Article Per Year (5 Year)
p-Index From 2021 - 2026
1.463
P-Index
This Author published in this journals
All Journal Jurnal Penelitian Pendidikan IPA (JPPIPA) IJID (International Journal on Informatics for Development) METIK JURNAL Jurnal Pengabdian pada Masyarakat Ilmu Pengetahuan dan Teknologi Terintegrasi Jurnal Informatika dan Multimedia
Yudha Riwanto
Universitas Amikom Yogyakarta
Agriculture, Biological Sciences & Forestry Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Materials Science & Nanotechnology Physics

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
Reduksi Dimensionalitas pada Klasifikasi Kualitas Air Sungai Menggunakan Algoritma Genetika dan Seleksi Fitur Berbasis Korelasi Yudha Riwanto; Fauzia Anis Sekar Ningrum
Jurnal Penelitian Pendidikan IPA Vol 11 No 9 (2025): September
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v11i9.11863

Abstract

Water quality monitoring is a crucial element in data-driven environmental management. This study aims to identify the most important parameters in river water quality classification through feature selection and machine learning approaches. Eleven physicochemical parameters were used as initial features, and two selection methods were applied: Genetic Algorithm (GA) and Spearman Rank Correlation (RS). Classification was performed using Radial Basis Function Support Vector Machine (RBF-SVM), with performance evaluation based on accuracy, F1 score, and recall. GA testing results identified influential parameters (pH, DHL, DO, BOD, COD, TSS, NO₂⁻-N), achieving an accuracy of 96.67% and an F1 score of 0.82. RS generated seven different features with an accuracy of 90.00% and an F1 score of 0.67. Both methods revealed five consistently significant features (DHL, BOD, COD, TSS, NO₂⁻-N), which are the influential features. The model without feature selection, despite producing high accuracy (93.33%), only achieved an F1 score of 0.48, indicating poor recognition of the minority class. These findings confirm that feature selection improves classification efficiency and capability. In conclusion, GA-based feature selection provides the most effective subset for water quality classification and supports the development of intelligent and cost-effective monitoring systems suitable for sensor-based field applications.
KU Band Proximity-Coupled Supply Based Microstrip Array Antenna for Microwave Imaging Applications Fauzia Anis Sekar Ningrum; Yudha Riwanto
Jurnal Penelitian Pendidikan IPA Vol 11 No 9 (2025): September
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v11i9.11991

Abstract

This research focuses on the design and simulation of a 4x1 microstrip array antenna with a proximity-coupled supply technique for Ku frequency band applications, especially in microwave imaging. The antenna is designed to operate in the frequency range 12 - 16 GHz, with a resonance frequency of 14 GHz, using a Duroid 5880 substrate which has a thickness of 3.15 mm and a relative permittivity of 2.2. Array configuration and proximity-coupled techniques are applied to improve impedance matching as well as expand bandwidth. Evaluation through simulation includes important parameters such as return loss, gain, and radiation patterns. The simulation results show a return loss of -26.46 dB at a frequency of 14 GHz, which shows high transmission efficiency with minimal reflections. The radiation patterns in the azimuthal and elevation planes show consistent directivity, with stable gain throughout the frequency range. These results confirm that the designed microstrip array antenna is suitable for microwave imaging applications in the Ku band. The antenna design in this research produces high efficiency, directional radiation, and minimal signal loss, so it is able to support accurate and detailed imaging.
Prediksi Keberhasilan Pengobatan dan Identifikasi Faktor Klinis Penting pada Kanker Tiroid Berdiferensiasi Menggunakan Kolmogorov-Arnold Networks dan SHAP: Prediction of Treatment Success and Identification of Important Clinical Factors in Differentiated Thyroid Cancer Using Kolmogorov-Arnold Networks and SHAP Muhammad Ainul Fikri; Ajie Kusuma Wardhana; Fauzia Anis Sekar Ningrum; Inggrid Yanuar Risca Pratiwi; Yudha Riwanto; Raditya Arief Pratama
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9909

Abstract

Kanker tiroid berdiferensiasi memerlukan evaluasi respons terapi yang akurat untuk menentukan strategi penanganan pasien tingkat lanjut. Penelitian ini bertujuan mengembangkan model prediksi keberhasilan pengobatan kanker tiroid berdiferensiasi menggunakan Kolmogorov-Arnold Networks (KAN) yang diintegrasikan dengan metode SHapley Additive exPlanations (SHAP). Integrasi ini bertujuan menghasilkan sistem prediktif yang tidak hanya akurat tetapi juga memiliki interpretabilitas intrinsik yang transparan bagi tenaga medis. Data klinis retrospektif sebanyak 383 pasien dengan 17 fitur dievaluasi menggunakan pemodelan KAN dengan optimasi pemangkasan (pruning) jaringan pembobot adaptif. Interpretasi kontribusi fitur dianalisis secara post-hoc menggunakan algoritma SHAP KernelExplainer. Hasil pengujian membuktikan bahwa model KAN mencapai performa yang sangat kompetitif dengan akurasi 97,40%, precision 97,87%, recall 97,40%, F1-score 97,47%, dan ROC-AUC 99,75%. Model ini mencatatkan tingkat sensitivitas 100% dalam memprediksi kelas keberhasilan terapi tanpa adanya kesalahan klasifikasi. Analisis SHAP mengungkap bahwa fitur Response (evaluasi respons terapi) memberikan kontribusi paling dominan terhadap hasil prediksi, diikuti oleh variabel Risk (stratifikasi risiko), Age (usia), dan M (status metastasis). Sebagai alat pendukung keputusan klinis, KAN secara efektif menyeleksi fitur otomatis melalui mekanisme sparsity pada spline-nya dan memberikan penjelasan yang komprehensif bersama metode SHAP. Sebagai saran pengembangan ke depan, penelitian selanjutnya dapat memperdalam analisis korelasi matematis antara representasi spline KAN dengan nilai distribusi SHAP, serta memperluas pengujian model menggunakan dataset multisenter dengan skala yang lebih besar.
Analyzing Anthropometric Feature Dependency in Obesity Classification Using Feature Ablation Esti Dwi Puspitasari; Yudha Riwanto
IJID (International Journal on Informatics for Development) Vol. 15 No. 1 (2026): IJID JUNE
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2026.5714

Abstract

Obesity classification models often rely heavily on anthropometric features, particularly weight and height, because both variables directly contribute to body mass index (BMI) calculation. This study investigates the extent of such dependency using feature ablation and error analysis. Experiments were conducted on the NObeyesdad dataset using Logistic Regression and Random Forest under three feature configurations: (1) baseline using all features, (2) ablation without weight, and (3) ablation without height. Model performance was evaluated using Balanced Accuracy, Macro F1-score, confusion matrices, and class-level analysis. Results show that Random Forest consistently outperformed Logistic Regression across all scenarios and demonstrated greater robustness to feature removal. Under the baseline setting, Random Forest achieved a Balanced Accuracy of 0.90 and a Macro F1-score of 0.90, while Logistic Regression obtained 0.89 for both metrics. Performance degradation became more pronounced when weight was removed compared with height, indicating stronger model dependence on weight-related information. Error analysis further revealed increased confusion among adjacent obesity categories, particularly overweight classes. These findings highlight the importance of feature dependency evaluation to improve robustness and interpretability in obesity classification models.
Klusterisasi Kemisikinan Berbasis Konsumsi dan Penilaian Kerentanan: Pendekatan Machine Learning untuk Penargetan Perlindungan Sosial di Indonesia (2013-2025) Muhammad Dawam Amali; Yudha Riwanto
METIK Jurnal Vol. 10 No. 1 (2026): METIK Jurnal Issue Published
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/x8tpdk58

Abstract

Poverty measurements based on static indicators often fail to capture the dynamics of economic vulnerability reflected in changes in consumption patterns over time. This study proposes a machine learning framework to identify the consumption vulnerability profiles of rural households in Indonesia using aggregate per capita expenditure data from the Central Statistics Agency (BPS) for the 2013–2024 period at the expenditure stratum level. The main stage of the analysis was conducted using K-Means clustering to form consumption pattern segments, which were then evaluated using internal validation metrics and compared with the Hierarchical Clustering and Gaussian Mixture Model approaches. The K-Means results at K=3 yielded three consumption profiles: STabel, Volatile, and Extreme, with a Silhouette Score of 0.5474, a Davies-Bouldin Index of 0.6471, and a Calinski-Harabasz Score of 291.57. To evaluate the separability of cluster labels, a Random Forest model was used for supervised validation and achieved an accuracy of 96.84% with a macro-F1 of 0.9552 under a stratified cross-validation scheme. SHAP analysis indicated that expenditure structure, particularly the ratio of non-food to food expenditures, was the most contributing feature in distinguishing cluster profiles. These findings suggest that a consumption-pattern-based approach can provide additional insights in economic vulnerability analysis and support the development of proxy simulations for social protection targeting. However, since this study uses aggregate data at the expenditure stratum level, the results are not intended to determine vulnerability or aid recipients at the individual household level without further validation using microdata.
Design and Development of an Edugame Arabic for Learning Media Yudha Riwanto; Inggrid Yanuar Risca Pratiwi; Asri Wulan Septiana; Fauzia Anis Sekar Ningrum; Ajie Kusuma Wardhana
IJID (International Journal on Informatics for Development) Vol. 12 No. 2 (2023): IJID December
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2023.4297

