Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiang Wang has a total of 2 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Systematic Method Combining Rotated Convolution and State Space Augmented Transformer for Digitizing and Classifying Paper ECGs

    by Xiang Wang, Jie Yang

    Billions of paper Electrocardiograms (ECGs) are recorded annually worldwide, particularly in the Global South. Manual review of this massive dataset is time-consuming and inefficient. Accurate digital reconstruction of these records is essential for efficient cardiac disease diagnosis. This paper proposes a systematic framework for digitizing paper ECGs with 12 symmetrically distributed leads and identifying abnormal samples. This method consists of three main components. First, we introduce an adaptive rotated convolution network to detect the positions of lead waveforms. By exploiting the symmetric distribution of 12 leads, a novel loss is proposed to improve the detection model’s performance. Second, image processing techniques, including denoising and connected component analysis, are employed to digitize ECG waveforms. Finally, we propose a transformer-based classification method combined with a state space model. Our process is evaluated on a large synthetic dataset, including ECG images characterized by rotations, noise, and creases. The results demonstrate that the proposed detection method can effectively reconstruct paper ECGs, achieving an 11% improvement in SNR compared to the baseline. Moreover, our classification model exhibits slightly higher performance than other counterparts. The proposed approach offers a promising solution for the automated analysis of paper ECGs, supporting clinical decision-making.


  • Open Access

    Integrating Spatial and Temporal Information for Violent Activity Detection from Video Using Deep Spiking Neural Networks

    by Xiang Wang, Jie Yang, Nikola K. Kasabov

    Increasing violence in workplaces such as hospitals seriously challenges public safety. However, it is time- and labor-consuming to visually monitor masses of video data in real time. Therefore, automatic and timely violent activity detection from videos is vital, especially for small monitoring systems. This paper proposes a two-stream deep learning architecture for video violent activity detection named SpikeConvFlowNet. First, RGB frames and their optical flow data are used as inputs for each stream to extract the spatiotemporal features of videos. After that, the spatiotemporal features from the two streams are concatenated and fed to the classifier for the final decision. Each stream utilizes a supervised neural network consisting of multiple convolutional spiking and pooling layers. Convolutional layers are used to extract high-quality spatial features within frames, and spiking neurons can efficiently extract temporal features across frames by remembering historical information. The spiking neuron-based optical flow can strengthen the capability of extracting critical motion information. This method combines their advantages to enhance the performance and efficiency for recognizing violent actions. The experimental results on public datasets demonstrate that, compared with the latest methods, this approach greatly reduces parameters and achieves higher inference efficiency with limited accuracy loss. It is a potential solution for applications in embedded devices that provide low computing power but require fast processing speeds.


  • Open Access

    A Big Data-Driven Deep Transfer Learning Approach for Path Loss Prediction in Mobile Communications

    by Xiang Wang, Jie Yang

    Radio base stations are quite crucial to the quality of mobile communication services. The path loss of the mobile signal is mainly affected by the physical parameters of the base station itself and the geographical structure within the service area. Efficiently optimizing the number and assignment of radio base stations by predicting the path loss of radio signals within the service range is of great significance for improving signal quality and saving costs. The traditional modeling method based on the physical parameters of the base station and wireless signal propagation mechanism cannot consider geographical structure information, and the prediction accuracy is low. Another method based on simulation software can improve prediction accuracy, but it requires professional knowledge to guide the experiment, and the cost is very high. In this work, based on the massive geographical data and the path loss data within the service range of the base station including real data and simulation data, our approach uses the deep transfer learning method to construct a data-driven model for predicting the signal path loss of the base station. Moreover, the polar coordinate transformation is used to enhance the capacity of extracting the features of radio propagation, and a two-stream model is constructed to decouple geographic information and physical parameters of the base station for improving prediction accuracy. Using the prediction accuracy obtained between the measured and the model outputs as a measure of performance, the experimental results show that compared with the baseline model, our method significantly improves the accuracy of predicting signal path loss on testing data, which verifies the effectiveness of our method.