Short-term multi-hour ahead country-wide wind power prediction for Germany using gated recurrent unit deep learning

The accuracy of wind power forecasting has a very important influence on the safe and stable operation of power system. However, wind power prediction is very difficult, especially under the environment of massive data. This paper presents a novel multi-step ahead wind power prediction model based on recurrent neural network (RNN) with long short-term memory (LSTM) unit or gated recurrent unit (GRU) to improve the accuracy. Firstly, an overall forecasting framework for wind power with diverse forms of optional hybrid models is proposed. Moreover, an innovative LSTM/GRU-based forecasting model is developed with a wind speed correction process using numerical weather prediction (NWP) data. Through the application of GRU network, the correction process can provide corrected wind speed at the predicted moment as an input of the forecasting model. Finally, the experimental results demonstrate the superiority of the proposed RNN approaches as compared to the ARIMA method and SVM method while the main distinctions between the LSTM and GRU network are also illustrated.

An algorithm for forecasting day-ahead wind power via novel long short-term memory and wind power ramp events

Human action identification has advanced significantly as a result of the development of deep learning algorithms. Convolutional Neural Networks (CNNs) are known for their adeptness at extracting crucial information within video frames, especially shapes and postures. However, understanding movements necessitates not just individual frames as well as the temporal flow of the movement; this is wherein LSTM (long short-term memory) variants of Recurrent Neural Networks (RNNs) come into play. By analyzing frame sequences, LSTMs are particularly effective in gathering temporal connections, recalling prior motions, and overcoming the gap amongst static features as well as dynamic actions. Even with CNNs and LSTMs' remarkable accuracy in human action recognition (HAR), challenges remain.

Abstract. Rainfall time series prediction is essential for monitoring urban hydrological systems, but it is challenging and complex due to the extreme variability of rainfall. A hybrid deep learning model (VMD-RNN) is used in order to improve prediction performance. In this study, variational mode decomposition (VMD) is first applied to decompose the original rainfall time series into several sub-sequences according to the frequency domain, where the number of decomposed sub-sequences is determined by power spectral density (PSD) analysis. To prevent the disclosure of forthcoming data, non-training time series are sequentially appended for generating the decomposed testing samples. Following that, different recurrent neural network (RNN) variant models are used to predict individual sub-sequences, and the final prediction is reconstructed by summing the prediction results of sub-sequences. These RNN variants are long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM) and bidirectional GRU (BiGRU), which are optimal for sequence prediction. In addition to three common evaluation criteria, mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE), the framework of universal multifractals (UMs) is also introduced to assess the performance of predictions, which enables the extreme variability of predicted rainfall time series to be characterized. The study employs two rainfall time series with daily and hourly resolutions, respectively. The results indicate that the hybrid VMD-RNN model provides a reliable one-step-ahead prediction, with better performance in predicting high and low values than the pure LSTM model without decomposition.

Recurrent transform learning

Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU)

Accurate wind power prediction can reduce the negative impact of wind power on power grid and reduce the operation cost of power system. Wind power forecasting is of great significance in spot trading, but the instability of wind power series brings difficulties to forecasting. With the rapid development of deep learning technology, prediction algorithm based on deep learning has been widely used in wind power prediction. The long short-term memory (LSTM) network performs well in a variety of prediction scenarios, but there is still room for improvement. In order to improve the prediction accuracy of LSTM in wind power prediction, this paper adopts a new gating mechanism in LSTM network, which can improve the context information modeling ability of LSTM network. The experimental results based on real data show that the proposed improved LSTM prediction model can improve the prediction accuracy of LSTM prediction model in ultra-short term wind power prediction scenarios.

A multi-modal Parkinson’s disease diagnosis system from EEG signals and online handwritten tasks using grey wolf optimization based deep learning model

With the large-scale wind integration into power grid, the intermittent and stochastic nature of wind power possess a threat to the safety of power grid, and wind power prediction has become one of the most important solutions to the current grid connection problem. However, the prediction error in point prediction of wind power cannot be ignored, so it is necessary to make probability prediction of wind power and improve reliable information to the power grid dispatch department. In this paper, by combing with the wavelet decomposition technology and the long short-term memory (LSTM) network, an ultra short-term probability model is proposed. Firstly, the original time series are smoothed by wavelet decomposition technology, then the LSTM network prediction model of each sub-series sample is developed. The Gaussian distribution function of the prediction error is obtained by using the maximum likelihood estimation method, and finally the probability interval prediction of the future wind power in four hours could be realized. Finally, by using the data collected from a wind farm in northeast china, a numerical example is presented to illustrate the usefulness of the proposed method, which show that combining wavelet decomposition with deep learning method can improve the accuracy of prediction, improve the interval reliability of probability prediction, and enhance the generalization ability of the model.

Speaker identification is the process of automatically determining who is speaking from the known speakers by the model. It is crucial in voice-based authentication, forensic investigations, security and surveillance. In recent studies, the combination of convolutional neural network (CNN) and recurrent neural network (RNN) variants performed better than separate models of both. However, only limited studies are conducted in speaker identification using a combination of CNN and RNN variants. In this study, we proposed speaker identification using hybrid two-dimensional CNN (2DCNN) and bidirectional gated recurrent unit (BiGRU) to improve performance. The proposed model integrates the advantage of 2DCNN and BiGRU layers to improve the performance of the model. 2DCNN layers have the advantage of extracting short-term spatial features from input data and it has a limited number of parameters for computation. BiGRU layers have an advantage in extracting long-term temporal dependency between the features in both directions (i.e. backward and forward) and it is efficient in achieving convergence during training. Spectrograms of the speech were used as input in our proposed model because of the rich acoustic features of the speaker. To compare the performance of the proposed model, additional experiments are conducted using the models 2DCNN, CNN-LSTM, CNN-BiLSTM and CNN-GRU. The experiments were conducted on the VoxCeleb1 audio dataset, which consists of 153,516 utterances collected from the 1251 speakers. The accuracy, precision, recall and f1 score of the proposed model are 98.28%, 99.08%, 98.92% and 98.97% respectively. The proposed model was compared with the existing works to show the effectiveness of the proposed model. The experiment results and the comparison with the existing works show that the proposed model has higher performance than both existing works and other models experimented in this study.

