ZXZhenchang Xia

Zhenchang Xia

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zhenchang Xia has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DMRAD: Dynamic Decomposition and Memory-Aware Reconstruction for Noise-Resilient Multivariate Time Series Anomaly Detection

    by Zhenchang Xia, Jun Ma, Bolong Zheng, Liangliang Wang, Yanan Chang, Jianqun Cui

    Unsupervised anomaly detection in multivariate time series can prevent large-scale system failures and is crucial for various applications. Most existing methods only consider a single temporal pattern and insufficiently model the normal pattern, causing the model to learn incorrect temporal patterns from anomalous or noisy data. This poses a significant challenge for accurate anomaly detection. To overcome these challenges, we introduce a new dynamic decomposition and reconstruction anomaly detection algorithm, DMRAD. DMRAD captures various regular patterns of multivariate time series by designing a dynamic decomposition module that learns trend and seasonal features. By integrating improved channel and temporal attention mechanisms, DMRAD effectively learns the correlations within the sequence and dependencies across different sequences, thereby enhancing the model’s capacity to distinguish between features and extract relevant information. DMRAD incorporates a latent anomaly-noise detection algorithm to identify and suppress the influence of noise and latent anomalies, elevating the overall accuracy of anomaly detection. Extensive experimental comparisons demonstrate that DMRAD achieves state-of-the-art performance on a variety of datasets for real-world application scenarios.


  • RDNet: Rotate-Groundtruth Augmentation and Decoupled Attention HEAD for 3D Object Detection

    by Zhenchang Xia, Guanqun Zheng, Shengwu Xiong, Junyin Wang, Jianqun Cui, Yanan Chang, Chenghu Du, Jia Wu

    LiDAR is one of the most important sensors in the field of autonomous driving and allows for better and more accurate perception of the changes in the surrounding environment. Most of the existing 3D object detection methods use data augmentation and feature fusion enhancement to improve the performance of detection, but the majority of the methods ignore the handling of sample imbalance problems during data augmentation. Also, the designed feature fusion and enhancement methods were not well suited to work with the enhancement methods. To this end, we developed a combined method involving data augmentation and feature enhancement. The designed approach has two main objectives: 1) to address the problem of unbalanced sample distribution in detection scenes through data augmentation, and 2) to enhance feature perception using a special feature enhancement module. Our proposed method solves the problem of class imbalance by directly increasing the number of pedestrian samples in the scene through mixed data augmentation, i.e., RG-Aug. In addition, we introduce the Decoupling and Attention Fusion module (DAF), which combines classification headers with high-level features and prediction branches with low-level features. Leverage data features between different layers of features to get a more robust feature representation. Finally, the multi-scale pyramid attention enhancement module is designed to achieve feature enhancement of multi-scale features by means of attention to improve the detection ability of small objects in the scene, especially the detection ability of pedestrians. Our method can achieve 1.57%, 2.16%, and 2.05% performance improvement on the KITTI dataset for Easy, Mod, and Hard samples, respectively. Furthermore, for the detection of pedestrians, our method has a significant competitive advantage over other state-of-the-art techniques with a mAP of 73.42%.

  • HybridBEV: Hybrid Encode and Distillation for Improved BEV 3D Object Detection

    by Junyin Wang, Chenghu Du, Huikai Liu, Zhenchang Xia, Bingyi Liu, Shengwu Xiong

    The development of surround-view cameras is crucial for the advancement of autonomous driving. Utilizing depth information and image features to simulate LiDAR bird’s-eye-view (BEV) features can accomplish efficient 3D object detection tasks. Existing dense BEV generation methods heavily rely on the use of depth features, however, the suboptimal exploitation of these features often results in ambiguity in object location and feature representation during the BEV generation process. To address this, we have designed a hybrid encode and distillation method to enhance 3D object detection performance, termed HybridBEV. Initially, we designed the HybridEncode module, which employs a resampling strategy of depth features in voxel space to obtain BEV features that more accurately reflect the distribution of objects. Subsequently, we introduced multiple distillation methods to supervise the network’s voxel features and BEV feature representations, assisting the student network in learning critical features from the teacher model and ensuring that BEV features can more distinctly represent object distribution. Furthermore, during network training, we loaded pre-trained weights from the teacher network to guide network optimization and accelerate training. Extensive experiments on the nuScenes benchmark demonstrate that HybridBEV can effectively improve the performance of the student network and outperform previous state-of-the-art methods based on surround-view cameras. The code will be published at https://github.com/wjyxx/HybridBEV


  • Multivariate Knowledge Tracking Based on Graph Neural Network in ASSISTments

    by Zhenchang Xia, Nan Dong, Jia Wu, Chuanguo Ma

    As an excellent means of improving students' effective learning, knowledge tracking can assess the level of knowledge mastery and discover latent learning patterns based on students' historical learning evaluation of related questions. The advantage of knowledge tracking is that it can better organize and adjust students' learning plans, provide personalized guidance, and thus achieve the purpose of artificial intelligence-assisted education. However, existing methods, for instance, Convolutional Knowledge Tracing(CKT), lacking consideration of graph structure and multi-variate time-series prediction, result in poor prediction accuracy. Inspired by recent successes of the graph neural network (GNN), we present a novel Multi-Variate Graph Knowledge Tracking (MVGKT) framework to address these limitations. Specifically, a multi-variate time-series knowledge tracking system based on spatio-temporal GNN is designed to model student learning trajectories in different spatial and temporal dimensions and capture both temporal dependencies and inter-student correlations. MVGKT incorporates a Gate Recurrent Unit (GRU) attentive mechanism and graph Fourier transform, discrete Fourier transform, and graph convolution network to increase the predictive accuracy of the student performances. Additionally, we design a question difficulty extraction system to obtain information on the difficulty of the questions and thus enhance the data features. Numerous experiments on the ASSISTments dataset have demonstrated that MVGKT is superior to existing knowledge-tracking methods on four metrics and has shown that our approach can enhance the predictive accuracy of student performance.


