Article Per Year (5 Year)
p-Index From 2021 - 2026
1.8
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Ilmu Komputer dan Informasi Indonesian Journal of Information System Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming Jurnal Teknik Informatika (JUTIF) Jurnal Pengabdian Masyarakat : Pemberdayaan, Inovasi dan Perubahan Jurnal Masyarakat Madani Indonesia Jurnal Sistem Informasi Galuh Jati Emas (Jurnal Aplikasi Teknik dan Pengabdian Masyarakat) IJCOSIN : Indonesian Journal of Community Service and Innovation
Muhammad Raafi'u Firmansyah
Telkom University
Religion Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mechanical Engineering Public Health Social Sciences Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Analisa Slope Wilayah Kebakaran Hutan menggunakan Metode Naive Bayes Lisda; Isnaeni, Nenen; Firmansyah, Muhammad Raafi'u
Jurnal Sistem Informasi Galuh Vol 2 No 2 (2024): Journal of Galuh Information Systems
Publisher : Fakultas Teknik Jurusan Sistem Informasi Universitas Galuh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25157/jsig.v2i2.3934

Abstract

Forest and land fires are an economic and environmental problem that can cause serious damage. We can predict what factors cause forest fires. It is undeniable that topographical conditions affect the triggering and propagation of fires. The topographical condition itself is in the form of a slope, where fire propagation will be faster when going up the slope than going down the slope. This study aims to match whether the slope and display locations that are prone to the spread of certain fires with high fire intensity actually have a high fire potential and report the magnitude of the influence of the slope in the prediction of fire potential. One of the common approaches to classifying data is to use data mining. So in this study the researchers used the Naive Bayes Classifier as a classification method by getting the highest accuracy value of 0.99%.
Elevasi Brand “LIMPUS” Melalui Kreativitas Digital: Program Pelatihan Konten Media Sosial dan Video Promosi Aldo, Dasril; Nur, Yohani Setiya Rafika; Lishobrina, Lina Fatimah; Firmansyah, Muhammad Raafi'u; Sulaeman, Gilang; Fathoni, M. Yoka
Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming Vol 7, No 3 (2024): Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstormin
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/japhb.v7i3.6786

Abstract

Dalam upaya meningkatkan kesadaran dan partisipasi masyarakat terhadap literasi serta pelestarian lingkungan melalui platform digital, program "Elevasi Brand 'Limbah Pustaka' Melalui Kreativitas Digital" telah dilaksanakan. Program dua hari ini dirancang untuk mengasah keterampilan digital para peserta, meliputi pengenalan dan praktik pembuatan konten media sosial dan video. Hari pertama fokus pada pengenalan YouTube, podcast, dan peran content creator, dilanjutkan dengan praktik pembuatan channel YouTube dan pengelolaan video yang efektif, termasuk pengambilan dan editing video. Hari kedua mengedepankan pentingnya kesadaran lingkungan melalui media digital, pengenalan Canva, serta praktik pembuatan poster dan konten visual lainnya. Hasil dari program ini menunjukkan peningkatan signifikan dalam kemampuan peserta dalam mengelola konten digital yang kreatif dan informatif, sekaligus meningkatkan branding dan visibilitas 'Limbah Pustaka' dalam masyarakat luas. Program ini menunjukkan bahwa dengan pelatihan yang tepat, teknologi digital dapat menjadi alat yang efektif untuk promosi dan edukasi publik terkait isu-isu penting seperti literasi dan pelestarian lingkungan.
Peningkatan Gaya Hidup Sehat Anak melalui Edukasi Pencegahan Diabetes Berbasis Multimedia Interaktif di Purbalingga Paramadini, Adanti Wido; Aldo, Dasril; Nur, Yohani Setiya Rafika; Firmansyah, Muhammad Raafi'u; Sa'adah, Aminatus; Fathan, Faizal Burhani Ulil; Sulaeman, Gilang; Faiz, M. Hanif Al; Hidayat, Afifah Naurah; Maulana, Ihsan; Fau, Andrew; Yasin, Feri; Suprapto, Amelia Rut; Muadin, Dika Alim
Jurnal Pengabdian Masyarakat: Pemberdayaan, Inovasi dan Perubahan Vol 5, No 4 (2025): JPM: Pemberdayaan, Inovasi dan Perubahan
Publisher : Penerbit Widina, Widina Media Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59818/jpm.v5i4.1685

