lstm  (Nonlinear Dynamics)

Journal: Scientific Reports

Article Title: Enhancing PV power forecasting through feature selection and artificial neural networks: a case study

doi: 10.1038/s41598-025-07038-x

Figure Lengend Snippet: LSTM model.

Article Snippet: The comparison between the best-performing models (Table ), MLP integrated with ReliefF feature selection (ReleifF_MLP), Random Forest, and LSTM integrated with Chi-square feature selection (Chi-square-LSTM), highlights clear trends in forecasting daily PV power production.

Techniques:

Journal: Scientific Reports

Article Title: Enhancing PV power forecasting through feature selection and artificial neural networks: a case study

doi: 10.1038/s41598-025-07038-x

Figure Lengend Snippet: The nMAE in function of the number of selected predictors for the seven different used features selection techniques LSTM_model.

Article Snippet: The comparison between the best-performing models (Table ), MLP integrated with ReliefF feature selection (ReleifF_MLP), Random Forest, and LSTM integrated with Chi-square feature selection (Chi-square-LSTM), highlights clear trends in forecasting daily PV power production.

Techniques: Selection

Journal: Scientific Reports

Article Title: Enhancing PV power forecasting through feature selection and artificial neural networks: a case study

doi: 10.1038/s41598-025-07038-x

Figure Lengend Snippet: Error Distribution MLP against LSTM.

Article Snippet: The comparison between the best-performing models (Table ), MLP integrated with ReliefF feature selection (ReleifF_MLP), Random Forest, and LSTM integrated with Chi-square feature selection (Chi-square-LSTM), highlights clear trends in forecasting daily PV power production.

Techniques:

Journal: Scientific Reports

Article Title: Enhancing PV power forecasting through feature selection and artificial neural networks: a case study

doi: 10.1038/s41598-025-07038-x

Figure Lengend Snippet: Error distribution MLP against LSTM bast feature case.

Article Snippet: The comparison between the best-performing models (Table ), MLP integrated with ReliefF feature selection (ReleifF_MLP), Random Forest, and LSTM integrated with Chi-square feature selection (Chi-square-LSTM), highlights clear trends in forecasting daily PV power production.

Techniques:

Journal: Scientific Reports

Article Title: A merged fuzzy system and neural network for improving management method and strategy in scientific research and education

doi: 10.1038/s41598-025-07564-8

Figure Lengend Snippet: The process and function expression of the LSTM.

Article Snippet: Proposed LSTM with fuzzy system , \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$O(T.\left({N}^{2}+H\right){e}^{\frac{{-\left(x-\mu \right)}^{2}}{2\sigma }})$$\end{document}.

Techniques: Expressing

Journal: Scientific Reports

Article Title: A merged fuzzy system and neural network for improving management method and strategy in scientific research and education

doi: 10.1038/s41598-025-07564-8

Figure Lengend Snippet: The proposed architecture of merged fuzzy systems and LSTM.

Article Snippet: Proposed LSTM with fuzzy system , \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$O(T.\left({N}^{2}+H\right){e}^{\frac{{-\left(x-\mu \right)}^{2}}{2\sigma }})$$\end{document}.

Techniques: