Search Results (161)

In order to comprehensively investigate the spatio-temporal dynamics of corrosion evolution under complex pipeline environments and improve the corrosion rate prediction accuracy, a novel framework for corrosion rate prediction based on adaptive multivariate time series graph neural network (MTGNN) multi-feature spatio-temporal correlation analysis is proposed. First, pipeline monitoring points are modeled as graph nodes to construct the pipeline corrosion spatio-temporal information graph, with corrosion rate and auxiliary features (selected through feature correlation analysis) forming node attributes. Then, a dynamic adjacency matrix is adaptively learned to capture hidden spatial dependencies, while temporal convolution modules extract multi-scale temporal patterns, and the node sequences with integrated corrosion features are input into the adaptive MTGNN for prediction. To reduce the accumulation of errors in multi-step prediction, a “chunked progressive” training strategy is adopted, incrementally expanding prediction horizons. Finally, experiments based on real urban drainage pipeline data show that in six-step predictions, the model reduces MAE, RMSE, and MAPE by 6.59–32.16%, 4.38–27.95%, and 5.01–22.22%, respectively, compared to traditional time series methods such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and non-adaptive MTGNN. The results indicate that the adaptive MTGNN, which integrates multi-source node features, has higher prediction accuracy across the three evaluation metrics, highlighting its capability to leverage spatio-temporal synergies for accurate short-term corrosion rate prediction. Full article

In the context of an ever-evolving global economy, ASEAN companies face dynamic systemic risk that reshapes their financial interrelationships. This study examines the transmission of these risks using advanced graph theory techniques, particularly the measurement of eigenvector centrality based on Euclidean distances, combined with a hidden model that incorporates macroeconomic variables, such as GDP. The research focuses on identifying critical nodes within the corporate network, evaluating their contagion potential—both in terms of reinforcing resilience and amplifying vulnerabilities—and analyzing the influence of external factors on the network’s structure and behavior. The findings offer an innovative framework for managing systemic risk and provide strategic guidelines for the formulation of economic policies in emerging ASEAN markets. Full article

Objectives: This study investigated the visual search behaviour of optometrists and fellowship-trained ophthalmologists when screening for diabetic retinopathy in retinal photographs. Methods: Participants assessed and graded retinal photographs on a computer screen while a Gazepoint GP3 HD eye tracker recorded their eye movements. Areas of interest were derived from the raw data using Hidden Markov modelling. Fixation strings were extracted by matching raw fixation data to areas of interest and resolving ambiguities with graph search algorithms. Fixation strings were clustered using Affinity Propagation to determine search behaviours characteristic of the correct and incorrect response groups. Results: A total of 23 participants (15 optometrists and 8 ophthalmologists) completed the grading task, with each assessing 20 images. Visual search behaviour differed between correct and incorrect responses, with data suggesting correct responses followed a visual search strategy incorporating the optic disc, macula, superior arcade, and inferior arcade as areas of interest. Data from incorrect responses suggest search behaviour driven by saliency or a search pattern unrelated to anatomical landmarks. Referable diabetic retinopathy was correctly identified in 86% of cases. Grader accuracy was 64.8% with good inter-grader agreement (α = 0.818). Conclusions: Our study suggests that a structured visual search strategy is correlated with higher accuracy when assessing retinal photographs for diabetic retinopathy. Referable diabetic retinopathy is detected at high rates; however, there is disagreement between clinicians when determining a precise severity grade. Full article

Personalized urban services are becoming increasingly significant in smart city systems. This shift from intelligent transportation to smart cities broadens the scope of personalized services, encompassing not just travel but a wide range of urban activities and needs. This study proposes a knowledge graph-based Hidden Markov Model (KHMM) to improve personalized route recommendations by incorporating both spatial and semantic relationships between Points of Interest (POIs) in a unified decision-making framework. The KHMM expands the state space of the traditional Hidden Markov Model using a knowledge graph, enabling the integration of multi-dimensional POI information and higher-order relationships. This approach reflects the spatial complexity of urban environments while addressing user-specific preferences. The model’s empirical evaluation, focused on Changsha, China, examined how temporal variations in public attention to POIs influence route selection. The results show that incorporating dynamic temporal and spatial data significantly enhances the model’s adaptability to changing user behaviors, supporting real-time, personalized route recommendations. By bridging individual preferences and road network structures, this research provides key insights into the factors shaping travel behavior and contributes to the development of adaptive and responsive urban transportation systems. These findings highlight the potential of the KHMM to advance intelligent travel services, offering improved spatial accuracy and personalized route planning. Full article

