Handover Strategy for LEO Satellite Networks Using Bipartite Graph and Hysteresis Margin by Sahar Eydian, Maryam Hosseini, Gunes Karabulut Kurt

“…The low Earth orbit (LEO) satellite constellation has become a highly effective solution for non-terrestrial networks (NTN), offering reliable, uninterrupted, and high-speed global communication. …”
Get full text

Dynamic climate graph network and adaptive climate action strategy for climate risk assessment and low-carbon policy responses by Fang Zhou, Yan Shi, Pengfei Zhao, Zhengzhao Gu, Ye Li

“…Traditional climate action models often struggle with capturing intricate spatial-temporal dependencies and integrating multi-modal data, resulting in limited scalability and real-world applicability.MethodsTo address these challenges, we propose a novel framework that integrates the Dynamic Climate Graph Network (DCGN) with the Adaptive Climate Action Strategy (ACAS). …”
Get full text

A Graph Convolutional Network-Based Fine-Grained Low-Latency Service Slicing Algorithm for 6G Networks by Yuan Ye, Caiming Zhang, Chenlan Wu, Xiaorong Zhu

“…A fine-grained network slicing algorithm for low-latency services in 6G based on GCNs (graph convolutional networks) is proposed. …”
Get full text

Inter-Satellite Cooperative Computing Scheme Driven by Business Graph in LEO Satellite Network by Xiaobo GUO, Zhiyuan REN, Wenchi CHENG, Zhe JI

“…Low earth orbit-satellite network (LEO-SN) has the advantages of wide coverage and short satellite-to-earth link, and has become a current hot research fi eld.A business graph-driven inter-satellite collaborative computing method in LEO-SN was proposed to solve the problem of high transmission delay when the task was offl oaded to the cloud computing center.This method shielded the dynamics of LEO-SN by relying on the weighted time expansion graph model, combined multiple satellite computing resources, and dispatches tasks in the form of a directed acyclic graph to the satellites in the transmission path, thereby realizing the ＆quot;computing while transmitting” of user services in the satellite cluster.The simulation results showed that when the data volume was 5 MB, the latency performance of on-orbit collaborative computing was improved by 58.9% compared to ground cloud computing.…”
Get full text

Using Graph Mining Method in Analyzing Turkish Loanwords Derived from Arabic Language by Abbood Kirebut Jassim, Muneam Jabbar Hamzah, Ahmed Hussein Aliwy

Get full text

Interpretable graph Kolmogorov–Arnold networks for multi-cancer classification and biomarker identification using multi-omics data by Fadi Alharbi, Nishant Budhiraja, Aleksandar Vakanski, Boyu Zhang, Murtada K. Elbashir, Harshith Guduru, Mohanad Mohammed

“…By integrating multi-omics data with graph-based deep learning, our proposed approach demonstrates robust predictive performance and interpretability with potential to enhance the translation of complex multi-omics data into clinically actionable cancer diagnostics.…”
Get full text

An integrated graph-spatial method for high-performance geospatial-temporal semantic query by Zichen Yue, Wei Zhu, Xin Mei, Shaobo Zhong

“…However, the efficiency of semantic querying of geospatial-temporal data in KGs remains a challenge. Graph databases excel at handling complex semantic associations but exhibit low efficiency in geospatial analysis tasks, such as topological analysis and geographic calculations, while relational databases excel at geospatial data storage and computation but struggle to efficiently process association analysis. …”
Get full text

Robust non-negative supervised low-rank discriminant embedding algorithm by Yu YAO, Minghua WAN

“…Non-negative matrix factorization (NMF) has been widely used.However, NMF pays more attention to the local information of the data, it ignores the global representation of the data.In terms of image classification, the global information of the data is often more robust to noise than the local information.In order to improve the robustness of the algorithm, combined with the data of local and global representation, and considered the characteristics of low-rank representation, a non-negative supervised low-rank discriminant embedded algorithm was proposed.This algorithm assumed the existence of noise in the data, decomposed the data into clean data and noise data, and made sparse constraints on the noise matrix through the L₁norm, so as to enhance the robustness to noise.In addition, the algorithm used low-rank representation to learn a low-rank matrix, then through non-negative decomposition, the robustness of the algorithm was enhanced again.Finally, combined with a study of graph embedding method, the local and global data were retained at the same time.The algorithm is applied to various noisy databases, and the recognition rate of this algorithm is improved by about 5%～15% compared with the comparison algorithm.…”
Get full text

Research on fault diagnosis of CTCS on-board equipment based on knowledge graph by CHEN Huiyuan

“…The knowledge graph model layer and data layer are separated by a business middle platform and a data middle platform within the entire system, which is ultimately constructed following a micro-service architecture. …”
Get full text

