Optimized LSTM Model for Day-Ahead Solar Power Prediction

Many countries around the globe, including Tanzania, are investing in renewable energy, partly because of the need to increase electric power generation and meet the ever-increasing electricity demands, and partly because of the need to combat global climate change caused by carbon emissions from fossil fuel-based electricity production. Kishapu Solar Project, located in Kishapu District, Shinyanga Region, Tanzania, is one of the renewable energy projects with a planned generation of 150 MW of electric power once completed, using solar photovoltaic technology. Accurate forecasting of solar radiation is important in managing and maintaining solar energy plants. Inaccurate forecasting of solar radiation can lead to poor harvest of solar energy and poor management of solar energy plants, which directly impacts electricity contribution to the national electricity grid. Long Short-Term Memory (LSTM) and its variant, PeepHole LSTM, are examples of Deep Learning models that can be used to predict solar radiation. The purpose of PeepHole LSTM is to introduce “peephole” connections in the LSTM model, which allow LSTM gates to directly inspect memory cell state and hence have richer information to process. However, there is still a research gap on the impact of “peephole” connections on the prediction performance of the LSTM model, especially in the context of forecasting solar radiation in Kishapu District, where the Kishapu Solar Project is located. The purpose of this study is to fill this research gap by developing both LSTM and PeepHole LSTM models and comparing their performances in forecasting solar radiation in Kishapu District. The 14-year Kishapu District daily solar radiation (Downward Shortwave Radiation) dataset was first pre-processed by scaling (normalizing) it using Standard Scaler and then split into training set (the first 70%), validation set (the next 15%) and test set (the last 15%) before being utilized to train and test the developed LSTM and PeepHole LSTM models. Both LSTM and PeepHole LSTM models used the previous 5 days' solar radiation values as inputs to predict the output (next day (6th day) solar radiation value). The trained and better-performing model between the two was finally saved in .h5 format and integrated with a Gradio based Web Application to provide a user interface for officials in Kishapu District and at Kishapu Solar Project to predict daily solar radiation. The findings from performance evaluation revealed that the LSTM model outperformed the PeepHole LSTM model in predicting solar radiation by achieving test Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) scores of 26.22 W/m2 and 36.65 W/m2, respectively, compared to MAE and RMSE scores of 30.84 W/m2 and 41.88 W/m2, respectively, achieved by the PeepHole LSTM model, concluding that “peephole” connections reduce the performance of the LSTM model rather than increasing it when used to forecast solar radiation in Kishapu District. This study’s recommendation to Artificial Intelligence (AI) software developers and researchers is to use the LSTM rather than the PeepHole LSTM Deep Learning model when forecasting solar radiation in Kishapu District and in locations with similar climatic conditions

Compressive strength is an important mechanical property of high-strength concrete (HSC), but testing methods are usually uneconomical, time-consuming, and labor-intensive. To this end, in this paper, a long short-term memory (LSTM) model was proposed to predict the HSC compressive strength using 324 data sets with five input independent variables, namely water, cement, fine aggregate, coarse aggregate, and superplasticizer. The prediction results were compared with those of the conventional support vector regression (SVR) model using four metrics, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R2). The results showed that the prediction accuracy and reliability of LSTM were higher with R2 = 0.997, RMSE = 0.508, MAE = 0.08, and MAPE = 0.653 compared to the evaluation metrics R2 = 0.973, RMSE = 1.595, MAE = 0.312, MAPE = 2.469 of the SVR model. The LSTM model is recommended for the pre-estimation of HSC compressive strength under a given mix ratio before the laboratory compression test. Additionally, the Shapley additive explanations (SHAP)-based approach was performed to analyze the relative importance and contribution of the input variables to the output compressive strength.

