Budiman

@unibi.ac.id

Faculty Technology and Informatic
Universitas Informatika dan Bisnis Indonesia

Budiman


                     Download Compact PDF  
https://researchid.co/budiman1982
I have expertise in machine learning and data science. Currently affiliated with Universitas Informatika dan Bisnis Indonesia, Bandung. This researcher has a strong academic background in informatics and experience in designing data-driven solutions. His research focuses on applying algorithms for big data analysis to support better business decision making. In addition, he is proficient in using several tools to process and analyze data effectively. This researcher continues to develop skills and knowledge in data-driven technology and innovation. He is committed to making significant contributions to computer science and technology.

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Science, Computer Vision and Pattern Recognition, Software
13

Scopus Publications

397

Scholar Citations

10

Scholar h-index

11

Scholar i10-index

Scopus Publications

  • Pareto-Fair Calorie Burn Classification from Lifestyle Data: A Multi-Class Baseline with Fairness-Aware Thresholding
    Zatin Niqotaini, Nur Alamsyah, Budiman, Valencia Claudia Jennifer Kaunang
    Proceedings 7th International Conference on Informatics Multimedia Cyber and Information System Icimcis 2025, 2025
    We present a reproducible pipeline for Pareto-Fair calorie-burn classification from heterogeneous lifestyle data. The task is framed as multi-class prediction with four levels (low, medium, high, very high) and evaluated under stratified 5-fold cross-validation. Our pipeline standardizes preprocessing for mixed numeric–categorical features (imputation, scaling, one-hot encoding) and benchmarks Logistic Regression, Random Forest, LightGBM, and XGBoost. To assess societal impact, we conduct fairness audits across gender, age band, and experience level using Demographic Parity (DP) and Equal Opportunity (EO). Because accuracy and fairness often trade off, we sweep decision thresholds on the positive superclass (high very high) and map the Pareto frontier between performance (F1) and fairness (maxDP-gap, EO-gap); this enables transparent operating-point selection without retraining. On our dataset, LightGBM/XGBoost deliver the strongest multi-class baselines (Macro-F1 0.36, Balanced Accuracy 0.36, AUROC-OvR 0.64), clearly above chance. Under the binary view for auditing, Random Forest attains the highest default F1 but exhibits larger DP gaps, while LightGBM/XGBoost show small DP gaps ( 0.036–0.037) and moderate EO gaps ( 0.09–0.10) on average—indicating measurable but not extreme disparity across groups. Using the Pareto map, practitioners can pick balanced, non-degenerate thresholds (e.g., with reasonable precision and positive rates) that provide an explicit compromise between utility and equity. Our contribution is a practical, end-to-end baseline and selection procedure for fair calorie-burn classification: (i) cross-validated multi-class results, (ii) DP/EO auditing over multiple sensitive attributes, and (iii) Pareto-aware thresholding for deployable operating points. We discuss limitations (probability calibration, hyperparameter tuning, ordinal structure) and outline extensions for future work.
  • Smart Vision: Enhancing Diabetic Retinopathy Classification with GAN and Deep Learning
    Dede Irman Pirdaus, Budiman, Nur Alamsyah, Muhamad Achya Arifudin
    2025 10th International Conference on Informatics and Computing Icic 2025, 2025
    Diabetic Retinopathy (DR) affects 10-32% of diabetic patients in Indonesia, with global cases projected to reach 161 million by 2045. Conventional augmentation techniques for DR classification yield limited performance, often failing to model complex retinal structures. This study integrates Deep Convolutional Generative Adversarial Networks (DCGAN) to augment fundus image datasets, followed by classification using ResNet-18 and EfficientNet-B0. Three experimental scenarios were conducted: (1) classification without augmentation, (2) classification with DCGAN-generated images, and (3) generalization testing on unseen data. A dataset of 800 images was used, equally distributed between normal and DR classes. Synthetic image quality was assessed using Fréchet Inception Distance (FID), yielding scores of 287 (normal) and 368 (DR). DCGAN-based augmentation led to consistent performance improvements across models. EfficientNet-B0 achieved the highest accuracy (93%) on the original dataset, while ResNet-18 showed greater robustness under domain shift, maintaining 92% accuracy. Both models recorded AUC-ROC scores above 0.97, indicating strong discriminative performance. Despite moderate FID values, DCGAN-generated images introduced valuable feature diversity that enhanced model generalization. The results validate DCGAN as an effective augmentation strategy for improving DR classification, with ResNet-18 demonstrating high potential for clinical deployment in real-world diagnostic systems.
  • Explainable AI for CO2 Emission Prediction Using XGBoost Enhanced by Optuna and SHAP
    Achya Arifudin, Nur Alamsyah, Budiman, Acep Hendra, Elia Setiana
    2025 International Conference on Smart Computing Iot and Machine Learning Siml 2025, 2025
    <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CO}_{2}$</tex> emissions significantly contribute to environmental challenges, particularly in the transportation and automotive sectors. Building predictive models for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CO}_{2}$</tex> emissions frequently involves balancing the goals of high accuracy and interpretability, particularly in the context of intricate, high-dimensional data. This study aims to address these challenges by proposing an explainable and optimized machine learning framework for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CO}_{2}$</tex> emission prediction. The framework employs XGBoost, a robust gradient boosting algorithm, and incorporates hyperparameter optimization using Optuna to enhance model performance. SHAP (SHapley Additive exPlanations) is utilized to ensure interpretability by analyzing feature contributions to model predictions. The framework was validated using an automotive dataset comprising fuel consumption and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CO}_{2}$</tex> emissions, achieving an MSE of 23.08 and an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R$</tex>-squared (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex>) score of 0.996. The integration of performance optimization and feature interpretability provides actionable insights into the key drivers of emissions.
  • t-SNE and KMeans-Based Dimensionality Reduction for Explainable Unsupervised Clustering in Mental Health Data Analysis
    Titan Parama Yoga, Nur Alamsyah, Acep Hendra, Imannudin Akbar, Budiman, Reni Nursyanti
    2025 7th International Conference on Cybernetics and Intelligent System Icoris 2025, 2025
    The analysis of mental health data presents significant challenges due to its high dimensionality and complex underlying patterns. This study proposes an explainable unsupervised clustering framework combining t-distributed Stochastic Neighbor Embedding (t-SNE) for non-linear dimensionality reduction and KMeans clustering. The dataset, consisting of lifestyle and psychological features, underwent preprocessing and feature scaling to ensure consistency across variables. Clustering quality was evaluated using Silhouette Score and Davies-Bouldin Index, where the integration of t-SNE significantly improved performance compared to traditional PCA-based approaches, achieving a Silhouette Score of 0.3850 and a Davies-Bouldin Index of 0.8415. To enhance interpretability, a Random Forest classifier was trained to predict the cluster labels, and SHAP (SHapley Additive exPlanations) was employed to identify the most influential features. Results revealed that Financial Stress, Self-Esteem, and Work Stress were key factors differentiating clusters. The proposed framework not only improves clustering performance but also provides explainable insights into mental health segmentation, contributing to better targeted interventions and personalized analysis.
  • Explainable Deep Feature Learning for Multi-Class Tomato Leaf Disease Classification Using CNN and Ridge Classifier
    Budiman, Nur Alamsyah, Muhamad Achya Arifudin, Elia Setiana, Titan Parama Yoga, Dede Irman Pirdaus
    Icaisd 2025 2025 International Conference on Advanced Information Scientific Development Artificial Intelligence Advancing Research and Computational Innovations for Global Welfare Proceedings, 2025
    Diseases in tomato plants can lead to a significant reduction in yield, thereby impacting food security in Indonesia. Early disease detection is crucial for rapid and effective disease control. This study aimed to develop a digital image-based classification model that achieves high accuracy and can be easily interpreted for the classification of tomato leaf diseases. The method employed combines a Convolutional Neural Network (CNN) for visual feature extraction and Ridge Classification for classification, along with dimension reduction and visualization techniques, including PCA and t-SNE, as well as model interpretation using SHAP. The training test results showed that the model achieved a 0.97 classification accuracy on the Ridge Classifier, with consistent performance across all disease classes. Feature visualization separates classes, whereas SHAP analysis reveals the contribution of each feature to the model's decision, thereby increasing transparency and user confidence. These findings demonstrate that the combination of CNN, Ridge Classifier, and XAI can yield an accurate, efficient, and comprehensible system for detecting plant diseases. This model has the potential to be applied in innovative farming systems to support automatic disease detection and assist decision-making in the field without requiring direct expert intervention
  • Hybrid CNN Framework for Enhanced Skin Cancer Detection: Merging Machine Learning and Explainable AI
    Budiman, Nur Alamsyah, Muhamad Achya Arifudin, Elia Setiana, Acep Hendra, Dede Irman Pirdaus
    2025 10th International Conference on Informatics and Computing Icic 2025, 2025
    Skin cancer is an important issue for public health and requires accurate and dependable diagnostic systems. The present study intended to develop a hybrid framework for skin cancer detection by incorporating machine learning techniques, especially convolutional neural networks, into an explainable AI model. The methods incorporated a systematic data collection approach by sourcing a complete dataset of 3,297 dermatoscopic images, image transformations, and extracting features. Various machine learning algorithms were then investigated to determine which was best suited for classifying images into a benign or malignant perspective using Logistic Regression, SGD Classifier, SVM, Gradient Boosting, XGBoost model, and K-Nearest Neighbors algorithms. Overall, the findings from this study revealed that the Gradient Boosting model achieved cross-validation accuracy of 0.8380 ± 0.0159, with both precision and recall values of 0.97 for both classes. The finding showed that the Gradient Boosting model performed best among all examined classification techniques. The contribution of this study is threefold: the provision of a comprehensive dataset, the use of advanced techniques such as t-SNE and SHAP for continuing with feature analysis and interpretability, and lastly, providing a model understandable for healthcare professionals to yield trust in AI-generated predictions. In conclusion, this study further enhanced skin cancer detection and helped inform and improve clinical decisions through model interpretation of predictions. The findings pave the way for more reliable and interpretable AI applications in dermatology, ultimately contributing to better patient outcomes and advancing healthcare technology.
  • Improving Churn Prediction in Banking: Hyperparameter Optimization of MLP with SHAP and Permutation Feature Importance
    Elia Setiana, Nur Alamsyah, Acep Hendra, Venia Restreva Danestiara, Budiman, Reni Nursyanti
    2025 10th International Conference on Informatics and Computing Icic 2025, 2025
    In the competitive banking industry, accurately predicting customer churn is essential for developing effective retention strategies. This study proposes a hyperparameter-optimized deep learning approach using a Multi-Layer Per-ceptron (MLP) model. The model is trained and evaluated on a publicly available bank churn dataset comprising 10,000 customer records, with a balanced representation of churn and non-churn instances. To enhance interpretability, feature impor- tance is analyzed using both permutation-based methods and game-theoretic explainability techniques. Comparative analysis is conducted against classical machine learning models such as Random Forest, Support Vector Machine, and Gradient Boosting Machine. The optimized model achieves a validation accuracy of 86.65%, demonstrating its potential for practi- cal implementation in customer relationship management. In addition to accuracy, this study highlights the importance of transparent decision-making by identifying the key drivers of churn through feature importance analysis. The inclusion of hyperparameter optimization not only improves model performance but also ensures better generalization across different data distributions. These findings offer valuable insights for financial institutions aiming to integrate data-driven approaches in personalized customer retention programs.
  • A stacking ensemble model with SMOTE for improved imbalanced classification on credit data
    Nur Alamsyah, Budiman Budiman, Titan Parama Yoga, R. Yadi Rakhman Alamsyah
    Telkomnika Telecommunication Computing Electronics and Control, 2024
