Forecasting Indonesia inflation using long short term memory method

This study aims to predict the Dollar-Rupiah exchange rate based on Indonesia's economic growth using the Long Short-Term Memory (LSTM) method. Exchange rate fluctuations that occurred from 1997 to 2024 have had a significant impact on national economic stability, so a predictive model capable of accurately interpreting historical patterns is needed. Research data was obtained from the Central Bureau of Statistics (BPS), Bank Indonesia (BI), and global economic sources with variables used including the Dollar-Rupiah exchange rate, Gross Domestic Product (GDP), inflation, and interest rates. The research stages include data preprocessing, LSTM architecture development, training, and testing using Google Colab. The results show that the LSTM model is able to produce exchange rate predictions that are close to actual data with a relatively low error rate. Thus, the LSTM method can be used as an effective approach to assisting in the analysis of exchange rate movements and supporting economic policymaking in Indonesia.

Research on sentiment analysis in recent years has increased. However, in sentiment analysis research there are still few ideas about the handling of negation, one of which is in the Indonesian sentence. This results in sentences that contain elements of the word negation have not found the exact polarity.The purpose of this research is to analyze the effect of the negation word in Indonesian. Based on positive, neutral and negative classes, using attention-based Long Short Term Memory and word2vec feature extraction method with continuous bag-of-word (CBOW) architecture. The dataset used is data from Twitter. Model performance is seen in the accuracy value.The use of word2vec with CBOW architecture and the addition of layer attention to the Long Short Term Memory (LSTM) and Bidirectional Long Short Term Memory (BiLSTM) methods obtained an accuracy of 78.16% and for BiLSTM resulted in an accuracy of 79.68%. whereas in the FSW algorithm is 73.50% and FWL 73.79%. It can be concluded that attention based BiLSTM has the highest accuracy, but the addition of layer attention in the Long Short Term Memory method is not too significant for negation handling. because the addition of the attention layer cannot determine the words that you want to pay attention to.

News text is text that contains information about an incident that is submitted in writing or not. In the news text there is a lot of unstructured information and makes it difficult for people to know what entities are contained in the news text. To overcome these problems, information extraction is carried out which is useful for adapting information entities in the form of structured text. In this study, information extraction was carried out using the Long Short-Term Memory (LSTM) method in a news data related to Telkom University. Therefore, in this study, the development of an information extraction system was carried out by focusing on the Person entity using the LSTM method. The test results obtained an F1 Score of 81% with a tuning parameter 256 word embedding size, 32 batch, 150 epochs, 0.1 dropout, 150 units, and 1 layer on LSTM.

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.

Analysis and prediction of fire water pressure in buildings based on IoT data

As an important index of solar activity, the 10.7-cm solar radio flux (F10.7) can indicate changes in the solar EUV radiation, which plays an important role in the relationship between the Sun and the Earth. Therefore, it is valuable to study and forecast F10.7. In this study, the long short-term memory (LSTM) method in machine learning is used to predict the daily value of F10.7. The F10.7 series from 1947 to 2019 are used. Among them, the data during 1947–1995 are adopted as the training dataset, and the data during 1996–2019 (solar cycles 23 and 24) are adopted as the test dataset. The fourfold cross validation method is used to group the training set for multiple validations. We find that the root mean square error (RMSE) of the prediction results is only 6.20~6.35 sfu, and the correlation coefficient (R) is as high as 0.9883~0.9889. The overall prediction accuracy of the LSTM method is equivalent to those of the widely used autoregressive (AR) and backpropagation neural network (BP) models. Especially for 2-day and 3-day forecasts, the LSTM model is slightly better. All this demonstrates the potentiality of the LSTM method in the real-time forecasting of F10.7 in future.

Gender classification by computer is essential for applications in many domains, such as human-computer interaction or biometric system applications. Generally, gender classification by computer can be done by using a face photo, fingerprint, or voice. However, researchers have demonstrated the potential of the electrocardiogram (ECG) as a biometric recognition and gender classification. In facilitating the process of gender classification based on ECG signals, a method is needed, namely Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM). Researchers use these two methods because of the ability of these two methods to deal with sequential problems such as ECG signals. The inputs used in both methods generally use one-dimensional data with a generally large number of signal features. The dataset used in this study has a total of 10,000 features. This research was conducted on changing the input shape to determine its effect on classification performance in the LSTM and Bi-LSTM methods. Each method will be tested with input with 11 different shapes. The best accuracy results obtained are 79.03% with an input shape size of 100×100 in the LSTM method. Moreover, the best accuracy in the Bi-LSTM method with input shapes of 250×40 is 74.19%. The main contribution of this study is to share the impact of various input shape sizes to enhance the performance of gender classification based on ECG signals using LSTM and Bi-LSTM methods. Additionally, this study contributes for selecting an appropriate method between LSTM and Bi-LSTM on ECG signals for gender classification.

