Machine learning model for Bitcoin exchange rate prediction using economic and technology determinants

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.

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.

Accurate real-time bus arrival information is essential for an efficient public transport network, as it significantly impacts passenger experience, system reliability, reduced waiting times, dwell times, and operational efficiency. In Sri Lanka's public transport system, current bus arrival time computations primarily rely on static data, neglecting real-time information and critical factors influencing travel times. This highlights the need to identify the unique variables affecting bus arrival times within the Sri Lankan context and to develop robust prediction models that account for these influences. While traditional methods such as Historical Average Models, Regression, Time Series Analysis, and Kalman Filtering have been used in previous research for short-term travel time predictions, Machine Learning (ML) approaches have proven to deliver superior accuracy. ML models are regarded as the most effective for heterogeneous, lane-less traffic conditions with varying traffic volumes, such as those found in Sri Lanka. ML techniques excel in processing large, high-quality datasets and provide accurate predictions by accounting for all relevant variables influencing travel times. Although research has been conducted on developing various basic ML models for travel time prediction, there is a noticeable gap in studies comparing these models to determine the most suitable one for the Sri Lankan context. A Long- Short Term Memory (LSTM) neural network is a deep learning model that is capable of handling long-term dependencies. In the context of bus travel time prediction, LSTMs can leverage historical traffic and travel data to capture temporal patterns and fluctuations that influence travel times. By evaluating LSTMs against basic machine learning models, this study seeks to explore the advantages of applying deep learning techniques to transportation forecasting, ultimately contributing to more accurate and efficient predictive systems in transit planning. The ML models selected in this study include two basic traditional models K- Nearest Neighbours (KNN) and Support Vector Regression (SVR) and four advanced models that utilize ensemble techniques and advanced optimization as Random Forest Regression (RFR), Ada Boost, XG Boost and Gradient Boosting Machine (GBM). The performance of these models was compared with the LSTM model to identify the gap in their accuracies.

The purpose of the study was to train and compare machine learning (ML) and deep learning (DL) models for long-term forecasting of minimum daily temperatures (frosts) - a key agrometeorological risk affecting crop productivity. The study was based on data from weather stations in St. Petersburg and the Leningrad region. To predict the year ahead, which aligns with the needs of operational agricultural production planning (sowing dates, harvest timing, protective measures), 8 methods were used: ForecasterAutoreg, Random Forest, Support Vector Regression (SVR), XGBoost, Convolutional Neural Network (CNN), SimpleRNN, Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM). The analysis was carried out on two datasets: for the periods 1936-2024 and 1881-1995. The quality of the models was assessed using the metrics MAE, MSE, RMSE, R2 and adjusted R2. The LSTM model showed the most accurate results on the main dataset (1936-2024): MAE 2.9, MSE 14.661, R2 0.789. The SVR method (MAE 3.461, R2 0.775) demonstrated the best metrics based on archived data (1881-1995). It has been established that DL models (LSTM, GRU, CNN) generally outperform classical ML methods based on modern data. The LSTM method is recognized as the most effective for integration into precision farming systems and agricultural monitoring in the region for the advance planning of agrotechnological measures to protect crops from frost, optimization of crop rotation systems, and minimization of crop loss risks.

Rainfall plays a crucial role in agricultural practices, influencing the growth of essential crops and impacting economies reliant on agriculture. In Rajasthan, India, where agriculture is predominantly rainfed and dependent on unpredictable monsoon rains, accurate rainfall forecasting is vital for effective crop management, irrigation, optimizing agricultural productivity, managing water resources, and addressing drought conditions and. This study evaluates various machine learning models for predicting rainfall in East and West Rajasthan. The models assessed include Support Vector Regression (SVR), Random Forest (RF), Artificial Neural Networks (ANN), and K-Nearest Neighbours (KNN). These models were compared based on their accuracy measures, including Root Mean Squared Error (RMSE), Relative Root Squared Error (RRSE), and Relative Absolute Error (RAE). The results indicate that ANN and KNN perform poorly compared to SVR and RF suggesting their inadequacy for rainfall forecasting in water-scarce regions. The performance of SVR and RF are comparable as the difference is less. However SVR is identified as the most effective model for rainfall prediction in both subdivisions, as highlighted in the study. This study suggest that SVR and RF model should be includes in prediction of amount of rainfall.

Accurate rainfall forecasting is crucial in activities such as agricultural planning, water resource management, and flood preparedness, so failure to accurately forecast rainfall might undermine these activities. This study aimed to improve the accuracy of daily rainfall prediction in Hai district, Kilimanjaro region, Tanzania, a region characterised by a bimodal rainfall pattern, by comparing rainfall prediction accuracies of Traditional Machine Learning (TML) and Deep Learning (DL) models. The 25-year daily rainfall dataset for Hai district was first pre-processed by cleaning, normalisation, and splitting into training (first 60%), validation (next 20%), and test (last 20%) sets. TML models (K-Nearest Neighbours (KNN) through its variant KNN Regressor and Support Vector Machine (SVM) through its variant Support Vector Regressor (SVR)) were developed, trained, and their performances compared with developed and trained DL models (Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU)). Each model’s test performance was evaluated using the Root Mean Squared Error (RMSE) metric. The findings revealed that the DL models, LSTM and GRU, achieved test RMSE scores of 6.35 mm and 6.49 mm, respectively, while the TML models, KNN and SVM, achieved test RMSE scores of 6.61 mm and 10.42 mm, respectively. The study demonstrated that DL models are more effective for accurate rainfall forecasting than TML models in regions with complex rainfall patterns. The insights gained will guide the development of more reliable, location-specific weather prediction systems, ultimately supporting informed decision-making in agriculture, environmental management, and flood risk reduction in Tanzania and other regions facing similar climatic challenges

The case of inflation can influence monetary policy. Therefore, in assisting policy decision-making, inflation forecasts can be made. Inflation forecasting is a connecting bridge to determine the value of inflation for the coming period. Running inflation allows it to change from time to time, resulting in a nonlinear model that will provide a more accurate forecast of inflation. The neural network is a general function approach capable of mapping any nonlinear function. One part of the neural network method used in forecasting is the Long Short Term Memory (LSTM) method. This method has the advantage of storing information for a more extended period. However, the efficiency of the neural network method depends on the network structure of the number of hidden neurons and epochs in converging conditions. This study aims to obtain the best inflation forecasting model in Indonesia using the LSTM method. This method is a development network of the Recurrent Neural Network, which is composed of forget gate, input gate, cell state, and output gate. Based on the research results, the best LSTM model in predicting inflation in Indonesia has more than one hidden neuron with the optimum number of epochs. However, too many hidden neurons are used, and the use of epochs that are not optimized will make the root mean square error value and mean absolute error based on the sample out worse. This indicates that too many hidden neurons and epochs will lead to overfitting in Indonesia's inflation forecasting.

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.

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

A CNN-STLSTM-AM model for forecasting USD/RMB exchange rate

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.

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.

Efficient irrigation scheduling is crucial for optimizing crop yields and conserving water resources. In this paper, we present robust models for predicting soil moisture trends in cotton based on the integration of IoT, machine learning (ML), and deep learning (DL) frameworks. We access soil moisture and weather forecast data from IoT field sensors using web APIs, then process and incorporate them into ML and DL models to predict soil moisture trends. Specifically, in DL we used the Long Short-Term Memory (LSTM) with two LSTM architectures (Single Stream LSTM and Dual LSTM), while in ML we used the Gradient Boosting (GB), XGBoost, Random Forest (RF), and AdaBoost methods. Experiment results show that, Single Stream LSTM achieved MSE (0.0710) and (0.9684) R 2 outperforming its Dual counterpart which recorded MSE (0.1200) and (0.9466) R 2 , while under ML, Gradient Boosting (MSE = 0.2822, R² = 0.9909) outperforms other ML models. In general, LSTM methods achieved the lowest error while ML methods recorded the highest R 2 -score. Predictive methods presented in this paper, have shown great potential in estimating soil moisture patterns for optimal irrigation schedules in cotton, thereby enhancing water use efficiency and increasing crops yield.

Due to the rapid adoption of renewable energy sources and the increasing complexity of residential electricity consumption, there is a growing need for intelligent, scalable, and context-aware energy management systems in smart homes. This paper presents an artificial intelligence (AI)-based model that integrates high-resolution household power forecasting with dynamic demand response (DR) simulations to optimize energy consumption, enhance grid stability, and support sustainable energy transitions. Using the publicly available UCI Smart Home Energy dataset, a seven-step framework was implemented, including data preprocessing, exploratory data analysis (EDA), feature engineering, and the development of various predictive models—linear regression (LR), random forest regressor (RFR), support vector regression (SVR), k-nearest neighbors (k-NN), and long short-term memory (LSTM) neural networks. Each model was evaluated under seven DR strategies to capture temporal dependencies and nonlinear load behaviors: Peak Clipping, Valley Filling, Load Shifting, Load Leveling, Time-of-Use (ToU) Optimization, Price-Based Control, and Behavioral DR. Model performance was assessed using the mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination ( R ²). Results revealed that the LSTM model achieved the highest accuracy, with the lowest MAE (18.95 Wh), lowest RMSE (24.83 Wh), and highest R ² (0.94) under the Price-Based DR strategy. Random forest emerged as the most effective traditional model, yielding an MAE of 25.13 Wh and R ² of 0.89, particularly for Behavioral and ToU-based DR strategies. The SVR and k-NN models provided moderate accuracy, while LR performed poorly, underscoring its limitation in modeling nonlinear and dynamic energy patterns. DR simulations indicated that Price-Based, Behavioral, and ToU Optimization strategies achieved the best alignment between household loads and grid requirements while maintaining user flexibility. Visualization tools such as heatmaps, grouped bar plots, and R ² comparisons further confirmed the superior temporal modeling capability of deep learning (DL) methods. Overall, the proposed framework offers a scalable and interpretable AI-driven platform that integrates load forecasting with DR evaluation, demonstrating that DL—particularly LSTM—can substantially enhance forecasting accuracy, enable smarter DR programs, and promote sustainable energy management in smart homes.