Article Per Year (5 Year)
p-Index From 2021 - 2026
2.177
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Jupiter Annual Research Seminar Sistemasi: Jurnal Sistem Informasi Dinamisia: Jurnal Pengabdian Kepada Masyarakat Journal of Information Technology and Computer Engineering Jurnal Generic Journal of Electrical, Electronic, Information, and Communication Technology (JEEICT) Jurnal Mandiri IT Nuansa Informatika
Rahmat Fadli Isnanto
Computer Systems Universitas Sriwijaya Palembang, Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mathematics Social Sciences Other

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Performance analysis of MobileNetV2 based automatic waste classification using transfer learning Firnando, Ricy; Buchari, Muhammad Ali; Marjusalinah, Anna Dwi; Willy; Abdurahman; Isnanto, Rahmat Fadli
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.451

Abstract

The significant increase in global waste requires innovative and accessible solutions, which aligns with Sustainable Development Goal (SDG) 12, which focuses on reducing the environmental impact of human activities. Automatic waste sorting using Computer Vision and Deep Learning offers a promising alternative to labor-intensive and risky manual methods. This study presents the design, implementation, and comprehensive performance analysis of an automated waste classification system, with a specific focus on evaluating its feasibility on hardware without specialized GPU accelerators. By leveraging transfer learning on a lightweight Convolutional Neural Network (CNN) architecture, MobileNetV2, a model was trained to classify six common waste categories: cardboard, glass, metal, paper, plastic, and other waste. The public “Garbage Classification” dataset from Kaggle, consisting of 2,527 images, was used as the basis for training and validation. The experiment was conducted using the tensorflow-cpu library, which does not require a dedicated GPU accelerator. After 10 training epochs, the model achieved a significant validation accuracy of 86.73%. Computational performance analysis showed an efficient average training time of 31.17 seconds per epoch and a fast average inference time of 14.47 milliseconds per image (~69 FPS) on the validation dataset. These findings demonstrate the feasibility of developing an effective AI-based waste classification system on hardware without a GPU accelerator, providing a realistic performance benchmark for the development of low-cost smart bins with embedded waste sorting solutions in the future, thereby contributing to sustainable waste management practices.
Scheduling Information System at SMA N 1 Madang Rasuan OKU Timur Kurniawan*, Dedy; Passarella, Rossi; Sutarno, Sutarno; Rifai, Ahmad; Isnanto, Rahmat Fadli; Ubaya, Huda; Exaudi, Kemahyanto; Sari, Purwita; Hanifah, Izzati Millah; Perdani, Tharisa Antya
Dinamisia : Jurnal Pengabdian Kepada Masyarakat Vol. 8 No. 1 (2024): Dinamisia: Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/dinamisia.v8i1.18009

Abstract

The development of technology and information systems is currently so rapid, especially after the corona pandemic era, everything began to use technological assistance, not spared until the elements of the school were required to use technology as a means of learning, one of the considerations of the school in using technology including as a schedule management system. In this website-based scheduling application system for SMAN 1 Madang Suku 1, the author and co-author create a scheduler application that can easily manage schedules that already have integrated data between subjects, teachers, majors, classes at school. the purpose of making this application system is to increase efficiency in the process of scheduling classes and rooms at SMA 1 Madang Rasuan OKU Timur, and also make it easier for students to access the required schedule so that the schedule does not have to be taken at school again. The final result of this research is to produce a web-based application program that can help teachers or school admins to create and manage subject schedules with a good appearance and equipped with various features so that the subject scheduling process becomes more efficient and organized.
TinyML-Based Stress Detection Using Time-Domain HRV Features and a Lightweight DNN on ESP32: Deteksi Stres Berbasis TinyML Menggunakan Fitur HRV Domain Waktu dan DNN Ringan pada ESP32 Sarmayanta Sembiring; Kemahyanto Exaudi; Abdurahman -; Jorena; Hadir Kaban; M. Buffon Prima; Rahmat Fadli Isnanto
NUANSA INFORMATIKA Vol. 20 No. 2 (2026): Nuansa Informatika 20.2 July 2026
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v20i2.624

