Publication Search

The increasing complexity and scale of modern cybersecurity threats necessitate the development of advanced systems capable of efficiently detecting, analyzing, and mitigating incidents in real time. This paper proposes an automated framework for digital forensics and incident response that leverages big data analytics and real time network traffic profiling. The framework integrates cutting-edge technologies, including Apache Spark for real time data processing and Hadoop for scalable data storage, combined with machine learning models like LSTM and Autoencoders to detect anomalies and threats in network traffic. By automating the process of incident detection and response, this framework significantly reduces the time required to identify threats and improves the accuracy of forensic evidence correlation across heterogeneous network environments. The study highlights the advantages of using machine learning models and big data tools to address the limitations of traditional manual and semi-automated systems, which often struggle to keep pace with large-scale data generation. Testing results demonstrate that the proposed framework can handle large data volumes efficiently, providing real time, actionable insights with significantly reduced response times. Additionally, the framework improves forensic analysis by enabling the correlation of evidence from different devices and protocols, making it more effective than traditional methods in identifying the root cause of security incidents. However, challenges related to data heterogeneity, scalability, and system integration were encountered during testing. The proposed framework holds promise for significantly enhancing the efficiency and effectiveness of cybersecurity operations, with future work focusing on further integration of advanced AI techniques and machine learning models for dynamic and adaptive incident response.

This research aims to develop a multiclass flower image classification system using the Convolutional Neural Network (CNN) algorithm with the EfficientNet architecture. The main problem addressed is the difficulty of manual identification of flower species that share high visual similarity. The research stages include collecting 17,299 flower images across 19 classes, performing data preprocessing such as image resizing, pixel normalization, and augmentation, followed by model training using the EfficientNet transfer learning approach. The model was trained for 10 epochs with an 80:20 training-validation data split. The evaluation results show that the model achieved a validation accuracy of 98.05% with a loss value of 0.0968, and an average precision, recall, and F1-score of 0.98. The trained model was then implemented into a web-based application built using the Next.js framework, enabling users to upload flower images and obtain real-time classification results via the Hugging Face API. The system successfully identified flower species with a confidence level of 99.87%. These findings demonstrate that combining a modern CNN architecture with transfer learning provides efficient and highly accurate flower classification performance, which can be effectively implemented for educational and digital conservation purposes.

Adulteration of rice bran is commonly done by mixing it with materials of similar appearance but lower nutritional value, such as ground rice husk. A key indicator of such adulteration is increased lignin content. Adding phloroglucinol solution to the mixture produces a red color that varies with lignin levels. This study aims to estimate lignin content in rice bran-husk mixtures using artificial intelligence and digital image processing. YCbCr color model images of eleven rice bran-husk compositions, treated with phloroglucinol, were analyzed. The lignin content of each variation was measured in the lab and used to define eleven classes. A Probabilistic Neural Network (PNN) was employed as the classifier, with image histograms of varying bin sizes as input. PNN performance was evaluated using 4-fold cross-validation. Results showed the highest average accuracy of 85.80% with 32 bins and histograms from all three YCbCr channels.     

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.

The rapid proliferation of Internet of Things (IoT) devices across diverse industries has significantly increased the vulnerability of IoT edge networks to sophisticated cyber threats. Traditional intrusion detection systems (IDS), such as signature-based and anomaly-based approaches, are often insufficient in addressing the dynamic and evolving nature of these threats. This study proposes a hybrid intrusion detection system (IDS) framework that combines supervised machine learning (ML) techniques with deep reinforcement learning (DRL) to enhance detection performance in real-time, resource-constrained IoT environments. The proposed framework utilizes supervised learning for initial traffic classification and DRL for adaptive decision-making, enabling the system to continuously learn and optimize its detection policies based on new attack patterns. The hybrid approach significantly improves detection accuracy and reduces false positives when compared to conventional signature-based and single-model ML systems. In addition to improved detection capabilities, the framework's computational efficiency allows it to operate effectively within the constraints of IoT devices, ensuring that it is suitable for large-scale deployments. Benchmark evaluations using publicly available datasets, such as NSL-KDD, IoT-23, and BoT-IoT, show that the hybrid IDS framework outperforms traditional methods, providing a more robust and adaptive solution to cybersecurity challenges in IoT edge networks. The findings of this study suggest that combining machine learning with deep reinforcement learning offers a promising approach to secure IoT environments and address the limitations of existing IDS techniques. Future work will explore enhancing real-time adaptability, scalability, and the detection of zero-day attacks in evolving IoT ecosystems.

