Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yunzhuo Liu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning

    by Yunzhuo Liu, Ruoning Zhang, Shijie Zhou

    Vehicle simulation algorithms play a crucial role in enhancing traffic efficiency and safety by predicting and evaluating vehicle behavior in various traffic scenarios. Recently, vehicle simulation algorithms based on reinforcement learning have demonstrated excellent performance in practical tasks due to their ability to exhibit superior performance with zero-shot learning. However, these algorithms face challenges in field adaptation problems when deployed in task sets with variable-dimensional observations, primarily due to the inherent limitations of neural network models. In this paper, we propose a neural network structure accommodating variations in specific dimensions to enhance existing reinforcement learning methods. Building upon this, a scene-compatible vehicle simulation algorithm is designed. We conducted experiments on multiple tasks and scenarios using the Highway-Env traffic environment simulator. The results of our experiments demonstrate that the algorithm can successfully operate on all tasks using a neural network model with fixed shape, even with variable-dimensional observations. Our model exhibits no degradation in simulation performance when compared to the baseline algorithm.


  • Open Access

    Swin-APT: An Enhancing Swin-Transformer Adaptor for Intelligent Transportation

    by Yunzhuo Liu, Chunjiang Wu, Yuting Zeng, Keyu Chen, Shijie Zhou

    Artificial Intelligence has been widely applied in intelligent transportation systems. In this work, Swin-APT, a deep learning-based approach for semantic segmentation and object detection in intelligent transportation systems is presented. Swin-APT includes a lightweight network and a multiscale adapter network designed for image semantic segmentation and object detection tasks. An inter-frame consistency module is proposed to extract more accurate road information from images. Experimental results on four datasets: BDD100K, CamVid, SYNTHIA, and CeyMo, demonstrate that Swin-APT outperforms the baseline by 13.1%. Furthermore, experiments on the road marking detection benchmark show an improvement of 1.85% of mAcc.


  • Open Access

    Mobile Payment Protocol with Deniably Authenticated Property

    by Yunzhuo Liu, Wen Huang, Ming Zhuo, Shijie Zhou, Mengshi Li

    Mobile payment services have been widely applied in our daily life, where users can conduct transactions in a convenient way. However, critical privacy concerns have arisen. Specifically, a risk of participating in a transaction is the disclosure of personal privacy. This might occur if, for example, the user pays for some special medicine, such as AIDS medicine or contraceptives. In this paper, we propose a mobile payment protocol that is suitable for mobile devices only with limited computing resources. In particular, the user in a transaction can confirm the identity of others in the same transaction while the user cannot show convincing evidence to prove that others also take part in the same transactions. We implement the proposed protocol and test its computation overhead. The experiment results corroborate that the proposed protocol is suitable for mobile devices with limited computing resources.


  • Open Access

    Local Cluster-Aware Attention for Non-Euclidean Structure Data

    by Ming Zhuo, Yunzhuo Liu, Leyuan Liu, Shijie Zhou

    Meaningful representation of large-scale non-Euclidean structured data, especially in complex domains like network security and IoT system, is one of the critical problems of contemporary machine learning and deep learning. Many successful cases of graph-based models and algorithms deal with non-Euclidean structured data. However, It is often undesirable to derive node representations by walking through the complete topology of a system or network (graph) when it has a very big or complicated structure. An important issue is using neighborhood knowledge to deduce the symmetric network’s topology or graph. The traditional approach to solving the graph representation learning issue is surveyed from machine learning and deep learning perspectives. Second, include local neighborhood data encoded to the attention mechanism to define node solidarity and enhance node capture and interactions. The performance of the proposed model is then assessed for transduction and induction tasks that include downstream node categorization. The attention model taking clustering into account has successfully equaled or reached the state-of-the-art performance of several well-established node classification benchmarks and does not depend on previous knowledge of the complete network structure, according to experiments. Following a summary of the research, we discuss problems and difficulties that must be addressed for developing future graph signal processing algorithms and graph deep learning models, such as graph embeddings’ interpretability and adversarial resilience. At the same time, it has a very positive impact on network security and artificial intelligence security.