Abstract

Stress is a psychophysiological condition that requires continuous and objective monitoring. However, existing wearable stress detection systems often rely on cloud-based processing or computationally intensive algorithms, limiting their applicability for real-time inference on resource-constrained embedded devices. This study presents a TinyML-based framework for real-time stress detection using the MAX30102 sensor and an ESP32 microcontroller. The proposed framework integrates four time-domain Heart Rate Variability (HRV) features (BPM, SDNN, RMSSD, and pNN50), a lightweight Deep Neural Network (DNN), full INT8 TensorFlow Lite quantization, and on-device inference to enable efficient edge-based stress classification. The DNN model was trained and evaluated using the WESAD dataset. Experimental results showed that a decision threshold of 0.70 yielded the best classification performance, achieving an accuracy of 82% and an F1-score of 0.63 for the stress class. The quantized TensorFlow Lite INT8 model preserved 100% prediction compatibility between the Python and ESP32 implementations. Furthermore, the MAX30102 sensor achieved a BPM measurement accuracy of 98.74%, while the HRV feature extraction implemented on the ESP32 produced results consistent with the reference calculations. These findings demonstrate that the proposed end-to-end TinyML framework enables accurate and computationally efficient HRV-based stress detection on resource-constrained microcontrollers, providing a practical foundation for real-time wearable edge-health monitoring
Performance Evaluation of a Cloud-Integrated IoT Hydroponic System Using Firebase Realtime Database and Netlify Web Dashboard Ricy Firnando; Prita Salma; Dwi Aurelia Rahmadani; Kemahyanto Exaudi; Rahmat Fadli Isnanto; Andre Hardoni
Journal of Electrical, Electronic, Information, and Communication Technology Vol 8, No 1 (2026): JOURNAL OF ELECTRICAL, ELECTRONIC, INFORMATION, AND COMMUNICATION TECHNOLOGY
Publisher : Universitas Sebelas Maret (UNS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/jeeict.8.1.118597

Abstract

Smart hydroponic monitoring often relies on third-party mobile applications and faces hardware limitations regarding analog pins on microcontrollers when acquiring data from multiple sensors. Furthermore, technical evaluations regarding the stability of data transmission to the cloud and the response speed of simultaneous sensor readings are rarely discussed. This study aims to evaluate the functionality and responsiveness of hardware integration with the cloud in a hydroponic smart showcase prototype. The NodeMCU ESP8266 microcontroller is used as the central processing unit. To overcome the analog pin limitation for water quality sensors (pH and TDS), the system is integrated with a CD4051BE IC multiplexer. Environmental and nutritional data are transmitted using the API protocol to the Firebase Realtime Database and visualized through a Netlify-hosted web dashboard interface, eliminating mobile application dependency. The high-speed multiplexing mechanism with a 40 ms recording interval was tested over 30 repeated trials per buffer solution. The transient response test recorded a mean error of 0.58 % (SD = 0.27 %) for pH 4.01 solution and 1.21 % (SD = 0.52 %) for pH 6.86 solution. Furthermore, a 10‑hour network stability test (100 samples per sensor) proved that logging transmission to the database ran persistently without packet loss, with average environmental reading errors below 1 % and Wi‑Fi RSSI fluctuations between –45 and –62 dBm. This system demonstrates that a cloud‑based pure web architecture can provide more independent, responsive, and stable IoT control monitoring.
Co-Authors A. Noviar Satria Mukti Abdurahman Abdurahman - Adi Hermansyah, Adi Aditya Putra Perdana Prasetyo Ahmad Rifai andre hardoni Ariansyah Saputra Asvi, M. Fauzi Bayu Wijaya Putra Buchari, M. Ali Buchari, Muhammad Ali Dedy Kurniawan Dudifa, Aldi Dwi Aurelia Rahmadani Fathoni - Hadir Kaban Haidar, Rosali Hanifah, Izzati Millah Huda Ubaya Huda Ubaya Jorena Kemahyanto Exaudi M. Buffon Prima M. Rudi Sanjaya Marjusalinah, Anna Dwi Muhammad Naufal Rachmatullah Nabillah Syafitri Novi Yusliani Osvari Arsalan Perdani, Tharisa Antya Prita Salma Purwita Sari Purwita Sari, Purwita Ricy Firnando Ricy Firnando Riyuda, Rafki Sahasika Rizki Kurniati Rizki Ramadandi Rossi Passarella Sarmayanta Sembiring Sarmayanta Sembiring Sitorus, Harlis Richard Sukemi Sutarno Sutarno Syamsuryadi Syamsuryadi Vindriani, Marsella Willy