Dengue hemorrhagic fever (DHF) is one of the most widespread and deadly diseases in several parts of Indonesia. An accurate forecast-based model is required to reduce the incidence rate of this disease. Time-series methods such as autoregressive integrated moving average (ARIMA) models are used in epidemiology as statistical tools to study and forecast DHF and other infectious diseases. The present study attempted to forecast the monthly confirmed DHF cases via a time-series approach. The ARIMA, seasonal ARIMA (SARIMA), and long short-term memory (LSTM) models were compared to select the most accurate forecasting method for the deadly disease. The data were obtained from the Surabaya Health Office covering January 2014 to December 2016. The data were partitioned into the training and testing sets. The best forecasting model was selected based on the lowest values of accuracy metrics such as the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The findings demonstrated that the SARIMA (2,1,1) (1,0,0) model was able to forecast the DHF outbreaks in Surabaya City compared to the ARIMA (2,1,1) and LSTM models. We further forecasted the DHF cases for 12 month horizons starting from January 2017 to December 2017 using the SARIMA (2,1,1) (1,0,0), ARIMA (2,1,1), and LSTM models. The results revealed that the SARIMA (2,1,1) (1,0,0) model outperformed the ARIMA (2,1,1) and LSTM models based on the goodness-of-fit measure. The results showed significant seasonal outbreaks of DHF, particularly from March to September. The highest cases observed in May suggested a significant seasonal correlation between DHF and air temperature. This research is the first attempt to analyze the time-series model for DHF cases in Surabaya City and forecast future outbreaks. The findings could help policymakers and public health specialists develop efficient public health strategies to detect and control the disease, especially in the early phases of outbreaks.

An accurate electrical Short-term Load Forecasting (STLF) is an eminent factor in the power generation, electrical load dispatching and energy planning for the power supply companies, specifically in developing countries. This paper proposes a novel temporal feature selection-based Long Short-term Memory (LSTM) model developed by the combination of standard Artificial Neural Network (ANN) layer and LSTM for electrical short term load forecasting. The LSTM model has excellent capability of predicting the stochastic nature of an hour ahead electrical loads. The standard ANN layer consisting 11 neurons is used as an input to LSTM cells. Such a combination of ANN layer with LSTM was never proposed before. The proposed model accommodates variations in weather as well as temporal inputs like humidity, holidays, and date-time features in the hourly load data of the power supply company situated in Johor, Malaysia. This paper gives the insights of hyper parameter tuning to capture the more generalized electrical load patterns in the dataset without compromising the time complexity of the proposed model. The proposed approach was compared with five existing approaches, namely: ANN, LSTM model 1, LSTM model 2, LSTM model 3 and Convolutional Neural Network-LSTM (CNN-LSTM) using hourly load dataset of Johor. The experimental results demonstrate that the proposed approach outperformed the existing approaches in terms of root mean square error, mean absolute percentage error and Diebold-Mariano statistical inference test within 95% confidence interval.

<span lang="EN-US">Multi-target vehicle detection in urban traffic faces challenges such as poor lighting, small object sizes, and diverse vehicle types, impacting traffic flow prediction accuracy. This study introduces an optimized long short-term memory (LSTM) model using the Komodo Mlipir algorithm (KMA) to enhance prediction accuracy. Traffic video data are processed with YOLO for vehicle classification and object counting. The LSTM model, trained to capture traffic patterns, employs parameters optimized by KMA, including learning rate, neuron count, and epochs. KMA integrates mutation and crossover strategies to enable adaptive selection in global and local searches. The model's performance was evaluated on an urban traffic dataset with uniform configurations for population size and key LSTM parameters, ensuring consistent evaluation. Results showed LSTM-KMA achieved a root mean square error (RMSE) of 14.5319, outperforming LSTM (16.6827), LSTM-improved dung beetle optimization (IDBO) (15.0946), and LSTM-particle swarm optimization (PSO) (15.0368). Its mean absolute error (MAE), at 8.7041, also surpassed LSTM (9.9903), LSTM-IDBO (9.0328), and LSTM-PSO (9.0015). LSTM-KMA effectively tackles multi-target detection challenges, improving prediction accuracy and transportation system efficiency. This reliable solution supports real-time urban traffic management, addressing the demands of dynamic urban environments.</span>

This study demonstrates the application of deep learning approach specifically the deep learning for cyberfraud incidence classification and time series prediction in the South African financial institutions. Secondary data from the South African Banking Risk Information Centre (SABRIC) was employed and the data was trained under the deep learning paradigm using the Long Short-Term Memory (LSTM) model and adaptive moment estimation (ADAM) algorithm for fraud incidence classification and time series prediction of fraud incidences. Overall, there were 94.1% correct classifications as opposed to 5.9% incorrect classifications. Moreover, the accuracy, precision, recall and F1-score of the LSTM classification model were 71.668%, 87.5%, 99.1% and 78.78% respectively. This indicates that the developed LSTM model is suitable for classification purposes. In addition, the model’s performance improves as new datasets are fed in. This is evident as the root mean square error (RMSE) reduced from 253.5116 obtained initially to 150.9 after new data was fed in. This study contributes conceptually, theoretically and empirical to knowledge on cyberfraud mitigation. The results show that the LSTM model can be deployed for fraud classification and time series analysis of fraud incidences. The outcome of this study may promote cyber resilience and sustain the fight against the perpetration of cyber-related fraud in South Africa’s financial institutions. The use of the LSTM model for cyberfraud classification and time series prediction of cyberfraud incidences in the South African financial institutions demonstrated in this study is unique.

