Publication Search

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.

Distribution transformers play a crucial role in delivering electrical energy from the distribution system to consumers to ensure power quality and supply continuity. However, in practice, overload conditions often occur due to increasing demand and load growth that exceed the transformer’s rated capacity. This situation can lead to reduced efficiency, increased power losses, and accelerated equipment aging. This study aims to analyze the performance of the CMY distribution transformer at PT PLN (Persero) ULP Labuan, which operates beyond its nominal capacity, and to propose an alternative solution through transformer mutation, namely the replacement of the existing unit with a transformer of more appropriate capacity based on load analysis results. The Least Square Method is employed to predict future load growth and determine the projected time when the transformer will again experience overload after the mutation. The results indicate that the existing 100 kVA transformer is overloaded and should be replaced with a 160 kVA unit. After the mutation, the loading percentage decreases significantly, the transformer’s lifespan is extended, and the reliability of the distribution system improves. Furthermore, the Least Square prediction suggests that the new transformer may experience overload again in future years if no further planning is carried out. Therefore, transformer mutation can be considered an effective and medium-term solution to enhance and maintain the reliability of the electrical distribution system within the operational area of PT PLN (Persero) ULP Labuan.

This study aims to evaluate and compare the performance of two neural network architectures under the Recurrent Neural Network (RNN) category, namely Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), in predicting earthquake magnitude in Indonesia. The dataset used consists of daily earthquake magnitude records from 2008 to 2023, preprocessed into time series format and normalized using the MinMax method. The training process was conducted using various combinations of batch size and epoch, and evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and relative prediction accuracy. The evaluation results show that LSTM with a batch size of 32 and 50 epochs provides the best prediction performance, achieving a MAE of 0.2227 and 93.65% accuracy. Meanwhile, GRU performed optimally at a batch size of 64 and 50 epochs, with a MAE of 0.2229 and 93.66% accuracy. The prediction visualization shows that LSTM offers greater stability and precision in tracking actual data patterns. These findings indicate that LSTM holds stronger potential for supporting earthquake prediction systems based on time series data.

Credit scoring is an important element in decision-making for providing financing, especially for microfinance institutions. Several methods for predicting credit scoring include Decession Tree, Gradient Boosted, Neural Network, K-NN, and Rule Induction. This study aims to improve the accuracy of financing risk prediction by efficiently integrating historical data. The Neural Network (NN) algorithm is a machine learning algorithm consisting of neurons (nodes) connected to each other in several layers (input, hidden, and output). NN is used for pattern recognition, classification, regression, and complex non-linear modeling. The NN algorithm has the advantage of working well on large and diverse data and unstructured data. However, the NN algorithm has weaknesses such as overfitting and data dependence. In this study, the integration of the Sample Bootstrapping and Weighted Principal Component Analysis (PCA) methods is proposed to improve optimal accuracy in the NN algorithm. The Sample Bootstrapping method is used to reduce the amount of training data to be processed. The Weighted PCA method is used to reduce attributes. This study uses a financing customer dataset. The results of the study show that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA resulted in an accuracy increase of 1-3% (97%-99%) compared to other algorithms. Therefore, it can be concluded that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA produces better accuracy than other algorithms

Current advances in information technology have encouraged universities to utilize student academic data as a basis for decision-making, one of which is predicting academic achievement. This study aims to apply the C4.5 algorithm to develop a system for predicting student academic success in the Islamic Religious Education Study Program. This method was chosen because it produces a decision tree model that is easy to understand and has a high level of accuracy. The data used comes from student achievement indexes from semesters 1 to 5. The research results showed that the prediction system achieved 99.62% accuracy and achieved high recall precision across each class category. This demonstrates the effectiveness of the C4.5 algorithm in predicting student academic achievement and has the potential to serve as a valuable tool for decision-makers in higher education.

