EEGDnet: Fusing non-local and local self-similarity for EEG signal denoising with transformer.

Electroencephalogram (EEG) has shown a useful approach to produce a brain-computer interface (BCI). One-dimensional (1-D) EEG signal is yet easily disturbed by certain artifacts (a.k.a. noise) due to the high temporal resolution. Thus, it is crucial to remove the noise in received EEG signal. Recently, deep learning-based EEG signal denoising approaches have achieved impressive performance compared with traditional ones. It is well known that the characteristics of self-similarity (including non-local and local ones) of data (e.g., natural images and time-domain signals) are widely leveraged for denoising. However, existing deep learning-based EEG signal denoising methods ignore either the non-local self-similarity (e.g., 1-D convolutional neural network) or local one (e.g., fully connected network and recurrent neural network). To address this issue, we propose a novel 1-D EEG signal denoising network with 2-D transformer, namely EEGDnet. Specifically, we comprehensively take into account the non-local and local self-similarity of EEG signal through the transformer module. By fusing non-local self-similarity in self-attention blocks and local self-similarity in feed forward blocks, the negative impact caused by noises and outliers can be reduced significantly. Extensive experiments show that, compared with other state-of-the-art models, EEGDnet achieves much better performance in terms of both quantitative and qualitative metrics. Specifically, EEGDnet can achieve 18% and 11% improvements in correlation coefficients when removing ocular artifacts and muscle artifacts, respectively.

A Review of Electrically Driven Soft Actuators for Soft Robotics.

In recent years, the field of soft robotics has gained much attention by virtue of its aptness to work in certain environments unsuitable for traditional rigid robotics. Along with the uprising field of soft robotics is the increased attention to soft actuators which provide soft machines the ability to move, manipulate, and deform actively. This article provides a focused review of various high-performance and novel electrically driven soft actuators due to their fast response, controllability, softness, and compactness. Furthermore, this review aims to act as a reference guide for building electrically driven soft machines. The focus of this paper lies on the actuation principle of each type of actuator, comprehensive performance comparison across different actuators, and up-to-date applications of each actuator. The range of actuators includes electro-static soft actuators, electro-thermal soft actuators, and electrically driven soft pumps.

Simulating the effect of individual upper airway anatomical features on drug deposition.

This study aims to systematically isolate different anatomical features of the human pharynx with the goal to investigate their independent influence on airflow dynamics and particle deposition characteristics in a geometrically realistic human airway. Specifically, the effects of the uvula, epiglottis and soft palate on drug particle deposition are studied systematically, by carefully removing each of these anatomical features from reconstructed models based on MRI data and comparing them to a benchmark realistic airway model. Computational Fluid Dynamics using established turbulence models is employed to simulate the transport of mono-dispersed particles (3 µm) in the airway at two flow-rates. The simulations suggest three findings: 1) widening the space between the oral cavity and oropharynx and where the soft palate is situated leads to the most dramatic reduction in drug deposition in the upper airway; 2) exclusion of the uvula and epiglottis: a) affects flow dynamics in the airway; b) alters regional deposition behaviour; c) does not significantly affect the total number of particles deposited in the pharynx; and 3) the space adjacent to the soft palate is a key determinant for aerosol deposition in the extrathoracic region and is related to mechanisms of flow acceleration, diversion and recirculation.