This study aims to develop an effective predictive model for identifying students at risk of academic dropout using the Decision Tree and Linear Regression algorithms. The data used are sourced from the public Kaggle dataset Students Dropout and Academic Success, which includes demographic, socioeconomic, and academic performance variables for each semester. The research method includes data preprocessing stages, such as data cleaning, label encoding for categorical variables, numeric feature normalization, and target class adjustment to focus on binary classification, namely Dropout and Graduate. The modeling process is carried out by comparing the performance of the two algorithms using evaluation metrics of accuracy, precision, and recall. The results show that the Decision Tree algorithm has superior performance compared to Linear Regression in mapping non-linear patterns in student data. Feature importance analysis revealed that the number of curricular units in the second semester and tuition payment status are the main predictors of dropout risk. These findings are expected to assist educational institutions in implementing early interventions to improve student academic success.  

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.

This study aims to design a web-based information system for vehicle management and monitoring at Bengkel Merdeka Motor, which previously relied on manual recording processes. Manual data management caused several problems, including data loss, inaccurate records, difficulties in monitoring service progress, and delays in report generation. This research applies the Object-Oriented Analysis and Design (OOAD) method supported by Unified Modeling Language (UML) to analyze system requirements and design the proposed system. The research methodology includes requirements analysis, analysis of existing and proposed systems, system design, and user interface design. The proposed system integrates vehicle data management, service offers, work orders (SPK), service progress monitoring, invoice generation, and automatic monthly reporting into a single web-based platform. The results show that the designed system improves data accuracy, operational efficiency, and transparency of service information. In addition, real-time monitoring features support better coordination between administrators and mechanics. The implementation of this system is expected to enhance service quality, reduce administrative errors, and support managerial decision-making at Bengkel Merdeka Motor.

Non-Cash Food Assistance (BPNT) is a government assistance program aimed at poor or underprivileged communities, distributed monthly through electronic accounts and used specifically to purchase basic necessities at designated E-Warong stores. However, in reality, the implementation of the BPNT program in the field still faces comprehensive challenges, such as issues related to targeting inaccuracy and the quality of food obtained by KPM not always meeting standards. The purpose of this study is to explore the evaluation of the Non-Cash Food Assistance (BPNT) program policy through a Systematic Literature Review (SLR) approach, so that researchers can trace various empirical findings regarding the implementation of the Non-Cash Food Assistance program policy in several regions. The policy evaluation model used is William N Dunn's model, which includes six indicators, namely effectiveness, efficiency, adequacy, equity, responsiveness, and accuracy. The results of this study are expected to provide a comprehensive and in-depth picture of the phenomenon being studied in an objective and systematic manner, and can be used as a reference for government agencies in evaluating and optimizing the implementation of the BPNT program policy so that it becomes a more effective and sustainable social assistance program.

