HDHao Dong

Hao Dong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hao Dong has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    LaCoCast: Traffic Flow Forecasting with Lag-Aware Cross-Sensor Corroboration

    by Yanji Jiang, Hongwei Zhou, Hao Dong, Haiyang Zhang, Zhongbin Luo

    Traffic flow forecasting estimates future vehicle counts at monitored road locations from historical observations. A central challenge is determining how strongly forecasts should respond when recent observations depart from recurring traffic patterns. We propose LaCoCast, which combines a periodic reference with lag-aware cross-sensor corroboration to regulate local forecast corrections. The reference encodes temporal translation symmetry by assigning the same baseline flow level to matching phases across cycles, while a local forecaster predicts deviations from this reference. Earlier neighbor observations reconstruct recent target deviations, providing evidence for evaluating their agreement with observed target behavior. A correction gate combines this agreement with evidence availability, neighbor coverage, and local context to adjust the residual candidate’s contribution at each forecast horizon. Experiments on PEMS03, PEMS04, PEMS07, and PEMS08 yielded mean absolute errors 0.38–6.13% below the lowest published baseline values included in the comparison for each dataset. Ablation and evidence perturbation experiments further support the use of temporally matched neighbor observations to regulate residual contributions, connecting a periodic structural reference with adaptive traffic flow forecasting.

  • Open Access

    Graph attention-driven relation network for 3D lane detection

    by Yanji Jiang, Yingyang Zhang, Jiayu Bi, Hao Dong, Daqian Liu, Ke Gao, Bowen Fei

    Lane detection is a crucial task in autonomous driving, but existing methods still struggle with occluded, missing, and complex road structures of lanes. To address these issues, we propose a graph attention-based 3D lane detection method-Graph-RMNet. This network enhances the model's understanding of the three-dimensional distribution of lanes by parsing the topological structure and semantic category relationships between them. First, we introduce a 3D positional query generation strategy that combines 3D spatial information with 2D image features to initialize queries, thereby enhancing the queries' perception of the three-dimensional distribution of lanes. Furthermore, we design a dual-path relation module that captures complex interactions through graph attention mechanisms and models lane relations from both spatial and categorical dimensions via a specially designed adaptive graph structure, improving the model's comprehension and expression of complex inter-lane relations. Ultimately, the prediction module outputs the 3D coordinates and categories of the lanes to construct a complete distribution of the lanes in 3D space. The experimental results show that Graph-RMNet achieves F-Score of 63.2% on the OpenLane dataset and F-Score of 80.63% on the ONCE-3DLanes dataset, both outperforming current popular algorithms. Notably, it demonstrates significant robustness in scenarios where lanes are occluded or missing.


  • Open Access

    Adaptive Neural Network Structure Optimization Algorithm Based on Dynamic Nodes

    by Miao Wang, Xu Yang, Yunchong Qian, Yunlin Lei, Jian Cai, Ziyi Huan, Xialv Lin, Hao Dong

    Large-scale artificial neural networks have many redundant structures, making the network fall into the issue of local optimization and extended training time. Moreover, existing neural network topology optimization algorithms have the disadvantage of many calculations and complex network structure modeling. We propose a Dynamic Node-based neural network Structure optimization algorithm (DNS) to handle these issues. DNS consists of two steps: the generation step and the pruning step. In the generation step, the network generates hidden layers layer by layer until accuracy reaches the threshold. Then, the network uses a pruning algorithm based on Hebb’s rule or Pearson’s correlation for adaptation in the pruning step. In addition, we combine genetic algorithm to optimize DNS (GA-DNS). Experimental results show that compared with traditional neural network topology optimization algorithms, GA-DNS can generate neural networks with higher construction efficiency, lower structure complexity, and higher classification accuracy.