  • TRCC: Transferable Congestion Control With Reinforcement Learning

    by Zhicong Zheng, Zhenchang Xia, Yu-Cheng Chou, Yanjiao Chen

    The breathtaking progress in machine learning has motivated studies in learning-based congestion control algorithms, which are expected to adjust congestion window choices according to the dynamic network environment. Nevertheless, existing learning-based congestion control protocols are mostly designed and trained for a specific network environment. When applied to a different network environment, the previously trained model may see a considerable degradation in performance. As the rapid development of communication technologies has given rise to the emergence of a diversity of new networks, it is desirable for learning-based congestion control models to quickly transfer to different network environments. Driven by this motivation, we propose a novel transferable congestion control (TRCC) protocol, which takes full advantage of both reinforcement learning (RL) and transfer learning to intelligently cope with network congestion in scenarios. The key idea to enable a fast transfer from the source network environment to the target network environment is to fine-tune a well-trained model in the source network to suit the target network in a time-effective way. We theoretically prove the transferability and quick convergence of our proposed transfer RL-based congestion control algorithm by deriving the Markov transition matrix and the similarity of the reward function. Our experiments validate that TRCC can converge in a new network environment in a short time while achieving comparable performance with baseline algorithms.


  • Deep Attentive Interest Collaborative Filtering for Recommender Systems

    by Libing Wu, Youhua Xia, Shuwen Min, Zhenchang Xia

    Collaborative filtering (CF) is a pivotal building block in commercial recommender systems due to its strength and utility in user interest modeling. Recently, many researchers have turned to deep learning as a way to capture richer collaborative signals from user-item feature interactions. However, most deep-based methods only consider nonlinear, high-order interactions while ignoring the explicit collaborative signals in low-order interactions. They also typically ignore the quality of the user and item profiles. These are cornerstones in item recommendation that, we argue, must be considered for high-quality recommendations. Hence, we propose Deep Attentive Interest Collaborative Filtering (DAICF) to overcome these limitations. DAICF profiles users based on their interactive items, i.e., user neighborhood information. Similarly, item profiles are based on users who had interacted with it, i.e., item neighborhood information. Given a user's profile varies over different items, DAICF accurately models his attentive interests based on the specific target item. Low-order collaborative signals are captured by a shallow component, and high-order collaborative signals are captured by a deep component. These two complementary collaborative signals are then fused to provide rich recommendations that cut through today's information overload. By designing a personalized feature extraction method based on bilateral neighborhood information to solve the data sparsity problem in recommender systems, DAICF can dynamically distinguish the importance of a user's historical interaction items for predicting user preferences for a specific target item. A set of experiments against four real-world datasets validate that DAICF outperforms the most recent state-of-the-art recommendation algorithms and justifies the effectiveness and interpretability of our method.


  • Glider: rethinking congestion control with deep reinforcement learning

    by Zhenchang Xia, Libing Wu, Fei Wang, Xudong Liao, Haiyan Hu, Jia Wu, Dan Wu


  • Deep Reinforcement Learning for Smart City Communication Networks

    by Zhenchang Xia, Shan Xue, Jia Wu, Yanjiao Chen, Junjie Chen, Libing Wu

    Smart city communication networks hold the promise of harnessing the Internet of Things, smart devices, intelligent energy grids, autonomous cars and many other data architectures to improve quality of life for every citizen. And, as time and progress have gradually shifted this concept from an idea into a reality, the possibilities for what services a smart city might provide have exploded. Along with that expansion, the number of devices that may need to be supported across a communications network has multiplied enormously. However, existing congestion control protocols are not equipped to support this higher requirement for network performance. New protocols are needed to provide higher data throughputs, reduce queuing delays and packet loss, and maintain stable, reliable communications pathways. The end-to-end congestion control protocol presented in this paper does all these things. Called high throughput congestion control (HTCC), the framework takes full advantage of reinforcement learning and a fast growth algorithm to adaptively control the bytes in flight across the network's links to suit the prevailing network conditions. The result is a protocol that not only finds the optimal tradeoff between throughput, latency and packet loss, but also significantly speeds up the learning process to avoid wasting network resources, use all free bandwidth and maximize network utilization. A comprehensive set of experiments with HTCC and six state-of-the-art protocols -- Copa, PCC Vivace, PCC-Allegro, TCP Cubic, TaoVA-100x and FillP-Sheep -- demonstrate that, in most conditions, HTCC is able to make the best tradeoff between throughput, delay and loss rate.


  • ForeXGBoost: passenger car sales prediction based on XGBoost

    by Zhenchang Xia, Shan Xue, Libing Wu, Jiaxin Sun, Yanjiao Chen, Rui Zhang