Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JTT (Jurnal Teknologi Terpadu)
Teguh Iman Hermanto
STT Wastukancana Purwakarta
Civil Engineering, Building, Construction & Architecture Control & Systems Engineering Materials Science & Nanotechnology Mechanical Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Analisis Algoritma Yolo V11n Untuk Deteksi Kepatuhan Penggunaan Alat Pelindung Diri Pada Live Cam Shandy Satria Nugraha; Teguh Iman Hermanto; Muhammad Rafi Muttaqin
Jurnal Teknologi Terpadu Vol 14 No 2 (2026): JTT (Jurnal Teknologi Terpadu)
Publisher : Pusat Penelitian dan Pengabdian Kepada Masyarakat

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

Abstract

Penerapan Keselamatan dan Kesehatan Kerja (K3) merupakan aspek krusial di sektor industri. Meskipun demikian, pemantauan kepatuhan penggunaan Alat Pelindung Diri (APD) secara manual sangat rentan terhadap kelalaian manusia, sementara kamera pengawas statis kerap memiliki keterbatasan area pantau. Penggunaan kamera langsung (live cam) portabel menawarkan fleksibilitas pengawasan seketika, namun menuntut arsitektur kecerdasan buatan yang sangat efisien secara komputasi. Oleh karena itu, penelitian ini bertujuan untuk mengevaluasi kinerja algoritma YOLOv11n (Nano) dalam mengidentifikasi enam kelas target (pekerja, helm, kacamata, sarung tangan, sepatu, dan kemeja reflektor) serta mengintegrasikannya pada sebuah antarmuka web. Metodologi penelitian menerapkan kerangka kerja OSEMN menggunakan 346 data citra privat. Fase pelatihan dieksekusi selama 50 epoch dengan memanfaatkan augmentasi data dinamis guna menyimulasikan kondisi riil di lapangan. Hasil pengujian memvalidasi bahwa model sukses mencatatkan nilai rata-rata presisi (mean Average Precision/mAP50) sebesar 99,2%. Model prediksi selanjutnya dikonversi ke dalam format TensorFlow.js untuk dijalankan secara murni pada peramban klien (client-side). Sistem ini mengadopsi algoritma irisan spasial guna menentukan status kepatuhan, di mana insiden pelanggaran secara otomatis ditransmisikan ke dalam basis data awan Firebase Firestore yang dikendalikan oleh filter pencegah duplikasi data. Kesimpulannya, YOLOv11n terbukti sangat presisi, tangguh, dan berbobot ringan untuk mewujudkan instrumen audit K3 yang terotomatisasi secara komprehensif. 
Optimasi Klasifikasi Pneumonia Pada Citra Chest X Ray MenggunakanTeknik Peningkatan Citra Dan Perbandingan Arsitektur Cnn (Efficientnet-V2Dan Vgg-16) Jasmine Mumtaz; Teguh Iman Hermanto; Muhammad Rafi Muttaqin
Jurnal Teknologi Terpadu Vol 14 No 2 (2026): JTT (Jurnal Teknologi Terpadu)
Publisher : Pusat Penelitian dan Pengabdian Kepada Masyarakat

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

Abstract

Pneumonia is an acute respiratory disease that contributes to a high global mortality rate. Clinical identification typically utilizes chest x-rays; however, manual analysis by medical practitioners is prone to subjectivity and is time-consuming. Therefore, this research designs an automatic classification system to recognize pneumonia utilizing a Convolutional Neural Network (CNN) while assessing the effectiveness of various image enhancement methods. During the initial preprocessing phase, data balancing was conducted through the random undersampling technique to reduce the majority class, generating a balanced dataset of 1,000 training images for each category. Image pixel quality was then improved using logarithmic transformation, Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and gamma correction. The model performance evaluation involved Base CNN, VGG-16, and EfficientNet-V2 architectures, which were validated using a stratified 5-fold cross-validation scheme. The experimental findings indicated that combining the VGG-16 architecture with the HE technique yielded the most optimal detection performance. This model achieved an accuracy of 93.44%, precision of 97.30%, recall of 89.40%, F1-score of 93.17%, and an Area Under the Curve (AUC) score of 0.9845. On the other hand, the EfficientNet-V2 model showed suboptimal performance on this dataset, which is indicated to be caused by the implementation of frozen layers during the training process.
Co-Authors Jasmine Mumtaz Muhammad Rafi Muttaqin Shandy Satria Nugraha