Dynamic heterogeneous graph neural networks (DHGNNs) have been shown to be effective in handling the ubiquitous dynamic heterogeneous graphs. However, the existing DHGNNs are hand-designed, requiring extensive human efforts and failing to adapt to diverse dynamic heterogeneous graph scenarios. In this paper, we propose to automate the design of DHGNN, which faces two major challenges: 1) how to design the search space to jointly consider the spatial-temporal dependencies and heterogeneous interactions in graphs; 2) how to design an efficient search algorithm in the potentially large and complex search space. To tackle these challenges, we propose a novel Dynamic Heterogeneous Graph Attention Search (DHGAS) method. Our proposed method can automatically discover the optimal DHGNN architecture and adapt to various dynamic heterogeneous graph scenarios without human guidance. In particular, we first propose a unified dynamic heterogeneous graph attention (DHGA) framework, which enables each node to jointly attend its heterogeneous and dynamic neighbors. Based on the framework, we design a localization space to determine where the attention should be applied and a parameterization space to determine how the attention should be parameterized. Lastly, we design a multi-stage differentiable search algorithm to efficiently explore the search space. Extensive experiments on real-world dynamic heterogeneous graph datasets demonstrate that our proposed method significantly outperforms state-of-the-art baselines for tasks including link prediction, node classification and node regression. To the best of our knowledge, DHGAS is the first dynamic heterogeneous graph neural architecture search method.

Background: Preoperative prediction of the origin site of premature ventricular complexes (PVCs) is critical for the success of operations. However, current methods are not efficient or accurate enough. In addition, among the proposed strategies, there are few good prediction methods for electrocardiogram (ECG) images combined with deep learning aspects. Methods: We propose ECGNet, a new neural network for the classification of 12-lead ECG images. In ECGNet, 609 ECG images from 310 patients who had undergone successful surgery in the Division of Cardiology, the First Affiliated Hospital of Soochow University, are utilized to construct the dataset. We adopt dense blocks, special convolution kernels and divergent paths to improve the performance of ECGNet. In addition, a new loss function is designed to address the sample imbalance situation, whose cause is the uneven distribution of cases themselves, which often occurs in the medical field. We also conduct extensive experiments in terms of network prediction accuracy to compare ECGNet with other networks, such as ResNet and DarkNet. Results: Our ECGNet achieves extremely high prediction accuracy (91.74%) and efficiency with very small datasets. Our newly proposed loss function can solve the problem of sample imbalance during the training process. Conclusion: The proposed ECGNet can quickly and accurately realize the multiclassification of PVCs after training with little data. Our network has the potential to be helpful to doctors with a preoperative diagnosis of PVCs. We will continue to collect similar cases and perfect our network structure to further improve the accuracy of our network's prediction.

Premature ventricular complexes (PVCs) are irregularities in heart rhythm where the ventricles contract earlier than expected, disrupting the normal cardiac cycle. Identifying the origin of PVCs before surgery is crucial as it can reduce operation duration, lower radiation exposure, and potentially enhance ablation success rates. Current detection methods face limitations in accuracy and data processing, often requiring large datasets and complex interpretations. This study presents PVCsNet, a deep-learning network specifically designed for classifying premature ventricular complexes (PVCs) in ECG images. It incorporates residual structures and attention mechanisms to enhance classification performance. PVCsNet consists of four 3×3 convolutional layers as feature extractors, followed by residual connections and attention blocks. This design enables the network to map image features to class probability distributions, enhancing performance even with limited data. Our experimental results demonstrate that using the SE Block with MaxPool and a ratio of 4, PVCsNet achieves an overall accuracy of 94.49%, with high precision in critical categories and a moderate parameter size. We successfully categorize the data into six distinct classes based on their origin locations in the heart: right ventricular outflow tract (RVOT), left ventricular outflow tract (LVOT), papillary muscle (PM), valvular annulus (VA), summit, and His-Purkinje system (HPS). Among these, RVOT is the most common and crucial origin of PVCs. PM and HPS are also significant origins due to their clinical implications. This study demonstrates the potential of PVCsNet in clinical diagnostics, providing promising results in classifying ECG images and contributing to future medical research and diagnosis.

Tracking aircraft and parachutes plays a vital role in airdrop experiments. It is necessary to study a parachute’s open state and flight trajectory. More scholars are looking into how to efficiently and accurately obtain parachute deformation data and trajectory data. At present, the actual data collection primarily involves experimenters holding high-definition high-speed cameras to track and shoot parachutes to obtain the image sequences of the parachutes during the airdrop process. However, these methods cannot obtain the trajectories of the parachutes and they are susceptible to interference from human factors. In this paper, we designed TuSeSy, an intelligent turntable servo system that can track the aircraft and parachutes in airdrop tests automatically. Specifically, TuSeSy generates the control commands according to the differences between the actual taken images and the inferred images by tracking algorithms (so as to actually track the target). In addition, we propose an effective multi-target tracking switch algorithm based on the image frame difference and optical flow, to achieve real-time switching from the aircraft to the parachute in an airdrop test. To evaluate the performance of TuSeSy, we conducted extensive experiments; the experimental results show that TuSeSy not only solves the problem of wrong target tracking, but it also reduces computational overhead. Moreover, the multi-target tracking switch algorithm has higher computing efficiency and reliability compared to other tracking switch approaches, ensuring the practical applications of the turntable servo system.

Traditional video object segmentation often has low detection speed and inaccurate results due to the jitter caused by the pan-and-tilt or hand-held devices. Deep neural network (DNN) has been widely adopted to address these problems; however, it relies on a large number of annotated data and high-performance computing units. Therefore, DNN is not suitable for some special scenarios (e.g., no prior knowledge or powerful computing ability). In this paper, we propose RoiSeg, an effective moving object segmentation approach based on Region-of-Interest (ROI), which utilizes unsupervised learning method to achieve automatic segmentation of moving objects. Specifically, we first hypothesize that the central n × n pixels of images act as the ROI to represent the features of the segmented moving object. Second, we pool the ROI to a central point of the foreground to simplify the segmentation problem into a classification problem based on ROI. Third but not the least, we implement a trajectory-based classifier and an online updating mechanism to address the classification problem and the compensation of class imbalance, respectively. We conduct extensive experiments to evaluate the performance of RoiSeg and the experimental results demonstrate that RoiSeg is more accurate and faster compared with other segmentation algorithms. Moreover, RoiSeg not only effectively handles ambient lighting changes, fog, salt and pepper noise, but also has a good ability to deal with camera jitter and windy scenes.

Object detection has attracted great attention in recent years. Many experts and scholars have proposed efficient solutions to address object detection problems and achieve perfect performance. For example, coordinate-based anchor-free (CBAF) module was proposed recently to predict the category and the adjustments to the box of the object by its feature part and its contextual part features, which are based on feature maps divided by spatial coordinates. However, these methods do not work very well for some particular situations (e.g., small object detection, scale variation, deformations, etc.), and the accuracy of object detection still needs to be improved. In this paper, to address these problems, we proposed ODEM-GAN based on CBAF, which utilizes generative adversarial networks to implement the detection of a deformed object. Specifically, ODEM-GAN first generates the object deformation features and then uses these features to enhance the learning ability of CBFA for improving the robustness of the detection. We also conducted extensive experiments to validate the effectiveness of ODEM-GAN in the simulation of a parachute opening process. The experimental results demonstrate that, with the assistance of ODEM-GAN, the AP score of CBAF for parachute detection is 88.4%, thereby the accuracy of detecting the deformed object by CBAF significantly increases.