Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification

Waste management remains a critical challenge for many countries, including Indonesia, which ranks as the world's second-largest contributor of waste. As tens of millions of tons are produced each year and the management system remains ineffective, environmental conditions and public health con...

Full description

Saved in:
Bibliographic Details
Main Authors: Aulia Afifah, Endah Ratna Arumi, Maimunah Maimunah, Setiya Nugroho
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2025-05-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/6211
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849708099942744064
author Aulia Afifah
Endah Ratna Arumi
Maimunah Maimunah
Setiya Nugroho
author_facet Aulia Afifah
Endah Ratna Arumi
Maimunah Maimunah
Setiya Nugroho
author_sort Aulia Afifah
collection DOAJ
description Waste management remains a critical challenge for many countries, including Indonesia, which ranks as the world's second-largest contributor of waste. As tens of millions of tons are produced each year and the management system remains ineffective, environmental conditions and public health continue to deteriorate. To address this issue, it is imperative to develop more accurate and efficient solutions to enhance waste classification and management. This study investigates the influence of various image preprocessing techniques on the performance of MobileNetV1 and MobileNetV2 models in the classification of waste images. Preprocessing is crucial for enhancing data quality, particularly when dealing with real-world images that are affected by inconsistent lighting, texture, and clarity. Five preprocessing scenarios were evaluated: Baseline, CLAHE with Bilateral Filtering, CLAHE with Sharpening, Grayscale with CLAHE, and Gaussian Blur with Bilateral Filtering. Among these, the combination of CLAHE and Bilateral Filtering applied to MobileNetV1 achieved the best results, with 85% training accuracy, 96% validation accuracy, a training loss of 0.3178, and the lowest validation loss of 0.1630. Overall, MobileNetV1 benefited more significantly from preprocessing variations than MobileNetV2, particularly in terms of accuracy improvement and reduction in prediction error. These findings underscore the importance of effective preprocessing in enhancing model performance for waste image classification
format Article
id doaj-art-4f39fefd62aa4671a6888b02cc3d21ea
institution DOAJ
issn 2580-0760
language English
publishDate 2025-05-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-4f39fefd62aa4671a6888b02cc3d21ea2025-08-20T03:15:47ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-05-019344445210.29207/resti.v9i3.62116211Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste ClassificationAulia Afifah0Endah Ratna Arumi1Maimunah Maimunah2Setiya Nugroho3Universitas Muhammadiyah MagelangUniversitas Muhammadiyah MagelangUniversitas Muhammadiyah MagelangUniversitas Muhammadiyah MagelangWaste management remains a critical challenge for many countries, including Indonesia, which ranks as the world's second-largest contributor of waste. As tens of millions of tons are produced each year and the management system remains ineffective, environmental conditions and public health continue to deteriorate. To address this issue, it is imperative to develop more accurate and efficient solutions to enhance waste classification and management. This study investigates the influence of various image preprocessing techniques on the performance of MobileNetV1 and MobileNetV2 models in the classification of waste images. Preprocessing is crucial for enhancing data quality, particularly when dealing with real-world images that are affected by inconsistent lighting, texture, and clarity. Five preprocessing scenarios were evaluated: Baseline, CLAHE with Bilateral Filtering, CLAHE with Sharpening, Grayscale with CLAHE, and Gaussian Blur with Bilateral Filtering. Among these, the combination of CLAHE and Bilateral Filtering applied to MobileNetV1 achieved the best results, with 85% training accuracy, 96% validation accuracy, a training loss of 0.3178, and the lowest validation loss of 0.1630. Overall, MobileNetV1 benefited more significantly from preprocessing variations than MobileNetV2, particularly in terms of accuracy improvement and reduction in prediction error. These findings underscore the importance of effective preprocessing in enhancing model performance for waste image classificationhttps://jurnal.iaii.or.id/index.php/RESTI/article/view/6211wastemobilenetv1mobilenetv2preprocessingwaste classification
spellingShingle Aulia Afifah
Endah Ratna Arumi
Maimunah Maimunah
Setiya Nugroho
Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
waste
mobilenetv1
mobilenetv2
preprocessing
waste classification
title Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification
title_full Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification
title_fullStr Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification
title_full_unstemmed Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification
title_short Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification
title_sort comparative evaluation of preprocessing methods for mobilenetv1 and v2 in waste classification
topic waste
mobilenetv1
mobilenetv2
preprocessing
waste classification
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/6211
work_keys_str_mv AT auliaafifah comparativeevaluationofpreprocessingmethodsformobilenetv1andv2inwasteclassification
AT endahratnaarumi comparativeevaluationofpreprocessingmethodsformobilenetv1andv2inwasteclassification
AT maimunahmaimunah comparativeevaluationofpreprocessingmethodsformobilenetv1andv2inwasteclassification
AT setiyanugroho comparativeevaluationofpreprocessingmethodsformobilenetv1andv2inwasteclassification