Multi-domain Attention Fusion Network For Language Recognition

Ju, Minghang; Xu, Yanyan; Deng, Ke; Su, Kaile

doi:10.1007/s42979-022-01447-9

Cited by 3 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in figure 1, the GRU model replaces the input gate, forget gate, and output gate in the LSTM with an update gate and a reset gate. The update gate can control how many states are retained at the previous moment, and the reset gate is to determine whether to merge the previous moment and the current moment [23,24]. The detailed process is as follows: Firstly, two gating states are obtained by outputtingh t−1 at the previous time and the input at the current time.…”

Section: Grumentioning

confidence: 99%

Prediction of anaerobic digestion performance by quantum convolutional reconstruction gated recurrent neural network*

Hou,

Che,

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

Methane as a renewable energy source has become a hot topic in recent years. Methane is a bioenergy source produced during the anaerobic digestion of organic waste, and the anaerobic digestion process must be monitored and controlled to produce the required amount of methane in a stable manner. Mathematical modeling is used to simulate digester operation to predict the biogas production from anaerobic digestion, to avoid reactor loading or performance degradation, and to ensure efficient operation of the system. In this paper, a Quantum Convolutional Reconstruction Gated Recurrent Neural Network is proposed. The original data features are extracted by convolutional neural network to reduce the dimensionality and retain the information, the parameterized quantum circuit is integrated in the gating recurrent unit, and the quantum reset gate and quantum update gate are constructed. The information extracted by the Convolution Neural networks is input into the quantum gated recurrent neural network, and the quantum storage unit integrates the information into the hidden layer state, thus processing the hidden layer state information more efficiently. The experimental results show that the prediction accuracy of the A Quantum Convolution Reconstructed Gated Recurrent Neural Network is improved from 81.95% to 88.21%, and the MAE value is reduced from 54.53% to 37.38%.

show abstract

Section: Grumentioning

confidence: 99%