Search

The problem of the predefined-time attitude tracking control for rigid spacecraft subject to internal parameter uncertainty and external disturbance is addressed in this brief. A new criterion is first derived for the tunable predefined-time stability. Then, a new tunable predefined-time controller based on a predefined-time extended state observer is designed for the attitude tracking of rigid spacecraft. Different from the existing predefined-time control methods, the proposed tunable predefined-time controller can guarantee that the settling time of the system is strictly bounded by a given constant, while the actual settling time can be sped up or slowed down by tuning an extra parameter. The stability of the resulting closed-loop system under the designed controller is proven by the Lyapunov stability theory. Some simulation results are provided to verify the advantages of the proposed controller.

Federated learning (FL) is a promising distributed machine learning scheme where multiple clients collaborate by sharing a common learning model while maintaining their private data locally. It can be applied to a lot of applications, e.g., training an automatic driving system by the perception of multiple vehicles. However, some clients may join the training system dynamically, which affects the stability and accuracy of the learning system a IoT. Meanwhile, data heterogeneity in the FL system exacerbates the above problem further due to imbalanced data distribution. To solve the above problems, we propose a novel FL framework named FedREM (Retain-Expansion and Matching), which guides clients training models by two mechanisms. They are 1) a Retain-Expansion mechanism that can let clients perform local training and extract data characteristics automatically during the training and 2) a Matching mechanism that can ensure new clients quickly adapt to the global model based on matching their data characteristics and adjusting the model accordingly. Results of extensive experiments verify that our FedREM outperforms various baselines in terms of model accuracy, communication efficiency, and system robustness.

This article presents a gait monitoring method for the home-based rehabilitation of Parkinson’s disease using a following robot. We use robot-based 2-D light detection and ranging (LiDAR) to collect environmental point clouds. The point clouds of the monitored person’s legs are identified from the static environment by an intersection of union (IOU) matching algorithm and the legs are continuously tracked with the Kalman filter (KF). The spatiotemporal information of gait is subsequently determined by legs segmentation. During this process, the robot follows behind the person along the trajectory just walked by the person, ensuring that both legs are always in the robot’s view. For Parkinson’s abnormal gait during rehabilitation, we propose a quantitative indicator to assess the patient’s recovery status. The experimental results demonstrate that the proposed method can effectively monitor and score the abnormality of Parkinson’s gait. In terms of gait detection, it achieves an F1 detection score of 0.983 and a root mean square error (RMSE) within 0.050 m while significantly extending the monitoring radius to 10 m of the room. This makes the method practical for home rehabilitation applications.

Residual blocks have been widely used in deep learning networks. However, information may be lost in residual blocks due to the relinquishment of information in rectifier linear units (ReLUs). To address this issue, invertible residual networks have been proposed recently but are generally under strict restrictions which limit their applications. In this brief, we investigate the conditions under which a residual block is invertible. A sufficient and necessary condition is presented for the invertibility of residual blocks with one layer of ReLU inside the block. In particular, for widely used residual blocks with convolutions, we show that such residual blocks are invertible under weak conditions if the convolution is implemented with certain zero-padding methods. Inverse algorithms are also proposed, and experiments are conducted to show the effectiveness of the proposed inverse algorithms and prove the correctness of the theoretical results.

The canonical correlation analysis (CCA) has attracted wide attention in fault detection (FD). To improve the detection performance, we propose a new joint sparse constrained CCA (JSCCCA) model that integrates the $\ell _{2,0}$ -norm joint sparse constraints into classical CCA. The key idea is that JSCCCA can fully exploit the joint sparse structure to determine the number of extracted variables. We then develop an efficient alternating minimization algorithm using the improved iterative hard thresholding and manifold constrained gradient descent method. More importantly, we establish the convergence guarantee with detailed analysis. Finally, we provide extensive numerical studies on the simulated dataset, the benchmark Tennessee Eastman process, and a practical cylinder-piston process. In some cases, the computing time is reduced by 600 times, and the FD rate is increased by 12.62% compared with classical CCA. The results suggest that the proposed approach is efficient and fast.