    This research is based on a significant problem in credit risk analysis in the banking sector caused by class imbalance. We face the problem of the model’s inability to accurately identify risks in the ‘‘Charged Off’’ class. As a solution, we propose a stacked ensemble approach that utilizes synthetic minority over-sampling technique (SMOTE) to balance the class distribution. Experiments were conducted by applying SMOTE to the training data before training the credit model using gradient boosting (XGBoost) and random forest (RF) algorithms in a single ensemble. The results show significant improvements in precision, recall, and F1-score after applying SMOTE on the unbalanced classes. The updated model achieved a striking accuracy rate of 0,97 on resampled training data. This re-search clearly identifies the problem of class imbalance as a major challenge in credit risk analysis. The application of SMOTE in a stacked ensemble was found to be effective in improving model performance, making a valuable contribution to the development of more reliable credit models for better risk management and revenue generation in financial institutions.
  • Predictive Boosting for Employee Retention with SMOTE and XGBoost Hyperparameter Tuning
    Indarta Priyana, Nur Alamsyah, Budiman, Aggi Panigoro Sarifiyono, Elan Rusnendar
    2024 International Conference on Smart Computing Iot and Machine Learning Siml 2024, 2024
    Companies today face challenges in understanding the factors that influence employee retention, especially in handling imbalanced datasets that depict low retention rates. This research aims to explore the impact of various variables on employee retention rates and improve predictive capabilities through a combination of SMOTE for data imbalance handling and hyperparameter tuning in the XGBoost model. The research method involved detailed analysis of employee profiles and application of SMOTE techniques to harmonize data imbalance, along with fine tuning of hyperparameters in the XGBoost model to improve model performance. The results of the first experiment using the XGBoost model showed that the model produced an accuracy rate of 0.81, but after going through the hyperparameter tuning process, the accuracy increased significantly to 0.85. The results of this study provide a deeper understanding of the factors that contribute to employee retention in different types of companies. The implementation of SMOTE and hyperparameter tuning in the XGBoost model proved its effectiveness in improving prediction accuracy. This research has the potential to provide strategic guidance for human resource management in improving employee retention in the future.
  • Driven Multivariate Regression - Feature Engineering with Random Forest and XGBoost for Accurate Weather Prediction
    Nur Alamsyah, Budiman, Venia Restreva Danestiara, Imannudin Akbar, Arnold Ropen Sinaga, Reni Nursyanti
    2024 6th International Conference on Cybernetics and Intelligent System Icoris 2024, 2024
    Fluctuations in weather conditions present a signif- icant challenge for accurate prediction, particularly when con- sidering multiple interdependent variables such as temperature and precipitation. To address this issue, this study proposes a multivariate regression approach driven by advanced feature engineering techniques. Specifically, we employed Random Forest and XGBoost models, leveraging temporal, interaction, and lag features to enhance the predictive accuracy. The proposed method was evaluated using a real-world weather dataset, where both models demonstrated substantial improvements in prediction per-formance. The Random Forest model achieved a Mean Squared Error (MSE) of 0.059 for temperature and 0.019 for precipitation, with an R-squared (R2) of 0.995 and 0.999, respectively. Similarly, the XGBoost model yielded an MSE of 0.043 for temperature and 1.826 for precipitation, with an R2 of 0.996 and 0.983. These results underscore the effectiveness of the feature engineering process combined with robust multivariate regression models, offering a promising approach for accurate weather prediction.
  • Improved Prediction Of Global Temperature Via LSTM Using ReLU Activation And Hyperparameter Optimization
    Nur Alamsyah, Budiman, Acep Hendra, Elia Setiana, Titan Parama Yoga, Venia Restreva Danestiara
    Proceeding 2024 International Conference on Information Technology Research and Innovation Icitri 2024, 2024
  • Optimizing Computational Efficiency in Feature Selection for Machine Learning Models: A Study Crime Detection Based on Criminal Data
    Nur Alamsyah, Budiman, Venia Restreva Danestiara, Imannudin Akbar, Elia Setiana
    2023 8th International Conference on Informatics and Computing Icic 2023, 2023
  • Machine Learning-Based Classification of House Prices: A Comparative Study
    Budiman Budiman, Nur Alamsyah, Titan Parama Yoga, R Yadi Rakhman Alamsyah, Chairul Habibi
    2023 5th International Conference on Cybernetics and Intelligent Systems Icoris 2023, 2023

RECENT SCHOLAR PUBLICATIONS

  • Integration of base64 encoding, vigenère cipher, and LSB steganography for securing learning materials in learning management systems.
    D Pradeka, DZ Vierdansyah, DAR Agustini, A Adiwilaga, SA Humaira, ...
    TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika 13 (2), 378-389 , 2026
    2026
  • Machine Learning Based Cervical Cancer Risk Prediction with SHAP-Driven Feature Interpretation
    F Ardiansyah, RDA Putra
    Bulletin of Intelligent Machines and Algorithms 1 (3), 79-87 , 2026
    2026
  • Comparative Analysis of Machine Learning Regression Models for Paddy Yield Prediction
    CC Sitohang, F Kinkin
    Bulletin of Intelligent Machines and Algorithms 1 (3), 93-100 , 2026
    2026
  • Activation Function Sensitivity in LSTM-Based Peak Stock Price Forecasting for High-Volatility Financial Time Series
    RR Nugraha, B Budiman, I Akbar
    SISINFO: Jurnal Sistem Informasi dan Informatika 8 (1), 52-59 , 2026
    2026
  • Peningkatan Literasi Digital dan Pemanfaatan Kecerdasan Buatan: Strategi Edukasi Inovatif bagi Masyarakat
    B Budiman, E Setiana, DI Pirdaus
    Bhakti Karya dan Inovatif 6 (1), 7-12 , 2026
    2026
  • Pareto-Fair Calorie Burn Classification from Lifestyle Data: A Multi-Class Baseline with Fairness-Aware Thresholding
    Z Niqotaini, N Alamsyah, VCJ Kaunang
    2025 International Conference on Informatics, Multimedia, Cyber and … , 2025
    2025
  • Anomaly Detection in Walking Data Using Isolation Forest: An Unsupervised Learning Approach
    NA Nur
    Journal Of Information System And Artificial Intelligence 6 (1), 1-11 , 2025
    2025
  • Comparative Analysis of Machine Learning Algorithms for Indonesian Twitter Sentiment Classification on the Jakarta–Bandung High-Speed Rail Project
    M Noerhadi
    Bulletin of Intelligent Machines and Algorithms 1 (1), 7-13 , 2025
    2025
  • Explainable Deep Feature Learning for Multi-Class Tomato Leaf Disease Classification Using CNN and Ridge Classifier
    N Alamsyah, MA Arifudin, E Setiana, TP Yoga, DI Pirdaus
    2025 IEEE International Conference on Advanced Information Scientific … , 2025
    2025
  • A Metaheuristic wrapper approach to feature selection with genetic algorithm for enhancing XGBoost classification in diabetes prediction
    N Alamsyah, VR Danestiara, TP Yoga, R Nursyanti, V Kaunang
    Kinetik: Game Technology, Information System, Computer Network, Computing … , 2025
    2025
  • Smart Vision: Enhancing Diabetic Retinopathy Classification with GAN and Deep Learning
    DI Pirdaus, N Alamsyah, MA Arifudin
    2025 Tenth International Conference on Informatics and Computing (ICIC), 1-6 , 2025
    2025
  • Hybrid CNN Framework for Enhanced Skin Cancer Detection: Merging Machine Learning and Explainable AI
    N Alamsyah, MA Arifudin, E Setiana, A Hendra, DI Pirdaus
    2025 Tenth International Conference on Informatics and Computing (ICIC), 1-6 , 2025
    2025
  • Improving Churn Prediction in Banking: Hyperparameter Optimization of MLP with SHAP and Permutation Feature Importance
    E Setiana, N Alamsyah, A Hendra, VR Danestiara, R Nursyanti
    2025 Tenth International Conference on Informatics and Computing (ICIC), 1-6 , 2025
    2025
  • OPTIMIZED DEEP AUTOENCODER WITH L1 REGULARIZATION AND DROPOUT FOR ANOMALY DETECTION IN 6G NETWORK SLICING
    VCJ Kaunang, N Alamsyah, TP Yoga, A Hendra, B Budiman
    Jurnal Techno Nusa Mandiri 20 (2), 189-194 , 2025
    2025
  • ISOLATION FOREST PARAMETER TUNING FOR MOBILE APP ANOMALY DETECTION BASED ON PERMISSION REQUESTS
    VCJ Kaunang, N Alamsyah, R Nursyanti, B Budiman, VR Danestiara, ...
    Jurnal Pilar Nusa Mandiri 21 (2), 187-197 , 2025
    2025
  • Fine-Tuned Autoencoder Neural Network for Anomaly Detection in Accounting Transactions
    N Alamsyah, HF Rahmani, W Erpurini, B Budiman
    Paradigma-Jurnal Komputer dan Informatika 27 (2), 65-73 , 2025
    2025
    Citations: 1
  • t-SNE and KMeans-Based Dimensionality Reduction for Explainable Unsupervised Clustering in Mental Health Data Analysis
    TP Yoga, N Alamsyah, A Hendra, I Akbar, R Nursyanti
    2025 7th International Conference on Cybernetics and Intelligent System … , 2025
    2025
  • HYBRID LEARNING STRATEGY COMBINING MODEL-LEVEL TRANSFER LEARNING AND DATA-LEVEL AUGMENTATION FOR BRAIN CANCER CLASSIFICATION
    B Budiman, N Alamsyah, VR Danestiara, MA Arifudin, DI Pirdaus
    JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 11 (1), 136-143 , 2025
    2025
    Citations: 1
  • A Data-Driven Approach to Comparative Evaluation of Regression Models for Accurate House Price Prediction: Pendekatan Berbasis Data untuk Evaluasi Komparatif Model Regresi …
    TP Hati, B Budiman, I Akbar, N Alamsyah
    NUANSA INFORMATIKA 19 (2), 25-34 , 2025
    2025
  • A Bidirectional GRU Approach with Hyperparameter Optimization for Sentiment Classification in Game Reviews: Pendekatan GRU Dua Arah dengan Optimasi Hiperparameter untuk …
    N Alamsyah, TP Yoga, I Akbar, A Hendra, AJ Prima
    NUANSA INFORMATIKA 19 (2), 88-95 , 2025
    2025
    Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