Computational modelling of an optical character recognition system for Yorùbá printed text images

This research deals with the industrial financial forecasting in order to calculate the yearly expenditure of the organization. Forecasting helps in estimation of the future trends and provides a valuable information to make the industrial decisions. With growing economies, the financial world spends billions in terms of expenses. These expenditures are also defined as budgets or operational resources for a functional workplace. These expenses carry a fluctuating property as opposed to a linear or constant growth and this information if extracted can reshape the future in terms of effective spending of finances and will give an insight for the future budgeting reforms. It is a challenge to grasp over the changing trends with an effective accuracy and for this purpose machine learning approaches can be utilized. In this study Long Short-Term Memory (LSTM), which is a variant of Recurrent Neural Network (RNN) from the family of Artificial Neural Networks (ANN), is used for forecasting purposes along with a statistical tool IBM SPSS for comparative analysis. In this study, the experiments are performed on the data set of Pakistan GDP by type of expenditure at current prices - national currency (1970-2016) produced by Economic Statistics Branch of the United Nations Statistics Division (UNSD). Results of this study demonstrate that the proposed model predicted the expenses with better accuracy than that of the classical statistical tools.

The integration of Explainable Artificial intelligence (XAI) into sports training offers transformative capabilities for enhancing athlete performance, injury prevention, and personalized coaching. This paper presents the design and development of an intelligent sports training assistance system that leverages advanced AI technologies such as computer vision, deep learning, and wearable sensor analytics. The system incorporates real-time pose estimation using models like OpenPose and PoseNet, enabling precise motion tracking and automated technique correction across various sports disciplines including running, basketball, and martial arts. A multimodal dataset consisting of over <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{5, 0 0 0}$</tex> annotated video frames and sensor-based motion logs was used to train deep learning models including 3D Convolutional Neural Networks (3D-CNNs) and Long Short-Term Memory (LSTM) networks-a variant of Recurrent Neural Networks (RNNs) for motion classification, fatigue detection, and feedback generation. The system achieved 95.2 % pose estimation accuracy, 93.4 % movement classification accuracy, under 1.8s feedback latency, and a 40 % improvement in training efficiency compared to traditional coaching. The suggested framework is deployed in university training centers, the system demonstrated high reliability and responsiveness, offering real-time guidance, objective performance analytics, and remote coaching support, making it a scalable and intelligent solution for modern sports training and performance enhancement.

Stocks are one of the most popular investment instruments among the public due to their potential for long-term returns through price appreciation and dividend distributions; however, stock price movements are heavily influenced by various factors such as macroeconomic conditions, market sentiment, and corporate actions, making accurate forecasting essential for investors to minimize risk and maximize profit. PT Bank BJB Tbk (ticker code: BJBR), a major bank in Indonesia that operates both conventional and Sharia-based services, has shown high volatility over the past few. Therefore, this research aims to develop a stock price prediction model for BJBR using the Long Short-Term Memory (LSTM) approach, a variant of Recurrent Neural Networks (RNN) well-suited for time series data. Historical closing price data from January 2020 to June 2025 were collected, preprocessed through normalization, dataset division, and transformation into supervised learning format, and then used to train an LSTM model with a two-layer architecture and dropout layers to prevent overfitting. The model was trained using the Adam optimizer and evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). Evaluation results showed that the model achieved a high level of accuracy, with an R² value of 0.9643 on the test data, while visualizations of predicted versus actual prices demonstrated a strong alignment, proving that the LSTM model is effective in capturing temporal patterns in financial time series data and can serve as a valuable tool for data-driven investment decision-making.

To quantitatively evaluate the performance of two types of recurrent neural networks (RNNs), long short-term memory (LSTM) and gated recurrent units (GRU), using Monte Carlo dropout (MCD) to predict pharmacokinetic (PK) parameters from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data. DCE-MRI data for simulation studies were synthesized using the extended Tofts model and a population-averaged arterial input function (AIF). The ranges of PK parameters for training the RNNs were determined from data of patients with brain tumors. The effects of the number of training samples, number of hidden units, dropout rate (DR), and bolus arrival time delay and dispersion in AIF on the accuracy of the PK parameters were investigated, and the uncertainties for different DRs and peak signal-to-noise ratios (PSNRs) were quantified. For comparison, PK parameters were estimated using the nonlinear least-squares method. In the clinical studies, the PK parameter and uncertainty images were generated by applying the trained RNNs to DCE-MRI data. Compared with GRU, the computational cost for training the LSTM was significantly higher. The prediction accuracy of GRU decreased with decreasing numbers of training samples and hidden units, whereas the performance of LSTM remained stable. Despite an increased computational cost, MCD reduced the prediction error at low PSNR and improved the quality of PK parameter images. The simulation results recommended using a DR of 0.25-0.5 at low PSNR and ≤ 0.25 for other PSNRs. The clinical studies recommended using a DR of 0.25 and 0.5 for LSTM and GRU, respectively. MCD is effective in quantifying uncertainty in PK parameter prediction from DCE-MRI data and improves their performance, particularly at low PSNR; however, at the expense of increased computational cost. This study helps deepen our understanding of RNNs with MCD and select suitable hyperparameters for creating an RNN architecture for DCE-MRI studies.