Article Per Year (5 Year)
p-Index From 2021 - 2026
3.466
P-Index
This Author published in this journals
All Journal Jurnal Sains dan Teknologi Jurnal Simetris JFA (Jurnal Fisika dan Aplikasinya) Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Jurnal Teknologi dan Sistem Komputer JST ( Jurnal Sains Terapan ) Journal of Physics and Its Applications MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer RESISTOR (Elektronika Kendali Telekomunikasi Tenaga Listrik Komputer) Jurnal Nasional Teknologi Terapan Jurnal Listrik, Instrumentasi, dan Elektronika Terapan Journal of Internet and Software Engineering Physical Therapy Journal of Indonesia Emitor: Jurnal Teknik Elektro
Budi Sumanto
Department Of Electrical Engineering And Informatics, Vocational College, UGM, Yogyakarta, Indonesia
Agriculture, Biological Sciences & Forestry Astronomy Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Health Professions Materials Science & Nanotechnology Mathematics Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Other

Published : 26 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 26 Documents
Search

 1   2   3 
Seleksi Fitur Terhadap Performa Kinerja Sistem E-Nose untuk Klasifikasi Aroma Kopi Gayo Budi Sumanto; Denting Romantika Java; Wahyu Wijaya; Jans Hendry
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 21 No. 2 (2022)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v21i2.1495

Abstract

Tujuan dari penelitian ini adalah mengoptimasi kinerja system E-Nose dengan melakukan seleksi fitur untuk memperoleh kombinasi fitur yang terbaik dalam mengklasifikasi aroma jenis kopi arabika Gayo. Kopi ini merupakan salah satu kopi spesial dari Indonesia yang berasal dari Provinsi Aceh. Berbagai faktor dapat mempengaruhi hasil akhir kopi salah satunya pada proses pengolahan pasca panen diantaranya teknik proses kering (drying) dengan metode Natural dan Wine. Perbedaan metode pengolahan pasca panen ini dapat mempengaruhi aroma kopi yang dihasilkan dari setiap kopi yang memiliki aroma dan cita rasa yang khas. Penerapan sistem Electronic Nose (E-Nose) dapat diaplikasikan untuk mengklasifikasi aroma yang berbeda dari jenis kopi Gayo natural dan Gayo wine, namun kesamaan respon sensor dan banyaknya data menyebabkan kurang spesifik dan menurunkan performa kinerja sistem. Implementasi seleksi fitur dapat diterapkan pada proses klasifikasi dengan menggunakan metode Support Vector Machine (SVM) berdasarkan jumlah galat Sum of Absolute Errors (SAE) untuk mendapatkan kombinasi fitur terbaik sehingga mendapatkan kinerja sistem yang lebih optimal. Hasil penelitian ini mendapatkan 5 fitur terbaik dengan nilai akurasi sebesar 93,33%, presisi sebesar 93,33% dan sensitivitas sebesar 93,33%.
Pengembangan Model Machine Learning untuk Deteksi Penyakit Diabetes Menggunakan Analisis Gini Importance Muhammad Aulia Alfarisi; Budi Sumanto; I Putu Fadya Rachmawan
Journal of Internet and Software Engineering Vol 6 No 2 (2025): Journal of Internet and Software Engineering
Publisher : Department of Electrical Engineering and Informatics, Vocational College, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jise.v6i2.16551

