Chronic Kidney Disease (CKD) is a menace that is affecting 10% of the world population and 15% of the South African population. The early and cheap diagnosis of this disease with accuracy and reliability will save 20,000 lives in South Africa per year. Scientists are developing smart solutions with Artificial Intelligence (AI). In this paper, several typical and recent AI algorithms are studied in the context of CKD and the extreme gradient boosting (XGBoost) is chosen as our base model for its high performance. Then, the model is optimized and the optimal full model trained on all the features achieves a testing accuracy, sensitivity and specificity of 1.000, 1.000 and 1.000, respectively. Note that, to cover the widest range of people, the time and monetary costs of CKD diagnosis have to be minimized with fewest patient tests. Thus the reduced model using fewer features is desirable while it should still maintain high performance. To this end, the set-theory based rule is presented which combines a few feature selection methods with their collective strengths. The reduced model using about a half of the original full features performs better than the models based on individual feature selection methods and achieves accuracy, sensitivity and specificity of 1.000, 1.000 and 1.000, respectively.

This paper is concerned with the output-feedback tracking control problem for a class of nonlinear systems. The challenge lies in how to drive the tracking error to a prescribed region in a given time globally, under both unknown nonlinear functions and unknown virtual control coefficients. To deal with the unknown control direction, an orientation function is exploited in lieu of the Nussbaum gain technique, the supervisory switching strategy, and the parameter estimation approach. To attain global tracking performance, a tuning function is employed to adjust the tracking error, and a barrier function is used to combat this error. The resulting controller guarantees the prescribed tracking performance and the boundedness of the signals in the closed loop for any initial condition.

Intelligent bearing fault diagnosis based on deep learning is one of the hotspots in mechanical equipment monitoring applications. However, traditional deep learning-based methods have a weak antinoise ability and poor generalization performance in a noisy environment. This article presents a new simple and effective deep attention mechanism network, namely, dual-path mixed-domain residual threshold network (DP-MRTN), which aims to improve the accuracy of the rolling bearing fault diagnosis in a noisy environment. The DP-MRTN combines the channel attention mechanism, spatial attention mechanism, and residual structure. The soft threshold function is used as the nonlinear transformation layer, and the dilated convolution is introduced to establish a dual-path neural network so as to select the important features in the signal without resorting to any signal denoising algorithm. The performance of the DP-MRTN is validated against those state-of-the-art results on the real three-phase asynchronous motor experiment platform in Zhejiang University of Technology. We have achieved 99.97 $\%$ ( $ \pm 0.09\%$ ) accuracy on Gaussian white noise, 99.87 $\%$ ( $ \pm 0.12\%$ ) accuracy on Laplacian noise, and 99.98 $\%$ ( $ \pm 0.02\%$ ) accuracy on real noise. The results show that the proposed method can significantly improve the accuracy of fault diagnosis in a noisy environment compared with the traditional deep learning method.

This paper is devoted to the fuzzy fault-tolerant tracking control of Markov jump systems with unknown mismatched faults. To reconstruct the faults and the system states, a sequence of proportional-integral observers are established via the system outputs. With the help of a structure separation technique, the proportional-integral gains and the observer gains are solved by a unified linear matrix inequality framework. Resorting to the rebuilt faults and states from an iterative estimation algorithm, a backstepping based fuzzy fault-tolerant tracking control scheme against the mismatched faults is established to make the resultant closed-loop system be uniform ultimate boundedness. Simulations are provided to verify the effectiveness of the proposed methods.

The problem of prescribed performance tracking control for unknown time-delay nonlinear systems subject to output constraints is dealt with in this paper. In contrast with related works, only the most fundamental requirements, i.e., boundedness and the local Lipschitz condition, are assumed for the allowable time delays. Moreover, we focus on the case where the reference is unknown beforehand, which renders the standard prescribed performance control designs under output constraints infeasible. To conquer these challenges, a novel robust prescribed performance control approach is put forward in this paper. Herein, a reverse tuning function is skillfully constructed and automatically generates a performance envelop for the tracking error. In addition, a unified performance analysis framework based on proof by contradiction and the barrier function is established to reveal the inherent robustness of the control system against the time delays. It turns out that the system output tracks the reference with a preassigned settling time and good accuracy, without constraint violations. A comparative simulation on a two-stage chemical reactor is carried out to illustrate the above theoretical findings.

This article presents a new asymmetric Lyapunov–Krasovskii functional method on the stability and stabilization of Takagi–Sugeno fuzzy systems with time delay. For the reduction of conservativeness, combining the method with the membership-function-dependent approach, we propose a novel delay-dependent stability condition in the form of linear matrix inequalities. Based on the condition, we further obtain a novel condition of stabilization. At the end, we provide two numerical examples to verify the advantage of the stability and stabilization approaches, respectively.