of pharmacokinetic limitations to mitigate risks at later stages. This study aimed to perform in silico profiling of a library containing 448 novel 2H,5H-chromeno[4’,3’:4,5]thiopyrano[2,3-d]thiazol-2-one derivatives to select lead compounds with an optimal balance of safety and efficacy. The study was conducted using the ADMET-AI platform, based on a graph neural network, to predict physicochemical, pharmacokinetic, and toxicological properties. The methodology involved calculating drug-likeness descriptors for primary screening and a comparative statistical analysis of the top 20 selected structures against 16 approved antiepileptic drugs and four reference compounds. Based on drug-likeness descriptors and predicted ADMET (absorption, distribution, metabolism, excretion, toxicity) related parameters, 20 structures were prioritized for further analysis. Their predicted profiles suggested high intestinal absorption and blood–brain barrier (BBB) permeability, which may be relevant for central nervous system (CNS) directed agents. In comparison with the reference thiazolidinones, the prioritized compounds showed comparatively more favorable predicted mutagenicity and carcinogenicity profiles. Elevated predicted risks of hepatotoxicity and cardiotoxicity were observed for several structures, indicating the need for further structural optimization. The results suggest that the thiopyranothiazolidinone scaffold merits further anticonvulsant-oriented investigation at the stage of early compound prioritization. Experimental validation will be required to confirm the actual pharmacokinetic, toxicological, and anticonvulsant properties of the prioritized compounds. Full article

Street-view imagery supports fine-grained urban monitoring, but most street-scene change detection methods are pixel-centric or object-centric and cannot explicitly capture the evolution of inter-entity spatial relations needed for interpretable tasks (e.g., compliance inspection and post-disaster assessment). To address this, we propose SSPRCD, a scene graph-based framework that extracts entity-relation triplets with pixel locations, builds spatial knowledge graphs, and achieves stable node alignment via intra-/inter-temporal consistency. Graph differencing then identifies added, removed, and unchanged entities/relations, while nGED and graph2vec jointly quantify structural discrepancies between temporal scenes. Experiments on the TSUNAMI dataset, with comparisons across two object detectors and seven scene graph generation backbones, show that SSPRCD achieves a macro-F1 of 0.65 for the object-level task, F1 of 0.72 for binary change detection, and F1 of 0.89 for relation-level detection, consistently outperforming baseline methods. Overall, SSPRCD delivers relation-aware and topology-informed change explanations that improve the interpretability of street-block level change analysis for geospatial in-formation updating and urban applications. Full article

The countries in the Belt and Road Initiative (BRI) significantly influence global carbon emissions, and the spatial correlation and driving mechanisms of their emissions are crucial for regional emission reduction and global climate governance. This study constructs a carbon emission spatial correlation network, where links represent pairwise spatial correlations derived from a modified gravity model, using data from 54 BRI countries (2011–2020). It applies social network analysis (SNA) to examine the network structure and uses the Temporal Exponential Random Graph Model (TERGM) to identify influencing factors. The main findings are as follows: (1) The BRI carbon emission network has become more interconnected and cohesive, with stronger regional connectivity and reduced inequality. (2) The network shows a core–periphery structure with notable spatial association patterns. Countries like Qatar, Israel, India, China, and the UAE have rapidly established carbon emission links, positioning them at the core due to their high connectivity and influence. (3) The network displays temporal dependence, with reciprocity associated with stronger mutual connections and transitivity associated with more cohesive network structures. Technological innovation and industrial structure optimization are positively associated with the formation of carbon emission connections, while energy structure and foreign investment are negatively associated with it. Economic development and technological innovation are associated with a country’s greater involvement in carbon emission connections, and countries with similar urbanization rates, energy, and industrial structures, but large economic disparities are more likely to form carbon emission associations, reflecting potential complementarities in the network structure. Full article

