On superposition of heterogeneous edge processes in dynamic random graphs

Random walks on dynamic configuration models:A trichotomy

Traffic forecasting is a challenging task due to complex spatial and temporal dependencies across sensor locations and time. Interest in solving this task has increased, but current research focuses on manually constructing neural network architectures without the aid of neural architecture search (NAS). In our work, we explore evolutionary neural architecture search (ENAS) by deploying a genetic algorithm (GA) to find optimal neural network architectures for predicting traffic conditions. The search space for the GA consists of arbitrary combinations of dilated convolutions and graph convolutions for modelling temporal and spatial dependencies respectively, limited in complexity only by technical constraints. Experimental results show that model architectures obtained via GA are able to match the current state-of-the-art on traffic prediction benchmarks.

Erratum: Dynamical random graphs with memory [Phys. Rev. E<b>65</b>, 066102 (2002)

In view of the problem that the IP address jump law is easy to predict in the current mobile target defense, this paper proposes a network address jump active defense method based on a dynamic random graph, designed to improve the unpredictability of IP address translation. Firstly, in order to make IP address transformation unpredictable in space and time, a random graph model is designed to generate a pseudo-random sequence of IP address randomization; these pseudo-random can meet the unpredictability of IP address translation in both space and time. Then, based on these pseudo-random sequences and IP address pool, a random map generation algorithm is proposed, which generates highly random IP address sequences through chaotic mapping (Logistic mapping) combined with encryption perturbation technology, meeting the requirements of resisting analysis attacks, while these transformed IP addresses are adapted to network target defense. And finally, this article uses buildMininet to build a cloud network trusted environment, by testing the spatial randomization and temporal randomization of the Random mapping model (CRM), the results show that the CRM model has a good effect on improving the local randomness. The test results of the ablation experiment further show that the CRM model can improve the local randomness while maintaining the global randomness.

We study a large-time limit of a Markov process whose states are finite graphs. The number of the vertices is described by a supercritical branching process, and the dynamics of edges is determined by the rates of appending and deleting. We find a phase transition in our model similar to the one in the random graph model G n,p . We derive a formula for the line of critical parameters which separates two different phases: one is where the size of the largest component is proportional to the size of the entire graph, and another one, where the size of the largest component is at most logarithmic with respect to the size of the entire graph. In the supercritical phase we find the asymptotics for the size of the largest component.

The focus of the meeting was on the mathematical analysis of complex networks, both on how networks emerge through microscopic interaction rules as well as on dynamic processes and optimization problems on networks, including random walks, interacting particle systems and search algorithms. Topics that were addressed included: percolation on graphs and critical regimes for the emergence of a giant component; graph limits and graphons; epidemics, propagation and competition; trees and forests; dynamic random graphs; local versus global algorithms; statistical learning on networks.

Human Activity Recognition (HAR) is essential for monitoring and analyzing human behavior, particularly in health applications such as fall detection and chronic disease management. Traditional methods, even those incorporating attention mechanisms, often oversimplify the complex temporal and spatial dependencies in sensor data by processing features uniformly, leading to inadequate modeling of high-dimensional interactions. To address these limitations, we propose a novel framework: the Temporal-Spatial Feature Decoupling Unit with Layer-wise Training Convolutional Neural Network (CNN-TSFDU-LW). Our model enhances HAR accuracy by decoupling temporal and spatial dependencies, facilitating more precise feature extraction and reducing computational overhead. The TSFDU mechanism enables parallel processing of temporal and spatial features, thereby enriching the learned representations. Furthermore, layer-wise training with a local error function allows for independent updates of each CNN layer, reducing the number of parameters and improving memory efficiency without compromising performance. Experiments on four benchmark datasets (UCI-HAR, PAMAP2, UNIMIB-SHAR, and USC-HAD) demonstrate accuracy improvements ranging from 0.9% to 4.19% over state-of-the-art methods while simultaneously reducing computational complexity. Specifically, our framework achieves accuracy rates of 97.90% on UCI-HAR, 94.34% on PAMAP2, 78.90% on UNIMIB-SHAR, and 94.71% on USC-HAD, underscoring its effectiveness in complex HAR tasks. In conclusion, the CNN-TSFDU-LW framework represents a significant advancement in sensor-based HAR, delivering both improved accuracy and computational efficiency, with promising potential for enhancing health monitoring applications.

