Article Per Year (5 Year)
p-Index From 2021 - 2026
8.208
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Teknoin Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jupiter TRANSIENT: Jurnal Ilmiah Teknik Elektro Coding: Jurnal Komputer dan Aplikasi Telematika : Jurnal Informatika dan Teknologi Informasi Jurnal Edukasi dan Penelitian Informatika (JEPIN) Jurnal Informatika dan Teknik Elektro Terapan CESS (Journal of Computer Engineering, System and Science) ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika CYBERNETICS BULETIN AL-RIBAATH Digital Zone: Jurnal Teknologi Informasi dan Komunikasi JURIKOM (Jurnal Riset Komputer) Indonesian Journal of Applied Informatics Jurnal Informatika dan Rekayasa Elektronik Abdi: Jurnal Pengabdian dan Pemberdayaan Masyarakat JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Computer System and Informatics (JoSYC) Jurnal Teknologi dan Sistem Tertanam JUSTIN (Jurnal Sistem dan Teknologi Informasi) Jurnal Informatika Polinema (JIP) Journal of Fuzzy Systems and Control (JFSC) Mekongga: Jurnal Pengabdian Masyarakat
Tedy Rismawan
Jurusan Rekayasa Sistem Komputer, Fakultas MIPA Universitas Tanjungpura
Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Mechanical Engineering Medicine & Pharmacology Public Health Social Sciences Other

Published : 82 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 82 Documents
Search

 5   6   7   8   9 
Imbalance Handling Strategies for Predictive Maintenance Under Leakage-Free Factorial Evaluation Tedy Rismawan; Irma Nirmala
Journal of Fuzzy Systems and Control Vol. 4 No. 1 (2026): Vol. 4 No. 1 (2026)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/jfsc.v4i1.399

Abstract

Predictive maintenance (PdM) in industrial manufacturing relies on machine learning classifiers trained on severely imbalanced sensor data, where failure events represent a small minority of observations. This study presents a controlled factorial experiment evaluating five algorithms (Decision Tree, Random Forest, SVM, XGBoost, and Logistic Regression) against four imbalance handling strategies (no handling, SMOTE, ADASYN, and class weighting) across binary and six-class failure mode identification tasks on the AI4I 2020 dataset (10,000 observations, 3.39% failure rate), yielding 40 experimental conditions. All oversampling steps were integrated within an ImbPipeline to prevent data leakage across cross-validation folds. Statistical comparisons were conducted via the Friedman test, post-hoc Nemenyi analysis, and one-tailed Wilcoxon signed-rank tests. XGBoost with no handling achieved the highest performance in both tasks (binary F1 = 0.8952; multiclass F1 = 0.6084). Contrary to common practice, no handling method outperformed SMOTE or ADASYN across four of five algorithms in the binary task (Wilcoxon, p = 0.0312), while class weighting improved macro recall from 0.8448 to 0.8908 without significant F1 degradation. Per-class analysis showed that heat dissipation, power, and overstrain failures were reliably detected (F1 > 0.82), while tool wear and random failures remained undetectable. In the multiclass task, ADASYN and XGBoost class weighting were replaced by SMOTE due to instability with extreme minority classes. These findings demonstrate that synthetic oversampling is not universally beneficial for imbalanced PdM data, and that leakage-free experimental design is essential for reliable performance estimation. Practitioners are advised to benchmark no handling and class weighting before applying synthetic oversampling in PdM deployments.
Sistem Identifikasi Jenis Tumbuhan Mangrove Menggunakan Metode Convolutional Neural Network (CNN) Samudra, Imam; Rismawan, Tedy; Nirmala, Irma
IJAI (Indonesian Journal of Applied Informatics) Vol 10, No 1 (2025)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v10i1.109260