With the proliferation of edge computing in IoT and smart security, there is a growing demand for large-scale encrypted traffic anomaly detection. However, the opaque nature of encrypted traffic makes it difficult for traditional detection methods to balance efficiency and accuracy. To address this challenge, this paper proposes FMTF, a Multi-Scale Feature Fusion method based on Federated Learning for encrypted traffic anomaly detection. FMTF constructs graph structures at three scales—spatial, statistical, and content—to comprehensively characterize traffic features. At the spatial scale, communication graphs are constructed based on host-to-host IP interactions, where each node represents the IP address of a host and edges capture the communication relationships between them. The statistical scale builds traffic statistic graphs based on interactions between port numbers, with nodes representing individual ports and edge weights corresponding to the lengths of transmitted packets. At the content scale, byte-level traffic graphs are generated, where nodes represent pairs of bytes extracted from the traffic data, and edges are weighted using pointwise mutual information (PMI) to reflect the statistical association between byte occurrences. To extract and fuse these multi-scale features, FMTF employs the Graph Attention Network (GAT), enhancing the model’s traffic representation capability. Furthermore, to reduce raw-data exposure in distributed edge environments, FMTF integrates a federated learning framework. In this framework, edge devices train models locally based on their multi-scale traffic features and periodically share model parameters with a central server for aggregation, thereby optimizing the global model without exposing raw data. Experimental results demonstrate that FMTF maintains efficient and accurate anomaly detection performance even under limited computing resources, offering a practical and effective solution for encrypted traffic identification and network security protection in edge computing environments. Full article

Large language models demonstrate strong in-context learning (ICL) capabilities, allowing them to perform diverse tasks without fine-tuning. In knowledge graph question answering (KGQA), natural language questions are translated into SPARQL queries. Existing ICL approaches mainly rely on semantic similarity, often neglecting structural features. To address this limitation, we developed a structure-aware example selection strategy that integrates both semantic and structural patterns by abstracting Resource Description Framework (RDF) triples. We compare four strategies: (1) fully random, (2) semantic similarity, (3) same-type random, and (4) same-type semantic similarity. Experiments on LC-QuAD 1.0 using FLAN-T5 show that in non-fine-tuned settings, structure-aware semantic selection achieves the best results, highlighting the importance of structural congruence, while after fine-tuning, differences between strategies converge but diversity and semantic relevance remain beneficial. These findings demonstrate the critical role of example quality in ICL and provide empirical insights for KGQA design. Full article

Structural reconstruction helps infer the spatial relationships and object layouts in a scene, which is an essential computer vision task for understanding visual content. However, it remains challenging due to the high complexity of scene structural topologies in real-world environments. To address this challenge, this paper proposes RegionGraph, a novel method for structural reconstruction of buildings from a satellite image. It utilizes a layout region graph construction and graph contraction approach, introducing a primitive (layout region) estimation network named ConPNet for detecting and estimating different structural primitives. By combining structural extraction and rendering synthesis processes, RegionGraph constructs a graph structure with layout regions as nodes and adjacency relationships as edges, and transforms the graph optimization process into a node-merging-based graph contraction problem to obtain the final structural representation. The experiments demonstrated that RegionGraph achieves a 4% improvement in average F1 scores across three types of primitives and exhibits higher regional completeness and structural coherency in the reconstructed structure. Full article

With the rapid development of e-commerce and smart manufacturing, automated warehouse systems have become critical infrastructure for modern logistics. In China’s vast market, the dynamic scheduling of Rail-Guided Vehicles (RGVs) faces significant challenges due to complex task uncertainties, hierarchical supply chain structures, and real-time collision avoidance requirements. Traditional rule-based methods and static optimization models often fail to adapt to such dynamic environments. To address these issues, this paper proposes a novel hybrid deep reinforcement learning framework integrating a Dynamic Graph Neural Network (DGNN) and a Transformer model. The DGNN captures the spatiotemporal dependencies of the warehouse network topology, while the Transformer mechanism enhances long-range feature extraction for task prioritization. Furthermore, we design a centralized Deep Q-network (DQN) framework with parameterized action spaces to coordinate multiple RGVs collaboratively. While the system manages multiple physical vehicles, the learning architecture employs a single-agent global scheduler to avoid the non-stationarity issues inherent in multi-agent reinforcement learning. Experimental results based on real-world data from a large-scale electronics manufacturing warehouse demonstrate that our method reduces average task completion time by 18.5% and improves system throughput by 22.3% compared to state-of-the-art baselines. The proposed approach demonstrates potential for intelligent warehouse management in dynamic industrial scenarios. Full article

