EUVIMEDEUVIMED entdecken
Crossref

Diseases of Vegetable Plant Recognition Based on Enhanced SqueezeNet

Kifaa Hadi Thanoon, Akram A. Abdulrahman, Ali Ibrahim Ahmed, Omar Ibrahim Alsaif, Ibrahim Ahmed Saleh

Pertanika Journal of Science and Technology · 30.10.2026 · 34 (5)

DOI: 10.47836/pjst.34.5.18 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pertanika Journal of Science and Technology, online erschienen am 30.10.2026. Verfasst von Kifaa Hadi Thanoon und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agricultural resources significantly affect food security, and plant diseases cause substantial production losses and economic losses. This paper presents a method for detecting plant diseases using the deep learning (DL) algorithm SqueezeNet. To do this, the SqueezeNet network was modified to detect plant diseases. Yet one disadvantage of SqueezeNet is that it has many parameters and achieves quite low accuracy, which limits its use due to its complexity. A new advanced network based on "improved squeeze architecture" was suggested for plant disease detection. This paper, however, presented the network by simplifying its architecture, thereby enhancing its feature-recognition capabilities. Moreover, changes were made to the fire module, including the size of the convolution kernel, the number of network layers, and the number of channels in the Expand layer. Also, the model was combined with the Efficient Channel Attention (ECA) module, which assigns attention values to each channel via local cross-channel interactions, thereby improving the network's ability to learn salient features. The algorithm was compared with three others—LeNet, MobileNet, and traditional SqueezeNet—using the "PlantVillage" dataset. The proposed model achieved a very high accuracy, exceeding the traditional SqueezeNet by 93.8% and reaching a minimum of 84%.

Zitieren

APA

Thanoon, K. H., Abdulrahman, A. A., Ahmed, A. I., Alsaif, O. I., & Saleh, I. A. (2026). Diseases of Vegetable Plant Recognition Based on Enhanced SqueezeNet. Pertanika Journal of Science and Technology, 34(5). https://doi.org/10.47836/pjst.34.5.18

Vancouver

Thanoon KH, Abdulrahman AA, Ahmed AI, Alsaif OI, Saleh IA. Diseases of Vegetable Plant Recognition Based on Enhanced SqueezeNet. Pertanika Journal of Science and Technology. 2026;34(5). doi:10.47836/pjst.34.5.18

BibTeX
@article{Thanoon2026,
  author = {Thanoon, Kifaa Hadi and Abdulrahman, Akram A. and Ahmed, Ali Ibrahim and Alsaif, Omar Ibrahim and Saleh, Ibrahim Ahmed},
  title = {Diseases of Vegetable Plant Recognition Based on Enhanced SqueezeNet},
  journal = {Pertanika Journal of Science and Technology},
  year = {2026},
  volume = {34},
  number = {5},
  doi = {10.47836/pjst.34.5.18}
}
Kostenlos starten →