A novel interpretable multilevel wavelet decomposition deep network for actual heartbeat classification

Arrhythmias may lead to sudden cardiac death if not detected and treated in time.A supraventricular premature beat(SPB)and premature ventricular contraction(PVC)are important categories of arrhythmia disease.Recently,deep learning methods have been applied to the PVC/SPB heartbeats detection.However,most researchers have focused on time-domain information of the electrocardiogram and there has been a lack of exploration of the interpretability of the model.In this study,we design an interpretable and accurate PVC/SPB recognition algorithm,called the interpretable multilevel wavelet decomposition deep network(IMWDDN).Wavelet decomposition is introduced into the deep network and the squeeze and excitation(SE)-Residual block is designed for extracting time-domain and frequency-domain features.Additionally,inspired by the idea of residual learning,we construct a novel loss function for the constant updating of the multilevel wavelet decomposition parameters.Finally,the IMWDDN is evaluated on the Third China Physiological Signal Challenge Dataset and the MIT-BIH Arrhythmia database.The comparison results show IMWDDN has better detection performance with 98.51%accuracy and a 93.75%F1-macro on average,and its areas of concern are similar to those of an expert diagnosis to a certain extent.Generally,the IMWDDN has good application value in the clinical screening of PVC/SPB heartbeats.

Research on Key Issues of Consistency Analysis of Vehicle Steering Characteristics

Given the global lack of effective analysis methods for the impact of design parameter tolerance on performance deviation in the vehicle proof-of-concept stage,it is difficult to decompose performance tolerance to design parameter tolerance.This study proposes a set of consistency analysis methods for vehicle steering performance.The process of consistency analysis and control of automotive performance in the conceptual design phase is proposed for the first time.A vehicle dynamics model is constructed,and the multi-objective optimization software Isight is used to optimize the steering performance of the car.Sensitivity analysis is used to optimize the design performance value.The tolerance interval of the performance is obtained by comparing the original car performance value with the optimized value.With the help of layer-by-layer decomposition theory and interval mathematics,automotive performance tolerance has been decomposed into design parameter tolerance.Through simulation and real vehicle experiments,the validity of the consistency analysis and control method presented in this paper are verified.The decomposition from parameter tolerance to performance tolerance can be achieved at the conceptual design stage.

THE ANALYSIS OF THE SEPARATED LAYERS ALGORITHM BY DOMAIN DECOMPOSITION METHOD

From the principle of of the Domain Decomposition Method (DDM), we analyse the 2nd-order linear elliptic partial differential problems and link the Separated-Layers Algorithm (SLA) with DDM. The mathematical properties of SLA and numerical example are presented to obtain satisfactory computation results. For general linear differential ones, also are the structure of SLA and its characteristics discussed.