Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

Performance evaluation of lightweight CNN architectures on Android devices: a case study in image classification

JURNAL INFOTEL · Vol. 18 No. 3 (2026) · pp. 371–387

DOI
10.20895/infotel.v18i3.11387
ISSN
2085-3688, 2460-0997
Published
2026-08-31
Publisher
LPPM Institut Teknologi Telkom Purwokerto
Language
en
License
creativecommons.org/licenses/by-nc-sa/4.0/

Abstract

This study proposes an end-to-end framework for evaluating lightweight Convolutional Neural Network (CNN) architectures for maize leaf disease classification in mobile environments. Unlike conventional approaches that primarily emphasize model accuracy, this research integrates performance evaluation with real-world deployment using TensorFlow Lite on Android devices. A dataset of 2,760 maize leaf images across six classes, including a Non-leaf category to improve robustness, was utilized. Five pre-trained CNN models VGG16, ResNet50, MobileNetV2, NasNetMobile, and EfficientNetB0 were evaluated using a consistent experimental setup with 5-fold cross-validation. The results demonstrate that ResNet50 achieves the best performance, reaching a test accuracy of 97.10% and an average K-Fold cross-validation accuracy of 96.38%, confirming its stability and reliability. Furthermore, deployment experiments confirm that the selected model performs real-time inference on Android devices with an average latency of approximately 180 ms and minimal memory overhead, ensuring a seamless, near-instantaneous classification experience for farmers in the field. This study contributes a practical evaluation framework that bridges the gap between deep learning research and real-world implementation in mobile-based plant disease detection.

Keywords

Collaboration network of the authors

12 authors · 19 co-authorship links · 2 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Diponegoro University
  • Politeknik Negeri Semarang
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Kusworo AdiDiponegoro University2
R. Rizal IsnantoDiponegoro University2
Yulaikha MaratullatifahDiponegoro University1
Ucky Pradestha NovettralitaDiponegoro University1
Arie IswantiDiponegoro University1
N IdrusDiponegoro University1
Budi WarsitoDiponegoro University1
Sima MaulinaDiponegoro University1
Dwi RochmayantiDiponegoro University1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S4210188896, first harvested 19 Nov 2026, last seen 19 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Performance evaluation of lightweight CNN architectures on Android devices: a case study in image classification</dc:title><dc:creator>Sirli Fahriah</dc:creator><dc:creator>Catur Edi Widodo</dc:creator><dc:creator>Prayitno</dc:creator><dc:subject>lightweight convolutional neural network</dc:subject><dc:subject>TensorFlow Lite</dc:subject><dc:subject>inference latency</dc:subject><dc:subject>model compression</dc:subject><dc:subject>pre-trained CNN models</dc:subject><dc:subject>ResNet50</dc:subject><dc:subject>real-time inference</dc:subject><dc:subject>agricultural decision support</dc:subject><dc:description xml:lang="en">This study proposes an end-to-end framework for evaluating lightweight Convolutional Neural Network (CNN) architectures for maize leaf disease classification in mobile environments. Unlike conventional approaches that primarily emphasize model accuracy, this research integrates performance evaluation with real-world deployment using TensorFlow Lite on Android devices. A dataset of 2,760 maize leaf images across six classes, including a Non-leaf category to improve robustness, was utilized. Five pre-trained CNN models VGG16, ResNet50, MobileNetV2, NasNetMobile, and EfficientNetB0 were evaluated using a consistent experimental setup with 5-fold cross-validation. The results demonstrate that ResNet50 achieves the best performance, reaching a test accuracy of 97.10% and an average K-Fold cross-validation accuracy of 96.38%, confirming its stability and reliability. Furthermore, deployment experiments confirm that the selected model performs real-time inference on Android devices with an average latency of approximately 180 ms and minimal memory overhead, ensuring a seamless, near-instantaneous classification experience for farmers in the field. This study contributes a practical evaluation framework that bridges the gap between deep learning research and real-world implementation in mobile-based plant disease detection.</dc:description><dc:publisher>LPPM Institut Teknologi Telkom Purwokerto</dc:publisher><dc:date>2026-08-31</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:identifier>https://doi.org/10.20895/infotel.v18i3.11387</dc:identifier><dc:identifier>10.20895/infotel.v18i3.11387</dc:identifier><dc:source>JURNAL INFOTEL; Vol 18 No 3 (2026); 371-387</dc:source><dc:source>2085-3688</dc:source><dc:source>2460-0997</dc:source><dc:language>en</dc:language><dc:rights>https://creativecommons.org/licenses/by-nc-sa/4.0/</dc:rights></oai_dc:dc>