In recent years, the problem of the multistability of neural networks has been studied extensively. From the research results obtained, the number of stable equilibrium points depends only on a power form of the network dimension. However, in practical applications, the number of stable equilibrium points needed is often not expressed in power form.
View Article and Find Full Text PDFBackground: Transthoracic echocardiography (TTE) is recommended as the most important noninvasive screening tool for the diagnosis of pulmonary hypertension (PH), sonographers usually measure the volume of regurgitant flow rather than evaluating the spectral quality, so physicians will determine whether the ultrasound measurements of pulmonary arterial systolic pressure (US-PASP) are reliable based on the volume of tricuspid regurgitation (TR). Therefore, for the first time, we grade the quality of TR spectrum (TRS) based on its integrity and clarity, aiming to assess clinical application value of different tricuspid regurgitant spectrum quality grades (TR-SQG), and investigate whether the accuracy of US-PASP is more trustworthy than TR.
Methods: We retrospectively analyzed 108 patients with chronic thromboembolic PH (CTEPH) to compare the correlation and agreement between US-PASP and right heart catheterization measurements of PASP (RHC-PASP).
IEEE Trans Neural Netw Learn Syst
August 2023
In many practical applications, it is difficult or impossible to obtain the exact solution of the mathematical model due to the limitations of solving methods and the complexity of the neural network itself. A natural problem is given as follows: does the exact solution of quaternion-valued neural networks (QVNNs) exist when successively improved approximate solutions can be obtained? Fortunately, the Hyers-Ulam stability happens to be one of the important means to deal with this problem. In this article, the issue of Hyers-Ulam stability of QVNNs with time-varying delays is addressed.
View Article and Find Full Text PDF