The performance of the Indonesian National Team (Timnas) in the 2026 World Cup qualifications has triggered massive and diverse responses on social media, particularly on platform X. This study aims to identify and classify public sentiment regarding Timnas Indonesia's performance into positive, negative, and neutral categories using a data mining approach. Text data was processed through pre-processing stages, term weighting using TF-IDF, and the application of the Synthetic Minority Over-sampling Technique (SMOTE) to address significant class distribution imbalance. The classification algorithm employed was Multinomial Naïve Bayes. Model performance evaluation was conducted by comparing two training-testing data split scenarios: 90:10 and 80:20 ratios. The results indicate that public opinion is dominated by negative sentiment at 73.2%, reflecting public disappointment. In terms of model performance, the 90:10 ratio scenario yielded the best accuracy of 80%, outperforming the 80:20 ratio which recorded an accuracy of 75%. These findings demonstrate that combining Multinomial Naïve Bayes with the SMOTE technique is effective in handling imbalanced text data and is capable of accurately mapping public perception.

The Lamongan Regency Communication and Informatics Office plays a strategic role in supporting regional government decision-making through the implementation of the Megilan Innovation and Technology Program. The role of the Lamongan Regency Communication and Informatics Office in this program is realized as the main manager of digital information and archive systems that serve as the basis for providing data and information for regional leaders. Through the Megilan Innovation and Technology Program, the Communication and Informatics Office is responsible for everything from formulating archive digitization policies, implementing technology-based incoming mail management techniques, to providing fast, accurate, and integrated information to support the decision-making process. This study uses a descriptive qualitative method with interview and observation techniques carried out in the context of internship activities at the Lamongan Regency Communication and Informatics Office. Data analysis was carried out using the Miles and Huberman model which includes data collection, data condensation, data presentation, and drawing conclusions. The results of the study indicate that archive digitization through the Megilan Innovation and Technology Program can accelerate information access, improve the accuracy of letter disposition, and strengthen transparency and accountability of regional government. However, obstacles are still found in the form of limited human resources, technological infrastructure, and synchronization of physical and digital archives. Therefore, strengthening organizational capacity and supporting policies is necessary to ensure the Communication and Informatics Agency's role in decision-making can be optimal and sustainable

This study aims to develop a predictive model using linear regression to identify potential arrhythmias in the elderly based on electrocardiogram (ECG) data. Data were collected through observations at healthcare facilities from elderly patients with indications of arrhythmia, then preprocessed such as cleaning, normalization, feature selection, and outlier checking were carried out. The features used include PR interval, QRS duration, QT interval, and heart rate. The dataset was divided into training data (80%) and test data (20%) to build and evaluate the model. The training results showed that the model was able to predict the risk of arrhythmia with a Mean Squared Error (MSE) value of 0.15 and a coefficient of determination (R²) close to 1. Evaluation using a confusion matrix showed an accuracy of 76.19%, precision of 82.80%, recall of 76.19%, and F1 score of 72.70%. These results prove that linear regression can be used as an initial approach in the early detection of arrhythmias non-invasively in the elderly. This study provides a foundation for the development of ECG data-based clinical decision support systems and suggests future exploration of more complex models and integration with real-time monitoring technologies.

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.

Behind the success of the Free Nutritious Meal Program (MBG), there are several problems related to the health factors of the program targets, namely, there are several cases of allergies that occur in schools, inadequate understanding of allergen management owned by food processing vendors, and the high cost of laboratory tests and the process that takes a long time. So, to overcome these problems, an application is proposed that can help detect allergens in food products using data mining and machine learning approaches. SVM and AdaBoost algorithms each have advantages that can be used to help build an optimal allergen detection model. This research uses a cross-validation model validation method with a value of K = 10 to help improve the performance of the model built. In this study, from the entire fold, an average accuracy value of 98.74% was obtained. To evaluate the model built, this research has also conducted several new data inputs, and in each new data input, the accuracy value is obtained above 99%. This indicates that the model built, namely the combination of SVM and AdaBoost algorithms with the cross-validation model validation method, produces high accuracy, so this model can greatly assist the allergen detection process in food products.