The increasing intensity of business competition requires companies to maintain strong financial conditions to avoid financial distress that may disrupt business continuity. This study aims to assess the financial stability and predict the potential bankruptcy of PT Sido Muncul Tbk for the 2022–2024 period using the Altman Z-Score model. A descriptive quantitative approach was applied, utilizing secondary data obtained from annual reports published by the Indonesia Stock Exchange and the company’s official website. Five key ratios in the Altman model were used as indicators to evaluate the company’s financial position and resilience. The results show Z-Score values of 4.74 in 2022, decreasing slightly to 4.66 in 2023, and rising again to 4.79 in 2024. These scores are significantly above the safe threshold of 2.675, indicating that the company is in a healthy financial state with a very low risk of bankruptcy. Overall, PT Sido Muncul Tbk demonstrates stable financial performance, supported by a strong capital structure and consistent operational results. The Altman Z-Score model also proves to be an effective early-warning tool for identifying potential financial problems.

Background: The development of industrial technology in the Industry 4.0 era has encouraged the implementation of intelligent monitoring systems to improve machine reliability and operational efficiency. However, machine fault diagnosis systems based on artificial intelligence often face limitations in terms of interpretability because the models used are complex and difficult to explain. Objective: This study aims to develop a deep learning-based industrial machine fault diagnosis system integrated with an Explainable Artificial Intelligence (XAI) approach to improve diagnostic accuracy while providing interpretable insights for users. Method: The research method involves collecting data from industrial machine sensors consisting of vibration signals, temperature measurements, and acoustic signals, followed by data preprocessing and feature extraction processes. The processed data are then used to train a deep learning-based diagnostic model, after which explainability methods such as SHAP or LIME are applied to analyze the contribution of each feature to the model’s prediction results. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Results: The results indicate that the proposed deep learning model achieves better performance compared to conventional machine learning methods such as Support Vector Machine and Random Forest. Furthermore, the explainability analysis reveals that vibration amplitude, increases in machine component temperature, and anomalies in acoustic signals are the main factors influencing machine fault detection. Therefore, the proposed system not only improves the accuracy of machine fault diagnosis but also provides transparency in the decision-making process, thereby supporting the implementation of predictive maintenance in smart manufacturing environments.

Unexpected downtime of a 2 kg/hour coffee grinder is crucial in cafe operations, thus less guaranteeing the availability of the grinder. The purpose of component replacement and repair planning is to obtain a prediction of the maintenance and repair schedule and costs in the 2026 period. The component replacement planning method includes collecting previous maintenance and repair data, applying the inspection-replace-repair-overhaul (IRRO) method, assessing component conditions, predicting component life, predicting technician costs, predicting supporting work equipment and supporting materials to be used in maintenance, predicting the time to replace spare parts or reinstall components after repair, estimating maintenance and repair costs for the 2026 period, and calculating the ratio of maintenance costs to profits. The results of component replacement and repair planning obtained maintenance costs for the 2026 period are IDR 2,350,000, - with an estimated coffee grinder rental rate of IDR 25,000/hour which has the potential to be rented for 1440 hours/year, and the ratio of maintenance costs to profits is 6.5% which implies that the coffee grinder with a capacity of 2 kg / hour is still suitable for use for the next few years and still has the opportunity to make a profit.

The rapid development of smartphone technology today creates challenges for consumers and manufacturers in determining an objective price range based on highly varied technical specifications. This study aims to implement the Random Forest algorithm in classifying smartphone price ranges into four main categories, namely low, mid-range, high, and flagship. The research method was carried out systematically through the stages of loading a dataset of 2,000 entries, exploratory data analysis (EDA) to ensure data integrity, and model training with a training and testing data split of 80:20. The results showed that the Random Forest model achieved a significant overall accuracy rate of 89%. Based on feature importance analysis, it was found that RAM capacity was the most dominant determining factor, contributing 47% to prediction accuracy, followed by battery power and screen resolution as supporting features. These findings have strategic implications for manufacturers to prioritize memory capacity upgrades in determining product pricing in the market, as well as providing guidance for consumers in assessing the fairness of a device's price based on its technical capabilities.