Abstract

The incidence of type 2 diabetes mellitus among children is rising due to poor dietary habits and lack of physical activity from an early age. Health education remains suboptimal, especially in areas with limited access to health information. This community service activity aimed to raise awareness and understanding among elementary school children and their parents regarding early diabetes prevention through multimedia-based educational technology. The method used included interactive counseling, sugar content demonstrations in food, introduction of the Diabetes Detective educational app, and blood glucose screening using a digital glucometer. The activity took place in Muntang Village, Purbalingga, involving 30 children and 25 parents. Results showed an increase in children’s understanding from 49.5% (pre-test) to 85.5% (post-test), while 92% of parents stated the media was easy for children to understand. Children’s average blood glucose level was normal (92.5 mg/dL), while four parents were in the prediabetic range. The activity demonstrates that an interactive, contextual educational approach can enhance health literacy and promote healthy habits in families. This model can be replicated as a preventive strategy using digital technology in other regions.ABSTRAKKasus diabetes mellitus tipe 2 pada anak-anak meningkat seiring pola makan buruk dan kurangnya aktivitas fisik sejak dini. Edukasi mengenai gaya hidup sehat masih belum optimal, terutama di daerah dengan akses informasi kesehatan terbatas. Kegiatan pengabdian ini bertujuan meningkatkan kesadaran dan pemahaman anak-anak sekolah dasar serta orang tua mengenai pencegahan dini diabetes melalui media edukasi berbasis teknologi multimedia. Metode yang digunakan adalah penyuluhan interaktif, demonstrasi kandungan gula pada makanan, pengenalan aplikasi edukatif Diabetes Detective, dan pemeriksaan gula darah menggunakan glukometer digital. Kegiatan dilaksanakan di Desa Muntang, Purbalingga, dengan melibatkan 30 anak dan 25 orang tua. Hasil menunjukkan peningkatan pemahaman anak dari rata-rata 49,5% (pre-test) menjadi 85,5% (post-test), dan 92% orang tua menyatakan media mudah dipahami. Rata-rata kadar gula darah anak normal (92,5 mg/dL), sedangkan empat orang tua berada pada kategori prediabetes. Kegiatan ini membuktikan bahwa pendekatan edukatif yang interaktif dan kontekstual dapat meningkatkan literasi kesehatan anak dan keluarga serta dapat direplikasi sebagai strategi preventif berbasis teknologi di wilayah lain.
Multivariate Forecasting of Paddy Production: A Comparative Study of Machine Learning Models Yasin, Feri; Firmansyah, Muhammad Raafi'u; Aldo, Dasril; Amrustian, Muhammad Afrizal
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 3 (2025): JUTIF Volume 6, Number 3, Juni 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.3.4681