Abstract

Diabetes mellitus adalah penyakit yang mengakibatkan kadar gula darah naik dan berpotensi menyebabkan komplikasi yang lebih serius. Skrining diabetes menjadi sangat penting agar tercegahnya terjadi masalah ini. Masalah tersebut dapat diatasi dengan perancangan sistem machine learning untuk memprediksi penyakit diabetes. Penelitian ini bertujuan untuk mengembangkan model klasifikasi machine learning untuk deteksi penyakit diabetes. Lima model klasifikasi seperti Random Forest, Support Vector Machine, Logistic Regression, Linear Discriminant Analysis, dan Artificial Neuron Network dibandingkan untuk menentukan model terbaik dalam memprediksi diabetes. Dataset yang digunakan diambil dari Kaggle dengan nama “Diabetes Prediction Dataset” sebanyak 100.000 data. Hasil Analisis kontribusi fitur menggunakan metode Gini Importance didapatkan hasil yaitu fitur blood_glucose, bmi, dan age merupakan fitur yang paling berkontribusi dalam memprediksi diabetes. Model dilatih menggunakan teknik hybrid resampling dan diuji menggunakan 10-fold cross validation serta pembagian data training (80%) dan data testing (20%). Hasil menunjukkan model Random Forest memiliki akurasi tertinggi sebesar 87%, diikuti oleh Support Vector Machine (86%), Artificial Neuron Network (83%), Logistic Regression (82%), dan Linear Discriminant Analysis (81%). Berdasarkan penelitian ini, model Random Forest dengan metode Gini Importance memberikan performa terbaik untuk deteksi dini diabetes.
Comparison of Supervised Learning Algorithms for Cigarette and Vape Smoke Classification Using Electronic Nose: Muhammad Agung Farghani, Nurul Izzah Wijayakusuma, Budi Sumanto Muhammad Agung Farghani Farghani; Nurul Izzah Wijayakusuma Wijayakusuma; Budi Sumanto Sumanto
Jurnal Fisika dan Aplikasinya Vol 20 No 3 (2024): October 2024 Edition
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat, LPPM-ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24604682.v20i3.17939

Abstract

This research discusses applying the Supervised Learning method using Electronic Nose to classify the types of cigarette and vape smoke in the air. Electronic Nose is used as a scent detector that can identify the characteristics of smoke from both sources. Three Supervised Learning algorithms, namely KNN, SVM, and Decision Tree, were applied to compare the performance in classifying smoke types. The data comprised reference air samples, air contaminated by manufactured cigarette smoke, rolled cigarettes, and vape. The results showed that all three Supervised Learning algorithms successfully provided an excellent classification for cigarette and vape smoke types using data from Electronic Nose. The best accuracy result was achieved by SVM, with an accuracy rate of 96.55%. This research contributes to identifying sources of air pollution that have the potential to endanger human health
Engineering of Organic Photodetector For Visible Light Detection By Vacuum Thermal Deposition Method: Chairadeya Chairadeya, Budi Sumanto, Richie Estrada, Sajal Biring, Shun-Wei Liu Chairadeya Chairadeya; Budi Sumanto Budi Sumanto; Richi Estrada Richi Estrada; Sajal Biring Sajal Biring; Shun-Wei Liu Shun-Wei Liu
Jurnal Fisika dan Aplikasinya Vol 20 No 1 (2024): January 2024 Edition
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat, LPPM-ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24604682.v20i1.17927

Abstract

This study aimed to determine the correlation between the photoactive layer thickness of an organic photodetector device and its performance. This research engineered organic photodetectors using zinc phthalocyanine (ZnPc) and fullerene (C60) as photoactive layers for detecting visible light using the vacuum thermal deposition method. Fabrication of organic photodetectors is done by varying the thickness of the photoactive layer at the same ratio. Of the four engineered organic photodetector variations, an active layer thickness of 90 nm produced the best organic photodetector performance. This photodetector has a dark current density of 1.43 × 10-6 A cm-2, a photocurrent density of 6.19 × 10-4 A cm-2, an external quantum efficiency (EQE) of 73.48% at a wavelength of 630 nm, with a responsivity of 0.39 A W-1 at a bias voltage of -3 V.
Development of therapy aids with electromyography technology for post-stroke patients Savitri Citra Budi; Budi Sumanto; Lilik Dwi Setyana; Prima Asmara Sejati; Siti Alimah
Physical Therapy Journal of Indonesia Vol. 6 No. 2 (2025): July-December 2025
Publisher : Universitas Udayana dan Diaspora Taipei Medical University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51559/ptji.v6i2.319

