Article Per Year (5 Year)
p-Index From 2021 - 2026
5.981
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Techno.Com: Jurnal Teknologi Informasi Jurnal Simetris Jurnal Buana Informatika Jurnal Inovasi Teknologi Pendidikan Jurnas Nasional Teknologi dan Sistem Informasi JAIS (Journal of Applied Intelligent System) Proceeding SENDI_U Jurnal Ilmiah Dinamika Rekayasa (DINAREK) Sistemasi: Jurnal Sistem Informasi Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control JOURNAL OF APPLIED INFORMATICS AND COMPUTING JISKa (Jurnal Informatika Sunan Kalijaga) Infotekmesin Abdimasku : Jurnal Pengabdian Masyarakat Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Nasional Teknik Elektro dan Teknologi Informasi Jurnal Komtekinfo Community: Jurnal Pengabdian Pada Masyarakat Jurnal Informatika: Jurnal Pengembangan IT Seminar Nasional Riset dan Teknologi (SEMNAS RISTEK) INOVTEK Polbeng - Seri Informatika
Utomo, Danang Wahyu
Universitas Dian Nuswantoro
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Mechanical Engineering Social Sciences Other

Published : 63 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search
Journal : Infotekmesin

 1   2 
Pembelajaran Ensemble untuk Klasifikasi Ulasan Pelanggan E-commerce Menggunakan Teknik Boosting Rama Hadi Suryanto, Matius; Wahyu Utomo, Danang
Infotekmesin Vol 15 No 2 (2024): Infotekmesin, Juli 2024
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v15i2.2314

Abstract

Technological developments have developed rapidly and impact changing behavior in daily activities. Now, selling and buying activities are carried out in e-commerce services. The increase in e-commerce users is the main factor in improving the quality of e-commerce services. One of the factors to improve the quality of e-commerce services is customer reviews. Customer reviews are useful for shop owners to find out whether the product offered has positive or negative reviews. The large number of customer reviews is the main factor in the difficulty of shop owners in classifying customer reviews. This study proposes classifying customer reviews using ensemble learning with boosting techniques such as XGBoost, AdaBoost, Gradient Boosting, and LightGBM. The use of an ensemble with a boosting technique aims to improve the algorithm’s performance. In a test scenario apply majority voting to produce the best performance from each algorithm. The result shows that the XGBoost algorithm produces higher accuracy than other techniques are 92.30%. On the analysis of matric evaluation of precision, recall, and F1-Score, XGBoost produces higher true positive values than other techniques such as AdaBoost, Gradient Boosting, and Light GBM
Rekomendasi Produk E-commerce Berbasis Klasifikasi Ulasan Menggunakan Ensemble Random Forest dan Teknik Boosting Saputro, Donny; Danang Wahyu Utomo
Infotekmesin Vol 15 No 2 (2024): Infotekmesin, Juli 2024
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v15i2.2315

Abstract

The increasing popularity of e-commerce poses a new challenge to provide customers with a more personalized and effective shopping experience. In situations like this, product recommendations are very important to increase consumer satisfaction and increase sales. Using Random Forest and Boosting ensemble techniques, this research introduces a method for e-commerce product recommendation based on user review analysis. The Aim is to test the Random Forest algorithm with several boosting techniques for ensemble learning. The results show that the Random Forest method combined with the Xgboost technique can provide product recommendations that are 87.25% more accurate and relevant than other boosting techniques. In precision analysis, Random Forest-XGBoost achieved a higher accuracy of 90% compared to other boosting techniques. Additionally, the combined use of Boosting and Random Forest techniques improves the model's performance in handling complexity and variation in e-commerce product reviews.
Klasifikasi Stunting Balita menggunakan Metode Ensemble Learning dan Random Forest Finda, Selma Marsya; Danang Wahyu Utomo
Infotekmesin Vol 15 No 2 (2024): Infotekmesin, Juli 2024
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v15i2.2326

Abstract

Stunting is a long-term condition that describes nutritional deficiencies that affect children's growth and development from an early age, especially linear growth. Examination of the stunting status of toddlers in Indonesia, especially at the Karanganyar Community Health Center, still uses book calculations so errors are still found in the use of formulas which result in inaccuracies in the classification of stunting. Efforts to improve research results were carried out using the Random Forest algorithm which was enhanced with ensemble methods such as the Bagging and Boosting methods to classify stunting data. The aim of this research is to find out which technique will produce the best and most accurate accuracy. The Ensemble Boosting techniques used are XGBoost and Gradient Boosting. This research uses a dataset from the Karanganyar Health Center, Semarang City with a total of 2000 data records. The test results produced the highest accuracy algorithm, namely the Random Forest + Bagging algorithm which obtained accuracy results of 98.25%. Based on the analysis results obtained, the Bagging and Boosting methods can accurately predict stunting data.
Prediksi Diabetes menggunakan Metode Ensemble Learning dengan Teknik Soft Voting Hilmi Hanif; Danang Wahyu Utomo
Infotekmesin Vol 16 No 1 (2025): Infotekmesin: Januari 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i1.2534

Abstract

Diabetes is a chronic disease characterized by high blood glucose levels due to the body's inability to produce or use insulin effectively. This disease is one of the serious global health problems, and it has a significant impact; therefore, early detection is very important. Efforts to overcome this challenge can be made by applying machine learning, which provides a new and effective approach. This study aims to predict diabetes with a higher accuracy level through the Ensemble Learning Soft Voting method. In addition, the data balancing technique using SMOTE is applied to overcome the problem of imbalance in the data set. This study also compares various classification models using Machine Learning algorithms, namely LightGBM, XGBoost, and Random Forest. The test results show that the Random Forest model achieves the highest level of accuracy at 97.20%. In comparison, the Ensemble Learning Soft Voting method that combines the three algorithms has increased the accuracy to 97.74%. This Ensemble Learning approach has proven effective in significantly improving predictions and performing better than a single model.
Deteksi Dini Gangguan Kesehatan Mental dengan Model Bert dan Algoritma Xgboost Rahmadika Putri Tresyani; Wahyu Utomo, Danang; Maldini, Naufal
Infotekmesin Vol 16 No 1 (2025): Infotekmesin: Januari 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i1.2535

Abstract

Mental health disorders are severe conditions that affect a person's thoughts, feelings, behavior, and well-being. Data from the World Health Organization (WHO) shows that more than 264 million people worldwide experience depression, one of the most common forms of mental health disorders. However, limited access to psychological services, such as lack of professionals and high costs, are major challenges in providing adequate support. Therefore, innovative technology-based solutions are needed for efficient and affordable psychological support. Efforts to improve research results to develop a mental health chatbot model by combining BERT (Bidirectional Encoder Representations from Transformers) and XGBoost (Extreme Gradient Boosting) models. The BERT model is used to understand the context of the conversation, while the XGBoost algorithm is used for text classification. The dataset used comes from Kaggle, which consists of 312 question patterns with several patterns or classes, namely 79 classes. The results of the program implementation test produced a percentage of 93.05% and output in the form of a program in the execution of the model on Google Colab..
Perbandingan Kinerja Model Deep Learning Convolutional Neural Network (CNN) dan Multilayer Perceptron (MLP) untuk Klasifikasi Penyakit Diabetes Melitus Putri, Cindy Arlita; Utomo, Danang Wahyu
Infotekmesin Vol 17 No 1 (2026): Infotekmesin: Januari 2026
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v17i1.2984

Abstract

Diabetes mellitus is a chronic disease with a continuously increasing number of sufferers. Early detection remains difficult because conventional methods often only recognize the disease at an advanced stage. This study evaluates the performance of the Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) in classifying diabetes using the NHANES dataset (2,278 samples; 21 positive for diabetes). The models were tested with k-fold cross-validation using the metrics accuracy, precision, recall, F1-Score, and ROC-AUC. Results show high accuracy and precision (0.99), an average recall of 0.67, and an F1-Score of 0.75. A paired t-test indicates that CNN is superior in some metrics with a p-value of 0.374, though the ROC-AUC difference is not significant. CNNs can capture complex patterns in health features such as glucose, BMI, and age, whereas MLPs remain reliable as a baseline. In conclusion, both CNN and MLP have the potential to be used for tabular data-based diabetes classification, with CNN showing a tendency to be more effective in detecting non-linear patterns in the imbalanced dataset.
Implementasi Stacking Ensemble Berbasis Cross Domain untuk Klasifikasi Diabetes Ijayanti, Selvi; Utomo, Danang Wahyu
Infotekmesin Vol 17 No 1 (2026): Infotekmesin: Januari 2026
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v17i1.3000

