Publication Search

Early detection of a potential heart attack is a crucial step in preventing sudden death from heart disease. This research aims to develop an Internet of Things (IoT)-based health monitoring system capable of measuring vital body data in real time and predicting the likelihood of a heart attack from CSV data obtained from sensors, integrated through RapidMiner as learning data using a machine learning algorithm, the Support Vector Machine (SVM). The system was built using an ESP32 microcontroller connected to a MAX30102 sensor to measure heart rate and finger oxygen levels (SpO₂), as well as a DHT22 sensor to measure temperature and humidity. The resulting data is sent to the Blynk application to display real-time data according to its parameters. The initial prediction logic was developed using a rule-based method based on medical thresholds for four vital parameters. The data was then used to train an SVM model as a classification system to detect potential heart attacks. Test results showed that the system can identify abnormal conditions with a good level of accuracy and provide early warnings based on changes in vital parameters in real time. This system is expected to be an initial solution for personal health monitoring, especially for individuals at risk of heart disease. It can be further developed with cloud integration and automatic notifications to users' devices.

This study examines customer churn prediction in subscription-based telecommunications from a digital marketing perspective using machine learning. The analysis utilizes a secondary dataset of 7,043 customer records that simulate behavioral, contractual, and financial attributes commonly found in telecom services. Three classification algorithms Logistic Regression, Random Forest, and Gradient Boosting are applied to model churn behavior. Data preprocessing includes handling missing values, encoding categorical variables, and splitting data into training and testing sets. Model performance is evaluated using accuracy, recall, and ROC-AUC, with emphasis on recall due to its importance in identifying at-risk customers. The results show that Gradient Boosting achieves the highest overall performance with an ROC-AUC of 0.84, while Logistic Regression provides relatively higher recall. Key drivers of churn include short-term contracts, higher monthly charges, and lower service engagement. However, recall remains moderate, indicating limitations in capturing complex behavioral factors. These findings suggest the need to combine predictive models with behavioral insights and highlight the importance of early customer engagement and long-term retention strategies.

High-dimensional clinical data exhibit complex and non-linear relationships among patient attributes, where outcomes are often influenced by feature interactions rather than isolated variables. However, many existing machine learning models prioritize predictive performance while providing limited interpretability and insufficient insight into interaction structures. This study aims to address this limitation by developing an interpretable and robust framework for feature interaction mining in clinical data. We propose a hybrid tree–neural modeling framework that explicitly captures and ranks feature interactions while maintaining stable predictive performance. Tree-based ensemble models are employed to identify non-linear interaction patterns, while neural representations enhance learning flexibility and generalization. The framework integrates interaction importance analysis, cross-validation–based stability assessment, and evaluation across multiple data splits to ensure robustness and interpretability. Experiments conducted on a real-world high-dimensional clinical dataset demonstrate that the proposed approach achieves consistent predictive performance, with AUC values ranging from 0.628 to 0.641 across five cross-validation folds (mean AUC ≈ 0.633). Performance remains stable under varying train–test splits, indicating strong generalizability. Interaction analysis reveals that a small number of dominant feature interactions—such as age combined with length of hospital stay and medication count combined with diagnostic information—consistently contribute to model predictions, appearing in over 80% of validation folds. Ablation studies further confirm that removing interaction-aware components leads to noticeable performance degradation, highlighting their importance.  In conclusion, this study demonstrates that explicit feature interaction modeling enhances interpretability, stability, and generalization in clinical prediction tasks. The proposed hybrid framework provides a reliable foundation for developing trustworthy and transparent clinical decision-support systems

This research benchmarks multiple machine learning (ML) algorithms for large-scale loan default prediction using a real-world dataset of 255,000 borrower records, where default cases represent only ~9–12% of total observations. The study addresses the persistent gap in comparative analyses of ML models that balance predictive accuracy, interpretability, and computational efficiency for credit risk assessment. Six algorithmic families were evaluated Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost, Artificial Neural Networks (ANN), and Stacked Ensemble—using standardized preprocessing, hybrid imbalance handling (SMOTE, class weighting, under-sampling), and comprehensive evaluation metrics (AUC, F1, Recall, Precision, PR-AUC, and Brier Score). Empirical results show Logistic Regression achieved the highest AUC of 0.732, outperforming nonlinear models under the baseline configuration, while LightGBM attained perfect recall (1.0) but low precision (0.116), indicating over-prediction of defaults. Gradient boosting models demonstrated robust calibration (Brier ≈ 0.114–0.116) and the best computational efficiency, with LightGBM showing the fastest training and lowest memory use. CatBoost exhibited strong recall but the slowest computation, and ANN underperformed on tabular data (AUC ≈ 0.56). The Stacked Ensemble delivered balanced results with AUC = 0.664 and improved overall stability. These findings confirm that boosting-based models, particularly LightGBM and CatBoost, offer superior scalability and calibration, whereas Logistic Regression remains a valuable interpretable baseline. The study concludes that effective default prediction requires integrating rebalancing, calibration, and threshold optimization to enhance recall and operational deployment reliability in large-scale credit ecosystems.