Abstract

Background: The prevalence of stroke in Indonesia has been increasing and has had a significant impact on individuals, families, and society. There is a pressing need for innovative assistive devices that support independent therapy and enhance patient motivation to improve post-stroke productivity. This study aimed to design and develop a post-stroke rehabilitation assistive device utilizing electromyography (EMG) technology. Methods: This study employed a research and development (R&D) design. Data were collected through documentation studies, interviews with physiotherapists, observations, and focus group discussions (FGDs). A documentation study was conducted using the medical records of stroke patients. Interviews were conducted with physiotherapists, and observations were carried out to understand patients’ therapeutic activities. Results: This study provided alternative therapy by developing post-stroke rehabilitation aids with EMG technology. Based on the documentation study, 88% of patients experienced ischemic stroke with a good level of consciousness (E4V5M6), indicated by the Glasgow Coma Scale (GCS) score of 15. Conclusion: This phenomenon supported the development of electrical therapy innovations to accelerate stroke recovery. This study successfully designed a hand therapy device using EMG technology to improve patients’ motor function, particularly among those with E4V5M6 levels of consciousness and limited motor skills.
Environmental Compensation for Robust Tea Aroma Classification Based on an Electronic Nose and Machine Learning Budi Sumanto; Ummi Kaltsum; Galih Setyawan; Ganjar Alfian; Dzulkifli Daeng Syauqi; Ariesta Martiningtyas Handayani; Kombo Othman Kombo
Journal of Physics and Its Applications Vol 8, No 3 (2026): August 2026
Publisher : Diponegoro University Semarang Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jpa.v8i3.33779

Abstract

Classifying tea aromas using an electronic nose (e-nose) system offers rapid, non-destructive quality assessment. However, metal oxide semiconductor (MOS)-based gas sensors are often affected by temperature and humidity, reducing classifier robustness. To address this, we propose an environmental compensation approach to boost robustness in machine learning-based tea aroma classification. Specifically, we analyzed 400 tea samples (100 per class: black, green, red, yellow) using an e-nose with 10 MOS sensors under three scenarios: (A) sensor features only, (B) integration of temperature–humidity features, and (C) temperature–humidity-based signal compensation before feature extraction. For classification, we used SVM, Random Forest, KNN, and a soft voting ensemble. Notably, Scenario C performed best, achieving 85.00% accuracy with SVM. Furthermore, robustness analysis revealed that KNN led on test data (RI=0.9851), while SVM was perfect in cross-validation (RI=1.000). These results confirm that environmental compensation effectively improves the MOS e-nose system stability.
Co-Authors Abelta Mika Setiarini Alfonzo Aruga Paripurna Barus Ariesta Martiningtyas Handayani Biring, Sajal Budianto, Hendi Chairadeya Chairadeya Chairadeya, Chairadeya Denting Romantika Java Dzulkifli Daeng Syauqi Farghani, Muhammad Agung Fiddariani, Agritian Sevty Galih Setyawan Ganjar Alfian Hendry, Jans HENDRY, JANS Humaira, Shafura I Putu Fadya Rachmawan Idianingrum TW, Yessi Iman Sabarisman IRSYADI, FAKIH Jans Hendry Kombo Othman Kombo Lestari Budiani, Ratna Lilik Dwi Setyana Liu, Shun-Wei Muhammad Agung Farghani Farghani Muhammad Arrofiq Muhammad Aulia Alfarisi Muhammad Fakhrurrifqi Muhammad Fakhrurrifqi NATHASYA, IOTA NUGROHO, ADHITYA ALVIAN Nurul Izzah Wijayakusuma Wijayakusuma P, Matthew Sebastian Pramesti, Risma Diyah Prima Asmara Sejati Purnomo Aji, Alief Putri Mawaring Wening Ramdani Febrian Rella Mareta Rendra Dwi Firmansyah Richi Estrada Richi Estrada Richie Estrada Rifai, Isnan Nur Ruciyanti, Febrian Sajal Biring Sajal Biring Salima Nurrahma Santoso, Ardhi Wicaksono Savitri Citra Budi Setiarini, Abelta Mika Shun-Wei Liu Shun-Wei Liu Siti Alimah Ummi Kaltsum Wahyu Sabani Wahyu Wijaya Wijaya, Wahyu Wijayakusuma, Nurul Izzah Yoga Mileniandi