Who is the Weakest Link? A Network Vulnerability Analysis Using a Congested Transport Assignment by Oded Cats, Sanmay Shelat

“…We propose a user-equilibrium congested transit assignment model for a full-scan network vulnerability analysis by relying on the computations of network science indicators for infrastructure and service graphs. …”
Get full text

Accelerating flood warnings by 10 hours: the power of river network topology in AI-enhanced flood forecasting by Hongjun Wang, Jiyuan Chen, Yinqiang Zheng, Xuan Song

“…Although AI-based approaches have demonstrated promise, the effectiveness of graph neural networks (GNNs) in modeling the intricate dynamics of river networks remains contested. …”
Get full text

Communication optimization method of digital-analog hybrid simulation system based on min-cut partition by Li Yiyuan, Mu Qing, Xue Wei

Get full text

Small Sample Fiber Full State Diagnosis Based on Fuzzy Clustering and Improved ResNet Network by Xiangqun Li, Jiawen Liang, Jinyu Zhu, Shengping Shi, Fangyu Ding, Jianpeng Sun, Bo Liu

“…In addition, the OTDR curve field fault data are scarce, and data-driven deep neural network that needs a lot of data training cannot meet the requirements. …”
Get full text

Enhanced Position-Aided Beam Prediction Using Real-World Data and Enhanced-Convolutional Neural Networks by Ahmed Abd El Moaty Mohamed Gouda, Ehab K. I. Hamad, Aziza I. Hussein, M. Mourad Mabrook, A. A. Donkol

“…The model realized as high as a 50% power loss reduction in arguably the most challenging graphs, which is an exercise in reliability. This research fills the existing gap between the simulated aid beam alignment and real-world position beam aided alignment, which can be useful in improving beamforming in the upcoming wireless networks.…”
Get full text

Construction of a traffic flow prediction model based on neural ordinary differential equations and Spatiotemporal adaptive networks by Li Ma, Yunshun Wang, Xiaoshi Lv, Lijun Guo

“…Experiments are conducted on four traffic flow and two traffic speed datasets, showing that compared to traditional time series models, the proposed model’s prediction accuracy indicators have relatively improved by 45.09%, 39.14%, and 0.47% on average; compared to recurrent neural network (RNN) series models, the improvements are 18.91%, 15.77%, and 0.18% on average; compared to graph convolution series models, the improvements are 21.31%, 16.65%, and 0.21% on average; and compared to Transformer series models, the improvements are 6.57%, 6.23%, and 0.05% on average. …”
Get full text

Random Access Optimization With Generative Adversarial Networks in Industrial IoT Using Deep Deterministic Policy Gradient Approach by Ishtiaq Ahmad, Ramsha Narmeen, Muhammad Waleed Aftab, Yazeed Alkhrijah, Mohamad A. Alawad, Aryan Kaushik

“…In addition, we implement a fully connected graph neural network (GNN) as the second neural network in the GAN to predict timing advance (TA), which improves the average packet success rate and reduces overall latency. …”
Get full text

An arbitrary segmentation method for loss allocation in power grids with distributed generation by Wenqiang Tao, Hongkun Chen, Lei Chen, Shengbin Chen

“…Finally, the power grid is divided into simpler regions using the arbitrary segmentation method and graph theory, and network losses are allocated to users and distributed generations via a power flow tracing method, coupled with enhancements to the average network loss coefficient method. …”
Get full text

Improvement of the Method of Calculation of Steady-State Modes of Urban Electric Networks Taking into Account Consumer Energy Sources by M. I. Fursanov, A. A. Zalotoy

“…The values of these parameters in single-line substitution schemes of 6–10 kV distribution networks with isolated neutral are assumed to be average for three phases. …”
Get full text

SPARQ: Efficient Entanglement Distribution and Routing in Space–Air–Ground Quantum Networks by Mohamed Shaban, Muhammad Ismail, Walid Saad

“…To solve the entanglement routing problem, a deep reinforcement learning (RL) framework is proposed and trained using deep Q-network (DQN) on multiple graphs of SPARQ to account for the network dynamics. …”
Get full text