We investigate whether an ontology-typed knowledge graph (KG) can improve SOAP note generation from clinician–patient encounter transcripts by serving as a structured intermediate representation that organizes clinically salient content while preserving provenance. We introduce Knowledge graph Ontology Supported Medical Output System (KOSMOS), which extracts typed clinical entities with attributes and relationships, grounds entities to UMLS concepts and a schema, and retains links to supporting transcript turns. The resulting graph is provided as context for large language model (LLM)-based SOAP generation either alone (KG-only) or combined with the original transcript (Transcript + Nodes, Transcript + KG). We evaluate these conditions against DocLens and Ambient Clinical Intelligence Benchmark (ACI-BENCH) baselines on their benchmark, claim, and citation analyses. Across all three test sets, transcript-inclusive KOSMOS variants achieve the highest raw scores, numerically exceeding the transcript-only baselines. Claim-level evaluation shows modest, non-significant recall gains for Transcript + Nodes and low hallucination under transcript-conditioned GPT-5.2, while citation analysis shows about a 3% accuracy gain for KOSMOS (Transcript + KG) over DocLens GPT-5.2. Overall, ontology-guided KG structure appears most beneficial as a complementary scaffold paired with transcript access, while relationships provide limited additional benefit under current extraction quality. Full article

Background: Single-target Alzheimer’s disease (AD) therapies have repeatedly failed to modify disease progression, highlighting a critical mismatch between multifactorial pathology and reductionist pharmacology. Methods: We developed a representation learning framework using Knowledge-guided Pre-trained Graph Transformers (KPGT) to enable rational multi-target drug discovery, analyzing 2446 molecules across APP, PSEN1, and VCP. Results: KPGT captured target-specific mechanistic signatures with 99.35% classification accuracy. Geometric midpoint analysis identified 15 bridging candidates with mean pIC₅₀ 8.09. We discovered two orthogonal molecular feature signatures, structural features driving multi-target breadth versus chemical features determining single-target potency, with zero descriptor overlap. Chemical orthogonality (d = 3.86) outperformed functional similarity for predicting synergistic pairs, with 95% overlap between multi-target molecules and synergistic combinations. Conclusions: This framework operationalizes systems-level AD drug discovery through interpretable representation learning. Full article

Accurate modeling of learners’ evolving cognitive states is essential for intelligent educational systems, yet many existing knowledge tracing and graph-based approaches rely on static structures or purely sequential representations that inadequately capture dynamic structural changes in learning processes. This study proposes a Learner Cognitive Graph (LCG) framework that integrates dynamic heterogeneous graph modeling, structured behavioral data acquisition, and reinforcement learning-based intervention optimization. A Dynamic Cognition Graph (DCG) is formally defined as a sequence of temporally evolving graph snapshots representing interactions among learners, knowledge concepts, and exercises. A reverse Turing test-based agent with structured prompting is introduced to collect reasoning-oriented behavioral evidence, improving data reliability for cognitive modeling. Temporal message passing, multi-scale memory updating, and self-supervised learning objectives are employed to construct dynamic cognitive representations. Personalized intervention is formulated as a Markov decision process to optimize long-term learning outcomes. Experiments conducted on real-world and simulated educational datasets demonstrate improved knowledge mastery prediction accuracy, cognitive state transition modeling, and intervention efficiency compared with representative baselines. The proposed framework provides a systematic and scalable approach for dynamic cognitive modeling and adaptive educational support. Full article