Accurate solar power forecasting is essential for effective grid energy management, minimizing reliance on supplementary power and improving the use of renewable energy. This research presents a Long Short-Term Memory (LSTM) model for forecasting short-term solar power production based on previous sun irradiance, temperature, and meteorological data. The approach enhances forecast accuracy by incorporating complex temporal relationships in solar energy patterns, surpassing standard techniques. The LSTM model was trained and verified using real-world datasets, with a Mean Absolute Percentage Error (MAPE) of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{3. 8 \%}$</tex> and a Root Mean Squared Error (RMSE) of 12.4 kW. These findings illustrate its efficacy in reducing forecasting inaccuracies and facilitating reliable grid operations. The integration of LSTM-based projections allows grid operators to enhance resource allocation, minimize energy waste, and make smart operational choices. The research emphasizes the capabilities of deep learning methods in predicting renewable energy and shows their significance in improving grid resilience, advancing sustainability, and enabling the effective incorporation of solar energy into contemporary power systems.

Abstract. The information available on the internet nowadays is diverse and moves very quickly. Information is becoming easier to obtain by the general public with the numerous online media outlets, including news portals that provide up-to-date information insights. Various news portals earn revenue from advertising using pay-per-click methods that encourage article writers to use clickbait techniques to attract visitors. However, the negative effects of clickbait include a decrease in journalism quality and the spread of hoaxes. This problem can be prevented by using text classification to classify clickbait in news titles. One method that can be used for text classification is a neural network. Artificial neural networks use algorithms that can independently adjust input coefficient weights. This makes this algorithm highly effective for modeling non-linear statistical data. The artificial neural network algorithm, especially the Long Short-Term Memory (LSTM), has been widely used in various natural language processing fields with satisfying results, including text classification. To improve the performance of the neural network model, adjustments can be made to the model's hyperparameters. Hyperparameters are parameters that cannot be obtained through data and must be defined before the training process. In this research, the Long Short-Term Memory (LSTM) model was used in clickbait classification in news titles. Sixteen neural network models were trained with different hyperparameter configurations for each model. Hyperparameter tuning was carried out using the random search algorithm. The dataset used was the CLICK-ID dataset published by William &amp; Sari, 2020[1], with a total of 15,000 annotated data. The research results show that the developed LSTM model has a validation accuracy of 0.8030, higher than William &amp; Sari's research, and a validation loss of 0.4876. Using this model, researchers were able to classify clickbait in news titles with fairly good accuracy. Purpose: The study was to develop and evaluate a LSTM model with hyperparameter tuning for clickbait classification on news headlines. The thesis also aims to compare the performance of simple LSTM and bidirectional LSTM for this task. Methods: This study uses CLICK-ID dataset and applies different text preprocessing techniques. The dataset later was used to build and train 16 LSTM models with different hyperparameters and evaluates them using validation accuracy and loss. This study uses random search for hyperparameter tuning. Result: The results of the study show that the best model for clickbait classification on news headlines is a bidirectional LSTM model with one layer, 64 units, 0.2 dropout rate, and 0.001 learning rate. This model achieves a validation accuracy of 0.8030 and a validation loss of 0.4876. The results also show that hyperparameter tuning using random search can improve the performance of the LSTM models by avoiding zero probabilities and finding the optimal values for the hyperparameters. Novelty: This study compares and analyzes the different preprocessing methods on text and the different configurations of the models to find the best model for clickbait classification on news headlines. The study also uses hyperparameter tuning to tune the model into the best model and finding the optimal values for the hyperparameters.

With increasing adoption of residential PV systems, net load forecasting is gradually shifting from forecasting pure load to forecasting pure load with PV generation. This paper explicitly compares two methods of net load forecasting for systems with high behind-the-meter (BTM) PV penetration. The first method is an additive method, in which PV generation and pure load are forecasted separately and combined to produce a net load forecast. First, a disaggregation algorithm is applied to aggregate net load measurements of residential homes to separate the pure load and PV generation. Then, a long short-term memory (LSTM) model is used to forecast pure load and PV separately using the historical disaggregated pure load and PV, respectively, and weather factors. The results are combined to generate a net load forecast. The additive model is compared to a direct net load forecast from an LSTM model. Results show that over the five-month test horizon, the additive method decreases the root mean square error (RMSE), maximum absolute error, and mean absolute error (MAE) of the net load forecast by 6.13%, 3.63%, and 6.06% respectively, compared to the direct method.

