No abstract

This work proposes a novel adaptive type 2 fuzzy sliding controller (AT2FC) for vibration control of magnetorheological damper-(MRD-) based railway suspensions subjected to uncertainty and disturbance (UAD). The AT2FC is constituted of four main parts. The first one is a sliding mode controller (SMC) for specifying the main damping force supporting the suspension. This controller is designed via Lyapunov stability theory. The second one is an interpolation model based on an interval type 2 fuzzy logic system for determination of optimal parameters of the SMC. The third one is a nonlinear UAD observer to compensate for external disturbances. The fourth one is an inverse MRD model (T2F-I-MRD) for specifying the input current. In the operating process, an adaptively optimal structure deriving from the SMC is created (called the Ad-op-SMC) to adapt to the real status. Working as an actuator, the input current for MRD is then determined by the T2F-I-MRD to generate the required damping force which is estimated by the Ad-op-SMC and the nonlinear observer. It is shown that the obtained survey results reflect the AT2FC's excellent vibration control performance compared with the other controllers.

Feature extraction and emotional classification are significant roles in speech emotion recognition. It is hard to extract and select the optimal features, researchers can not be sure what the features should be. With deep learning approaches, features could be extracted by using hierarchical abstraction layers, but it requires high computational resources and a large number of data. In this article, we choose static, differential, and acceleration coefficients of log Mel-spectrogram as inputs for the deep learning model. To avoid performance degradation, we also add a skip connection with dilated convolution network integration. All representatives are fed into a self-attention mechanism with bidirectional recurrent neural networks to learn long term global features and exploit context for each time step. Finally, we investigate contrastive center loss with softmax loss as loss function to improve the accuracy of emotion recognition. For validating robustness and effectiveness, we tested the proposed method on the Emo-DB and ERC2019 datasets. Experimental results show that the performance of the proposed method is strongly comparable with the existing state-of-the-art methods on the Emo-DB and ERC2019 with 88% and 67%, respectively. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.