Improper water management in rice cultivation can lead to water stress, which reduces productivity. Conventional monitoring has limitations on large-scale lands, necessitating more efficient remote sensing technologies. This study aims to develop a water stress identification system for rice plants in the late vegetative phase using multispectral drone imagery integrated with an Artificial neural network (ANN). The research method employs an experimental approach with six water availability levels in Karyamukti Village, Sumedang. Field reference data were obtained through soil moisture sensors converted into Available Water (AW) values. Image processing stages included orthomosaic reconstruction, leaf object segmentation, and transformation of vegetation indices (NDVI, NDRE, GNDVI, etc.) as model inputs. The results show that the ANN model with a four-hidden-layer architecture achieved training and validation accuracies of 94–95%. In the independent testing phase, the model produced an accuracy of 94.60% with an F1-Score of 93.33%. Spatial visualization of the prediction results indicates a consistent water condition distribution across rice plots. In conclusion, the integration of multispectral drones and ANN provides an accurate non-destructive solution for spatial monitoring of water availability in rice plants.

This research develops a machine learning model to classify customer loyalty using the Random Forest algorithm. Customer churn is a critical issue that reduces revenue and increases acquisition costs. A dataset of 50,000 customers from global e-commerce and subscription platforms was processed through data cleaning, imputation, outlier handling, and class balancing with SMOTE. The Random Forest model was built as a baseline and optimized with hyperparameter tuning. Evaluation using accuracy, precision, recall, and F1-score shows that the optimized model achieved 90.81% accuracy and 83.87% F1-score, outperforming previous Naïve Bayes approaches. Feature importance analysis highlights customer service interactions, lifetime value, and demographic factors as key predictors of churn. These findings demonstrate Random Forest’s effectiveness in churn prediction and provide practical insights for customer retention strategies

Customer churn is a strategic challenge for digital streaming platforms because it directly Impacts revenue and business sustainability. This study aims to analyze the factors influencing customer Churn and develop a churn prediction model using the Random Forest algorithm. The study uses a Quantitative approach with an explanatory design and utilizes secondary data from the Netflix Customer Churn and Engagement Dataset available on Kaggle. The dataset consists of 1,000 customer data with 16 Variables covering demographic characteristics, service usage behavior, financial condition, and customer Satisfaction level. The data was processed through preprocessing, one-hot encoding, and a 70:30 split Between training and test data. Model performance was evaluated using accuracy, precision, recall, F1 Score, and ROC-AUC metrics. The results show that the Random Forest model produces an accuracy of 53.7%, precision of 56.3%, recall of 63.6%, F1-score of 59.7%, and ROC-AUC of 0.534, indicating Moderate predictive ability and only slightly better than random classification. Feature importanceAn.evealed that user engagement levels, such as viewing duration and frequency of interactions, Were the most dominant factors influencing churn, followed by economic factors and customer satisfaction. The results of this study are expected to provide a basis for streaming platforms to design more effective Customer retention strategies.

This study examines the integration of technology in the process of Human Resource (HR) transformation through the perspective of employee data analytics as a strategic approach to modern HR management. The primary focus of the study is to analyze the impact of the simultaneous integration of digital HR systems and organizational digital transformation on improving the efficiency of HR functions, with organizational agility positioned as a moderating variable that strengthens this relationship. In addition, the study explores the potential optimization of Artificial Intelligence (AI) technologies and predictive analytics methods, such as Bayesian Optimization, in predicting workforce dynamics, including employee attrition risk and competency development needs, while also bridging the analytical skills gap among HR practitioners. The research method employed is a systematic literature review of relevant scientific publications from 2021 to 2025, selecting sources that address digital HR transformation, HR analytics, and the application of AI in organizational contexts. The findings indicate that digital HR systems have a strong and significant effect on enhancing operational efficiency and the quality of HR decision-making, and this effect becomes more optimal when supported by a high level of organizational agility. Furthermore, AI and predictive analytics are proven to generate more accurate predictions and simplify technical complexity, making them easier for HR practitioners to adopt. This study concludes that the success of HR transformation requires a holistic approach that aligns the use of advanced technologies with organizational capabilities, human resource readiness, and ethical considerations to create sustainable organizational value.

