Search Results (31)

Spatiotemporal prediction of gas extraction-induced seismicity is a key challenge in regional seismic risk management, hindered by heterogeneous spatial coupling among reservoir blocks and extreme class imbalance in seismicity records. This study proposes a multi-task spatiotemporal forecasting framework based on a dual-encoder architecture combining a Graph Attention Network (GAT) with a Long Short-Term Memory (LSTM) network. The monitoring network is represented as a graph with node-level features including monthly production, reservoir pressure, compaction, and historical seismicity. A Voronoi tessellation strategy maps continuous epicentral coordinates to discrete graph nodes. The GAT encodes heterogeneous spatial interactions via adaptive attention, while a two-layer LSTM extracts multiscale temporal dependencies. Event detection and magnitude classification are treated as parallel tasks, jointly optimized using focal loss and focal-adjusted weighted cross-entropy to mitigate class imbalance. A Seismic Risk Index (SRI) integrates event occurrence and magnitude class probabilities into a continuous risk estimate. Validated on the KNMI seismic catalog and Groningen production data, the model achieves an event Probability of Detection (POD) of 0.677 and a magnitude classification macro average recall (MAvA) of 0.548 under an event rate of 0.07%. Compared with a pure LSTM baseline, the GAT improves POD by 2.1% and MAvA by 7.9%. The time-averaged risk field exhibits spatial heterogeneity broadly consistent with observed seismicity patterns, indicating the potential of this framework for fine-grained spatiotemporal risk assessment of extraction-induced seismicity. Full article

In long-horizon multi-party conversations, human-centric AI agents face a persistent structural problem: similarity-based retrieval may fail to reconnect semantically dispersed fragments of the same evolving event. This problem severely weakens causal continuity and multi-hop context recovery. To improve attribution trust and reduce structural erasure, we propose MemLoom, a dual-loop causality-traceable retrieval framework that organizes conversational history as an event memory graph. MemLoom decouples latency-sensitive online interaction from off-peak structural curation through online event formation, sentence-level buffering, asynchronous neuro-symbolic graph synthesis, and bounded dual-stream retrieval. Evaluations across QMSum, LoCoMo, and the synthetic causal diagnostic suite (SCDS) support the structural utility of MemLoom. For LoCoMo, under our unified local evaluation setup, MemLoom shows favorable temporal and multi-hop reasoning results (J = 65.77 and 58.14) relative to contemporary agentic baselines, such as Mem0, Zep, and A-Mem. For SCDS, within a controlled diagnostic setting, it recovers demanded causal chains more reliably than GraphRAG (SCR = 0.72 vs. 0.35) and maintains stronger answer-level auditability (AA = 0.80 vs. 0.50). This is achieved with a bounded online P95 latency of 1.67 s. These results indicate that asynchronous dual-loop stewardship has practical value for causality-traceable, event-centric conversational memory in multi-party settings. Full article

Frequent rainfall events threaten expressway operations, and toll stations, as critical network nodes, are vulnerable to functional degradation and cascading effects. However, existing traffic resilience studies mainly focus on urban road networks or static assessments, making it difficult to characterize the resilience evolution, recovery process, and predictability of toll-station nodes. This study proposes a resilience quantification and recovery prediction method for expressway toll-station nodes under rainfall disturbances. By integrating multi-source meteorological data, neighborhood propagation relationships, and network topology, a three-level resilience quantification framework is developed across the functional, neighborhood, and network layers. A piecewise exponential function is used to model the damage–valley–recovery process of node resilience and to extract parameters including damage depth and recovery rate. Focusing on the recovery stage, a node recovery prediction model is constructed by combining resilience sequences, meteorological disturbance features, and dual-graph spatial relationships, while dual-graph convolution and long short-term memory (LSTM) are used to capture the spatiotemporal evolution of node recovery. Results show that the proposed method quantifies toll-station node resilience, captures its staged evolution, and effectively predicts recovery. Baseline, cross-scene, and ablation results confirm the value of multi-source feature fusion and dual-graph propagation, supporting the sustainable operation of expressway systems under rainfall disturbances. Full article