The growing sophistication of cyber-attacks demands encryption processes that go beyond the confines of conventional cryptographic methods. Traditional cryptographic systems based on numerical algorithms or standard graph theory are still open to structural and computational attacks, particularly in light of advances in computation power. Fuzzy logic’s in-built ability to manage uncertainty together with the representation ability of fuzzy hypergraphs for describing complex interrelations offers an exciting avenue in the direction of developing highly evolved and secure cryptosystems. This paper lays out a new framework for cryptography using fuzzy hypergraph networks in which a hidden value is converted into a complex structure of dual fuzzy hypergraphs that remains completely connected. This technique not only increases the complexity of the encryption process, but also significantly enhances security, thus making it highly resistant to modern-day cryptographic attacks and appropriate for high security application. This approach improves security through enhanced entropy and the introduction of intricate multi-path data exchange through simulated nodes, rendering it highly resistant to contemporary cryptographic attacks. It ensures effective key distribution, accelerated encryption–decryption processes, and enhanced fault tolerance through dynamic path switching and redundancy. The adaptability of the framework to high-security, large-scale applications further enhances its robustness and performance. Full article

Point of Interest (POI) data play a critical role in enabling location-based services (LBS) by providing intrinsic attributes, including geographic coordinates and semantic categories, alongside a spatial context that reflects relationships among POIs. However, the inherent label sparsity in POI datasets poses significant challenges for traditional supervised learning approaches. To address this limitation, we propose MaskPOI, a novel self-supervised learning framework that combines the strengths of graph neural networks and masked modeling. MaskPOI incorporates two complementary modules: an edge mask-based graph autoencoder that models the spatial topology by predicting edge existence and uncovering hidden spatial relationships and a feature mask-based graph autoencoder that reconstructs masked node features to explore the rich attribute characteristics of POIs. Together, these modules enable MaskPOI to jointly capture the spatial and attribute information essential for robust representation learning. Extensive experiments demonstrate MaskPOI’s effectiveness in improving performance on downstream tasks such as functional zone classification and population density prediction. Ablation studies further validate the contributions of its components, highlighting MaskPOI as a powerful and versatile framework for POI representation learning. Full article

Inter-state cyberattacks are increasingly becoming a major hidden threat to national security and global order. However, current prediction models are often constrained by single-source data due to insufficient consideration of complex influencing factors, resulting in limitations in understanding and predicting cyberattacks. To address this issue, we comprehensively consider multiple data sources including cyberattacks, bilateral interactions, armed conflicts, international trade, and national attributes, and propose an interpretable multimodal data fusion framework for predicting cyberattacks among countries. On one hand, we design a dynamic multi-view graph neural network model incorporating temporal interaction attention and multi-view attention, which effectively captures time-varying dynamic features and the importance of node representations from various modalities. Our proposed model exhibits greater performance in comparison to many cutting-edge models, achieving an F1 score of 0.838. On the other hand, our interpretability analysis reveals unique characteristics of national cyberattack behavior. For example, countries with different income levels show varying preferences for data sources, reflecting their different strategic focuses in cyberspace. This unveils the factors and regional differences that affect cyberattack prediction, enhancing the transparency and credibility of the proposed model. Full article

The rapid expansion of digital news sources has necessitated intelligent systems capable of filtering, analyzing, and deriving meaningful insights from vast amounts of information in real time. This study presents an AI-driven chatbot designed for real-time news automation, integrating advanced natural language processing techniques, knowledge graphs, and generative AI models to improve news summarization and correlation analysis. The chatbot processes over 1,306,518 news reports spanning from 25 September 2023 to 17 February 2025, categorizing them into 15 primary event categories and extracting key insights through structured analysis. By employing state-of-the-art machine learning techniques, the system enables real-time classification, interactive query-based exploration, and automated event correlation. The chatbot demonstrated high accuracy in both summarization and correlation tasks, achieving an average F1 score of 0.94 for summarization and 0.92 for correlation analysis. Summarization queries were processed within an average response time of 9 s, while correlation analyses required approximately 21 s per query. The chatbot’s ability to generate real-time, concise news summaries and uncover hidden relationships between events makes it a valuable tool for applications in disaster response, policy analysis, cybersecurity, and public communication. This research contributes to the field of AI-driven news analytics by bridging the gap between static news retrieval platforms and interactive conversational agents. Future work will focus on expanding multilingual support, enhancing misinformation detection, and optimizing computational efficiency for broader real-world applicability. The proposed chatbot stands as a scalable and adaptive solution for real-time decision support in dynamic information environments. Full article