Indonesia, as a country with the highest seismicity in the world, requires an accurate earthquake prediction system through the use of the BMKG earthquake catalogue. This research aims to implement ETL-based data pipeline engineering to process 92,887 earthquake catalog entries for the 2008-2023 period into ready-to-use daily time series for the LSTM seismicity forecasting model. The ETL process includes raw data extraction, cleaning of 97% missing values columns on focal mechanism parameters, datetime conversion, daily resampling producing 5,200 entries with earthquake count, total magnitude, and average magnitude features, as well as Min-Max Scaler normalization for LSTM compatibility. The dataset was processed using Google Colab with a stacked LSTM architecture of two layers of 50 and 25 units, dropout 0.2, Adam optimizer, and a sequence window of 30 days to predict the daily earthquake count. The model trained for 100 epochs shows the ability to capture stable seismic activity trends with a consistent decrease in MSE loss, although it shows deviations in extreme spikes due to aftershock sequences. The ETL pipeline proved crucial in ensuring temporal consistency, 100% data completeness, and relevant physics representation, resulting in a reproducible end-to-end framework for disaster mitigation.

Stock price prediction remains a complex challenge due to the dynamic and non-linear nature of financial markets, especially for banking stocks like PT Bank Negara Indonesia (Persero) Tbk (BBNI). This study aims to optimize BBNI stock price forecasting by integrating an automated Extract, Transform, Load (ETL) pipeline with the Long Short-Term Memory (LSTM) algorithm within a data engineering framework. Historical data from 2019 to 2025 were processed through a structured ETL sequence—including data cleaning, feature engineering, and MinMaxScaler normalization—to ensure high data quality. The dataset was partitioned into 80% for model training and 20% for testing to ensure rigorous evaluation. The results demonstrate that the systematic ETL approach significantly enhances model stability and predictive accuracy compared to conventional methods. The LSTM model effectively captured long-term temporal dependencies, providing reliable trend forecasts with an impressive test accuracy, achieving a Root Mean Squared Error (RMSE) of 0.0354. This research underscores that integrating robust data engineering practices with deep learning is essential for building resilient financial decision-support systems.

Rainfall is a crucial factor in the stability of the Earth's ecosystem and has a significant impact on agriculture, forestry, energy, and water management. However, increasingly unstable climate change makes rainfall patterns difficult to predict accurately using traditional methods. The city of Medan, the capital of North Sumatra Province, has a tropical rainforest climate with an average annual rainfall of approximately ±2200 mm and an average temperature of 27°C. Significant weather fluctuations in this area can trigger flooding when rainfall increases and cause water shortages when rainfall decreases (BMKG, 2021). Therefore, a prediction approach that can manage non-linear and dynamic data is needed. Artificial Neural Networks (ANN) are one of the reliable machine learning methods for detecting data patterns. By using the backpropagation algorithm, the model can gradually reduce prediction errors, making it widely used in weather forecasting applications. In this regard, this study uses ANN with the backpropagation method to forecast monthly rainfall in Medan City by utilizing data from 2022–2024 as training and testing data.

This study examines the development of a Crude Palm Oil (CPO) price forecasting model using an artificial neural network algorithm, specifically the backpropagation algorithm. As one of Indonesia’s main export commodities, CPO has a significant economic impact and influences the income of oil palm farmers. The CPO price data used in this study were obtained from CIF Rotterdam, covering the period from January 2019 to December 2023. The research methodology consists of several stages, including data collection, preprocessing, model design, and model implementation using Python programming. The training results of the backpropagation algorithm show an error value of 0.537829578 after 1,000 epochs, while the evaluation using Mean Squared Error (MSE) indicates an MSE of 0.022709 during the training process and 0.017604 during the testing process. The model also produces CPO price predictions for the next three months, namely 932.578 for the first month, 949.568 for the second month, and 774.855 for the third month. These findings indicate that the developed model is capable of predicting future CPO prices with adequate accuracy, which can assist companies in making better financial decisions and managing risks associated with CPO price fluctuations.

