H
Haiyang Yu
Researcher at Beihang University
Publications - 46
Citations - 3092
Haiyang Yu is an academic researcher from Beihang University. The author has contributed to research in topics: Computer science & Platoon. The author has an hindex of 8, co-authored 17 publications receiving 2022 citations.
Papers
More filters
Journal ArticleDOI
Modeling and Simulation of Traffic Flow Considering Driver Perception Error Effect
TL;DR: This work attempts to understand the role of driver’s perception error in determining the dynamical properties of a platoon of vehicles driving on a straight road.
Journal ArticleDOI
Connected and Automated Vehicles (CAVs) Platoon Stability Analysis Based on Dynamic Topology-based Model Under Communication Failure
TL;DR: In this article , the authors proposed a dynamic topology-based car-following model and its generalized form to characterize the change of the platoon system status and explored the stability analysis method.
Journal ArticleDOI
QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
TL;DR: The QH9 dataset as mentioned in this paper provides precise Hamiltonian matrices for 2,399 molecular dynamics trajectories and 130,831 stable molecular geometries, based on the QM9 dataset.
Proceedings ArticleDOI
Frontiers of Graph Neural Networks with DIG
TL;DR: This tutorial is proposed based upon the recently released open-source library Dive into Graphs along with hands-on code examples to demonstrate how to effortlessly implement benchmarks using DIG, a turnkey library that considers four frontiers in graph deep learning, including self-supervised learning of GNNs, 3D GNNS, explainability of Gnns, and graph generation.
Proceedings ArticleDOI
A participant selection based vehicle platoon asynchronous federated learning framework
TL;DR: In this paper , a participant selection-based asynchronous federated learning framework for an intelligent connected vehicle platoon is proposed, which effectively improves training efficiency through data share and asynchronous optimization, and a signaling game-based participant selection strategy is designed to accurately identify the potentially malicious participants by analyzing the Perfect Bayesian Equilibrium.