Artificial intelligence-powered multiclass deep learning model for detection of aflatoxin related defects in Ugandan groundnuts.

dc.contributor.authorLillian, Tamale
dc.contributor.authorSsebuggwawo, Denis
dc.contributor.authorMirembe, Drake Patrick
dc.contributor.authorMirugwe, Alex
dc.contributor.authorLubega, Jude T.
dc.date.accessioned2026-10-05T06:10:06Z
dc.date.issued2026-06
dc.descriptionArticle
dc.description.abstractAflatoxin contamination poses a persistent challenge to groundnut value chains in sub-Saharan Africa, where conventional laboratory-based detection methods are costly, time-consuming, and often inaccessible to smallholder farmers. This study presents an artificial intelligence–powered multiclass deep learning framework for image-based detection of aflatoxin-related defects in groundnuts. A curated dataset of 2252 groundnut kernel images was compiled and categorized into four classes: Healthy, Moldy, pest-infested, and physiological disorder. The dataset was partitioned into training, validation, and test sets, with targeted data augmentation applied to address class imbalance. The proposed model employs an Inception-ResNet-V2 architecture with transfer learning, class-weighted categorical cross-entropy loss, and optimized hyperparameters to enhance multiclass discrimination. Model performance was evaluated using accuracy, class-wise precision, recall, F1-score, and receiver operating characteristic analysis. The model achieved an overall classification accuracy of 99.29% on the independent test set, with class-specific AUC values of 1.00 (Moldy), 0.98 (Healthy), 0.97 (Pest-Infested), and 0.99 (Physiological Disorder). These results demonstrate strong generalization and robust differentiation of visually similar defect classes. The findings indicate that multiclass deep learning can effectively support early-stage screening of aflatoxin-associated defects in groundnuts, providing a scalable and low-cost complementary tool to conventional aflatoxin testing methods. Keywords Multiclass deep learning, Aflatoxin detection, Convolutional neural networks, Inception-ResNet-V2, Agricultural image analysis, Groundnut quality assessment
dc.identifier.citationLillian, T., Ssebuggwawo, D., Mirembe, Drake P., Mirugwe, A., Lubega, J. T. (2026). Artificial intelligence-powered multiclass deep learning model for detection of aflatoxin related defects in Ugandan groundnuts, Discover Artificial Intelligence.
dc.identifier.urihttps://ir.nkumbauniversity.ac.ug/handle/123456789/460
dc.language.isoen
dc.publisherDiscover Artificial Intelligence
dc.subjectMulticlass deep learning
dc.subjectAflatoxin detection
dc.subjectConvolutional neural networks
dc.titleArtificial intelligence-powered multiclass deep learning model for detection of aflatoxin related defects in Ugandan groundnuts.
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Artificial intelligence-powered multiclass deep learning model for detection of aflatoxinrelated defects in Ugandan groundnuts.pdf
Size:
2.12 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description: