9 January 2020 in IEEE Access
Delineating the crucial waves in electrocardiogram records is a paramount work for the automatic diagnosis system of heart diseases. In this paper, a novel method is described to determine the boundaries and the peaks of P waves, QRS complexes and T waves by utilizing twelve-lead electrocardiogram signals. It avoids the difficulty of setting the thresholds when determining the boundaries of crucial waves and also the trouble of selection of wavelet basis as the wavelet-based method does. The signals are first preprocessed by a bandpass filter. After that, the locations of QRS complexes are identified. And based on the QRS locations, adaptive search windows are set to detect the locations of P waves and T waves. Then, a method called local distance transform decides the wave boundary in each lead. Finally, the final boundary determination rule is applied to obtain reliable boundaries. We justify the performance of our algorithm on LUDB database. When the tolerance window interval is 40ms, the peak accuracies of P wave, QRS complex and T wave are all beyond 98% and their boundary accuracies are all above 96%. Compared with the derivative threshold method and the wavelet-based method where the tolerance window interval is 150ms, the algorithm shows a sensitivity and a positive predictive value of peaks and boundaries greater than or equal to 98.43% and 96.44% for the P wave, 99.89% and 99.86% for the QRS complex and 99.21% and 99.85% for the T wave. For the critera of average error and standard deviation, our method has the performance similar to those methods. In addition, our algorithm can also handle such several situations where the boundary determination of crucial waves is tough as high T wave, high noise and baseline wandering well.
9 June 2015 in International Journal of Machine Learning and Cybernetics
6 April 2021 in IEEE Transactions on Multimedia
Detecting points of interest on 3D shapes is a fundamental research problem in geometry processing. Due to the complicated relationship between points of interest and their geometric features, detecting points of interest on any given 3D shape remains challenging. Due to the lack of training data, previous data-driven methods for detecting 3D points of interest mainly focus on utilizing hand-crafted geometric features to predict the probabilities of each point being a POI, which greatly limits detection performance. In this paper, we propose a novel algorithm for detecting 3D points of interest by using projective neural networks. Our method first projects the labeled training 3D shapes into multiple 2D views and then learns the required features from the 2D views in an end-to-end fashion. The points of interest on test 3D shapes are then automatically detected by applying the learned neural network and our improved density peak clustering. Our method relies neither on hand-crafted feature descriptors nor a large quantity of expensive 3D training data to obtain satisfactory results. Experimental results show significantly superior detection performance of our method over the state-of-the-art methods.
22 August 2022 in IEEE Transactions on Human-Machine Systems
3-D human pose estimation or human tracking has always been the focus of research in the human–computer interaction community. As the calibration step of human pose estimation, subject-specific modeling is crucially important to the subsequent pose estimation process. It not only provides a priori knowledge but also clearly defines the tracking target. This article presents a fully automatic subject modeling framework to reconstruct human pose, shape, as well as the body texture in a challenging optimization scenario. By integrating powerful differentiable rendering into the subject-specific modeling pipeline, the proposed method transforms the texture reconstruction problem into analysis by synthesis minimization and solves it efficiently by a gradient-based method. Furthermore, a novel covariance matrix adaptation annealing algorithm is proposed to attack the high-dimensional multimodal optimization problem in an adaptive manner. The domain knowledge of hierarchical human anatomy is seamlessly injected to the annealing optimization process by using a soft covariance matrix mask. All together contributes to the novel algorithm robust to the temptation of local minima. Experiments on the Human3.6 M dataset and the People-Snapshot dataset demonstrate the competitive results to the state of the art both qualitatively and quantitatively.
26 September 2023 in Health Information Science and Systems