In this study, we examined how disinformation and trustworthy news differ in their narrative construction across nine theoretically motivated dimensions. We address the following research question: how do disinformation and trustworthy news differ in narrative organisation and epistemic grounding? We analysed 610 English-language news articles (308 pro-Kremlin disinformation and 302 trustworthy articles) covering selected international events from 2015 to 2023, using data derived from the EUvsDisinfo dataset. Narrative elements were extracted using a hybrid pipeline combining large language models and knowledge graphs, resulting in article-level representations for comparative analysis. Ordinal scores (1–5) were assigned for emotional intensity, cultural complexity, conspiracist structure, source diversity, crisis intensity, evidence support, media control, solutions orientation and memory work. Non-parametric comparisons showed significant differences in eight of these nine dimensions. Disinformation articles revealed stronger conspiracist structuring and greater meta-media hostility, as well as significantly lower source diversity, evidence support, cultural complexity and weaker memory work. Emotional intensity did not differ reliably across disinformation and trustworthy news. A simple additive NarrativeRisk score, which we designed as a transparent and interpretable summary measure, showed between-group differences in both parametric and non-parametric tests. As a univariate discrimination indicator, NarrativeRisk achieved ROC AUC ≈ 0.84. Cluster analysis identified three recurrent narrative profiles, including one dominated by disinformation, one by trustworthy news and one mixed profile. These findings indicate that disinformation is distinguished not only by factual unreliability but also by different patterns in narrative organisation. Full article

Accurate short-term traffic flow prediction in complex urban road networks is of great significance for capacity organization and dispatch optimization in intelligent transportation systems. Using publicly available historical taxi trip records released by the New York City Taxi and Limousine Commission from January to June 2016, this study develops a spatiotemporal fusion framework for short-term traffic flow prediction. To address the nonlinearity, sparsity, and complex spatiotemporal dependencies of traffic flow sequences, the raw trajectory data are first cleaned, spatially gridded, and temporally discretized. Based on the spatial adjacency relationships among grid nodes, a graph structure is then constructed, and a serially coupled graph convolutional network and long short-term memory model is developed to capture spatial dependency features and temporal dynamic features, respectively. Experimental results on the New York City taxi dataset show that, compared with baseline models including the historical average model, long short-term memory network, graph convolutional network, and Transformer, the proposed model achieves better performance in terms of mean absolute error, root mean square error, and coefficient of determination. Furthermore, the SHAP (SHapley Additive exPlanations) method is employed to ANALYZE the differences in feature contributions across nodes in different functional zones from both temporal and spatial perspectives. The results indicate that the model exhibits heterogeneous temporal dependency depths and spatial aggregation patterns across different types of regions within the study area. In addition, regions with high feature contributions show a certain degree of spatial correspondence with the major traffic corridors in Manhattan, suggesting that the model is able to capture part of the spatiotemporal correlation structure of traffic flow in this dataset. Finally, the limitations of the proposed method in terms of static graph structure, response to extreme events, and integration of external factors are discussed. It should be noted that these findings are derived from New York City taxi data from the first half of 2016, and their generalizability to other cities, time periods, or traffic scenarios remains to be further validated. Full article

The frequency of extreme weather events has become higher, and electricity consumption has also become more complex. These changes increase the risk of overload in distribution transformers (DTs), and this risk threatens the stability and reliability of the power grid. Existing methods have significant limitations. Traditional static threshold methods (based on DGA gas ratios and electrical signal thresholds) fail to consider temporal changes and complex links between factors, while modern machine learning models lack cause–effect relationships over time and clear ways to describe uncertainty. With such motivations, this paper proposes a causal-enhanced hybrid framework, which combines Long Short-Term Memory (LSTM) networks and Random Forest (RF) algorithms. The framework uses causal Seasonal Trend decomposition using Loess (STL) to reveal load patterns at different time scales. The mutual information index and spatiotemporal graph convolutional network (ST-GCN) are used to explore nonlinear relations and reveal how temperature affects load changes. The LSTM model captures time dependence in load series, and the Bayesian optimized Random Forest is used to solve the problem of data imbalance and quantify uncertainty. In addition, the framework constructs an early warning system that combines data from many sources in real time. Test results show that the proposed algorithm exhibits excellent performance in multi-source data environments. Full article

