A Bi-GRU-attention neural network to identify motor units from high-density surface electromyographic signals in real time.

To utilize surface electromyographics (sEMG) for control purposes, it is necessary to perform real-time estimation of the neural drive to the muscles, which involves real-time decomposition of the EMG signals. In this paper, we propose a Bidirectional Gate Recurrent Unit (Bi-GRU) network with attention to perform online decomposition of high-density sEMG signals. The model can give different levels of attention to different parts of the sEMG signal according to their importance using the attention mechanism. The output of gradient convolutional kernel compensation (gCKC) algorithm was used as the training label, and simulated and experimental sEMG data were divided into windows with 120 sample points for model training, the sampling rate of sEMG signal is 2048 Hz. We test different attention mechanisms and find out the ones that could bring the highest F1-score of the model. The simulated sEMG signal is synthesized from Fuglevand method (J. Neurophysiol., 1993). For the decomposition of 10 Motor Units (MUs), the network trained on simulated data achieved an average F1-score of 0.974 (range from 0.96 to 0.98), and the network trained on experimental data achieved an average F1-score of 0.876 (range from 0.82 to 0.97). The average decomposition time for each window was 28 ms (range from 25.6 ms to 30.5 ms), which falls within the lower bound of the human electromechanical delay. The experimental results show the feasibility of using Bi-GRU-Attention network for the real-time decomposition of Motor Units. Compared to the gCKC algorithm, which is considered the gold standard in the medical field, this model sacrifices a small amount of accuracy but significantly improves computational speed by eliminating the need for calculating the cross-correlation matrix and performing iterative computations.

Forecasting Carbon Dioxide Price Using a Time-Varying High-Order Moment Hybrid Model of NAGARCHSK and Gated Recurrent Unit Network.

The carbon market is recognized as the most effective means for reducing global carbon dioxide emissions. Effective carbon price forecasting can help the carbon market to solve environmental problems at a lower economic cost. However, the existing studies focus on the carbon premium explanation from the perspective of return and volatility spillover under the framework of the mean-variance low-order moment. Specifically, the time-varying, high-order moment shock of market asymmetry and extreme policies on carbon price have been ignored. The innovation of this paper is constructing a new hybrid model, NAGARCHSK-GRU, that is consistent with the special characteristics of the carbon market. In the proposed model, the NAGARCHSK model is designed to extract the time-varying, high-order moment parameter characteristics of carbon price, and the multilayer GRU model is used to train the obtained time-varying parameter and improve the forecasting accuracy. The results conclude that the NAGARCHSK-GRU model has better accuracy and robustness for forecasting carbon price. Moreover, the long-term forecasting performance has been proved. This conclusion proves the rationality of incorporating the time-varying impact of asymmetric information and extreme factors into the forecasting model, and contributes to a powerful reference for investors to formulate investment strategies and assist a reduction in carbon emissions.

C-RNNCrispr: Prediction of CRISPR/Cas9 sgRNA activity using convolutional and recurrent neural networks.

CRISPR/Cas9 is a hot genomic editing tool, but its success is limited by the widely varying target efficiencies among different single guide RNAs (sgRNAs). In this study, we proposed C-RNNCrispr, a hybrid convolutional neural networks (CNNs) and bidirectional gate recurrent unit network (BGRU) framework, to predict CRISPR/Cas9 sgRNA on-target activity. C-RNNCrispr consists of two branches: sgRNA branch and epigenetic branch. The network receives the encoded binary matrix of sgRNA sequence and four epigenetic features as inputs, and produces a regression score. We introduced a transfer learning approach by using small-size datasets to fine-tune C-RNNCrispr model that were pre-trained from benchmark dataset, leading to substantially improved predictive performance. Experiments on commonly used datasets showed C-RNNCrispr outperforms the state-of-the-art methods in terms of prediction accuracy and generalization. Source codes are available at https://github.com/Peppags/C_RNNCrispr.