Regression analysis and prediction using LSTM model and machine learning methods

Tan, Fangbi

doi:10.1088/1742-6596/1982/1/012013

Cited by 5 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One, because of reduced computational complexity; and two, we find that adapting Harvey's approach yields similar results to using an adapted version of, for example, the more complex Pfeffermann and Allon [16] approach. The second reason is due to the LSTM's ability to model complex interdependency between covariates [17,18], which negates the need to model the cross-correlation using the preprocessing layer statistical methods.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

Thabang

Zyl

2021

Forecasting

View full text Add to dashboard Cite

Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at forecasting tasks and quantifying the associated uncertainty with those forecasts (prediction intervals). One example is Exponential Smoothing Recurrent Neural Network (ES-RNN), a hybrid between a statistical forecasting model and a recurrent neural network variant. ES-RNN achieves a 9.4% improvement in absolute error in the Makridakis-4 Forecasting Competition. This improvement and similar outperformance from other hybrid models have primarily been demonstrated only on univariate datasets. Difficulties with applying hybrid forecast methods to multivariate data include (i) the high computational cost involved in hyperparameter tuning for models that are not parsimonious, (ii) challenges associated with auto-correlation inherent in the data, as well as (iii) complex dependency (cross-correlation) between the covariates that may be hard to capture. This paper presents Multivariate Exponential Smoothing Long Short Term Memory (MES-LSTM), a generalized multivariate extension to ES-RNN, that overcomes these challenges. MES-LSTM utilizes a vectorized implementation. We test MES-LSTM on several aggregated coronavirus disease of 2019 (COVID-19) morbidity datasets and find our hybrid approach shows consistent, significant improvement over pure statistical and deep learning methods at forecast accuracy and prediction interval construction.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…where the LSTM takes as input a vector of de-trended and de-seasonalized observations of which a scalar element x i is computed using Equation (17). Finally, the multivariate multiplicative case is thus expressed as ŷt,t+1...t+m = LSTM(X t ) lt ŝt,t+1...t+m (18)…”

Section: Preprocessing Layermentioning

confidence: 99%

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

Thabang

Zyl

2021

Forecasting

View full text Add to dashboard Cite

show abstract

“…Long short-term memory (LSTM) is proposed as a model for deep learning to enhance the relevance of training samples. The LSTM method as a predictor has the best accuracy results than other traditional methods [21]. The LSTM model is commonly employed to handle discriminatory and generative issues in nonlinear data processing [21], in the field of time series, such as [22][23][24], and the limited use of LSTM in the field of regression, such as [21,25,26].…”

Section: Introductionmentioning

confidence: 99%

“…The LSTM method as a predictor has the best accuracy results than other traditional methods [21]. The LSTM model is commonly employed to handle discriminatory and generative issues in nonlinear data processing [21], in the field of time series, such as [22][23][24], and the limited use of LSTM in the field of regression, such as [21,25,26]. LSTM networks are efficient and flexible in conserving long-term memory [27].…”

Section: Introductionmentioning

confidence: 99%

An Improving Long Short Term Memory-Grid Search Based Deep Learning Neural Network for Software Effort Estimation

2023

IJIES

View full text Add to dashboard Cite

One of the main reasons that hinders making software effort estimation remains a most of the unresolved problem due to the heterogeneous nature of software data with complex structures. In processing nonlinear data, the long short-term memory (LSTM) model is often used for the purpose of solving discriminative and generative problems. Taking into account the fact that the LSTM network have low computational efficiency, due to the need to set a large number of hyperparameters. However, training deep learning models requires expensive work in terms of specifying hyperparameter configurations in the model. The grid search (GS) optimization method is used to find the best hyperparameter values for deep learning networks, which have many different hyperparameters that affect how well the network architecture works. In this paper, we proposed the grid search method as a quick step toward optimizing the parameters of the LSTM model. An empirical study was conducted using five datasets. From our results, we have seen that the LSTM-grid search model consistently performs better across datasets in mean absolute error (MAE) and root mean squared error (RMSE) compare to existing work on using machine learning approach for software effort estimation. The main advantage of training the LSTM show that the grid search finds hyperparameters which results in faster convergent, the possibility of generalization, and better coefficient of determination in estimating software effort.

show abstract

Prediction of Ladle Furnace Refining Endpoint Temperature Based on Particle Swarm Optimization Algorithm and Long Short-Term Memory Neural Network

Wang,

Liu

et al. 2024

JOM

View full text Add to dashboard Cite

Regression analysis and prediction using LSTM model and machine learning methods

Cited by 5 publications

References 7 publications

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

An Improving Long Short Term Memory-Grid Search Based Deep Learning Neural Network for Software Effort Estimation

Prediction of Ladle Furnace Refining Endpoint Temperature Based on Particle Swarm Optimization Algorithm and Long Short-Term Memory Neural Network

Contact Info

Product

Resources

About