Analyzing events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly rely on visual–text models; however, these methods often capture information implicitly from images, lacking interpretable and structured spatio-temporal object representations and their relationships. To address this issue, we introduce DyGEnc—a novel method for dynamic graph encoding. This method integrates compressed spatio-temporal representation with the cognitive capabilities of large language models. The purpose of this integration is to enable advanced question answering based on sequences of textual scene graphs. Extensive evaluations on the STAR and AGQA datasets demonstrate that DyGEnc improves large language model performance when addressing queries related to the history of human–object interactions. Furthermore, the proposed method can be extended to process input images by leveraging foundation models to extract explicit textual scene graphs, as validated by the evaluation results. We expect these findings to contribute to the development of robust and compact graph-based memory for long-horizon reasoning in real-world applications, as demonstrated in a robotic experiment conducted using a wheeled manipulator platform. Full article

The rapid expansion of Internet of Things (IoT)-enabled smart grids has intensified the need for reliable fault detection and autonomous self-healing under non-stationary operating conditions characterized by frequent concept drift. To address the limitations of static and single-strategy adaptive models, this paper proposes H-CLAS, a novel Hybrid Continual Learning for Adaptive Self-healing framework that unifies regularization-based, memory-based, architectural, and meta-learning strategies within a single adaptive pipeline. The framework integrates convolutional neural networks (CNNs) for fault detection, graph neural networks for topology-aware fault localization, reinforcement learning for self-healing control, and a hybrid drift detection mechanism combining ADWIN and Page–Hinkley tests. Continual adaptation is achieved through the synergistic use of Elastic Weight Consolidation, memory-augmented replay, progressive neural network expansion, and Model-Agnostic Meta-Learning for rapid adaptation to emerging drifts. Extensive experiments conducted on the Smart City Air Quality and Network Intrusion Detection Dataset (NSL-KDD) demonstrate that H-CLAS achieves accuracy improvements of 12–15% over baseline methods, reduces false positives by over 50%, and enables 2–3× faster recovery after drift events. By enhancing resilience, reliability, and autonomy in critical IoT-driven infrastructures, the proposed framework contributes to improved grid stability, reduced downtime, and safer, more sustainable energy and urban monitoring systems, thereby providing significant societal and environmental benefits. Full article

Detecting botnets in IoT environments is difficult because most intrusion detection systems treat network events as independent observations. In practice, infections spread through device relationships and evolve through distinct temporal phases. A system that ignores either aspect will miss important patterns. This paper explores a hybrid architecture combining Graph Neural Networks with Long Short-Term Memory networks to capture both structural and temporal dynamics. The GNN component models behavioral similarity between traffic flows in feature space, while the LSTM tracks how patterns change as attacks progress. The two components are trained jointly so that relational context is preserved during temporal learning. We evaluated the approach on two datasets with different characteristics. N-BaIoT contains traffic from nine devices infected with Mirai and BASHLITE, while CICIoT2023 covers 105 devices across 33 attack types. On N-BaIoT, the model achieved 99.88% accuracy with F1 of 0.9988 and Brier score of 0.0015. Cross-validation on CICIoT2023 yielded 99.73% accuracy with Brier score of 0.0030. The low Brier scores suggest that probability outputs are reasonably well calibrated for risk-based decision making. Consistent performance across both datasets provides some evidence that the architecture generalizes beyond a single benchmark setting. Full article

