graph neural networks

Evaluation and Planning Method for Renewable Energy Carrying Capacity of Novel Power Systems Based on Deep Spatiotemporal Feature Learning and Inter-Provincial Mutual Assistance Synergy

INTRODUCTION: With the in-depth advancement of novel power system construction, the randomness and volatility brought by high-proportion renewable energy grid connections pose severe challenges to long-term planning. Traditional methods struggle with extracting complex non-linear features from massive data and face lim...

CTH-RiskGNN

Credit card fraud detection has become increasingly challenging because modern financial transactions are highly heterogeneous, temporally evolving, structurally connected, and severely imbalanced. To address these challenges, this paper proposes CTH-RiskGNN, a causal temporal heterogeneous graph neural network designe...

MR-H2SAGE intermediate files: graph and model results for "Not all edges are equal: separating edge types in graph neural networks for lithology prediction from borehole logs"

Intermediate files of the MR-H2SAGE workflow (https://gitlab.com/frederikke-storm-phd/mr-h2sage) to reproduce every figure and table of the paper with notebook 05: graph_data_structure.pkl: the PyTorch Geometric graph of 63 Danish boreholes with processed borehole logs, lithology classes and depth, spatial and feature-...

Classroom Teaching Behavior Analysis System Based on Multi-Feature Behavior Attitude Recognition Algorithm

To address the limitations of traditional and single-modality methods in classroom teaching analysis, this study proposes a Classroom Teaching Behavior Analysis (CTBA) system based on a multi-feature behavior posture recognition algorithm. The system initially employs object detection and pose estimation to locate key...

KHANH MATHEMATICS - Chapter 2: Directed Graphs for AI, Knowledge Graphs & Neural DAGs: From Basics of Directed Graphs (Lecture 6, 2012) to Deep-Tech Graph Systems 2026

KHANH MATHEMATICS - Chapter 2: Directed Graphs for AI, Knowledge Graphs & Neural DAGs Author: Nguyen Kim KhanhAffiliation: Khanh UniversityORCID: 0009-0006-9191-1441Email: khanhtbys@gmail.comDate: 20 Oct 2026, Ho Chi Minh City, Vietnam Abstract:This chapter reconstructs Lecture 6 (Basics of Directed Graphs, Definition...

Deep Learning-Powered Spatial Transcriptomics Analysis to Predict Immune Checkpoint Inhibitor Response from Pre-Treatment Digital Pathology Slides

Response to immune checkpoint inhibitors (ICIs) is governed in part by the spatial organization of the tumour microenvironment, yet most deep learning models applied to digital pathology treat tissue regions independently and therefore do not represent the neighbourhood interactions that shape immune activation. This s...

Jointly predicting courses and grades using a transformer-based model

Existing predictive models in learning analytics often treat student academic history as a simple sequence, overlooking the concurrent nature of courses taken within a semester. This simplification can lead to inaccurate performance predictions, particularly for students with heavy or challenging course loads. This pap...

Recursive computation of path homology for stratified digraphs

An AI powered, proactive security framework for IoT threat detection and response

The rapid expansion of Internet of Things (IoT) networks has introduced unprecedented connectivity and functionality across domains, but it has also exposed systems to increasingly sophisticated and evolving cyber threats. Traditional intrusion detection systems (IDS) are often inadequate for handling the complexity of...

THE CHEMICAL ALGORITHMIC INTELLIGENCE FRAMEWORK FROM QUANTUM MOLECULES TO REGULATORY COMPLIANCE A Unified Theory of Artificial Intelligence, Computational Chemistry, Algorithmic Design, and Chemical Law

The Chemical Algorithmic Intelligence Framework: From Quantum Molecules to Regulatory Compliance by Dr. Mohamed Kamal Arafa El-Rakhawi (DOI: 10.5281/zenodo.23460404) establishes Chemical Algorithmic Intelligence as a groundbreaking academic field integrating artificial intelligence, computational chemistry, algorithmic...

THE HYDRO-CARBON INTELLIGENCE FRAMEWORK FROM QUANTUM MOLECULES TO GLOBAL GOVERNANCE A Unified Theory of Artificial Intelligence, Physics, Mathematics, Carbon, Water, Hydrogen, and Environmental Law

The Hydro-Carbon Intelligence Framework: From Quantum Molecules to Global Governance by Dr. Mohamed Kamal Arafa El-Rakhawi (DOI: 10.5281/zenodo.23460269) establishes Hydro-Carbon Intelligence as a groundbreaking academic field integrating artificial intelligence, physics, mathematics, and environmental law to address t...

Beyond accuracy in crop classification: calibration, selective prediction, and robustness

Introduction: Near-perfect crop-label accuracy can conceal uncertainty, perturbation sensitivity, and weak explanations. This study evaluates these reliability dimensions without treating benchmark classification as an agronomic recommendation. Materials and methods: Ten classifiers were evaluated using five matched st...