Abstract

Accurate rice production forecasting plays an important role in supporting national food security planning. This study aims to evaluate the performance of four machine learning algorithms, namely Random Forest, XGBoost, Support Vector Regression (SVR), and Linear Regression, in predicting three target variables simultaneously: harvest area, productivity, and production. The dataset used includes annual data per province in Indonesia from 2018 to 2024 obtained from the Central Statistics Agency (BPS). Evaluation was conducted using five metrics: MAE, RMSE, MAPE, R², and training time. The results of the experiment showed that the Random Forest Regressor performed best in the 80:20 scenario, with an MAE of 76,259.52, an RMSE of 154,036.91, a MAPE of 0.61%, and an R² of 0.997. XGBoost showed a competitive performance with an MAE of 79,381.44 and faster training times. In contrast, the SVR showed the worst performance with the MAPE reaching 198.56% and the R² of 0.209. Linear Regression as baseline recorded an MAE of 1,194,355.28 and an R² of 0.503, indicating that the linear model is not effective enough for this data. The 80:20 scenario is considered the best configuration because it is able to balance the accuracy and generalization of the model. These findings show that the use of ensemble algorithms, especially Random Forest and XGBoost, has the potential to be applied practically by agricultural agencies or local governments in designing data-driven policies for more proactive and predictive rice production management. Furthermore, this study contributes to the advancement of applied informatics by demonstrating how machine learning models can be effectively used in multivariate forecasting for complex, real-world problems, thereby supporting the development of intelligent decision-support systems in the agricultural domain.
Exploring bibliometric trends in speech emotion recognition (2020-2024) Rosita, Yesy Diah; Firmansyah, Muhammad Raafi'u; Utami, Annisaa
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp3421-3434

Abstract

Speech Emotion Recognition (SER) is crucial in various real-world applications, including healthcare, human-computer interaction, and affective computing. By enabling systems to detect and respond to human emotions through vocal cues, SER enhances user experience, supports mental health monitoring, and improves adaptive technologies. This research presents a bibliometric analysis of SER based on 68 articles from 2020 to early 2024. The findings show a significant increase in publications each year, reflecting the growing interest in SER research. The analysis highlights various approaches in preprocessing, data sources, feature extraction, and emotion classification. India and China emerged as the most active contributors, with external funding, particularly from the NSFC, playing a significant role in the advancement of SER research. SVM remains the most widely used classification model, followed by KNN and CNN. However, several critical challenges persist, including inconsistent data quality, cross-linguistic variability, limited emotional diversity in datasets, and the complexity of real-time implementation. These limitations hinder the generalizability and scalability of SER systems in practical environments. Addressing these gaps is essential to enhance SER performance, especially for multimodal and multilingual applications. This study provides a detailed understanding of SER research trends, offering valuable insights for future advances in speech-based emotion recognition.
Peningkatan Literasi dan Kepedulian Lingkungan Anak melalui Program Penukaran Sampah dengan Buku dan Mainan Edukasi di Desa Muntang Dasril Aldo; Muhammad Raafi'u Firmansyah; Evia Zunita Dwi Pratiwi; Yohani Setiya Rafika Nur; Angga Kurniawan; Affriza Brilyan Relo Pambudi Agus Putra
Jurnal Masyarakat Madani Indonesia Vol. 4 No. 4 (2025): November
Publisher : Alesha Media Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59025/e1jfeb45

Abstract

Rendahnya literasi dan kepedulian lingkungan pada anak-anak di wilayah pedesaan masih menjadi permasalahan utama, termasuk di Desa Muntang, Kabupaten Purbalingga. Kurangnya akses terhadap bahan ajar interaktif dan minimnya kebiasaan memilah sampah menyebabkan anak-anak belum memiliki perilaku ramah lingkungan yang konsisten. Kegiatan pengabdian kepada masyarakat ini bertujuan meningkatkan literasi dan kesadaran lingkungan anak usia 4–6 tahun melalui program penukaran sampah dengan buku dan mainan edukatif. Program dilaksanakan oleh dosen dan mahasiswa Universitas Telkom Purwokerto bekerja sama dengan Komunitas Limbah Pustaka menggunakan pendekatan pembelajaran berbasis pengalaman (learning by playing) dan sistem penghargaan (reward-based learning). Sebanyak 35 anak mengikuti kegiatan yang mencakup sesi dongeng interaktif, penukaran sampah anorganik seperti plastik dan kertas dengan buku bergambar, serta permainan edukatif bertema lingkungan. Hasil kegiatan menunjukkan 88,6% anak fokus mendengarkan cerita, 85,7% mampu memilah sampah dengan benar, dan 94,3% aktif dalam permainan edukatif. Anak-anak menunjukkan peningkatan antusiasme dan pemahaman terhadap kebersihan lingkungan. Program ini terbukti efektif menumbuhkan perilaku pro-lingkungan sejak dini dan berkelanjutan melalui pembentukan Pojok Literasi Hijau di Desa Muntang.
Sistem Irigasi Tetes Berbasis IoT dan Pengendalian Hama untuk Produktivitas Optimal di Lahan Kering (INOTANI) Aulia Desy Nur Utomo; Anggi Zafia; Muhammad Raafi'u Firmansyah; Anisah Syifa Mustika Riyanto; Ibnu Rizal Mutaqim; Muhammad Aulia Muzzaki Nugraha
Indonesian Journal of Community Service and Innovation Vol. 5 No. 3 (2025): Desember 2025
Publisher : LPPM IT Telkom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/ijcosin.v5i3.9866

