EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Rapid Detection and Classification of Escherichia Coli, Salmonella Typhi, and Staphylococcus Aureus using Smartphone-Based Deep Learning System

Maryam Arain, Sheeraz Ahmed Memon, Attiya Baqai, Mohsin Memon, Kundan Kumar, Sajid Hussain, Zuhaib Siddiqui

Mehran University Research Journal of Engineering and Technology · 01.07.2026 · 45 (3) · 162-177

DOI: 10.22581/muet1982.0782 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mehran University Research Journal of Engineering and Technology, online erschienen am 01.07.2026. Verfasst von Maryam Arain und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate and rapid detection of pathogens is important for maintaining infection control, ensuring food safety, supporting environmental monitoring, and supporting public health surveillance. Relying on traditional methods is time-consuming, which typically takes 24-72 hours to generate results. This study presents a machine-learning-based bacterial detection system that integrates smartphone imaging with convolutional neural networks to classify Escherichia coli, Salmonella typhi, and Staphylococcus aureus. In this study, a portable smartphone-compatible microscope with a magnification of 750x and a resolution of 1 µm was used, enabling high-quality bacterial imaging directly at the sampling site. To train three CNN architectures, namely, ResNet50, VGG16, and InceptionV3, hundreds of microscopic images were obtained by preparing, scanning stained bacterial slides, and then pre-processing them for this study. Furthermore, these models were assessed using various bacterial pair combinations to evaluate the classification accuracy. The results revealed that the system achieved 98.6% accuracy, demonstrating robust classification performance. The developed system was shown to outperform traditional cultural laboratory methods, enabling it to transform an ordinary smartphone into a handheld bioresearch machine that provides diagnostic results within minutes. The novelty lies in the comparative assessment of three CNN architectures across multiple bacterial class combinations, enabling robust assessment of model performance in distinguishing morphologically similar and distinct bacterial species. Through the combination of optical imaging, convolutional neural networks, and adaptive mobile computing, the investigation gains a significant decrease in the turnaround and operational cost of the assay and maintains the same level of accuracy as gold-standard assays.

Zitieren

APA

Arain, M., Memon, S. A., Baqai, A., Memon, M., Kumar, K., Hussain, S., & Siddiqui, Z. (2026). Rapid Detection and Classification of Escherichia Coli, Salmonella Typhi, and Staphylococcus Aureus using Smartphone-Based Deep Learning System. Mehran University Research Journal of Engineering and Technology, 45(3), 162-177. https://doi.org/10.22581/muet1982.0782

Vancouver

Arain M, Memon SA, Baqai A, Memon M, Kumar K, Hussain S, et al. Rapid Detection and Classification of Escherichia Coli, Salmonella Typhi, and Staphylococcus Aureus using Smartphone-Based Deep Learning System. Mehran University Research Journal of Engineering and Technology. 2026;45(3):162-177. doi:10.22581/muet1982.0782

BibTeX
@article{Arain2026,
  author = {Arain, Maryam and Memon, Sheeraz Ahmed and Baqai, Attiya and Memon, Mohsin and Kumar, Kundan and Hussain, Sajid and Siddiqui, Zuhaib},
  title = {Rapid Detection and Classification of Escherichia Coli, Salmonella Typhi, and Staphylococcus Aureus using Smartphone-Based Deep Learning System},
  journal = {Mehran University Research Journal of Engineering and Technology},
  year = {2026},
  volume = {45},
  number = {3},
  pages = {162--177},
  doi = {10.22581/muet1982.0782}
}
Kostenlos starten →