Wearable electroencephalography (EEG) devices for seizure detection accuracy and reliability are deep learning (DL) applications in the field of epilepsy diagnosis. In this study, we sought to increase the accuracy of seizure detection using advanced DL algorithms on the Children’s Hospital Boston - Massachusetts Institute of Technology (CHB-MIT) EEG database. First, a fully convolutional network (FCN) was trained and assessed using accuracy and recall/precision metrics, and the early stopping technique was used to avoid overfitting. To assess the performance, the FCN was evaluated in terms of various metrics, including accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC)-area under the curve (AUC). In addition, two-dimensional (2D) convolutional neural networks (CNNs) and long short-term memory (LSTM) models were used to model the database, and their performance was thoroughly measured using different metrics, graphs, and confusion matrices. Using LSTM variants, such as standard LSTM, bidirectional LSTM, stacked LSTM, and LSTM attention mechanisms, hybrid convolutional LSTM (ConvLSTM) models were trained and compared. The comparison was conducted based on the training and validation accuracy and loss, as well as the graphs resulting from the precision–recall curves. Apart from DL approaches, EEG signal analysis using time–frequency techniques, such as wavelet transform and short-time Fourier transform, has also been investigated. These methods assisted in the analysis of the time–frequency features of EEG signals in combination with DL models. This study demonstrates that the performance of wearable EEG devices can be augmented using a combination of DL and seizure signal processing techniques. The FCN achieved an accuracy of 92%, with a recall for seizures of 33%, an F1-score of 0.03, and strong ROC-AUC results. The 2D CNN achieved 96% accuracy, a seizure recall of 70%, an F1-score of 0.12, and an ROC-AUC score of 78%. The baseline LSTM struggled with effectiveness at 53% accuracy with a seizure recall of 18%. In contrast, the LSTM model, which incorporated synthetic minority oversampling technique (SMOTE) balancing, was able to reach improvements of up to 89% accuracy, with a precision of 91%, a recall of 86%, an F1-score of 0.89, and a strong ROC curve performance. Among the models, the LSTM with SMOTE was the best performer, with 89% accuracy, 91% precision, 86% recall, and an F1-score of 0.89. These results provide evidence that applying techniques for data balancing in combination with certain DL network architectures significantly improves the detection of seizures using wearable EEG devices worn on the body. We believe that real-time monitoring and high-performance systems are feasible using optimized DL frameworks. The analysis of the performance of different models allows for the understanding of the possibilities of optimizing the architectures of DL algorithms for the modern diagnosis of epilepsy in real time. The source code used to carry out the experiments is publicly available at CHB-MIT EEG Dataset Python Scripts (https://www.kaggle.com/code/adnankust/adnaneeg1).

Wave runup prediction is necessary for offshore structure designs and early warnings. Data-driven methods based on machine learning have inspired reduced-order solutions for wave–structure interaction problems. This study provides the quantification of deep learning algorithms’ potential for wave runup prediction. Two prominent deep learning models were utilized to predict the wave runups along the fore column of semisubmersible under head seas. The long short-term memory (LSTM) and the temporal convolutional networks (TCNs) were comprehensively compared based on the datasets from a model test carried out in the deep ocean basin. The LSTM and TCN model structures were optimized to compare prediction accuracy and computational complexity reasonably. The results reveal that (1) both developed TCN and LSTM models had a satisfied prediction accuracy of over 90%. Their predictions were extended to 10 s into the future with accuracies over 80% and 45%, respectively. (2) With the noise-extended datasets, the LSTM model was robust to noises, while the TCN model showed better prediction performance on the extreme wave runup events. (3) The incident wave and dominant rotation provided the major information for wave runup prediction. TCN and LSTM models’ prediction accuracies were 91.5% and 89.3% based on the simplified input tensors composed of incident wave and pitch. The comparison showed the great potential of the TCN model to predict the nonlinear wave runup with less time and memory costs. The input tensors’ design and optimization based on physical understanding also play a significant role in the prediction performance.