Dengue Hemorrhagic Fever (DHF) an infectious disease with fluctuating case numbers that can suddenly increase, posing significant public health challenges. In Pontianak City, 106 cases with 1 death were recorded in 2019, decreasing from 195 cases with 3 deaths in 2018. In 2020, the number dropped further to 27 cases with no fatalities. This condition indicates the need for a prediction system capable of accurately estimating the number of cases to support decision-making processes. This study aims to develop a model for predicting daily DHF cases in Pontianak City using the Long Short-Term Memory (LSTM) method. The data used includes daily DHF cases, average temperature, average humidity, and rainfall from 2020 to 2025. The research stages included data cleaning, normalization using Min-Max Scaling, historical data formation, model training, and evaluation using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The best model employed a single LSTM layer with 64 neurons, 50 epochs, and a batch size of 32, yielding an RMSE of 0.87 and MAE of 0.63. These results indicate that the LSTM method is capable of generating predictions close to actual values and is reliable for estimating daily DHF cases in Pontianak City. The developed Streamlit-based application provides interactive visualization and accurate predictions, making it a valuable tool for health authorities in DHF prevention and control efforts.

The wide proliferation of renewable energy and deregulation of power grid systems require small power utilization systems to deploy intelligent methods of adjustment to the user power demand. Small power utilization systems can benefit from the techniques developed for the smart grid in general. The present paper is devoted to the development of the forecasting model based on the Long Short-Term Memory (LSTM) method. The paper describes the small smart grid architecture and role of the LSTM in this architecture. The LSTM method is implemented with a number of interruptible appliances to predict power demand over 24 hour segments. The experiments demonstrate that the developed algorithm generates a stable pattern of daily power demand; therefore, it has a high predictive power.

Mining activities may trigger hazards such as mountain subsidence. To predict the extent of mountain subsidence and analyze the evolutionary characteristics of mountain subsidence, the optical images and Small Baseline Subset InSAR (SBAS-InSAR) method were used, and the mountain subsidence was circled and interpreted. The cumulative subsidence in the area from 2024 to 2026 was predicted by combining the long short-term memory (LSTM) method, and the mountain surface subsidence slip was derived using MatDEM. The results of the study show that mountain surface subsidence begins with the formation of a primary subsidence zone, which slowly leads to the formation of primary and secondary subsidence zones. Under the influence of the penetrating channel, the primary and secondary subsidence areas merge to form a larger subsidence area. The subsidence area gradually disintegrates into several small areas during the sliding process, and the small areas underneath contribute to the main force of the subsidence movement, with a substantial slip displacement. Based on this study, it is concluded that the accuracy of the results obtained from the LSTM method is higher than that of the numerical simulation results, and the maximum cumulative subsidence is expected to reach 2,180 mm in 2026.

The purpose of this study is to predict the decade rainfall in Semarang City using two main methods, namely Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) and Long Short Term Memory (LSTM). The methodology of this study begins with data pre-processing, which includes data deletion analysis using dropna and data normalization using Min-Max Scaling to reduce scale the to between 0 and 1. The dataset is then divided into 80% training data and 20% test data. The validity of the data (X_test, Y_test) using the best 56-epoch data validation (val_loss) is better than the validity of the training data (loss). On the other hand, SARIMAX uses the (2,1,2), (2,1,2,36) model, and its validation techniques include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). Specifically, the RMSE of the LSTM model is 19.6, and its RMSE of the SARIMAX is 31.05. The MAE of LSTM is 15.0, SARIMAX is 24.5, and the R2 of LSTM is 0.814, and SARIMAX is 0.52. Lower RMSE and MAE values indicate lower prediction errors, but a higher R2 value of 1 indicates that LSTM can explain 81% of the actual data variation, which is better than SARIMAX, which is only about 52%. The main finding of this study is that the LSTM model performs better when recommending rainfall datasets.

Physics-Informed Neural Network for modeling and predicting temperature fluctuations in proton exchange membrane electrolysis

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 & 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 & 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.

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.

Cryptocurrency price prediction is a crucial task for financial investors as it helps determine appropriate investment strategies and mitigate risk. In recent years, deep learning methods have shown promise in predicting time-series data, making them a viable approach for cryptocurrency price prediction. In this study, we compare the effectiveness of two deep learning techniques, the Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM), in predicting the prices of Bitcoin and Ethereum. Results of this research show that the LSTM method outperformed the RNN method, obtaining lower Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) values for predicting both cryptocurrencies. Bitcoin and Ethereum. Specifically, the LSTM model had a RMSE of 0.061 and MAPE of 5.66% for predicting Bitcoin, and a RMSE of 0.036 and MAPE of 4.58% for predicting Ethereum. In this research, we found that the LSTM model is a more effective method for predicting cryptocurrency prices than the RNN model.