  • Data Mining: Algoritma dan Penerapannya
    RF Putra, RSY Zebua, B Budiman, PW Rahayu, MTA Bangsa, ...
    PT. Sonpedia Publishing Indonesia , 2023
    2023
    Citations: 51
  • Analisis Penerimaan Google Classroom Menggunakan Pendekatan Technology Acceptance Model (TAM) Dan End-User Computing Satisfaction (EUCS)(Studi Kasus: Universitas Informatika …
    Z Niqotaini, B Budiman
    Sistemasi: Jurnal Sistem Informasi 10 (3), 637-661 , 2021
    2021
    Citations: 48
  • ANALISIS PENERIMAAN GOOGLE CLASSROOM MENGGUNAKAN PENDEKATAN TECHNOLOGY ACCEPTANCE MODEL (TAM) DAN END-USER COMPUTING SATISFACTION (EUCS) (STUDI KASUS: UNIVERSITAS INFORMATIKA …
    Z Niqotaini, Budiman
    Technologia: Jurnal Ilmiah 12 (4), 259-273 , 2021
    2021
    Citations: 48
  • Analisis Dan Perancangan Sistem Penjualan Pada Toko XYZ Berbasis Web Dan Mobile Menggunakan UML
    I Akbar, Budiman, Z Niqotaini, AR Fauzi
    NUANSA INFORMATIKA 17 (2), 71-82 , 2023
    2023
    Citations: 30
  • XGBOOST HYPERPARAMETER OPTIMIZATION USING RANDOMIZEDSEARCHCV FOR ACCURATE FOREST FIRE DROUGHT CONDITION PREDICTION
    N Alamsyah, B Budiman, TP Yoga, RYR Alamsyah
    Jurnal Pilar Nusa Mandiri 20 (2), 103-110 , 2024
    2024
    Citations: 24
  • Perbandingan Algoritma Klasifikasi Data Mining untuk Penelusuran Minat Calon Mahasiswa Baru
    B Budiman
    Nuansa Informatika 15 (2), 37-52 , 2021
    2021
    Citations: 22
  • Perancangan Prototype User Interface Dan Pengujian User Experience Aplikasi Rental Mobil Berbasis Menggunakan Metode Design Thinking (Studi Kasus: Pt Trans Berjaya Khatulistiwa)
    TPY Titan, Budiman, JHFE Putra
    NUANSA INFORMATIKA 17 (2), 48-65 , 2023
    2023
    Citations: 20
  • IMPROVING TRAFFIC DENSITY PREDICTION USING LSTM WITH PARAMETRIC ReLU (PReLU) ACTIVATION
    N Alamsyah, TP Yoga, B Budiman
    JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 9 (2), 154-160 , 2024
    2024
    Citations: 12
  • A stacking ensemble model with SMOTE for improved imbalanced classification on credit data
    N Alamsyah, B Budiman, TP Yoga, RYR Alamsyah
    TELKOMNIKA (Telecommunication Computing Electronics and Control) 22 (3), 657-664 , 2024
    2024
    Citations: 11
  • Data mining implementation using naïve Bayes algorithm and decision tree J48 in determining concentration selection
    B Budiman, R Nursyanti, RYR Alamsyah, I Akbar
    International Journal of Quantitative Research and Modeling 1 (3), 123-134 , 2020
    2020
    Citations: 11