The massive adoption of Internet of Things (IoT) devices is expanding the cyberattacks surface, particularly by the Mirai botnet, which exploits the dynamic characteristics of data traffic. This research proposes a Mirai detection approach based on a Recurrent Neural Network (RNN) optimized using Bayesian Optimization to improve prediction accuracy on sequential data. Unlike previous studies, this research utilizes the latest CIC IoT-DIAD 2024 dataset and applies probabilistic optimization to the hyperparameter space, including RNN units, dropout, and learning rate. The experiment was conducted on 201,021 valid data points, with dimensionality reduction using PCA as the optimal point to represent essential features without redundancy. The results show a significant increase in accuracy from 97.95% to 99.69%, accompanied by an 84% decrease in False Negatives, an 86% decrease in False Positives, and an AUC value of 0.9999. These findings confirm that integrating RNN and Bayesian Optimization not only improves numerical performance but also strengthens the reliability of the intrusion detection system for modern IoT ecosystems with controlled computational loads.

This study develops an interpretable machine learning model to predict the settlement status of Hajj fees in Jambi Province, Indonesia. Utilizing the XGBoost algorithm on a dataset of 4,332 prospective pilgrims from 2025, the research addresses the critical challenge of class imbalance where only 28.5% of samples are labeled "Unsettled". The baseline XGBoost model achieved a ROC-AUC of 0.7778, with a recall of 0.3482 for the minority class. SHAP (SHapley Additive exPlanations) analysis was employed to interpret model predictions, revealing that financial features specifically NILAI_VA (Virtual Account Value), JML_SETORAN (Deposit Amount), and JML_PELUNASAN (Settlement Amount) are the most significant factors influencing repayment risk, with negative SHAP values indicating increased default probability. The findings demonstrate that an interpretable XGBoost framework can provide both predictive accuracy and actionable insights for policymakers, enabling targeted interventions such as flexible payment schemes and enhanced financial monitoring for high-risk pilgrims..

Student dropout remains a significant challenge for higher education institutions as it impacts academic quality, educational management efficiency, and students' success in completing their studies. Therefore, an approach that can identify students at risk of dropping out is necessary so that timely academic interventions can be made. This study aims to develop a dropout detection model using an Artificial Neural Network (ANN). The data used come from a publicly available higher education dataset, ensuring research reproducibility. Data preprocessing steps were carried out to improve data quality before modeling, and the Synthetic Minority Over-Sampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) was applied to address class imbalance issues. The ANN model's performance was evaluated using accuracy, precision, recall, F1-score, and area under the ROC curve (ROC-AUC). The test results show that the ANN model can provide excellent predictive performance in detecting at-risk students. The application of SMOTE-ENN also proved to enhance the model’s sensitivity toward the minority class, as indicated by improvements in recall and F1-score. These findings indicate that the developed ANN model has the potential to be used as a student dropout detection system to support data-driven decision-making and strategy development within higher education institutions.

Rapid developments in the era of digital transformation, which refer to the emergence of business and technology innovations based on artificial intelligence, big data, and the Internet of Things (IoT), have great potential for strategic sustainability for businesses in the digital age. Efforts to transform digital business models as a global competitive advantage and provide outputs that can be oriented towards future predictions. Digital business models refer to strategic designs for creating platform networks that are implemented through relationships with consumers and cross-sector collaboration. Challenges and opportunities for development between transformation and innovation are necessary in order to create and capture competitive value and provide added value in the digital economy era. The use of bibliometric analysis in research provides direction in understanding the perspectives and issues that require further research, opens up space for exploring publication trends, and identifies the mapping of key concepts that form the basis of main ideas, thereby providing a more structured understanding and developing new research opportunities, especially in the field of digital business models. Bibliometric analysis aims to gain an in-depth understanding of research using the R studio application as a tool for processing data trends over time and VOSviewer as a knowledge map visualization tool. The research was conducted to provide an understanding of current and future developments in a dynamic environment.

Tebing Tinggi City, which has a strategic position in North Sumatra, is experiencing changes in population growth that need to be predicted for development planning purposes. The purpose of this study is to forecast the population of Tebing Tinggi City in 2030 by applying the Double Integral method, and visualize the results in 3D using GeoGebra. The method used is a quantitative approach with a case study, where the population density function is created based on secondary data from the Central Statistics Agency (BPS) of Tebing Tinggi City for the period 2010 to 2024. Data on area and population per sub-district are used to develop a population growth model calculated using the double integral. The forecast results show that the population of Tebing Tinggi City is estimated to reach 26,038 people in 2030, with varying growth rates in each sub-district. 3D visualization through GeoGebra is able to depict the distribution of population density in an interactive geometric form, thus facilitating the understanding of complex mathematical concepts. The conclusion of this study is that double integrals can be applied effectively to predict population size, and GeoGebra serves as a very useful visual aid in presenting the results of multivariable calculus analysis.