Electricity is the most substantial energy form that significantly affects the development of modern life, work efficiency, quality of life, production, and competitiveness of the society in the ever-growing global world. In this respect, forecasting accurate electricity energy consumption (EEC) is fairly essential for any country?s energy consumption planning and management regarding its growth. In this study, four time-series methods; long short-term memory (LSTM) neural network, adaptive neuro-fuzzy inference system (ANFIS) with subtractive clustering (SC), ANFIS with fuzzy cmeans (FCM), and ANFIS with grid partition (GP) were implemented for the short-term one-day ahead EEC prediction. Root mean square error (RMSE), correlation coefficient (R), mean absolute error (MAE) and mean absolute percentage error (MAPE) were considered as statistical accuracy criteria. Those forecasted results by the LSTM, ANFIS-FCM, ANFIS-SC and ANFIS-GP models were evaluated by comparing with the actual data using statistical accuracy metrics. According to the testing process, the best MAPE values were obtained to be 4.47%, 3.21%, 2.34%, and 1.91% for the ANFIS-GP, ANFIS-SC, ANFIS-FCM, and LSTM, respectively. Furthermore, the best RMSE values were found as 25.94 GWh, 41.17 GWh, 29.50 GWh, and 80.14 GWh for the LSTM, ANFIS-SC, ANFIS-FCM, and ANFIS-GP models, respectively. As a consequence, the LSTM model generally outperformed all ANFIS models. The results revealed that forecasting of short-term daily EEC time series using the LSTM approach can provide high accuracy results.

Tanzania heavily depends on United States Dollar (USD) foreign currency to import various goods and services into the country. Failure to correctly forecast exchange rates between USD and Tanzanian Shillings (TZS) may pose risks such as inability to import intended goods and services, possibility of losing money in stock exchange markets and other investment businesses in case of unexpected currency appreciation or depreciation as well as poor investment decisions in foreign exchange markets. To address this, this study has developed and comparatively evaluated performances of LSTM (Long Short-Term Memory) and BiLSTM (Bidirectional LSTM) deep learning models for forecasting daily USD to TZS exchange rates. The findings reveal that, BiLSTM model outperforms LSTM in forecasting daily USD to TZS exchange rates, achieving a MAPE (Mean Absolute Percentage Error) score of 0.363 on test set (unseen data) compared to a MAPE score of 1.471 achieved by LSTM model. This study recommends to the prospective Artificial Intelligence (AI) researchers and software developers to use BiLSTM instead of LSTM model to forecast (predict) USD to TZS exchange rates. Also, this study has developed USD to TZS exchange rates dataset which can be used by AI researchers, saving them time and costs involved with creating datasets from scratch. This study has also developed ready to use BiLSTM and LSTM models which can be used by Tanzanian business men and women involved in stock exchange markets, foreign exchange markets and other businesses, to predict daily USD to TZS exchange rates and make appropriate business and investment decisions.

Stock price prediction targets to predict the future development direction of the stock market and the degree of rise and fall of the stock price according to stock market quotations. However, since the stock price has high nonlinear, high noisy, and dynamic characteristics, it is challenging to predict stock prices. This paper predicts stock price prediction with a long-short term memory (LSTM) model according to the above data characteristics. First, because the stock price is distributed in different price ranges, we pre-process the data by normalizing all the data to the range of 0 to 1. Then, we improve the model performance by adjusting the three main parameters, hidden layers, learning rate, and time window. LSTM adds a control part into LSTM to further catch these data to make the best of historical data. We compare the proposed method with Recurrent Neural Network (RNN) on a related dataset with relative root mean square error (RRMSE), mean absolute error (MAE) and mean absolute error percentage (MAPE). The lower the score on all three indicators, the more accurate the prediction. The experimental results show that the scores of LSTM are lower than RNN in three indicators, so its prediction is more accurate than RNN with appropriate parameters. Our analyses illustrate that LSTM can better predict the dynamic non-linear data like a stock price by considering the historical data.

The long short-term memory (LSTM) model is widely used in multiple areas, mainly for speech recognition, natural language processing and activity recognition. In the last few years, we started to see many variants of LSTM for recurrent neural networks since its inception in 1997. However, there weren’t many studies that have addressed the LSTM’s gating mechanism. In this paper, we propose a novel LSTM framework where we modify the architecture of the LSTM unit by adding a new layer that we call the “outlier gate”. The latter controls the flow of information that goes into the LSTM cell. This added signal allows us to avoid both the carry-over effect that the outliers have on the forecasted point and a bias in the estimates of our LSTM model – caused by unusual or non-repetitive events. The proposed architecture led us to an end-to-end trainable model that we applied in this paper to a financial time-series forecasting problem. Our results demonstrate that the new proposed LSTM architecture achieves better performance than the state-of-the-art original LSTM model.