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

This study evaluates the efficiency of two artificial intelligence models, DeepSeek and OpenAI, in generating code for algorithmic systems. Efficiency is assessed through execution speed, code accuracy, and the number of code characters produced. Data were collected from 100 tests covering search, sorting, graph, dynamic programming, optimization, data processing, text, and machine learning algorithms. The objective is to compare the performance of both models to support the development of efficient information retrieval systems. The method involves algorithm testing with statistical analysis of execution time, accuracy, and code length. Results indicate that DeepSeek has an average execution time of 28.74 seconds, slightly slower than OpenAI’s 28.49 seconds. However, DeepSeek’s accuracy (85.88%) surpasses OpenAI’s (85.03%). The average number of code characters is identical at 96.35 characters. The study concludes that DeepSeek excels in accuracy, while OpenAI is faster in certain cases, providing valuable insights for developers in selecting AI models for information retrieval applications.

Credit card fraud is a critical issue in digital financial transactions. This study aims to develop and evaluate fraud detection models using Logistic Regression and Gradient Boosting on an imbalanced dataset, where fraudulent transactions constitute only a small portion of the data. To address this imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied during preprocessing. Logistic Regression, used as a baseline model, achieved 95% accuracy, 78.6% precision, 55.9% recall, and a 65.3% F1-score. After applying class weighting and SMOTE, recall improved to 88.7%, but precision dropped to 52%, indicating that the model became overly sensitive and prone to false positives. Gradient Boosting initially produced better results, with 98% accuracy, 95.5% precision, 84.3% recall, and an 89.5% F1-score. After hyperparameter tuning and resampling, its performance improved further to 96.7% precision, 86.1% recall, and a 91.1% F1-score. These results indicate that Gradient Boosting is more effective in handling imbalanced data and offers greater reliability in detecting fraudulent transactions. The findings support the growing evidence in favor of ensemble learning techniques in fraud detection applications. This research contributes practical insights into improving the accuracy and security of machine learning-based fraud detection systems in financial services.

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.

This study compares two service management models to evaluate the governance of the Wi-Fi network in Dusun Gita Nagari Baru. The main objective is to measure user satisfaction and service quality following the implementation of the COBIT 2019 framework, particularly the DSS02 domain (Manage Service Requests and Incidents). The research employed a mixed methods approach, using historical-comparative document analysis and Likert scale questionnaires distributed to 21 active users. The data were analysed through gap analysis, capability level mapping, and descriptive statistical analysis to identify performance differences between two periods. The results indicate that most indicators in the COBIT 2019 capability model are at Level 4 (Predictable), one indicator reaches Level 5 (Optimising), and another indicator is at Level 3. Indicators directly related to the DSS02 domain, such as ease of reporting, response speed, schedule accuracy, and repair time, demonstrate the most significant improvements. These findings support the hypothesis that implementing COBIT 2019-based governance for DSS02 can enhance user satisfaction and the quality of Wi-Fi network services in rural areas. This study also provides practical recommendations for the sustainable management of digital infrastructure in areas with limited access.

Infectious diseases remain a dynamic and evolving public health threat, requiring data-driven approaches for early detection and targeted policy planning. This study aims to model spatio-temporal trends and clustering patterns of HIV transmission in Bogor Regency during the period 2020–2023 by utilizing a combination of unsupervised and supervised machine learning techniques. The dataset was obtained from the Bogor Regency Health Office and includes annual data on the number of HIV cases across 40 sub-districts. The research methodology consists of data preprocessing stages, clustering using the K-Means algorithm, and classification using a Decision Tree model. The preprocessing steps include data integration, attribute selection, temporal aggregation, handling of missing data, and normalization using Z-score. K-Means clustering is applied to identify hidden patterns in the development of HIV cases, resulting in three distinct clusters based on multi-year trends. The resulting cluster labels are then used as target classes in the supervised classification process. The Decision Tree classification model demonstrates high accuracy in predicting cluster membership, indicating a strong relationship between the temporal patterns of HIV cases and cluster identity. The integration of clustering and classification techniques provides a robust analytical framework for understanding the dynamics of HIV transmission, while also supporting the formulation of more precise, evidence-based, and region-specific public health interventions.