There is a close correlation between brain aging and age. However, traditional neural networks cannot fully capture the potential correlation between age and brain aging due to the limited receptive field. Furthermore, they are more concerned with deep spatial semantics, ignoring the fact that effective temporal information can enrich the representation of low-level semantics. To address these limitations, a local attention spatio-temporal graph inference network (LSTGINet) was developed to explore the details of the association between age and brain aging, taking into account both spatio-temporal and temporal perspectives. First, multi-scale temporal and spatial branches are used to increase the receptive field and model the age information simultaneously, achieving the perception of static correlation. Second, these spatio-temporal feature graphs are reconstructed, and large topographies are constructed. The graph inference node aggregation and transfer functions fully capture the hidden dynamic correlation between brain aging and age. A new local attention module is embedded in the graph inference component to enrich the global context semantics, establish dependencies and interactivity between different spatio-temporal features, and balance the differences in the spatio-temporal distribution of different semantics. We use a newly designed weighted loss function to supervise the learning of the entire prediction framework to strengthen the inference process of spatio-temporal correlation. The final experimental results show that the MAE on baseline datasets such as CamCAN and NKI are 6.33 and 6.28, respectively, better than the current state-of-the-art age prediction methods, and provides a basis for assessing the state of brain aging in adults. Full article

The use of the Visibility Graph Algorithm (VGA) has proven to be a valuable tool for analyzing both real and synthetic seismicity series. Specifically, VGA transforms time series into a network representation in which structural properties such as node connectivity, clustering, and community structure can be quantitatively measured, thereby revealing underlying correlations and dynamics that may remain hidden in traditional linear or spectral analyses. The time series transformation into complex networks with VGA provides a new approach to analyze seismic dynamics, allowing scientists to extract trends and behaviors that may not be possible by classical time-series analysis. On the other hand, many studies attempt to find viable trends in order to identify preparation mechanisms prior to a strong earthquake or to analyze the aftershocks. In this work, the seismic activity of Southern California Earthquake was analyzed focusing only on the significant earthquakes. For this purpose, seismic series preceding and following each earthquake were constructed using a windowing method with different overlaps and the slope of the connectivity (k) versus magnitude (M) graph (k-M slope) and the average degree were computed from the mapped complex networks. The results revealed a significant decrease in these parameters after the earthquake, due to the contribution of the aftershocks from the main event. Interestingly, the study was extended to synthetic seismicity series and the same behavior was observed for both k-M slope and average degree. This finding suggests that the spring-block model reproduces a relaxation mechanism following a large-magnitude event like those of real seismic aftershocks. However, this conclusion contrasts with conclusions drawn by other researchers. These results highlight the utility of VGA in studying events that precede and follow major earthquakes. This technique may be used to extract some useful trends in seismicity, which could eventually be employed for a deeper understanding and possible forecasting of seismic behavior. Full article

With the increasing research of deep learning in the EEG field, it becomes more and more important to fully extract the characteristics of EEG signals. Traditional EEG signal classification prediction neither considers the topological structure between the electrodes of the signal collection device nor the data structure of the Euclidean space to accurately reflect the interaction between signals. Graph neural networks can effectively extract features of non-Euclidean spatial data. Therefore, this paper proposes a feature selection method for epilepsy EEG classification based on graph convolutional neural networks (GCNs) and long short-term memory (LSTM) cells. While enriching the input of LSTM, it also makes full use of the information hidden in the EEG signals. In the automatic detection of epileptic seizures based on neural networks, due to the strong non-stationarity and large background noise of the EEG signal, the analysis and processing of the EEG signal has always been a challenging research. Therefore, experiments were conducted using the preprocessed Boston Children’s Hospital epilepsy EEG dataset, and input it into the GCN-LSTM model for deep feature extraction. The GCN network built by the graph convolution layer learns spatial features, then LSTM extracts sequence information, and the final prediction is performed by fully connected and softmax layers. The introduced method has been experimentally proven to be effective in improving the accuracy of epileptic EEG seizure detection. Experimental results show that the average accuracy of binary classification on the CHB-MIT dataset is 99.39%, and the average accuracy of ternary classification is 98.69%. Full article