  • Predictive Boosting for Employee Retention with SMOTE and XGBoost Hyperparameter Tuning
    I Priyana, N Alamsyah, AP Sarifiyono, E Rusnendar
    2024 International Conference on Smart Computing, IoT and Machine Learning … , 2024
    2024
    Citations: 10
  • Analysis of E-learning user Acceptance using the Technology Acceptance Model (TAM) and end-User Computing Satisfaction (EUCS)
    Budiman, N Alamsyah, T Parama
    Formosa Journal of Applied Sciences 2 (8), 1873-1892 , 2023
    2023
    Citations: 10
  • Analisis Perbandingan Sentimen Pengguna Twitter Terhadap Layanan Salah Satu Provider Internet Di Indonesia Menggunakan Metode Klasifikasi
    DP Sari, B Budiman, N Alamsyah
    TEMATIK 10 (2), 246-251 , 2023
    2023
    Citations: 8
  • Optimizing Computational Efficiency in Feature Selection for Machine Learning Models: A Study Crime Detection Based on Criminal Data
    N Alamsyah, B Budiman, VR Danestiara, I Akbar, E Setiana
    2023 Eighth International Conference on Informatics and Computing (ICIC), 1-6 , 2023
    2023
    Citations: 7
  • Improved Prediction Of Global Temperature Via LSTM Using ReLU Activation And Hyperparameter Optimization
    N Alamsyah, A Hendra, E Setiana, TP Yoga, VR Danestiara
    2024 International Conference on Information Technology Research and … , 2024
    2024
    Citations: 6
  • ACTIVATION FUNCTION IN LSTM FOR IMPROVED FORECASTING OF CLOSING NATURAL GAS STOCK PRICES
    B Budiman, N Alamsyah, RYR Alamsyah
    JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 10 (1), 100-107 , 2024
    2024
    Citations: 6
  • COMPARISON LINEAR REGRESSION AND RANDOM FOREST MODELS FOR PREDICTION OF UNDERGROUND DROUGHT LEVELS IN FOREST FIRES
    N Alamsyah, B Budiman, TP Yoga, RYR Alamsyah
    Jurnal Techno Nusa Mandiri 21 (2), 81-86 , 2024
    2024
    Citations: 6
  • Analisis Penerimaan Google Classroom Menggunakan Pendekatan Technology Acceptance Model (Tam) Dan End-User Computing Satisfaction (Eucs)(Studi Kasus Universitas Informatika Dan …
    Z Niqotaini, B Budiman
    2021
    Citations: 6
  • PERANCANGAN APLIKASI SISTEM TINDAK LANJUT PELANGGAN PADA PT. XYZ
    Budiman
    SisInfo e-ISSN: 2655-867X p-ISSN: 2655-8661 2 (1), 1-7 , 2020
    2020
    Citations: 6
  • Analisis Sentimen Publik pada Media Sosial Twitter Terhadap Tiket. com Menggunakan Algoritma Klasifikasi
    B Budiman, ZS Anggraeni, C Habibi, N Alamsyah
    Jurnal Informatika 11 (1), 1-10 , 2024
    2024
    Citations: 5