Abstract

Abstrak : Mangrove merupakan tumbuhan pesisir yang berperan penting dalam menjaga keseimbangan ekosistem. Penelitian ini bertujuan membangun sistem identifikasi jenis tumbuhan mangrove berbasis citra daun dengan metode Convolutional Neural Network (CNN) untuk memudahkan dalam mengidentifikasi jenis mangrove. Dataset yang digunakan terdiri dari 810 citra daun mangrove, masing-masing 270 citra untuk tiga kelas: Acanthus Ilicifolius, Rhizophora Apiculata, dan Sonneratia Alba. Proses pelatihan model CNN dilakukan untuk mengenali pola dan karakteristik visual daun. Pengujian dilakukan menggunakan 81 data uji dengan dua skenario pengujian, yaitu tanpa menggunakan kamera Raspberry Pi dan dengan integrasi kamera Raspberry Pi. Hasil pengujian tanpa kamera Raspberry Pi mendapatkan akurasi 88%, sedangkan menggunakan kamera Raspberry Pi mencapai 96%. Peningkatan akurasi sebesar 8% membuktikan bahwa penerapan sistem pada perangkat keras Raspberry Pi mampu meningkatkan kinerja identifikasi. Selain itu, sistem dapat beroperasi secara portabel tanpa memerlukan koneksi internet, sehingga berpotensi untuk mengidentifikasi mangrove secara mudah di lapangan.=================================================Abstract : Mangroves are coastal plants that play an important role in maintaining ecosystem balance. This study aims to build a mangrove plant species identification system based on leaf images using the Convolutional Neural Network (CNN) method to facilitate the identification of mangrove species. The dataset used consists of 810 mangrove leaf images, 270 images each for three classes: Acanthus Ilicifolius, Rhizophora Apiculata, and Sonneratia Alba. The CNN model training process was carried out to recognize leaf patterns and visual characteristics. Testing was carried out using 81 test data with two test scenarios, namely without using a Raspberry Pi camera and with Raspberry Pi camera integration. The test results without a Raspberry Pi camera achieved 88% accuracy, while using a Raspberry Pi camera reached 96%. The 8% increase in accuracy proves that the implementation of the system on Raspberry Pi hardware is able to improve identification performance. In addition, the system can operate portable without requiring an internet connection, thus having the potential to easily identify mangroves in the field.
Co-Authors AA Sudharmawan, AA Ananda, Muharam Rizqi Andika Eka Putra Andre, Hendrikus Anita Sulvia Ardhitya Wiedha Irawan Asrul Gunawan Aulia Amin, Muhammad Azmi AYU WARDANI, AYU Bariandi, Muhammad Rizki Cucu Suhery Damiyanto, Edwan Dedi Triyanto Dedi Triyanto Desyandri Desyandri Dwi Marisa Midyanti Fikri Alwan Ramadhan Fioni Puspa Sari Firdaus, Sabang Fratama, Indra Sukma Hafidza Nur 'Ainika Rani Hafiz Muhardi Herry Sujaini Hirzen Hasfani Hutomo Sakti Kartiko Ikhwan Ruslianto Irma Nirmala Irvan Denata Irwan Argi Himawan Kartika Sari Kartika Sari Kasliono Kasliono Kustiati Kustiati M Agus Prastyio Marisa Midyanti, Dwi Maulidia Utami Muhamad Reksy Mulia Muhammad Luthfi Mulyana, Dandi Nia Handayani Nugra Zurus Pratama Prastika, Ranny Prawira Putra, Dhany Putra, Ade Mandala Putri, Nabila Adinda Dwi Rahmi Hidayati Randily, Dhea Ramadhanti Putri Rasyid HS, Zubair Retno Vipyana Suryani Ridho Prabowo Rizky Risan R Rizky, Sri Sabang Firdaus Salma Salsabilla Sampe Hotlan Sitorus Samudra, Imam Sibarani, Yohana Oktavia Sri Hartati Sri Kusumadewi Suhardi Suhardi Suhardi Suhardi Suprayoga, Rifqi Dwi Surayya Safira Milania Syamsul Bahri Syamsul Bahri Trianny Syantikha Uray Ristian Utami, Retnaning Tyas Vidyana, Irma WAHYU PRABOWO Yunizar, Ahmad