Network Science and Graph Analytics

Graph Convolutional Network with Multi-View Topology for Lightweight Skeleton-Based Action Recognition Skeleton-based action recognition is an important subject in deep learning. Graph Convolutional Networks (GCNs) have demonstrated strong performance by modeling the human skeleton as a natural topological graph, representing the connections between joints. However, most existing methods rely on non-adaptive topologies or insufficiently expressive representations. To address these limitations, we propose a Multi-view Topology Refinement Graph Convolutional Network (MTR-GCN), which is efficient, lightweight, and delivers high performance. Specifically: We propose a new spatial topology modeling approach that incorporates two views. A dynamic view fuses joint information from dual streams in a pairwise manner, while a static view encodes the shortest static paths between joints, preserving the original connectivity relationships. We propose a new MultiScale Temporal Convolutional Network...

Network science disentangles internal climate variability in global spatial dependence structures A comprehensive characterization of internal climate variability (ICV) in initial-condition (IC) large ensembles of Earth system models (ESMs) remains a significant challenge in climate science. In this study, we leverage the spatial connectivity structures of temperature networks to characterize ICV, observing substantial differences across ensemble members, particularly in the prevalence of long-range connections. Based on this feature, we introduce the ‘Connectivity Ratio’ (CR), a new quantifier that captures long-range spatial connectivity within climate networks. CR is applied to two ESMs, EC-Earth3 and MPI-ESM1-2-LR, to evaluate structural variability across IC ensemble members, models, and climate time horizons. CR reveals systematic differences in long-range connectivity between forced and unforced simulations, as well as across future climate periods. As such, CR provides an inter...

Network Parameters of Mental Health Concerns in Adolescents: An Examination of Age and Sex Differences Introduction Adolescent mental health concerns are crucial for early intervention. This study examined networks of mental health concerns with the aim of identifying central issues and analyzing age and sex differences in these networks during adolescence. Methods A total of 3723 middle and high school students (aged 11–19 years; M = 14.39, SD = 1.38; 43.6% girls) were recruited for this cross-sectional study from May 8, 2023 to September 10, 2023, in Chongqing and Nanning, China. Loneliness, social anxiety, generalized anxiety, depression, suicidal behavior, Internet addiction, sleep quality, self-esteem, and self-efficacy were assessed using a questionnaire. Centrality indices were analyzed to identify the most central mental health concerns. A network comparison test was conducted to examine whether the network parameters varied by age and sex. Results Loneliness was the most centr...

A simplified method for estimating the alpha coefficient in surface velocity based river discharge measurements Remote sensing techniques for river monitoring facilitate faster measurement campaigns compared to traditional methods, reduce risks to personnel and instruments, and allow measurements under critical flow conditions. An alpha coefficient (α) is commonly employed to convert surface velocities, obtained by contactless techniques, into depth-averaged velocities , which are used for the application of the velocity-area method for assessing discharge. Some optical-based software programs use a constant α value, based on a theoretical “standard”. However, analyses of empirical vertical velocity profiles in real cases reveal that α can significantly deviate from this standard due to various factors (roughness, turbulence, etc.). This study analyzes several ADCP (Acoustic Doppler Current Profiler)-based measurements in Sicily, Italy, to explore factors influencing flow velocity dist...

A deep learning strategy for the 3D segmentation of colorectal tumors from ultrasound imaging Colorectal cancer remains a leading cause of cancer-related mortality worldwide, highlighting the need for accurate and efficient diagnostic tools. While Deep Learning has shown promise in medical imaging, its application to transrectal ultrasound for colorectal tumor segmentation remains underexplored. Currently, lesion segmentation is performed manually, relying on clinician expertise and leading to significant variability across treatment centers. To overcome this limitations, we propose a novel strategy that addresses both practical challenges and technical constraints, particularly in scenarios with limited data availability, offering a robust framework for accurate 3D colorectal tumor segmentation from ultrasound imaging. We evaluate eight state-of-the-art models, including convolutional neural networks and transformer-based architectures, and introduce domain-tailored pre- and post-pro...

A machine learning framework for seismic risk assessment of industrial equipment The paper aims to propose a novel machine learning framework for seismic risk assessment of industrial facilities. In this respect, a compound artificial neural network model is employed, which is based on two different artificial neural network models in series. The first artificial neural network is a regression model employed to generate samples of a vector-valued intensity measure. The second one is a classification model that is used to predict structural damage, starting from the outcomes of the first artificial neural network model . The datasets used for training and validation of the two artificial neural networks are based on hazard-consistent accelerograms and numerical analyses that are performed with an efficient finite element model of the structure. The methodology entails a preliminary feature selection phase for the identification of the aforementioned vector-valued of intensity measures t...

EE and BT network outage resolved, firm says A network outage affecting thousands of EE and BT customers has been resolved, a spokesperson has said. Customers reported they were unable to make or receive calls as the mobile phone and landline networks faced an outage. Some customers reported issues with making 999 calls, but the government said these had "now been restored". A spokesperson from BT, which owns EE, apologised for the outage and said it has "resolved the problem and the service is running as normal". The spokesperson said late on Thursday the issue happened "following a technical fault impacting voice services on our network earlier today". Outages tracker Downdetector, which relies on self-reported user data, showed over 2,500 EE customers experiencing outages at 14:00 BST, with many also reporting issues with other networks. Vodafone and Three confirmed to the BBC that they did not have network issues. Other networks had seen spikes in repo...