Experimental Study on Transfer Learning in Denoising Autoencoders for Speech Enhancement

Coto-Jiménez, Marvin

doi:10.1007/978-3-030-49076-8_29

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [23], despite being the most significant advantage of time series, long-term dependencies remain a considerable challenge. Besides, one of the most common drawbacks of the LSTM model and BI-LSTM model is the high computational cost during training procedures [24], where potential time series forecasting in floods has yet to be unfolded. Despite advances in developing models based on RNN, these models remain challenging to scale to long data sequences.…”

Section: Introductionmentioning

confidence: 99%

Flood Prediction using Deep Learning Models

Ali¹,

Asmai²,

Abidin³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Deep learning has recently appeared as one of the best reliable approaches for forecasting time series. Even though there are numerous data-driven models for flood prediction, most studies focus on prediction using a single flood variable. The creation of various data-driven models may require unfeasible computing resources when estimating multiple flood variables. Furthermore, the trends of several flood variables can only be revealed by analysing long-term historical observations, which conventional data-driven models do not adequately support. This study proposed a time series model with layer normalization and Leaky ReLU activation function in multivariable long-term short memory (LSTM), bidirectional long-term short memory (BI-LSTM) and deep recurrent neural network (DRNN). The proposed models were trained and evaluated by using the sensory historical data of river water level and rainfall in the east coast state of Malaysia. It were then, compared to the other six deep learning models. In terms of prediction accuracy, the experimental results also demonstrated that the deep recurrent neural network model with layer normalization and Leaky ReLU activation function performed better than other models.

show abstract

Section: Introductionmentioning

confidence: 99%