The retail industry generates an extremely large and continuously growing volume of transactional data along with the advancement of digital technology, thereby requiring sophisticated and systematic data analysis approaches to support effective and evidence-based business decision-making. This study aims to analyze retail sales data by utilizing the Retail Sales Dataset obtained from the Kaggle platform, which consists of 100,000 transaction records and broadly represents the characteristics of retail transactions. The main focus of this study is to classify product categories and predict customer segments, including the identification of high-spending customers (high spenders), based on demographic attributes such as age and gender, as well as various transaction-related features. The research methodology includes data preprocessing, label encoding, and feature engineering to generate additional variables, including Age_Group, Is_Holiday, and Spender_Group, which are expected to enhance the predictive capability of the models. Several machine learning algorithms, namely Decision Tree, Random Forest, and XGBoost, were implemented and evaluated to compare their respective performance. The experimental results indicate that multiclass product category classification achieves relatively low accuracy, ranging from 27% to 34%. These findings suggest the high complexity of retail data and highlight the need for further model optimization, class balancing techniques, and feature refinement to improve predictive performance in future studies.

The increasing number of Indonesian Migrant Workers (TKW) working abroad, particularly through programs organized by BP2MI, has become a significant concern in managing the labor export process. One of the challenges faced is the uncertainty of the number of TKW to be sent each year, which is influenced by various external and internal factors. Therefore, this study aims to apply artificial neural networks (ANN) with a backpropagation algorithm approach to predict the number of TKW that will be processed by BP2MI. This method was chosen due to its ability to recognize patterns and nonlinear relationships between variables that affect the decision-making process for TKW export. In this study, the data used includes factors such as the number of job seekers, government policies, and the condition of the international labor market. The artificial neural network with the backpropagation algorithm is used to train the model based on existing historical data, with the goal of generating accurate predictions regarding the number of TKW to be processed in the coming years. The results of the tests show that the developed model can provide fairly accurate predictions and can serve as a tool for BP2MI in planning and managing the export of TKW more effectively. With the application of this technology, it is expected that the decision-making process related to TKW export can become more efficient and well-predicted.

The dynamic fluctuations in stock prices present a major challenge for investors in making informed decisions. To anticipate such uncertainties, forecasting methods that can provide accurate predictions are required. This study compares two time series forecasting methods Autoregressive Integrated Moving Average (ARIMA) and Double Exponential Smoothing (Holt) in predicting the stock prices of PT Telkom Indonesia (TLKM). The dataset consists of monthly closing prices from January 2018 to December 2023. The performance of each model is evaluated using three error metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results show that the ARIMA(1,1,1) model yields higher predictive accuracy than the Holt method, with MAE of 787.71, MSE of 771,844.2, and RMSE of 878.55. In contrast, the Holt method records a MAE of 837.19, MSE of 878,393.4, and RMSE of 937.23. These findings confirm that ARIMA is superior in capturing the complex patterns of stock price movements and is more effective in volatile market conditions such as the stock exchange.

This study aims to design, implement, and compare the performance of the Backpropagation algorithm from Artificial Neural Networks and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model in predicting the optimal daily rice requirement at Grillme Restaurant in Pontianak. The main problem faced by the restaurant is the uncertainty in determining the required daily rice stock, which periodically results in either understocking (shortage) or overstocking (wastage), leading to operational losses. To address this, the study utilizes historical daily rice sales data from January 2023 to April 2025 as the database for training and testing both predictive models. The SARIMA approach is employed to capture time series components (trend and seasonality), while Backpropagation is utilized to model non-linear patterns. Comparative test results indicate that the SARIMA model achieved superior accuracy compared to the Backpropagation model. This is confirmed by the Mean Absolute Percentage Error (MAPE) value of the SARIMA algorithm being 17.35%, which is lower than the MAPE value of Backpropagation at 19.62%. The MAPE values obtained by both models demonstrate good predictive capability, but it is concluded that SARIMA is more recommended for a more efficient and planned management of rice stock at Grillme Restaurant in Pontianak.

