Article Per Year (5 Year)
p-Index From 2021 - 2026
2.47
P-Index
This Author published in this journals
All Journal Healthy Journal International Journal Software Engineering and Computer Science (IJSECS) Agro Tatanen Computing Jurnal Informatika Competitive Jurnal Pengabdian Nasional (JPN) Indonesia BHAKTI JIVANA
Mohammad Bayu Anggara
Universitas Bale Bandung
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Dentistry Economics, Econometrics & Finance Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Nursing Public Health Social Sciences Transportation Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Web Attack Detection for SQLi and XSS Using Ensemble Learning Based on Character-Level N-Gram Features Yaya Suharya; Mohammad Bayu Anggara
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7193

Abstract

SQL Injection (SQLi) and Cross-Site Scripting (XSS) remain severe threats to web application security, particularly as attackers employ increasingly sophisticated obfuscation techniques to bypass conventional detection systems. This research constructs a machine learning framework using ensemble learning — specifically combining Random Forest and XGBoost — integrated with character-level n-gram feature extraction. The methodology involved rigorous data curation of a large-scale dataset, refining 156,636 raw samples into 151,783 unique entries to ensure high-quality training data. By extracting 10,000 character-level n-gram features, the model captures the intricate structural patterns of complex and obfuscated payloads. Experimental results show consistent and measurable performance: the proposed ensemble model achieved an overall accuracy of 99.67%. Stability was confirmed through a 5-fold cross-validation process, yielding a mean accuracy of 99.64% and a standard deviation of 0.0003. These findings are reinforced by ROC AUC scores of 1.0000 for XSS and 0.9999 for SQLi, indicating near-perfect discriminative capability. The combination of character-level representation and ensemble learning produces a precise and resilient solution for safeguarding modern web environments against dynamic and evolving cyber threats.
Akselerasi Daya Saing Produk Lokal Melalui Transformasi Visual Produk UMKM Menggunakan Teknologi AI Mohammad Bayu Anggara; Wini Fetia Wardhani; Inka Aqila Nurfalqi
Jurnal Pengabdian Nasional (JPN) Indonesia Vol. 7 No. 2 (2026): Mei
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jpni.v7i2.1821

Abstract

Limited capability of Micro, Small, and Medium Enterprises (MSMEs) in producing appealing promotional visuals remains a major challenge in advancing local product competitiveness within the digital marketing environment. This issue is generally associated with inadequate visual design skills and restricted access to supporting technologies. This community service program aimed to improve the understanding and practical skills of MSME actors in Bandung Regency in the use of Artificial Intelligence (AI) technology as a supporting tool for creating promotional visual content. The program was conducted using a participatory approach through a seminar and workshop held on January 31, 2026, attended by 17 MSME participants. The learning methods combined lectures, group discussions, hands-on practice, and mentoring sessions. Program evaluation was carried out using pre-test and post-test instruments, accompanied by a participant satisfaction survey. The evaluation results indicated an increase in participants' understanding by 16.2%, rising from 78.7% in the pre-test to 94.9% in the post-test. Beyond cognitive improvement, the satisfaction survey results showed that most participants rated the program very positively, with average scores exceeding 4.5 on a 5-point Likert scale for material relevance, clarity of delivery, and overall program benefits. Participants were also able to produce tangible outputs in the form of AI-assisted promotional visuals, including product photographs, poster designs, and digital promotional content. These findings indicate that the application of AI technology in promotional visual training for MSMEs is effective in building business actors' capacities while achieving a high level of participant satisfaction
ANALISIS KOMPARATIF ALGORITMA MACHINE LEARNING UNTUK PREDIKSI PRODUKSI PADI KABUPATEN BANDUNG Wini Fetia Wardhiani; Mohammad Bayu Anggara; Inka Aqila Nurfalqi3
AGRO TATANEN | Jurnal Ilmiah Pertanian Vol. 8 No. 2 (2026): AGRO TATANEN Edisi Juli 2026 | Jurnal Ilmiah Pertanian
Publisher : Program Studi Agroteknologi Faperta UNIBBA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55222/9bd6jc54