Decision level scheme for fusing multiomics and histology slide images using deep neural network for tumor prognosis prediction by Tingting Zhao, Yongyong Ren, Hui Lu, Yan Kong

Get full text

A few-shot learning-based dual-input neural network for complex spectrogram recognition system with millimeter-wave radar by Kaiyu Chen, Shaoxi Wang, Wei Li, Yucheng Wang, Cunqian Feng, Yannian Zhou, Jian Cao, Binfeng Zong, Minming Gu

Get full text

A Novel Approach Based on Hypergraph Convolutional Neural Networks for Cartilage Shape Description and Longitudinal Prediction of Knee Osteoarthritis Progression by John B. Theocharis, Christos G. Chadoulos, Andreas L. Symeonidis

“…The predictor is a spatio-temporal <i>HGCN</i> network (<i>ST_HGCN</i>), following the sequence-to-sequence learning scheme. …”
Get full text

A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach by Terence Kibula Lukong, Derick Nganyu Tanyu, Yannick Nkongtchou, Thomas Tamo Tatietse, Detlef Schulz

“…Advanced methods like spatiotemporal graph transformers, graph convolutional networks, and improved scale-limited dynamic time warping better capture these dependencies, thereby enhancing prediction accuracy. …”
Get full text

A Fault Diagnosis Framework for Pressurized Water Reactor Nuclear Power Plants Based on an Improved Deep Subdomain Adaptation Network by Zhaohui Liu, Enhong Hu, Hua Liu

“…To address these issues, this study proposes a novel framework integrating three key stages: (1) feature selection via a signed directed graph to identify key parameters within datasets; (2) temporal feature encoding using Gramian Angular Difference Field (GADF) imaging; and (3) an improved Deep Subdomain Adaptation Network (DSAN) using weighted Focal Loss and confidence-based pseudo-label calibration. …”
Get full text

Classification and recognition method of dangerous behaviors of electric power operators based on improved OpenPose algorithm by Ningtao Liu, Jie Du, Shiliang Chang, Ke Zheng, Ji Xiao, Jiaming Zhang, Shishun Tan

“…Abstract To achieve intelligent identification of dangerous behaviors of electric power workers in complex environment, a classification and identification method based on improved OpenPose algorithm is proposed. The GSP-Darknet network is used to enhance the extraction of key points of small bones, and the missing joint coordinates are filled in by the average values of adjacent frames. …”
Get full text

Dynamic topology adaptability of adaptive multimodal transmission strategy based on environment perception in multi-hop routing of 5G vehicle network by Shengxia Tan, Xianshuang Zong, Feng Xiao

“…Then, graph sample and aggregation (GraphSAGE) is used to process the network topology and extract node and edge features of the data. …”
Get full text

Robust topology construction method with radio interface constraint for multi-radio multi-channel wireless mesh network using directional antennas by Xuecai Bao, Longzhe Han, Chengzhi Deng, Hai Zhang, Wenqun Tan

“…Multi-radio and multi-channel wireless mesh networks using directional antenna (MR-MC DWMN) greatly improve the spatial reuse of wireless channels and increase network capacity. …”
Get full text

Factors Associated With the Level of Trust in Health Information Robots Among the General Population From a Socioecological Model Perspective: Network Analysis by Jiukai Zhao, Yuqi Yang, Juanxia Miao, Xue Wang, Dianjun Qi, Shuang Zang

“…In addition, using a network approach, central indicators were identified in the network of the level of trust in health information robots and its associated factors, including family health and perceived social support. …”
Get full text

Network-based machine learning reveals cardiometabolic multimorbidity patterns and modifiable lifestyle factors: a community-focused analysis of NHANES 2015–2018 by Danhui Mao, Junfang Mu, Yajing Li, Lu He, Qianhui Chai, Xin Zhao, Xiaojun Ren, Hui Cheng

“…The Louvain algorithm was used to divide the CMM graph network into communities to obtain CMM patterns. …”
Get full text