Abstract

Diabetes mellitus is a chronic disease whose prevalence continues to increase and demands accurate early detection solutions that are adaptive to patient data diversity. This study implements the stacking ensemble method for diabetes risk classification with a cross-domain approach, integrating two popular datasets, namely the PIMA Indians Diabetes and NHANES. The experimental pipeline includes feature and label harmonization, missing value imputation using the median, standardization, and class balancing through oversampling. The base models used include Random Forest, Support Vector Machine, Decision Tree, and Multi-Layer Perceptron, with Logistic Regression as the meta learner in the stacking scheme. The evaluation was conducted systematically using stratified k-fold cross-validation and test split, as well as cross-domain scenarios to measure the model's cross-domain adaptation capabilities. In the adaptive domain scenario, the stacking ensemble achieved an accuracy of approximately 0.987% with a recall of 1.000% and an ROC-AUC of approximately 0.987%, while the accuracy of the single base learner reached an accuracy of 0.976% with a recall of 1.000% and an ROC-AUC of approximately 0.977%, thus demonstrating that the adaptive domain stacking approach provides consistently higher performance than the base model. These findings confirm the superiority of adaptive domain-based stacking in dealing with medical data heterogeneity and class imbalance issues, and reinforce its potential as a decision support system for early detection of diabetes in a wider population.
Co-Authors Abu Salam Abu Salam Aden Rahmat, Aden Rahmat Agustina, Feri Aldhi Ari Kurniawan Ardytha Luthfiarta Arifin, Muhammad Farhan Astuti, Yani Parti Astuti, Yani Parti Catur Supriyanto Christy Atika Sari Churniansyah, Faskal Defri Kurniawan Defri Kurniawan Defri Kurniawan Defri Kurniawan Dhita Aulia Octaviani Doheir, Mohamed A S Donny Saputro Donny Saputro Dzaki, Azmi Abiyyu Egia Rosi Subhiyakto Egia Rosi Subhiyakto Egia Rosi Subhiyakto Egia Rosi Subhiyakto Egia Rosi Subhiyakto Egia Rosi Subhiyakto, Egia Rosi Eka Putra, Zaky Dafalas Eko Hari Rachmawanto Erlin Dolphina Etika Kartikadarma Fahmi Amiq Faskal Churniansyah Finda, Selma Marsya Gusnita Darmawati Haresta, Alif Agsakli Hilmi Hanif Husin Sufi Ijayanti, Selvi Ika Novita Dewi Jullita, Efandra Eka Junta Zeniarja Kurniawan, Defri Kurniawan, Defri Liya Umaroh Maldini, Naufal Matius Rama Hadi Suryanto Muljono Muljono Ningrum, Novita Kurnia Norman, Maria Bernadette Chayeenee Novita Kurnia Ningrum Octaviani, Dhita Aulia parti astuti, yani Prajanto Wahyu Adi Prajanto Wahyu Adi, Prajanto Wahyu Pratama, Naufal Adhi Purwanto Purwanto Putri, Cindy Arlita Rahmadika Putri Tresyani Rama Hadi Suryanto, Matius Ramadhan Rakhmat Sani Riski, Habibu Rosi Subhiyakto, Egia Salsabilla, Cinta Selma Marsya Finda Sepbriant, Genta Dwigi Sindhu Rakasiwi Subhiyakto, Egia Rosi Sudibyo, Usman Tanjung, Reza Phina Tresyani, Rahmadika Putri Yani Parti Astuti Yani Parti Astuti Zaky Dafalas Eka Putra