Microservice architecture has become a foundational component of modern distributed systems due to its modularity, scalability, and deployment flexibility. However, the increasing complexity and dynamic nature of service interactions have introduced substantial challenges in accurately detecting runtime anomalies. Existing methods often rely on multiple monitoring metrics, which introduce redundancy and noise while increasing the complexity of data collection and model design. This paper proposes a novel spatiotemporal anomaly detection framework that integrates Dynamic Graph Neural Networks (D-GNN) combined with Long Short-Term Memory (LSTM) networks to model both the structural dependencies and temporal evolution of microservice behaviors. Unlike traditional approaches, our method uses only CPU utilization as the sole monitoring metric, leveraging its high observability and strong correlation with service performance. From a symmetry perspective, normal microservice behaviors exhibit approximately symmetric spatiotemporal patterns: structurally similar services tend to share similar CPU trajectories, and recurring workload cycles induce quasi-periodic temporal symmetries in utilization signals. Runtime anomalies can therefore be interpreted as symmetry-breaking events that create localized structural and temporal asymmetries in the service graph. The proposed framework is explicitly designed to exploit such symmetry properties: the D-GNN component respects permutation symmetry on the microservice graph while embedding the evolving structural context of each service, and the LSTM module captures shift-invariant temporal trends in CPU usage to highlight asymmetric deviations over time. Experiments conducted on real-world microservice datasets demonstrate that the proposed method delivers excellent performance, achieving 98 percent accuracy and 98 percent F1-score. Compared to baseline methods such as DeepTraLog, which achieves 0.93 precision, 0.978 recall, and 0.954 F1-score, our approach performs competitively, achieving 0.980 precision, 0.980 recall, and 0.980 F1-score. Our results indicate that a single-metric, symmetry-aware spatiotemporal modeling approach can achieve competitive performance without the complexity of multi-metric inputs, providing a lightweight and robust solution for real-time anomaly detection in large-scale microservice environments. Full article

In today’s volatile business environment, securing a sustainable competitive advantage hinges on retaining and effectively managing talent. While talent turnover is inevitable, strategic internal human resource (HR) transfers offer a solution to prevent talent outflow and supplement skill gaps. However, previous models for identifying internal substitutes often focus solely on individual work capabilities, neglecting the critical role of group interactions and collaborative structure. Drawing on social network theory, transactive memory systems, and person–group fit, this study proposes a graph-based analytical approach that models the organization as a complex system. Our methodology provides a holistic framework that integrates both (1) individual capabilities and (2) group-level characteristics (e.g., work-relationship networks and cluster-level similarity) to identify the most suitable substitutes. At the macroscopic level, we use an inductive graph neural network (GraphSAGE) to learn node embeddings from a work relationship network constructed from process event logs and to quantify group-level similarity. At the microscopic level, we compute dynamic collaboration intensity, frequency, and task similarity between employees over time. To validate the approach, we develop four simulation scenarios using an enriched incident management process event log and implement them in a SimPy-based simulator, benchmarking against an existing method that considers only individual factors. Across all scenarios, the proposed dual-factor model significantly outperforms the baseline in terms of efficiency, accuracy, and suitability. This research provides a practical, validated algorithm that supports evidence-based workforce management and more effective internal talent allocation. Full article

A special class of complex adaptive systems—biological and social—thrive not by passively accumulating patterns, but by engineering coherence, i.e., the deliberate alignment of prior knowledge, real-time updates, and teleonomic purposes. By contrast, today’s AI stacks—Large Language Models (LLMs) wrapped in agentic toolchains—remain rooted in a Turing-paradigm architecture: statistical world models (opaque weights) bolted onto brittle, imperative workflows. They excel at pattern completion, but they externalize governance, memory, and purpose, thereby accumulating coherence debt—a structural fragility manifested as hallucinations, shallow and siloed memory, ad hoc guardrails, and costly human oversight. The shortcoming of current AI relative to human-like intelligence is therefore less about raw performance or scaling, and more about an architectural limitation: knowledge is treated as an after-the-fact annotation on computation, rather than as an organizing substrate that shapes computation. This paper introduces Mindful Machines, a computational paradigm that operationalizes coherence as an architectural property rather than an emergent afterthought. A Mindful Machine is specified by a Digital Genome (encoding purposes, constraints, and knowledge structures) and orchestrated by an Autopoietic and Meta-Cognitive Operating System (AMOS) that runs a continuous Discover–Reflect–Apply–Share (D-R-A-S) loop. Instead of a static model embedded in a one-shot ML pipeline or deep learning neural network, the architecture separates (1) a structural knowledge layer (Digital Genome and knowledge graphs), (2) an autopoietic control plane (health checks, rollback, and self-repair), and (3) meta-cognitive governance (critique-then-commit gates, audit trails, and policy enforcement). We validate this approach on the classic Credit Default Prediction problem by comparing a traditional, static Logistic Regression pipeline (monolithic training, fixed features, external scripting for deployment) with a distributed Mindful Machine implementation whose components can reconfigure logic, update rules, and migrate workloads at runtime. The Mindful Machine not only matches the predictive task, but also achieves autopoiesis (self-healing services and live schema evolution), explainability (causal, event-driven audit trails), and dynamic adaptation (real-time logic and threshold switching driven by knowledge constraints), thereby reducing the coherence debt that characterizes contemporary ML- and LLM-centric AI architectures. The case study demonstrates “a hybrid, runtime-switchable combination of machine learning and rule-based simulation, orchestrated by AMOS under knowledge and policy constraints”. Full article