Abstract

Produksi padi merupakan indikator penting dalam mendukung ketahanan pangan daerah, termasuk di Kabupaten Bandung. Penelitian ini bertujuan membandingkan performa empat algoritma machine learning, yaitu Linear Regression, Support Vector Regression (SVR), Random Forest, dan XGBoost, dalam memprediksi produksi padi berdasarkan data luas panen dan produktivitas periode 2018-2025. Data penelitian diproses melalui pemeriksaan nilai kosong, pengurutan data berdasarkan tahun, serta feature engineering berupa lag produksi, rolling mean, dan interaksi antara luas panen dan produktivitas. Validasi model dilakukan menggunakan Leave-One-Out Cross Validation (LOO-CV) karena jumlah data yang digunakan terbatas, yaitu delapan observasi tahunan. Evaluasi model menggunakan Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa Linear Regression memperoleh performa terbaik dengan MAE 75.277 ton, RMSE 207.530 ton, MAPE 0,24%, dan R² 0,9931. Random Forest berada pada urutan kedua dengan MAPE 4,45% dan R² 0,5508. XGBoost menghasilkan MAPE 5,08% dan R² 0,4810, sedangkan SVR menunjukkan performa terendah dengan MAPE 7,36% dan R² -0,1583. Prediksi produksi padi periode 2026-2030 menunjukkan kecenderungan stabil pada kisaran 31,28-35,37 juta ton, bergantung pada model yang digunakan. Hasil penelitian ini dapat menjadi dasar awal dalam pengembangan sistem prediksi produksi padi berbasis data di tingkat kabupaten.
IMPLEMENTASI SISTEM MONITORING KELAYAKAN AIR MINUM BERBASIS IOT DENGAN FUZZY TSUKAMOTO PADA MATA AIR DESA SUKAMAJU Riska Nurhayan; Mohammad Bayu Anggara
COMPUTING | Jurnal Informatika Vol. 13 No. 01 (2026): Computing Jurnal Informatika | Volume 13 Nomor 01 Bulan Juni Tahun 2026
Publisher : Program Studi Teknik Informatika FTI UNIBBA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55222/5mq6vq93

Abstract

Air layak konsumsi merupakan kebutuhan dasar manusia yang penting bagi kesehatan, namun banyakwilayah pedesaan seperti Desa Sukamaju belum memiliki sistem pemantauan kualitas air secara real-timesesuai standar kesehatan. Penilaian kelayakan air umumnya masih subjektif tanpa indikator ilmiah yang pasti.Penelitian ini bertujuan merancang dan mengimplementasikan sistem monitoring kualitas air minum berbasisInternet of Things (IoT) dengan empat parameter utama: pH, TDS, kekeruhan, dan suhu. Sistemmenggunakan algoritma Fuzzy Tsukamoto untuk menentukan tingkat kelayakan air secara otomatis melaluidashboard web yang mudah diakses. Panel surya digunakan sebagai sumber energi mandiri, serta disertaifitur notifikasi WhatsApp untuk peringatan dini. Pengembangan sistem mengikuti metode Waterfall, dengandata dikumpulkan melalui observasi, wawancara, dan studi literatur. Hasil implementasi menunjukkan sistemdapat bekerja dengan baik dalam menampilkan data sensor dan mengklasifikasikan kualitas air secaraotomatis. Berdasarkan uji lapangan di dua sumber mata air, seluruh sampel terklasifikasi sebagai “LayakMinum” dengan rata-rata tingkat error sensor 15,17% (pH), 52,20% (TDS), dan 6,83% (suhu). Sistem iniberpotensi menjadi solusi awal pemantauan kualitas air di pedesaan, meskipun tetap diperlukan verifikasilaboratorium untuk parameter mikrobiologis dan kimia yang lebih kompleks.
PENGOLAHAN LIMBAH RUMAH TANGGA DALAM RANGKA PROGRAM ZERO WASTE DI SEKTOR 6 CITARUM HARUM KABUPATEN BANDUNG Wini Fetia Wardhiani; Rimelke Rahmadea Febryane; Mohammad Bayu Anggara
AGRO TATANEN | Jurnal Ilmiah Pertanian Vol. 7 No. 2 (2025): AGRO TATANEN Edisi Juli 2025 | Jurnal Ilmiah Pertanian
Publisher : Program Studi Agroteknologi Faperta UNIBBA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55222/xdyt7m12

Abstract

The Citarum Harum Program is a government initiative to rehabilitate and preserve the Citarum River, which is known as one of the dirtiest rivers in the world. One of the important strategies in this program is the application of the zero waste principle at the household level, especially in Sector 6 of Bandung Regency. This study examines efforts to process household waste as part of implementing the zero waste program in the area. The research method used is a qualitative-descriptive approach through field observations, interviews with residents and stakeholders, and documentation studies. The results of the study indicate that public education, provision of waste sorting facilities, and collaboration between the government, community, and residents are key factors in the success of waste processing. Processing organic waste through composting and utilizing inorganic waste into goods of economic value has been proven to reduce the volume of waste disposed of at the landfill. And for residual waste, it is used as paving blocks that have an economic selling value. Although there are still challenges such as low community participation evenly and limited facilities, the efforts made show a positive direction towards sustainable waste management. These findings are expected to be a reference for the development of community-based waste management policies in other areas.  
Co-Authors Anzani, Elvira Aprilia Aulia Hanifa Ardita Chanra Satria Putra Fahrul Zaman Fetia Wardhiani, Wini INFORMATIKA, COMPUTING Inka Aqila Nurfalqi Inka Aqila Nurfalqi3 Iyus A Muslimin Iyus A Muslimin Khilda Nistrina Rimelke Rahmadea Febryane Riska Nurhayan ROSMALINA ROSMALINA, ROSMALINA Rudi Hermawan Rudi Hermawan Septiansyah, Ridwan Sukiman Sukiman Wini Fetia Wardhani Wini Fetia Wardhiani Yaya Suharya