Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press

Mateus, Balduíno César; Mendes, Mateus; Farinha, José Torres; Assis, Rui; Cardoso, António J. Marques

doi:10.3390/en14216958

Cited by 75 publications

(35 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GRU is a simplified version of the LSTM recurrent neural network model [ 18 , 19 ]. GRU uses only one state vector and two gate vectors, reset gate and update gate.…”

Section: Methodsmentioning

confidence: 99%

Bi-directional long short term memory-gated recurrent unit model for Amharic next word prediction

2022

View full text Add to dashboard Cite

The next word prediction is useful for the users and helps them to write more accurately and quickly. Next word prediction is vital for the Amharic Language since different characters can be written by pressing the same consonants along with different vowels, combinations of vowels, and special keys. As a result, we present a Bi-directional Long Short Term-Gated Recurrent Unit (BLST-GRU) network model for the prediction of the next word for the Amharic Language. We evaluate the proposed network model with 63,300 Amharic sentence and produces 78.6% accuracy. In addition, we have compared the proposed model with state-of-the-art models such as LSTM, GRU, and BLSTM. The experimental result shows, that the proposed network model produces a promising result.

show abstract

“…GRU is a simplified version of the LSTM recurrent neural network model [ 18 , 19 ]. GRU uses only one state vector and two gate vectors, reset gate and update gate.…”

Section: Methodsmentioning

confidence: 99%

Bi-directional long short term memory-gated recurrent unit model for Amharic next word prediction

2022

View full text Add to dashboard Cite

show abstract

“…LSTM is more accurate when working with datasets that contain longer sequences, but GRU is faster and uses fewer memory [ 37 ]. Additionally, GRUs address the problem of vanishing gradients that affects conventional recurrent neural networks [ 38 ].…”

Section: Methodsmentioning

confidence: 99%

Light-Weight Deep Learning Techniques with Advanced Processing for Real-Time Hand Gesture Recognition

Abdallah

Samaan

Wadie

et al. 2022

Sensors

View full text Add to dashboard Cite

In the discipline of hand gesture and dynamic sign language recognition, deep learning approaches with high computational complexity and a wide range of parameters have been an extremely remarkable success. However, the implementation of sign language recognition applications for mobile phones with restricted storage and computing capacities is usually greatly constrained by those limited resources. In light of this situation, we suggest lightweight deep neural networks with advanced processing for real-time dynamic sign language recognition (DSLR). This paper presents a DSLR application to minimize the gap between hearing-impaired communities and regular society. The DSLR application was developed using two robust deep learning models, the GRU and the 1D CNN, combined with the MediaPipe framework. In this paper, the authors implement advanced processes to solve most of the DSLR problems, especially in real-time detection, e.g., differences in depth and location. The solution method consists of three main parts. First, the input dataset is preprocessed with our algorithm to standardize the number of frames. Then, the MediaPipe framework extracts hands and poses landmarks (features) to detect and locate them. Finally, the features of the models are passed after processing the unification of the depth and location of the body to recognize the DSL accurately. To accomplish this, the authors built a new American video-based sign dataset and named it DSL-46. DSL-46 contains 46 daily used signs that were presented with all the needed details and properties for recording the new dataset. The results of the experiments show that the presented solution method can recognize dynamic signs extremely fast and accurately, even in real-time detection. The DSLR reaches an accuracy of 98.8%, 99.84%, and 88.40% on the DSL-46, LSA64, and LIBRAS-BSL datasets, respectively.

show abstract

“…Usually, this is because the system doesn't have enough storage bandwidth to support the computational units. Adding more computing units is also simple, but increasing storage bandwidth is more difficult Hence, hardware acceleration is not a good fit for LSTM and its variations [10].…”

Section: Fig 1 Cell State In Lstmmentioning

confidence: 99%

Prediction of Gold ROI Based on LSTM model

Sheng¹

2023

BCPBM

View full text Add to dashboard Cite

The developed financial market system must develop the gold market and play an important role in the financial market. Like other financial markets, the gold market also faces the risk of price fluctuation. Although gold has the monetary attribute, its own value is stable, and it has the hedging function, the price of any commodity always fluctuates around its own value, and the market risk caused by gold price fluctuation is inevitable. At the same time, the gold market trading products are almost homogeneous, which determines that the price of gold in the domestic market and the domestic and foreign markets cannot deviate too much, and the existence of certain price differences between different markets will lead to arbitrage between markets. Therefore, it is necessary to forecast the gold yield. Based on this, this paper uses LSTM model to forecast the price yield of gold. The research results show that the price of gold will still fluctuate in the near future. This research has certain theoretical and practical significance for the application of LSTM model in the financial field.

show abstract

Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press

Cited by 75 publications

References 69 publications

Bi-directional long short term memory-gated recurrent unit model for Amharic next word prediction

Bi-directional long short term memory-gated recurrent unit model for Amharic next word prediction

Light-Weight Deep Learning Techniques with Advanced Processing for Real-Time Hand Gesture Recognition

Prediction of Gold ROI Based on LSTM model

Contact Info

Product

Resources

About