We propose State-DynAttn, a hybrid architecture for robust air traffic flow prediction under weather disruptions, which integrates state-space models (SSMs) with dynamic graph attention to address the challenges of long-range dependency modeling and adaptive spatial–temporal relationship learning. The increasing complexity of air traffic systems, exacerbated by unpredictable weather events, demands methods that can simultaneously capture global temporal patterns and localized disruptions; existing approaches often struggle to balance these requirements efficiently. The proposed method employs two parallel branches: an SSM branch for continuous-time recurrent modeling of long-range dependencies with linear complexity, and a dynamic graph attention branch that adaptively computes node-pair weights while incorporating weather severity features through sparsification strategies for scalability. These branches are fused via a data-dependent gating mechanism, enabling the model to dynamically prioritize either global temporal dynamics or localized spatial interactions based on input conditions. Moreover, the architecture leverages memory-efficient attention computation and HiPPO initialization to ensure stable training and inference. Experiments on real-world air traffic datasets demonstrate that State-DynAttn outperforms existing baselines in prediction accuracy and robustness, particularly under severe weather scenarios. The framework’s ability to handle both gradual traffic evolution and abrupt disruption-induced changes makes it suitable for real-world deployment in air traffic management systems. Furthermore, the design principles of State-DynAttn can be extended to other spatiotemporal prediction tasks where long-range dependencies and dynamic relational structures coexist. This work contributes a principled approach to hybridizing state-space models with graph-based attention, offering insights into the trade-offs between computational efficiency and modeling flexibility in complex dynamical systems. Full article

Traditional detection methods and security defenses are gradually insufficient to cope with evolving attack techniques and strategies, and have coarse detection granularity and high memory overhead. As a result, we propose Sylph, a lightweight unsupervised APT detection method based on a provenance graph, which not only detects APT attacks but also localizes APT attacks with a fine event granularity and feeds possible attacks back to system detectors to reduce their localization burden. Sylph proposes a whole-process architecture from provenance graph collection to anomaly detection, starting from the system audit logs, and dividing subgraphs based on time slices of the provenance graph it transforms into to reduce memory overhead. Starting from the system audit logs, the provenance graph it transforms into is divided into subgraphs based on time slices, which reduces the memory occupation and improves the detection efficiency at the same time; on the basis of generating the sequence of subgraphs, the full graph embedding of the subgraphs is carried out by using Graph2Vec to obtain their feature vectors, and the anomaly detection based on unsupervised learning is carried out by using an autoencoder, which is capable of detecting new types of attacks that have not yet appeared. After the experimental evaluation, Sylph can realize the APT attack detection with higher accuracy and achieve an accuracy rate. Full article

Modelling events that change over time is one of the most difficult problems in data analysis. Forecasting of time-varying electric power values is also an important problem in data analysis. Regression methods, machine learning, and deep learning methods are used to learn different patterns from data and develop a consumption prediction model. The aim of this study is to determine the most successful models for short-term power consumption prediction with deep learning and to achieve the highest prediction accuracy. In this study, firstly, the data was evaluated and organized with exploratory data analysis (EDA) on a ready dataset and the features of the data were extracted. Studies were carried out on long short-term memory (LSTM), gated recurrent unit (GRU), simple recurrent neural networks (SimpleRNN) and bidirectional long short-term memory (BiLSTM) architectures. First, four architectures were used with 11 different optimization methods. In this study, it was seen that a high success rate of 0.9972 was achieved according to the R² score index. In the following, the first study was tried with different epoch numbers. Afterwards, this study was carried out with 264 separate models produced using four architectures, 11 optimization methods, and six activation functions in order. The results of all these studies were obtained according to the root mean square error (RMSE), mean absolute error (MAE), and R²_score indexes. The R²_score indexes graphs are presented. Finally, the 10 most successful applications are listed. Full article