Abstract

Program INOTANI: Sistem Irigasi Tetes Berbasis IoT dan Pengendalian Hama untuk Produktivitas Optimal di Lahan Kering Desa Sudagaran, Banyumas, Jawa Tengah, merupakan solusi inovatif untuk mengatasi tantangan yang dihadapi oleh para petani di daerah tersebut. Desa Sudagaran terletak di wilayah yang terkena dampak perubahan iklim, yang ditandai dengan musim kemarau panjang dan curah hujan yang tidak teratur. Hal ini mengakibatkan lahan pertanian mengalami kekeringan, yang mempengaruhi produktivitas tanaman. Selain itu, serangan hama seperti bakteri dan virus juga memperburuk kondisi pertanian. INOTANI hadir untuk menjawab permasalahan tersebut dengan memanfaatkan teknologi sistem irigasi tetes berbasis Internet of Things (IoT). Dengan demikian, petani dapat mengoptimalkan penggunaan air dengan jumlah yang tepat sesuai dengan kebutuhan tanaman. Teknologi ini juga menggunakan energi bersih dari panel surya untuk menjalankan pompa air dan sistem irigasi, yang dapat mengurangi biaya operasional dan ketergantungan pada sumber daya energi konvensional. Program ini diimplementasikan melalui kemitraan antara masyarakat, kelompok tani "Sida Waras" dan "Sida Makmur", perangkat desa, serta mahasiswa yang terlibat dalam pengembangan dan pelatihan sistem.
Adaptive Integration of Distributed Deep Q-Networks for Enhancing OLSR Routing in Dynamic Mobile Ad-Hoc Networks Alon Jala Tirta Segara; Arief Rais Bahtiar; Muhammad Raafi'u Firmansyah; Fahrudin Mukti Wibowo
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.11760

Abstract

Adaptive routing in Mobile Ad-Hoc Networks (MANETs) poses considerable difficulty owing to the network's dynamic characteristics, lack of stable infrastructure, and swift topology alterations. The Optimized Link State Routing (OLSR) protocol provides a proactive routing mechanism via topology dissemination and MultiPoint Relay (MPR) selection. Nevertheless, it exhibits diminished responsiveness to real-time topology alterations, as it depends on periodic updates and does not explicitly account for link quality. This paper suggests the incorporation of the Deep Q-Network (DQN) methodology into OLSR as a reinforcement learning strategy to improve routing adaptability and efficiency. The DQN model employs network metrics like latency, ETX, buffer occupancy, and neighbor count as state inputs, with actions determined by Q-values obtained via environmental interactions. Simulations conducted with NS-3 and PyTorch demonstrate that OLSR-DQN enhances Packet Delivery Ratio (PDR) by as much as 20%, decreases delay by 15–25%, and markedly boosts throughput in dynamic MANET situations. Keywords: MANET, OLSR, Deep Q-Network, adaptive routing, reinforcement learning
Comparative Analysis of Hyperparameter Optimization Methods for LSTM in Cryptocurrency Price Prediction: An Application to TRX–USD Aldo, Dasril; Firmansyah, Muhammad Raafi'u; Amrustian, Muhammad Afrizal
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.3.5355

Abstract

The rapid growth of cryptocurrencies increases the demand for accurate forecasting models to support investment decisions and automated trading systems. This study analyzes and compares the performance of several hyperparameter optimization methods applied to a Long Short-Term Memory (LSTM) model for predicting the price of TRX–USD. The dataset consists of 2,096 daily historical records obtained from the Binance platform, including open, high, low, close, volume, and percentage change, with the closing price selected as the forecasting target. A baseline LSTM model was evaluated against six optimization techniques: Grid Search, Random Search, Bayesian Optimization (Hyperopt), Optuna, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA). Experimental results show that GA provides the best performance with an R² score of 0.88, MAE of 0.0123, RMSE of 0.0189, and a validation loss of 0.069. In contrast, Random Search yields the lowest performance, achieving an R² of only 0.2979. These findings highlight significant performance gaps among optimization strategies and demonstrate the superiority of metaheuristic-based approaches over conventional tuning methods. This research contributes to the advancement of computational intelligence by providing empirical evidence on the effectiveness of hyperparameter optimization techniques for deep learning–based time series forecasting, particularly in high-volatility financial environments. 
Comparative Analysis on Data Balancing and Augmentation in Skin Cancer Image Classification Using Multiple Datasets with Explainable AI Dimas Fanny Hebrasianto Permadi; Annisaa Utami; Muhammad Raafi’u Firmansyah
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1598

Abstract

Skin cancer is one of the most common types of cancer worldwide, with a continuously increasing incidence rate. Early detection and accurate classification of skin lesions are crucial for improving patient survival, particularly for melanoma. This study presents a comparative analysis of data-balancing strategies for skin cancer image classification across multiple publicly available datasets, including ISIC 2024, ISIC 2019, ISIC 2020, HAM10000, and PROVe-AI. The ConvNeXt-Tiny architecture is employed as the classification model and evaluated under three dataset configurations, namely RAW without balancing, Undersampling, and Oversampling via data augmentation, combined with two Learning Rate (LR) settings of 0.001 and 0.0001. In addition to reporting classification performance, this study emphasizes a comparative evaluation of accuracy, training stability, and computational efficiency across different balancing strategies. The experimental results indicate that the RAW dataset with an LR=0.0001 provides the best trade-off between performance and efficiency, achieving a validation accuracy of 99.88% and an F1-score of 0.9988. Oversampling via augmentation achieves the highest performance, with a validation accuracy of 99.93% and an F1-score of 0.9993, but requires substantially higher computational resources. Undersampling enables faster training with lower resource consumption, although it results in a slight performance degradation. Furthermore, Explainable Artificial Intelligence techniques, including Grad-CAM and LIME, demonstrate that models trained with an appropriate learning rate consistently focus on clinically relevant lesion regions, thereby improving interpretability and trustworthiness.
Co-Authors Adanti Wido Paramadini Adventus Angga Kurniawan Affriza Brilyan Relo Pambudi Agus Putra Alon Jala Tirta Segara Anggi Zafia Anisah Syifa Mustika Riyanto Annisaa Utami Arief Rais Bahtiar Aulia Desy Nur Utomo Dasril Aldo Dimas Fanny Hebrasianto Permadi Evia Zunita Dwi Pratiwi Fahrudin Mukti Wibowo Faiz, M. Hanif Al Fathan, Faizal Burhani Ulil Fau, Andrew Hidayat, Afifah Naurah Ibnu Rizal Mutaqim Lina Fatimah Lishobrina Lisda Lisda M Yoka Fathoni Maulana, Ihsan Muadin, Dika Alim Muhammad Afrizal Amrustian Muhammad Agung Nugroho Muhammad Aulia Muzzaki Nugraha Nenen Isnaeni Nenen Isnaini Rakhmad Maulidi Sa'adah, Aminatus Sulaeman, Gilang Suprapto, Amelia Rut Utami, Annisaa Yasin, Feri Yohani Setiya Rafika Nur