Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal JTERA (Jurnal Teknologi Rekayasa) Didaktik : Jurnal Ilmiah PGSD STKIP Subang Jurnal Ilmiah Teknik Informatika (TEKINFO)
Adhi Kusnadi
UNIVERSITAS NUSA PUTRA
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Industrial & Manufacturing Engineering Mechanical Engineering Social Sciences Transportation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Evaluasi Komparatif Algoritma Machine Learning Menggunakan SMOTENC pada Klasifikasi Status Gizi Balita Berbasis Data Antropometri Erip Suratno; Adhi Kusnadi; Zeldi Suryady
JTERA (Jurnal Teknologi Rekayasa) Vol 11 No 1: Vol. 11 No. 1: Juni 2026
Publisher : Politeknik Sukabumi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31544/jtera.v11.i1.2026.101-110

Abstract

Ketidakseimbangan distribusi kelas pada data status gizi balita dapat membuat model klasifikasi tampak akurat, tetapi kurang mampu mengenali kelas minoritas. Penelitian ini mengevaluasi Support Vector Machine, K-Nearest Neighbors, Naive Bayes, Decision Tree, dan Random Forest untuk klasifikasi multikelas status gizi balita berbasis data antropometri. Dataset berjumlah 3.716 data Posyandu Desa Ujunggenteng tahun 2025 dengan fitur jenis kelamin, usia, berat badan, dan tinggi badan serta empat kelas target: kurang gizi, gizi baik, risiko gizi lebih, dan gizi lebih. Label diperlakukan sebagai label operasional dalam dataset, bukan hasil penghitungan ulang z-score WHO/Kementerian Kesehatan. Eksperimen menggunakan pembagian data latih-uji terstratifikasi 80:20, 5-fold Stratified K-Fold Cross-Validation, pencarian kandidat parameter terbatas, preprocessing numerik-kategorik, dan SMOTENC hanya pada data latih atau fold pelatihan. Hasil cross-validation menunjukkan SVM memperoleh CV F1 Macro tertinggi sebesar 0,829578. Pada data uji, Random Forest memperoleh F1 Macro tertinggi sebesar 0,827132, sedangkan KNN memperoleh akurasi tertinggi sebesar 0,956989 dan balanced accuracy tertinggi sebesar 0,883393. Pemilihan model perlu mempertimbangkan F1 Macro, balanced accuracy, confusion matrix, dan performa per kelas. Berdasarkan cross-validation, SVM ditetapkan sebagai model final, sedangkan Random Forest dilaporkan terbaik pada data uji berdasarkan F1 Macro.
Perbandingan Kinerja YOLOv8 dan SSD MobileNet untuk Deteksi Kelengkapan Atribut Seragam Siswa Argi Ginanjar; Adhi Kusnadi
Jurnal Ilmiah Teknik Informatika (TEKINFO) Vol. 27 No. 2 (2026): TEKINFO Vol 27 No 2 Oktober 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Inspecting the completeness of student uniform attributes is challenging because several items, suchas epaulettes, name tags, belts, black shoes, and caps, may appear small, partially occluded, orvisually unclear. This study compares YOLOv8n and SSD MobileNet for detecting student uniformattributes using a self-collected dataset. The dataset contains 1,532 augmented images, five objectclasses, and 5,294 YOLO-format bounding box annotations. The experimental procedure includeddataset preparation, object annotation, train-validation-test splitting, model training, and finalevaluation on the test set. The evaluation used precision, recall, mAP@50, mAP@50-95, inferencetime, and FPS. On the test set, YOLOv8n achieved a precision of 0.8966, recall of 0.8689, mAP@50of 0.9276, mAP@50-95 of 0.6723, inference time of 10.36 ms, and 96.47 FPS. SSD MobileNetachieved a precision of 0.5140, recall of 0.5169, mAP@50 of 0.6034, mAP@50-95 of 0.3171,inference time of 11.00 ms, and 90.87 FPS. These findings indicate that YOLOv8n performed betterin the tested dataset and experimental setting.
PEMBERDAYAAN MASYARAKAT DESA CIRENDANG MELALUI PROGRAM KULIAH KERJA NYATA BERBASIS EDUKASI, KESEHATAN, DAN POTENSI LOKAL Neng Endang Nur'asih; Anisa Cikal Virgifiani; Erin Nurfajrina; Wardatul Jannah; Muhammad Falwa Direngga; Zaki Rizki; Muhammad Muhammad Arbi Pebriansyah; Siti Nur Azizah; Tasya Amanda Maulidia; Silfi Hermaliani Hafitri; Dinda Halwalia Deviani; Mike Masangga; Gregorius Agung Wahyu Utomo; Aditya Prayoga Jaelani; Muhammad Alawi; Giri Putra Wahid; Rafli Al Fadli Nurliana; Raihan Putra Kusumah; Adhi Kusnadi
Didaktik : Jurnal Ilmiah PGSD STKIP Subang Vol. 12 No. 03 (2026): Volume 12 Nomer 03, September 2026 Publication
Publisher : STKIP Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36989/didaktik.v12i03.18859

Abstract

Community Service Program (KKN) is a tangible manifestation of the Tri Dharma of Higher Education, particularly in the aspect of community service. This KKN activity was conducted in Cirendang Village, Cikakak District, Sukabumi Regency, aiming to enhance community capacity, health, literacy, and self-reliance through educational, participatory, and collaborative approaches. Field observation identified core issues in nutrition awareness (stunting risk), lack of disaster preparedness among elementary students, limited village visual navigation aids, and low adoption of digital identity among local MSMEs. In response, 15 integrated work programs were executed, covering Mother and Child Nutrition Classes (Pos Gizi Mini), disaster mitigation simulations, environmental greening ("Satu Pohon Seribu Manfaat"), village mapping and road signage installation, fish pond revitalization, reading corner activation (Jam Baca Ceria), MSME visual rebranding, digital email registration for BPJS administration, primary school teaching assistance, IT literacy workshops, and free health checkups at Puncak Bohai. The implementation methods involved participatory observation, direct practice, socializations, and community collaboration. The results revealed a significant improvement in public health awareness, enhanced disaster safety skills among school children, the creation of official visual village assets, and greater digital independence for 98 residents managing public healthcare access. Active community participation and multi-stakeholder collaboration were the principal factors in successfully realizing a resilient, healthy, and self-sustaining village ecosystem.
Co-Authors Aditya Prayoga Jaelani Anisa Cikal Virgifiani Argi Ginanjar Dinda Halwalia Deviani Erin Nurfajrina Erip Suratno Giri Putra Wahid Gregorius Agung Wahyu Utomo Mike Masangga Muhammad Alawi Muhammad Falwa Direngga Muhammad Muhammad Arbi Pebriansyah Neng Endang Nur'asih Rafli Al Fadli Nurliana Raihan Putra Kusumah Silfi Hermaliani Hafitri Siti Nur Azizah Tasya Amanda Maulidia Wardatul Jannah Zaki Rizki Zeldi Suryady