Abstract

Learning media provides significant advantages to students by improving their learning experience through the use of multimedia applications, resulting in a more engaging and fascinating learning environment while reducing the monotony associated with traditional manual learning techniques. Digital learning material, provides a platform for interesting learning activities, encouraging a delightful and cost-effective learning experience. The impact of learning media is especially noticeable in the subject of the Arabic language. Arabic is traditionally regarded as a difficult language, and many students dislike this language course. However, the Edugame Arabic was created to overcome this issue. Using the GDLC process, which includes phases of initialization, pre-production, production, testing, and publishing. This game-learning application was evaluated through a testing phase that included groups of school students who were actively involved in Arabic language lessons. Edugame Arabic has successfully been installed and runs smoothly on various Android smartphones. Moreover, the game's offline capability allows users to continue their learning without an internet connection. The questionnaire responds, with users strongly agreeing that the app has an appealing design, an intriguing game premise, good material delivery, and considerable aid in learning Arabic. Furthermore, users generally acknowledged that the Edugame is simple to use and helps with vocabulary learning.
Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches Muhammad Ainul Fikri; Ajie Kusuma Wardhana; Yudha Riwanto; Inggrid Yanuar Risca Partiwi; Fauzia Sekar Anis Sekar Ningrum; Iqbal Kurniawan Asmar Putra
IJID (International Journal on Informatics for Development) Vol. 13 No. 2 (2024): IJID December
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2024.4890

Abstract

Osteosarcoma is an aggressive and highly malignant bone cancer primarily affecting adolescents and young adults, with males being more commonly affected. Although deep learning models such as YOLO (95.73% accuracy) and VGG19 (95.25% accuracy), have demonstrated effectiveness in osteosarcoma detection, their large model sizes and extensive computational requirements limit their feasibility in resource-constrained environments. This study proposes a lightweight AI approach that optimizes osteosarcoma detection while maintaining high diagnostic accuracy, leveraging machine learning models under 5MB, manually or semi-automatically extracted features, and SMOTE for data balancing. Experimental results show that Random Forest, SVM, and XGBoost achieve accuracies of 94.70%, 94.23%, and 94.39%, respectively, closely matching the performance of YOLO and VGG19 while maintaining computational efficiency. Furthermore, the inference time for SVM is under one second (0.97s), demonstrating the speed advantage of lightweight models. These findings highlight the potential of small-size (lightweight) machine learning models to deliver high diagnostic accuracy with minimal computational requirements, providing a scalable and practical solution for early osteosarcoma detection in resource-limited settings. By balancing simplicity, efficiency, and high performance, this study establishes a new benchmark for achieving state-of-the-art results with lightweight models and paving the way for improved healthcare accessibility in underserved regions.
Pengembangan Website dan Konten Karang Taruna Rukun Agawe Santosa Ngijo Bantul sebagai Optimalisasi Media Digital: Development of Web Platforms and Digital Content for Karang Taruna Rukun Agawe Santosa Ngijo Bantul as Digital Media Optimization Inggrid Yanuar Risca Pratiwi; Yudha Riwanto; Ajie Kusuma Wardhana; Fauzia Anis Sekar Ningrum; Muhammad Ainul Fikri
Jurnal Pengabdian pada Masyarakat Ilmu Pengetahuan dan Teknologi Terintegrasi Vol. 10 No. 1 (2025): December
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jindeks.v10i1.9093

Abstract

Kegiatan ini bertujuan untuk mengoptimalkan pemanfaatan media digital sebagai sarana informasi, publikasi, dan komunikasi organisasi kepemudaan melalui pengembangan website serta pelatihan manajemen konten bagi Karang Taruna Rukun Agawe Santosa (RAS) Dusun Ngijo, Kabupaten Bantul, Daerah Istimewa Yogyakarta. Permasalahan utama yang dihadapi Karang Taruna RAS meliputi keterbatasan media publikasi kegiatan dan rendahnya kemampuan pengurus dalam mengelola informasi secara digital. Kegiatan dilaksanakan melalui empat tahapan, yaitu observasi dan pengembangan, sosialisasi dan pelatihan, implementasi teknologi dan evaluasi. Website yang dikembangkan memiliki fitur-fitur utama yaitu Manajemen Agenda, Keuangan, Inventaris Perlengkapan, dan Broadcast WhatsApp. Hasil sosialisasi dan pelatihan ini telah berhasil mengembangkan dan menyerahkan website untuk Karang Taruna yang fungsional dan dapat diakses melalui internet kapan saja dan di mana saja. Dari sisi sumber daya manusia, para pengurus Karang Taruna RAS telah menerima transfer pengetahuan melalui pelatihan manajemen konten dan terbukti mampu mengelola website secara mandiri, termasuk mempublikasikan beberapa konten awal pasca-pelatihan. Berdasarkan hasil pengujian UAT terhadap website oleh pengurus dan anggota Karang Taruna RAS  didapatkan nilai rata-rata 97,8%. Hal ini menunjukkan peningkatan kemampuan digital yang signifikan dalam pengelolaan informasi organisasi. Luaran kegiatan ini mencakup website dan buku panduan penggunaan website (manual book) yang diberikan kepada Karang Taruna RAS.
Co-Authors Ajie Kusuma Wardhana Ajie Kusuma Wardhana Ajie Kusuma Wardhana Asri Wulan Septiana Esti Dwi Puspitasari Fauzia Anis Sekar Ningrum Fauzia Sekar Anis Sekar Ningrum Inggrid Yanuar Risca Partiwi Inggrid Yanuar Risca Pratiwi Inggrid Yanuar Risca Pratiwi Iqbal Kurniawan Asmar Putra Muhammad Ainul Fikri Muhammad Ainul Fikri Muhammad Ainul Fikri Muhammad Dawam Amali Raditya Arief Pratama