Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Prosiding SNITP (Seminar Nasional Inovasi Teknologi Penerbangan) bit-Tech
Syaifullah J. S, Wahyu
Unknown Affiliation
Aerospace Engineering Computer Science & IT Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Transportation

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

Found 2 Documents
Search

 1 
DEPLOYMENT DETEKSI KEMATANGAN BUAH KELAPA SAWIT BERBASIS YOLOV11 DENGAN ONNX RUNTIME DAN STREMLIT Ramadhan Anniswa, Iqbal; Syaifullah J. S, Wahyu; Idhom, Mohammad; Rizaldy Pratama, Alfan; Gede Susrama Mas Diyasa, I
Prosiding SNITP (Seminar Nasional Inovasi Teknologi Penerbangan) Vol. 9 No. 1 (2025): SNITP 2025
Publisher : Politeknik Penerbangan Surabaya

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

Abstract

Kelapa Sawit merupakan komoditas strategis di Indonesia yang menjadi salah satusumber devisa utama. Tingkat kematangan buah kelapa sawit sangat berpengaruhterhadap kualitas minyak yang dihasilkan, sehingga diperlukan metode yang cepat,tepat, dan konsisten untuk mendeteksi tingkat kematangan buah. Dalam metedoKonversional masih mengandalkan pengamatan visual oleh pekerja lapangan seringbersifat subjektif dan tidak efesien.Dengan hal tersebut,penelitian ini mengusulkanpenerapan model object detection berbasis YOLOv11 untuk mendeteksikematangan buah kelapa sawit. Model YOLOv11 dipilih karena memilikikeunggulan dalam kecepatan inferensi dan akurasi deteksi pada objek kecil maupunkompleks. Untuk memfasilitasi penggunaan di lingkungan produksi,Model yangtelah dilatih dikonversi ke format ONNX dan dijalankan menggunakan ONNXRuntime agar memperoleh perfoma inferensi yang lebih optimal pada sumber dayaterbatas. Selanjutnya, aplikasi antarmuka berbasis Streamlit dikembangkan untukmemudahkan pengguna dalam mengunggah gambar atau video dan memperolehhasil deteksi secara real-time. Diharapkan, sistem ini mampu memberikan solusipraktis, efisien, dan akurat dalam mendukung proses panen buah kelapa sawit.
A Deep Learning Approach Using Bidirectional-LSTM and Word2Vec for Fake News Classification Nur Hidayat, Fadhilah; Syaifullah J. S, Wahyu; Idhom, Mohammad
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3575

Abstract

The rapid growth of online news consumption in Indonesia has intensified the challenge of combating fake news, which undermines public trust and threatens social stability. Conventional approaches, including manual verification, are increasingly inadequate to address the scale and speed of digital information dissemination. This study aims to develop an automatic Indonesian fake news classification system using a deep learning framework that integrates Bidirectional Long Short-Term Memory (Bi-LSTM) with Word2Vec embeddings. Unlike many existing fake news detection models that rely on limited validation settings or focus predominantly on English-language data, this work explicitly addresses the linguistic characteristics and practical constraints of the Indonesian context, thereby strengthening model relevance for real-world deployment. The dataset comprises 6,000 balanced news articles, including 3,000 valid items from Detik.com and 3,000 hoax items from Turnbackhoax.id, collected between January and October 2024. Text preprocessing involved cleaning, stopword removal, tokenization, and padding. A 300-dimensional Word2Vec embedding model was employed, and the classifier was trained using stratified 3-fold cross-validation to ensure robust performance estimation. An ensemble inference strategy was further applied to reduce inter-fold variance and enhance generalization on unseen data, directly addressing a common limitation of prior single-model approaches. Experimental results show that the proposed model achieves an accuracy of 86.43% and an F1-score of 86.28%, alongside a high mean Average Precision of 0.927 during validation. Compared with previously reported deep learning baselines, this framework demonstrates competitive yet more stable performance under realistic evaluation settings, supporting scalable deployment.
Co-Authors Alfan Rizaldy Pratama Gede Susrama Mas Diyasa, I idhom, Mohammad Nur Hidayat, Fadhilah Ramadhan Anniswa, Iqbal