R.K. Ula, Nafisah Nur Laila, Risnandar, Aryo De Wibowo Muhammad Sidik, Anggy Pradiftha Junfithrana, Tasqia Alzahra
Plastic fragments that contain microplastic can have an impact on ecosystems and human health. Since the 1970s, the complexity of microplastic analysis has been a big challenge. This study introduces a machine learning-based approach, which has demonstrated a faster and safer microplastic analysis. In the evaluation, we compare human annotation, machine learning, and image processing methods by using the structural similarity index (SSIM), which shows overall alignment results, except for the Grogol River sample (2). The performance of machine learning is satisfactory, but there are discrepancies in detecting microplastic types in this sample. Notably, the study identifies the potential PP and LDPE microplastics and diverges from human annotation. Our proposed methods are highlighted in the results, which demonstrate 78 © 2024 IEEE.
Nusa Putra University, Research Center for Electronics Nat. Research and Innovation Agency, Dept. of Electrical Engineering, Sukabumi, Indonesia; State University of Surabaya, Departement of Physics, Surabaya, Indonesia; Nusa Putra University, R. C. for Artf. Intell. & Cybersecurity Nat. Research and Innovation Agency, Dept. of Electrical Engineering, Sukabumi, Indonesia; Nusa Putra University, Dept of Elecrical Engineering, Sukabumi, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock