Badrul Huda Husain
Balai Pelatihan Lingkungan Hidup dan Kehutanan Pekanbaru

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

Found 2 Documents
Search

Advancing Fauna Conservation through Machine Learning-Based Spectrogram Recognition: A Study on Object Detection using YOLOv5 Badrul Huda Husain; Takahiro Osawa
Jurnal Sumberdaya Alam dan Lingkungan Vol 10, No 2 (2023)
Publisher : Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/ub.jsal.2023.010.02.2

Abstract

ABSTRACT The protection and monitoring of fauna species are essential for maintaining biodiversity and ensuring the sustainability of ecosystems. Traditional methods of fauna conservation and habitat monitoring rely heavily on manual observation and data collection, which can be time-consuming, and labor-intensive. In recent years, the application of machine learning techniques, such as object detection, has shown great potential in automating the identification of fauna species. In this study, we propose an approach to advancing fauna conservation through the utilization of machine learning-based spectrogram recognition. Specifically, we employ an object detection algorithm, YOLOv5, to detect and classify fauna species from spectrogram images obtained from acoustic recordings. The spectrograms provide a visual representation of audio signals, capturing distinct patterns and characteristics unique to different fauna species. Through extensive experimentation and evaluation, our approach achieved promising results, demonstrating a precision of 0.95, recall of 0.98, F1 score of 0.91, and mean Average Precision (mAP) of 0.934. These performance metrics indicate a high level of accuracy and reliability in fauna species detection. By automating the identification process, our approach provides a scalable solution for monitoring fauna populations over large geographical areas and enables the collection of comprehensive data, facilitating better decision-making and targeted conservation strategies. Keywords: acoustic recording, fauna conservation, machine learning, spectrogram, YOLOv5
Deteksi Lubang Jalan Secara Otomatis dari Rekaman Drone Menggunakan Model Machine Learning Berbasis YOLOv5 Instance Segmentation di Kota Pekanbaru, Provinsi Riau, Indonesia Badrul Huda Husain; Takahiro Osawa; Sagung Putri Chandra Astiti; Dodi Frianto; Muhammad Rizki Nandika; Dewi Agustine
Jurnal Zona Vol 8, No 2 (2024)
Publisher : Pelantar Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52364/zona.v8i2.126

Abstract

This scientific journal presents an approach to automatically detect road potholes from drone footage using a machine-learning model based on YOLOv5. The primary objective of this research is to develop a reliable and efficient system for road quality inspection. The proposed model achieves promising results with an F1 confidence of 0.83, Precision confidence of 0.96, Precision-Recall of 0.716, and Recall confidence of 0.8. The study aims to serve as a preliminary development toward the future implementation of road quality inspection. By leveraging drone footage and advanced machine learning techniques, the automated detection of potholes can significantly enhance the efficiency and accuracy of road maintenance efforts. Early detection and prompt repair of potholes can lead to improve road safety and reduce vehicle damage. Using drones and machine learning models allows for efficient monitoring and assessment of road infrastructure, contributing to sustainable transportation systems and minimizing the environmental impact of inefficient road maintenance. Moreover, this research contributes to the advancement of technology application in the field of environmental science. Overall, this study highlights the potential of YOLOv5-based machine learning models in automating the detection of road potholes from drone footage. The results demonstrate its effectiveness in accurately identifying and localizing potholes, paving the way for further advancements in road quality inspection and technology applications within the field of environmental science.