Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control and time series prediction. In this paper, the learning algorithm of radial basis function neural networks is analyzed in a feedback structure. The robustness of the learning algorithm is discussed in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. An intelligent adaptation rule is developed for the learning rate of RBFNN which gives faster convergence via an estimate of error energy while giving guarantee to the l 2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development.
In the present study, the effect of concentration of titanium carbide (TiC) particles on the structural, mechanical, and electrochemical properties of Ni-P composite coatings was investigated. Various amounts of TiC particles (0, 0.5, 1.0, 1.5, and 2.0 g L-1) were co-electrodeposited in the Ni-P matrix under optimized conditions and then characterized by employing various techniques. The structural analysis of prepared coatings indicates uniform, compact, and nodular structured coatings without any noticeable defects. Vickers microhardness and nanoindentation results demonstrate the increase in the hardness with an increasing amount of TiC particles attaining its terminal value (593HV100) at the concentration of 1.5 g L-1. Further increase in the concentration of TiC particles results in a decrease in hardness, which can be ascribed to their accumulation in the Ni-P matrix. The electrochemical results indicate the improvement in corrosion protection efficiency of coatings with an increasing amount of TiC particles reaching to ~ 92% at 2.0 g L-1, which can be ascribed to a reduction in the active area of the Ni-P matrix by the presence of inactive ceramic particles. The favorable structural, mechanical, and corrosion protection characteristics of Ni-P-TiC composite coatings suggest their potential applications in many industrial applications.
Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.