Multi-Scale Graph Attention Network Based on Encoding Decomposition for Electricity Consumption Prediction by Sheng Huang, Huakun Que, Lukun Zeng, Jingxu Yang, Kaihong Zheng

“…To this end, we propose an encoding decomposition-based multi-scale graph neural network (CMNN). The CMNN starts by decomposing the electricity data into various components. …”
Get full text

Knowledge Graph Construction Method for Commercial Aircraft Fault Diagnosis Based on Logic Diagram Model by Huanchun Peng, Weidong Yang

“…The results show that the logic diagram model can perform model simulation and fault diagnosis based on operational data, and the fault knowledge graph can quickly locate abnormal monitoring parameters and guide troubleshooting work based on existing information.…”
Get full text

Low Streamflow Analysis in Yeşilırmak Basin by Sümeyye Özkan, Turgay Partal

“…By using 31 years of data, flow rate continuous graphs were drawn first, and low flows were determined by reading Q90, Q95, and Q99 flow rates over these graphs. …”
Get full text

Exploring the Latent Information in Spatial Transcriptomics Data via Multi‐View Graph Convolutional Network Based on Implicit Contrastive Learning by Sheng Ren, Xingyu Liao, Farong Liu, Jie Li, Xin Gao, Bin Yu

“…To further refine the obtained low‐dimensional representations, a graph contrastive learning method with contrastive enhancement in the latent space is employed, aiming to better capture critical information in the data and improve the accuracy and discriminative power of the embeddings. …”
Get full text

Unmanned Aerial Vehicle Anomaly Detection Based on Causality-Enhanced Graph Neural Networks by Chen Feng, Jun Fan, Zhiliang Liu, Guang Jin, Siya Chen

“…Furthermore, CEG incorporates a trend-decomposed temporal feature extraction module to capture temporal dependencies in high-dimensional flight data. A low-rank regularization training paradigm is designed for CEG, and a residual adaptive bidirectional smoothing strategy is employed to eliminate the influence of noise. …”
Get full text

A novel Knowledge Graph recommendation algorithm based on Graph Convolutional Network by Hui Guo, Chengyong Yang, Liqing Zhou, Shiwei Wei

“…KGs often need to be complete, missing relationships between users and items, data sparsity, weak associations, and difficulties in knowledge inference, resulting in low credibility of recommendation results. …”
Get full text

An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data by Huan Tao, Ziyang Li, Shengdong Nie, Hengkai Li, Dan Zhao

“…By integrating spatial autocorrelation with deep graph representation, ASI-GCN redefines sparse data 3D mapping, offering a transformative tool for precise environmental governance and human health assessment.…”
Get full text

GeoFAN: Point Pattern Recognition in Spatial Vector Data by Zhuoyi Yang, Zeyi Li, Haitao Zhang, Wei Zhang, Yanwei Wang, Yihang Huang

“…Secondly, the lack of edge connectivity relationships in spatial vector data directly hinders the application of graph models. …”
Get full text

Regional and sub-regional estimates of low birth weight and its determinants in 44 low- and middle-income countries: evidence from demographic and health survey data by Kusse Urmale Mare, Gashaye Gobena Andarge, Kebede Gemeda Sabo, Osman Ahmed Mohammed, Ahmed Adem Mohammed, Abdulkerim Hassen Moloro, Oumer Abdulkadir Ebrahim, Beminate Lemma Seifu, Bizunesh Fantahun Kase, Habtamu Solomon Demeke, Temesgen Gebeyehu Wondmeneh, Setognal Birara Aychiluhm, Abay Woday Tadesse, Getahun Fentaw Mulaw, Simeon Meskele Leyto, Begetayinoral Kussia Lahole, Tesfahun Simon Hadaro, Beriso Furo Wengoro

Get full text

Text classification model based on GNN and attention mechanism by ZENG Shuifei, MENG Yao, LIU Jing

“…Addressing the issue of low classification accuracy raised by the poor performance of the model, which is caused by the difficulty in learning from dynamic aggregation unknown neighboring nodes of graph data and insufficient fusion of semantic features, a model named graph attention text classification(GATC) based on graph neural network (GNN) and attention mechanism was proposed. …”
Get full text

Pre-processing of paleogenomes: mitigating reference bias and postmortem damage in ancient genome data by Dilek Koptekin, Etka Yapar, Kıvılcım Başak Vural, Ekin Sağlıcan, N. Ezgi Altınışık, Anna-Sapfo Malaspinas, Can Alkan, Mehmet Somel

“…Abstract We investigate alternative strategies against reference bias and postmortem damage in low coverage paleogenomes. Compared to alignment to the linear reference genome, we show that masking known polymorphic sites and graph alignment effectively remove reference bias, but only starting from raw read files. …”
Get full text