Magnetic resonance imaging (MRI) provides rich anatomical contrast for brain tumor assessment, yet routine interpretation remains time-intensive and demands high precision. This work develops a pipeline for four-class brain MRI image classification (glioma, meningioma, pituitary tumor, and no tumor) by combining automated brain-region cropping, data augmentation, and transfer learning with EfficientNetB1. Experimental results demonstrate exceptional performance, achieving an overall accuracy of 0.99 (99%) on the test set. Specifically, the model reached an F1-score of 1.00 for the no tumor class, 0.99 for pituitary, and 0.98 for both glioma and meningioma classes. Beyond reporting numerical performance, the study utilizes Grad-CAM heatmaps to verify that predictions rely on clinically plausible regions rather than spurious background cues. These results indicate that an efficiency-oriented backbone, paired with systematic preprocessing, can achieve reliable and interpretable performance for brain tumor classification tasks.

AImbalanced data remains a significant issue in heart disease classification using machine learning, as it tends to cause models to overestimate the majority class while ignoring minority classes with high clinical value. This can lead to a decrease in accuracy and the model's ability to accurately detect disease cases. Therefore, this study aims to assess the effectiveness of oversampling techniques, namely Random Oversampling and Synthetic Minority Oversampling Technique (SMOTE), in improving the performance of the K-Nearest Neighbors (KNN), Naive Bayes (NB), and Random Forest (RF) algorithms. The dataset used comes from Kaggle and consists of 918 data sets with 12 attributes representing patient information related to heart disease prediction. The research stages include data preprocessing, baseline model testing, and re-evaluation using the two oversampling methods. Experimental results show that oversampling can improve the performance of all algorithms. KNN achieved the best results with SMOTE, with an accuracy of 72.98% and an F1-score of 75.39%. In the Naive Bayes algorithm, both oversampling techniques produced relatively stable performance, with the highest F1-score of 73.56% using SMOTE. Meanwhile, Random Forest showed the most optimal performance when combined with Random Oversampling, with an accuracy of 79.19% and an F1-score of 81.51%. These findings confirm that the success of data balancing techniques is strongly influenced by the characteristics of the classification algorithm used, and provide a practical contribution in determining strategies for handling imbalanced data in health research.

Diabetes Mellitus is a chronic disease that requires early detection to prevent serious complications. This study aims to implement the Artificial Neural Network (ANN) algorithm with the Backpropagation method to predict the risk of diabetes. The dataset used is the Pima Indians Diabetes Dataset, consisting of 768 medical records with 8 feature attributes. This study employs the Multi-Layer Perceptron method with an architecture of 8 input neurons, two hidden layers, and 1 output neuron. Model evaluation is conducted using a Confusion Matrix to measure accuracy levels. The test results show that the model is capable of predicting diabetes diagnosis with an accuracy rate of 76.62%. Based on these results, it can be concluded that the Backpropagation algorithm is effective as an alternative method for early detection of diabetes, although further development is needed to improve the model's sensitivity to positive cases.  

Hypertension is a major global health risk that requires accurate early detection, yet conventional methods struggle with complex and imbalanced health datasets. This study aims to optimize hypertension prediction using a Logistic Regression model integrated with Borderline-SMOTE to enhance recall and provide model transparency through SHAP (Shapley Additive Explanations). The method utilizes the BRFSS dataset, applying Borderline-SMOTE to address class imbalance at the decision boundary and XAI techniques for global and local interpretation. The findings show that the model achieved an accuracy of 0.719, an AUC of 0.800, and a significantly improved recall of 0.756. SHAP analysis identified age, high cholesterol, and BMI as the most influential risk factors, while waterfall plots successfully clarified individual risk extremes, ranging from 1.72% to 99.43% probability. These results imply that the proposed approach provides a sensitive and transparent screening tool for public health practitioners, effectively balancing statistical efficiency with clinical accountability.