The growing number of interconnected systems in consumer IoT environments and the increasing intelligence of AI-enabled cyber threats have introduced significant security challenges. Intrusion detection systems must be not only accurate but also resilient to evolving threats and robust against adversarial manipulation. A major limitation is the lack of labeled data for evolving adversarial attacks, which limits the generalization of detection models, making them less practical for the dynamic and heterogeneous nature of IoT networks. To overcome these limitations, we propose, a hierarchical graph neural network designed for accurate and resilient network intrusion detection using few labeled examples. utilizes a packet-level graph attention network for adaptive feature filtering, which enhances resilience to subtle data perturbations, coupled with a flow-level temporal model to capture complex spatial and temporal dependencies in traffic patterns. By hierarchically abstracting these features, it learns robust representations of normal and malicious network behavior from limited data. Experimental results on multiple widely used network intrusion datasets demonstrate the ’s remarkable data efficiency and resilience. With as little as 5% of labeled training data, achieves an F1-score of 0.97 and an accuracy of 0.98 across all the benchmarks. Even in extreme data scarcity, using just 0.1% of labeled data, it maintains a high F1-score of 0.94+ and an accuracy of 0.96+. Furthermore, we demonstrate the model’s resilience by evaluating it against common adversarial evasion attacks, such as the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD). Under these attacks, ś accuracy only degrades minimally to 0.95, outperforming standard deep learning baselines whose performance drops below 90% under similar conditions. These results validate as a scalable, resilient, and practical method for efficient network intrusion detection with high accuracy and low false positives, even in data-scarce and adversarial IoT environments.

This paper focuses on analysis of spatiotemporal binary data with absorbing states. The research was motivated by a clinical study on amyotrophic lateral sclerosis (ALS), a neurological disease marked by gradual loss of muscle strength over time in multiple body regions. We propose an autologistic regression model to capture complex spatial and temporal dependencies in muscle strength among different muscles. As it is not clear how the disease spreads from one muscle to another, it may not be reasonable to define a neighborhood structure based on spatial proximity. Relaxing the requirement for prespecification of spatial neighborhoods as in existing models, our method identifies an underlying network structure empirically to describe the pattern of spreading disease. The model also allows the network autoregressive effects to vary depending on the muscles' previous status. Based on the joint distribution derived from this autologistic model, the joint transition probabilities of responses among locations can be estimated and the disease status can be predicted in the next time interval. Model parameters are estimated through maximization of penalized pseudo-likelihood. Postmodel selection inference was conducted via a bias-correction method, for which the asymptotic distributions were derived. Simulation studies were conducted to evaluate the performance of the proposed method. The method was applied to the analysis of muscle strength loss from the ALS clinical study.

The regional climate change index (RCCI) is employed to investigate hot-spots under 21st century global warming over East Asia. The RCCI is calculated on a 1-degree resolution grid from the ensemble of CMIP3 simulations for the B1, A1B, and A2 IPCC emission scenarios. The RCCI over East Asia exhibits marked sub-regional variability. Five sub-regional hot-spots are identified over the area of investigation: three in the northern regions (Northeast China, Mongolia, and Northwest China), one in eastern China, and one over the Tibetan Plateau. Contributions from different factors to the RCCI are discussed for the sub-regions. Analysis of the temporal evolution of the hot-spots throughout the 21st century shows different speeds of response time to global warming for the different sub-regions. Hot-spots firstly emerge in Northwest China and Mongolia. The Northeast China hot-spot becomes evident by the mid of the 21st century and it is the most prominent by the end of the century. While hot-spots are generally evident in all the 5 sub-regions for the A1B and A2 scenarios, only the Tibetan Plateau and Northwest China hot-spots emerge in the B1 scenario, which has the lowest greenhouse gas (GHG) concentrations. Our analysis indicates that subregional hot-spots show a rather complex spatial and temporal dependency on the GHG concentration and on the different factors contributing to the RCCI.

