Claim Missing Document
Check
Articles

Found 26 Documents
Search

Expansive Soil Stabilization Using Mud (Lapindo) and Asphalt Emulsion Resti Meysita Pramaesti; Syahril; Hendry
Potensi: Jurnal Sipil Politeknik Vol. 23 No. 2 (2021): Potensi: Jurnal Sipil Politeknik
Publisher : Department of Civil Engineering, Politeknik Negeri Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (464.731 KB) | DOI: 10.35313/potensi.v23i2.2549

Abstract

Most of Gedebage area consist of expansive soil and always greatly induce disturbance to structure of foundation. Nature properties of expansive soil is a high plasticity value, low soil shear strength, high swelling, and large potential for shrinkage. One solution for soil improvement is to use an additional material to stabilize this soil. Additional material uses locked emulsion asphalt 8% and mud from Lapindo area in variation of 3%, 6%, 9% and 12%. The results of testing the physical and mechanical properties after stabilization indicates increasing of density value around 68%. Plasticity index tends to decrease until 10% from CBR test. CBR values with curing time of 14 days are 8.1% for unsoaked and by 4.6% for soaked conditions.
Design of a Web-Based Visiting Service System for Inmates at the Class IIA Binjai Correctional Facility Rahmah, Siti; Barani Fachri; Hendry
Bahasa Indonesia Vol 18 No 02 (2026): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v18i02.498

Abstract

This study aims to design and develop a web-based inmate visiting service system at the Class IIA Binjai Correctional Facility to improve efficiency, transparency, and accessibility for the public. The research method includes system requirements analysis, structured design approach, and implementation using web technologies that enable online visit registration. The system is designed to minimize queues, reduce administrative errors, and provide real-time visiting schedule information for both visitors and officers. The results of this study indicate that the developed system is capable of enhancing the quality of visiting services, accelerating administrative processes, and supporting more integrated and secure data management within the correctional facility environment.
Comparative Analysis of YOLOv8s and Faster R-CNN for High-Resolution UAV RGB Oil Palm Health Detection: Accuracy versus Inference Speed Trade-Off Kristia Yuliawan; Danny Manongga; Hendry Hendry
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1430

Abstract

Accurate and rapid detection of oil palm health conditions using UAV imagery is essential for supporting precision agriculture and large-scale plantation monitoring. However, challenges such as overlapping canopies, complex background textures, varying illumination, and severe class imbalance often reduce the reliability of automated detection systems. This study presents a comparative evaluation between YOLOv8s, a one-stage object detector, and Faster R-CNN, a two-stage detector, for identifying healthy and unhealthy oil palm trees using high-resolution UAV RGB imagery. The dataset consists of 2,303 annotated images collected from drone surveys and divided into training (70%), validation (20%), and testing (10%) subsets under a controlled experimental design. Both models were trained and evaluated using identical preprocessing pipelines and annotation formats to ensure fairness in comparison. Performance was assessed using precision, recall, F1-score, mean Average Precision (mAP@50 and mAP@50–95), and inference time. Experimental results show that YOLOv8s achieves superior performance with 0.987 precision, 0.998 recall, 0.977 mAP@50–95, and extremely fast inference speed of 1.1 ms per image. In contrast, Faster R-CNN achieves comparable detection accuracy at 0.981 precision and 0.993 recall but with significantly higher computational cost, reaching 875 ms per image. These findings indicate that YOLOv8s provides an optimal balance between accuracy and efficiency, making it more suitable for real-time UAV-based monitoring systems, while Faster R-CNN is more appropriate for offline and high-precision analytical tasks. The study contributes a standardized benchmarking framework for deep learning-based oil palm health detection and provides practical insights for selecting appropriate models in smart agricultural applications.
MEMPREDIKSI TINGKAT KECELAKAN JALAN RAYA DI SALATIGA MENGGUNAKAN MACHINE LEARNING Andika Rossy Febrian; Hendry Hendry
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 4 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i4.6959

Abstract

Kecelakaan merupakan suatu kejadian dijalan yang tidak terduga yang melibatkan kendaraan dan mengakibatkan korban jiwa maupun kerugian material, kecelakaan juga disebut sebagai kejadian yang memiliki multi faktor atau memiliki banyak penyebab yang mempengaruhi terjadinya kecelakaan. Penelitian ini memiliki tujuan yaitu untuk meramalkan atau memprediksi kecelakaan lalu lintas menggunakan metode Random Forest dan Linear Reggresion dengan bahasa pemrograman Python. Data yang digunakan dalam penelitian ini yaitu data dari BPS (Badan pusat Statistik) kota Salatiga dengan periode dari Tahun 2017 sampai dengan Tahun 2023 dengan selang waktu perbulan. Penerapan dari kedua model menunjukan untuk model Linear Reggression memiliki hasil yang lebih baik dari pada model Random Forest ini dikarenakan pada perhitungan Random Forest selalu menunjukan hasil decimal dan tidak genap akan tetapi kekurangan tersebut dapat dibenahi dengan menggunakan tools Difference yang beeguna untuk membantu mengidentifikasi pola atau kesalahan system dan memberikan arahan untuk perbaikan kedepannya
Natural Language Processing for Happiness: Analyzing Public Optimism on Timor-Leste’s ASEAN Membership Using Machine Learning Marcelino Caetano Noronha; Hendry Hendry; Krsimiyati Krsimiyati; Evi Maria
Proceeding International Collaborative Conference on Multidisciplinary Science Vol. 3 No. 1 (2026): June : ICCMS (Proceeding International Collaborative Conference on Multidiscipl
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/iccms.v3i1.287

Abstract

Timor-Leste’s ASEAN integration triggers diverse public psychological responses. Grounded in Orange Technology, which leverages technology for social well-being, this study utilizes Natural Language Processing (NLP) and Machine Learning to evaluate public optimism and anxiety regarding this geopolitical shift. Public comments were harvested from YouTube, preprocessed, and classified using a Support Vector Machine (SVM) model. Positive sentiments were mapped as indicators of public optimism, while negative sentiments represented public anxiety. The experimental results revealed that 42.97% of the digital discourse exhibited positive sentiment, signaling collective optimism toward regional integration. Conversely, 16.10% negative sentiment highlighted specific anxieties regarding labor market competition and economic readiness. This study demonstrates how single-classifier NLP systems serve as effective emotional-sensing tools, providing actionable media intelligence for governments to design supportive communication strategies that foster public reassurance and happiness during major national transitions. This study highlights the potential of sentiment analysis to support evidence-based policy communication and strengthen public trust during Timor-Leste’s ASEAN integration process.
Comparative Analysis of YOLOv8s and Faster R-CNN for High-Resolution UAV RGB Oil Palm Health Detection: Accuracy versus Inference Speed Trade-Off Kristia Yuliawan; Danny Manongga; Hendry Hendry
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1430

Abstract

Accurate and rapid detection of oil palm health conditions using UAV imagery is essential for supporting precision agriculture and large-scale plantation monitoring. However, challenges such as overlapping canopies, complex background textures, varying illumination, and severe class imbalance often reduce the reliability of automated detection systems. This study presents a comparative evaluation between YOLOv8s, a one-stage object detector, and Faster R-CNN, a two-stage detector, for identifying healthy and unhealthy oil palm trees using high-resolution UAV RGB imagery. The dataset consists of 2,303 annotated images collected from drone surveys and divided into training (70%), validation (20%), and testing (10%) subsets under a controlled experimental design. Both models were trained and evaluated using identical preprocessing pipelines and annotation formats to ensure fairness in comparison. Performance was assessed using precision, recall, F1-score, mean Average Precision (mAP@50 and mAP@50–95), and inference time. Experimental results show that YOLOv8s achieves superior performance with 0.987 precision, 0.998 recall, 0.977 mAP@50–95, and extremely fast inference speed of 1.1 ms per image. In contrast, Faster R-CNN achieves comparable detection accuracy at 0.981 precision and 0.993 recall but with significantly higher computational cost, reaching 875 ms per image. These findings indicate that YOLOv8s provides an optimal balance between accuracy and efficiency, making it more suitable for real-time UAV-based monitoring systems, while Faster R-CNN is more appropriate for offline and high-precision analytical tasks. The study contributes a standardized benchmarking framework for deep learning-based oil palm health detection and provides practical insights for selecting appropriate models in smart agricultural applications.