With the acceleration of the global energy transition, the photovoltaic industry has become a significant force in the promotion of green development, and photovoltaic raw materials play a crucial role in this process. In this paper, 177 countries during the period of 2001 to 2024 were taken as the research subjects, with a focus on polysilicon and silicon wafers as components of upstream photovoltaic raw materials. Through a combination of the evolutionary analysis of nodes, the overall structure, and the three-dimensional structure with an exponential random graph model, the evolution and dynamic mechanisms of the global photovoltaic raw material trade network are explored. The study reveals the following: (1) The global PV raw material trade volume tended to increase from 2001 to 2024. (2) The global photovoltaic raw material trade network showed a tendency towards the “enhanced dominance of core countries and denser trade connections,” with the trade volume between core countries continuously expanding and the network density, average clustering coefficient, and connection efficiency increasing annually, which is a reflection of the globalization and regional cooperation of the global photovoltaic industry. (3) From the weighted out-degree and in-degree ranking evolution of the global photovoltaic raw materials trade network, it can be seen that China consolidated its core position, while Southeast Asian countries tended to transfer their processing and manufacturing links. The status of the United States and traditional industrial powers gradually declined, which is a reflection of the restructuring of the global industrial chain along with regional geopolitical agglomeration effects. (4) Internal attributes such as the national economic level, population size, and urbanization rate, as well as external network effects such as common language and geographical proximity, significantly influence the formation path of the photovoltaic raw material trade network. Moreover, the network exhibits distinct heterogeneous complementarity mechanisms and path dependence characteristics, with a structural evolution that tends toward stability and cooperative relationships showing significant time inertia. Overall, the global trade volume of photovoltaic raw materials continues to grow, and the core positions of major countries such as China, the United States, and Germany remain prominent but show a transitional trend towards Southeast Asian countries. The strengthening of the level of coordination and cooperation among global photovoltaic raw material producers to ensure supply chain stability, promote resource sharing and technological progress, and achieve the sustainable development of green energy policies is necessary. Full article

The B cell receptor (BCR) repertoire captures an individual’s immunological history and antigen-driven evolution within a vast, high-dimensional sequence space. Although bulk and single-cell adaptive immune receptor repertoire sequencing (AIRR-seq) now enables deep profiling of BCR diversity, interpreting these datasets remains challenging due to strong inter-individual heterogeneity, nonlinear sequence–structure–function relationships, dynamic clonal evolution, and the rarity of functionally relevant clones. Artificial intelligence (AI) provides a conceptual and computational framework for addressing these challenges. Here, we summarize how advanced deep learning architectures, including antibody-specific language models, graph neural networks (GNNs), and generative frameworks, uncover clonal topology, structural features, and antigen-binding semantics. We further highlight applications in cancer, infectious disease, and autoimmunity. Finally, we propose a closed-loop framework that integrates multimodal datasets, interpretable AI, and iterative experimental validation to advance predictive immunology and accelerate therapeutic antibody discovery. Full article

Accurate trajectory tracking of redundant manipulators is difficult because the controller must simultaneously model local couplings between adjacent joints and global dependencies across the whole kinematic chain. Existing reinforcement learning methods typically employ multilayer perceptrons, which do not explicitly exploit manipulator structure and therefore show limited stability and representation ability in high-dimensional continuous control tasks. This paper proposes GT-TD3, a Graph Transformer-enhanced-Twin Delayed Deep Deterministic Policy Gradient framework, for redundant manipulator trajectory tracking. The proposed actor first converts the raw system state into joint-level node features and uses a graph neural network to extract local kinematic coupling information. A Transformer is then employed to capture long-range dependencies among joints. To strengthen the use of structural priors, topology- and distance-related bias terms are incorporated into the attention mechanism, enabling the network to encode manipulator structure during global feature learning. Experiments on a 7-DoF KUKA iiwa manipulator in PyBullet demonstrate that GT-TD3 outperforms MLP, pure GNN, and pure Transformer baselines in tracking performance. The proposed method achieves more stable training, faster convergence, and smoother and more accurate end-effector motion. The results show that the integration of local graph modeling and structure-aware global attention provides an effective solution for high-precision trajectory tracking of redundant manipulators. Full article