Predicting crop yield is a crucial factor in precision agriculture, especially under the conditions of increasing environmental uncertainty and climatic variability. This interest in predicting crop yield increased the necessity to develop advanced machine learning and dl models to refine the capabilities of accurate and efficient crop yield prediction. Existing models fail to handle real-time data and multiple types of data like weather conditions and IoT sensor readings. So it is crucial for us to implement a better crop yield prediction framework that can work well in all scenarios. In this paper, an Integrated Multi Stage Transformer (IMST) framework is discussed that uses an advanced Deep Learning (DL) approach. This IMST model uses a self-attention mechanism that captures complex spatial and temporal dependencies. The dataset contains different data like weather conditions, IoT sensor readings. The model is implemented and their performance is assessed using several evaluation metrics like accuracy, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and F1 score. The transformer model results with an accuracy of 94.3%. It addresses the difficulties commonly found in real-world applications and exhibits good performance with real-time data.

As one of the most widely used applications of the Internet of Things (IoT), intelligent transportation system (ITS) is of great significance for urban traffic planning, traffic control, and traffic guidance. However, widespread traffic congestion occurs with the increased number of vehicles. The traffic flow prediction is a good idea for traffic congestion. Therefore, many schemes have been proposed for accurate and real-time traffic flow prediction, but there still exist many issues, including low accuracy, weak adaptability and inferior real-time. Meanwhile, the complex spatial and temporal dependencies in traffic flow are still challenging. To address the above issues, we propose a novel spatial-temporal Chebyshev graph neural network model (ST-ChebNet) for traffic flow prediction to capture the spatial-temporal features, which can ensure accurate traffic flow prediction. Concretely, we first add a fully connected layer to fuse the features of traffic data into a new feature to generate a matrix, and then the long short-term memory (LSTM) model is adopted to learn traffic state changes for capturing the temporal dependencies. Then, we use the Chebyshev graph neural network (ChebNet) to learn the complex topological structures in the traffic network for capturing the spatial dependencies. Eventually, the spatial features and the temporal features are fused to guarantee the traffic flow prediction. The experiments show that ST-ChebNet can make accurate and real-time traffic flow prediction compared with other eight baseline methods on real-world traffic data sets PeMS.

Schizophrenia is associated with disrupted neural connectivity and abnormal brain dynamics that can be captured through electroencephalogram (EEG) analysis. However, traditional EEG analysis methods often fail to represent the complex spatial and temporal dependencies in brain activity. This paper addresses this challenge by modeling EEG signals as graph signals and comparing three graph construction strategies for schizophrenia classification: a Gaussian kernelbased similarity graph, a functional-causal fusion graph, and a Semilocal graph. EEG recordings from healthy controls and schizophrenia patients were preprocessed, band-pass filtered into canonical frequency bands (delta, theta, alpha, beta, gamma), and represented as graphs according to each construction method. Graph-based features were extracted and used for classification with a support vector machine under fivefold stratified cross-validation. Experimental results demonstrate that the functional-causal fusion graph consistently achieved the highest accuracy across all frequency bands, reaching perfect classification in several cases, while the Gaussian kernel and Semilocal graphs produced slightly lower but competitive results. These findings indicate that integrating functional and causal connectivity information provides a more discriminative graph representation for schizophrenia EEG classification and emphasize the importance of graph construction strategy in EEG analysis using graph signal processing.

CPNet: Conditionally parameterized graph convolutional network for traffic forecasting

Dynamic networks require effective methods of monitoring and surveillance in order to respond promptly to unusual disturbances. In many applications, it is of interest to identify anomalous behavior within a dynamic interacting system. Such anomalous interactions are reflected by structural changes in the network representation of the system. In this paper, a dynamic random graph model is proposed that takes into account the past activities of the individuals in the social network and also represents temporal dependency of the network. The model parameters are appearance and disappearance probabilities of an edge which are estimated using a maximum likelihood approach. A generalization of a single path‐dependent likelihood ratio test is employed to detect changes in the parameters of the proposed model. Through monitoring the estimated parameters, one can effectively detect structural changes in a temporal‐dependent network. The proposed model is employed to describe the behavior of a real network, and its parameters are monitored via dependent likelihood ratio test and multivariate exponentially weighted moving average control chart. Results indicate that the proposed dynamic random graph model is a reliable mean to modeling and detecting changes in temporally dependent networks.