Sensors (Basel, Switzerland)
Nov 9, 2021
A bilateral neural network adaptive controller is designed for a class of teleoperation systems with constant time delay, external disturbance and internal friction. The stability of the teleoperation force feedback system with constant communication...
Scientific reports
Nov 1, 2021
In this study, we proposed a new data-driven hybrid technique by integrating an ensemble empirical mode decomposition (EEMD), an autoregressive integrated moving average (ARIMA), with a nonlinear autoregressive artificial neural network (NARANN), cal...
Computational intelligence and neuroscience
Oct 31, 2021
In our lives, we cannot avoid the uncertainty. Randomness, rough knowledge, and vagueness lead us to uncertainty. In mathematics, the fuzzy set (FS) theory and logics are used to model uncertain events. This article defines a new concept of complex p...
Journal of computer-aided molecular design
Oct 30, 2021
Predicting the sensory properties of compounds is challenging due to the subjective nature of the experimental measurements. This testing relies on a panel of human participants and is therefore also expensive and time-consuming. We describe the appl...
Computational intelligence and neuroscience
Oct 30, 2021
The main purpose of this manuscript is to present a novel idea on the -rung orthopair fuzzy rough set (-ROFRS) by the hybridized notion of -ROFRSs and rough sets (RSs) and discuss its basic operations. Furthermore, by utilizing the developed concept,...
Neural networks : the official journal of the International Neural Network Society
Oct 28, 2021
Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to out-of-distr...
IEEE transactions on neural networks and learning systems
Oct 27, 2021
Machine learning (ML) methods are popular in several application areas of multimedia signal processing. However, most existing solutions in the said area, including the popular least squares, rely on penalizing predictions that deviate from the targe...
Computational intelligence and neuroscience
Oct 27, 2021
The purpose of this paper is to define the concept of (3, 2)-fuzzy sets and discuss their relationship with other kinds of fuzzy sets. We describe some of the basic set operations on (3, 2)-fuzzy sets. (3, 2)-Fuzzy sets can deal with more uncertain s...
PLoS computational biology
Oct 25, 2021
Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventio...
Neural networks : the official journal of the International Neural Network Society
Oct 23, 2021
The Delta method is a classical procedure for quantifying epistemic uncertainty in statistical models, but its direct application to deep neural networks is prevented by the large number of parameters P. We propose a low cost approximation of the Del...