A growing body of biomedical literature suggests a bidirectional regulatory relationship between cardiac calcium (Ca²⁺)-regulating proteins and reactive oxygen species (ROS) that is integral to the pathogenesis of various cardiac disorders via oxidative stress (OS) signaling. To address the challenge of finding hidden connections within the growing volume of biomedical research, we developed a data science pipeline for efficient data extraction, transformation, and loading. Employing the CaseOLAP (Context-Aware Semantic Analytic Processing) algorithm, our pipeline quantifies interactions between 128 human cardiomyocyte Ca²⁺-regulating proteins and eight cardiovascular disease (CVD) categories. Our machine-learning analysis of CaseOLAP scores reveals that the molecular interfaces of Ca²⁺-regulating proteins uniquely associate with cardiac arrhythmias and diseases of the cardiac conduction system, distinguishing them from other CVDs. Additionally, a knowledge graph analysis identified 59 of the 128 Ca²⁺-regulating proteins as involved in OS-related cardiac diseases, with cardiomyopathy emerging as the predominant category. By leveraging a link prediction algorithm, our research illuminates the interactions between Ca²⁺-regulating proteins, OS, and CVDs. The insights gained from our study provide a deeper understanding of the molecular interplay between cardiac ROS and Ca²⁺-regulating proteins in the context of CVDs. Such an understanding is essential for the innovation and development of targeted therapeutic strategies. Full article

The design process of heating, ventilation, and air conditioning (HVAC) systems is complex and time consuming due to the need to follow design codes. Since the design standards are not fixed, the final outcome often depends on the designer’s experience. The development of building information modeling (BIM) technology has made information throughout the building lifecycle more integrated. BIM-based forward design is now widely used, providing a data foundation for combining HVAC system design with machine learning. This paper proposes an unsupervised learning method based on deep graph generative models to uncover hidden design patterns and optimization strategies from the design results. We trained and validated four deep graph generative models—GAE, GNF, GAN, and diffusion—using HVAC system terminal pipeline layout data. Accuracy and precision metrics were used to compare the generated designs with automated forward design solutions, assessing the models’ ability to capture both local variations and broader changes in design logic. A graph-neural-network-based evaluation method was employed to measure the models’ capacity to detect changes. The results indicate that all four models achieved prediction accuracies exceeding 90% and precision rates above 75%. The models effectively captured both local modifications made by designers and global design changes, showing greater sensitivity to global layout adjustments than to local updates. When comparing the results generated by deep graph generative models and the actual design, it is obvious that the accuracy of the predictions varies significantly due to the complexity of the test buildings. Full article

Graph neural networks (GNNs) typically exhibit superior performance in shallow architectures. However, as the network depth increases, issues such as overfitting and oversmoothing of hidden vector representations arise, significantly diminishing model performance. To address these challenges, this paper proposes a Two-Channel Classification Algorithm Based on Graph Attention Network (TCC_GAT). Initially, nodes exhibiting similar interaction behaviors are identified through cosine similarity, thereby enhancing the foundational graph structure. Subsequently, an attention mechanism is employed to adaptively integrate neighborhood information within the enhanced graph structure, with a multi-head attention mechanism applied to mitigate overfitting. Furthermore, the K-nearest neighbors algorithm is adopted to reconstruct the basic graph structure, facilitating the learning of structural information and neighborhood features that are challenging to capture on interaction graphs. This approach addresses the difficulties associated with learning high-order neighborhood information. Finally, the embedding representations of identical nodes across different graph structures are fused to optimize model classification performance, significantly enhancing node embedding representations and effectively alleviating the over-smoothing issue. Semi-supervised experiments and ablation studies conducted on the Cora, Citeseer, and Pubmed datasets reveal an accuracy improvement ranging from 1.4% to 4.5% compared to existing node classification algorithms. The experimental outcomes demonstrate that the proposed TCC_GAT achieves superior classification results in node classification tasks. Full article

The combination of few-shot learning and graph neural networks can effectively solve the issue of extracting more useful information from limited data. However, most graph-based few-shot models only consider the global feature information extracted by the backbone during the construction process, while ignoring the dependency information hidden within the features. Additionally, the essence of graph convolution is the filtering of graph signals, and the majority of graph-based few-shot models construct fixed, single-property filters to process these graph signals. Therefore, in this paper, we propose an Adaptive Filtering Graph Convolutional Neural Network (AFGN) for few-shot classification. AFGN explores the hidden dependency information within the features, providing a new approach for constructing graph tasks in few-shot scenarios. Furthermore, we design an adaptive filter for the graph convolution of AFGN, which can adaptively adjust its strategy for acquiring high and low-frequency information from graph signals based on different few-shot episodic tasks. We conducted experiments on three standard few-shot benchmarks, including image recognition and fine-grained categorization. The experimental results demonstrate that our AFGN performs better compared to other state-of-the-art models. Full article