Cloud-native systems are essential for modern software development, offering enhanced scalability, flexibility, and resilience through cloud computing environments. However, ensuring the reliability and performance of these systems presents a challenge due to their dynamic and distributed nature. Traditional testing methods, such as unit and integration testing, while valuable for detecting individual component defects and interactions, are insufficient for predicting failure rates in complex, cloud-native applications. This study explores the effectiveness of various testing techniques and quality metrics in predicting failure rates within scalable cloud-native systems. A comparative experimental study was conducted using three primary testing techniques: unit testing, integration testing, and chaos testing. The results indicate that chaos testing, when combined with advanced quality metrics such as migration rate and mismigration rate, significantly outperforms traditional methods in predicting failure rates and evaluating system resilience. These findings suggest that chaos testing offers a more comprehensive evaluation, simulating real-world disruptions to test system behavior under stress, which is essential for cloud-native environments where high availability and fault tolerance are critical. The study also highlights the importance of integrating predictive quality metrics, which improve the accuracy of failure predictions and enhance system reliability. The study concludes that for cloud-native systems, a combination of advanced testing techniques and predictive metrics is essential for ensuring high availability, scalability, and reliability in dynamic environments. Future research should focus on refining predictive testing approaches, developing standardized frameworks, and empirically validating new testing methods to address the growing complexity of cloud-native systems.

Concept drift, the phenomenon where the statistical properties of data streams change over time, poses a significant challenge in machine learning, particularly for long term data streams. Traditional machine learning models, including batch learning and non-adaptive approaches, struggle to detect and adapt to these changes, leading to degraded performance and inaccurate predictions. This study proposes an adaptive computational model designed to detect and respond to concept drift using incremental learning techniques and statistical drift detection mechanisms. The model integrates an Adaptive Drift Detector (ADD) and Incremental Learning System, enabling real-time adjustments to data distribution changes. The model is evaluated across synthetic and real-world datasets, demonstrating its superior ability to detect abrupt, gradual, and recurring drifts compared to traditional models. Experimental results indicate that the adaptive model maintains high prediction accuracy, minimizes false positive rates, and reduces detection delays. Furthermore, the model performs well in resource-constrained environments, making it suitable for real-time applications such as healthcare prediction, fault detection, and IoT systems. Despite its promising performance, the study identifies challenges related to computational complexity and the model’s performance with imbalanced datasets and noisy data. Future research should focus on optimizing the model’s scalability, computational efficiency, and adaptability to more complex data types to ensure broader applicability in dynamic environments. This work contributes to advancing the detection and adaptation of concept drift, offering a robust solution for dynamic and evolving data streams.

Explainable Artificial Intelligence (XAI) has become a critical area of research within artificial intelligence, focusing on improving the transparency and interpretability of machine learning (ML) models, often referred to as "black-box" models. The need for XAI techniques arises from the inherent complexity of ML models, which can make their decision-making processes difficult for users to understand. This study investigates various XAI techniques, including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to assess their impact on model interpretability without significantly compromising predictive performance. A comparative experimental design was used, applying these XAI methods to different ML models, including deep neural networks and ensemble methods, within large-scale enterprise data analytics systems. The results indicate that XAI methods significantly enhance model transparency and decision traceability, allowing users to understand the influence of individual features on predictions. While a slight reduction in predictive accuracy was observed, especially with simpler models, the trade-off between interpretability and performance was deemed acceptable, particularly in fields requiring transparency, such as healthcare, finance, and autonomous systems. The use of XAI in enterprise data systems has practical implications for fostering trust and enabling informed decision-making among stakeholders. Furthermore, the study discusses the challenges and limitations of applying XAI techniques, such as complexity, scalability, and model-specific limitations. Future research is suggested to focus on developing more scalable and efficient XAI methods, enhancing their applicability across various model types, and addressing the challenges of real-time applications. This will be crucial in ensuring the widespread adoption of XAI in critical domains, promoting the ethical use of AI while maintaining predictive accuracy.

Detection and identification of plant diseases is critical to the success and efficiency of agricultural production. Plant disease outbreaks are becoming more frequent throughout the world, and the presence of these diseases in cultivated plants has a significant impact on productivity. Therefore, researchers are focusing on developing effective and reliable plant disease detection methods. Thus, farmers can take advantage of early detection of this disease to minimize future losses. This article discusses machine learning approaches as well as decision trees, K-nearest neighbors, naive Bayes, support vector machines (SVM), and random forests for detecting coffee leaf diseases using leaf images. The above-mentioned classifications were researched and compared to determine the most suitable plant disease prediction model with the highest accuracy. Compared with other classification algorithms, the SVM algorithm achieves the highest accuracy of 99.75%. All the models trained above will be used by farmers to quickly identify and classify new diseases in images as a prevention strategy. As a preventive measure, farmers can detect and classify new diseases in images early.