{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:53:18Z","timestamp":1781639598492,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":37,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Aflatoxin 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\u2013powered 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.<\/jats:p>","DOI":"10.1007\/s44163-026-01027-3","type":"journal-article","created":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T15:55:08Z","timestamp":1772380508000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence-powered multiclass deep learning model for detection of aflatoxin-related defects in Ugandan groundnuts"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6179-5436","authenticated-orcid":false,"given":"Lillian","family":"Tamale","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Ssebuggwawo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Drake Patrick","family":"Mirembe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Mirugwe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jude T.","family":"Lubega","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,1]]},"reference":[{"key":"1027_CR1","doi-asserted-by":"publisher","DOI":"10.1155\/js\/2460098","volume":"1","author":"MKO Aarif","year":"2025","unstructured":"Aarif MKO, Alam A, Hotak Y. Smart sensor technologies shaping the future of precision agriculture: recent advances and future outlooks. J Sens. 2025;1:2460098. https:\/\/doi.org\/10.1155\/js\/2460098.","journal-title":"J Sens"},{"issue":"2","key":"1027_CR2","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1287\/isre.2024.editorial.v35.n2","volume":"35","author":"A Abbasi","year":"2024","unstructured":"Abbasi A, Parsons J, Pant G, Liu Sheng OR, Sarker S. Pathways for design research on artificial intelligence. Inf Syst Res. 2024;35(2):441\u201359. https:\/\/doi.org\/10.1287\/isre.2024.editorial.v35.n2.","journal-title":"Inf Syst Res"},{"key":"1027_CR3","doi-asserted-by":"publisher","DOI":"10.1155\/jfq\/2810946","author":"JO Akullo","year":"2025","unstructured":"Akullo JO, Okello DK, Mohammed A, Muyinda R, Amayo R, Magumba D, et al. A comprehensive review of aflatoxin in groundnut and maize products in Africa: prevalence, detection and mitigation strategies. J Food Qual. 2025. https:\/\/doi.org\/10.1155\/jfq\/2810946.","journal-title":"J Food Qual"},{"issue":"3","key":"1027_CR4","doi-asserted-by":"publisher","first-page":"48","DOI":"10.5815\/ijigsp.2023.03.04","volume":"15","author":"B Balaji","year":"2023","unstructured":"Balaji B, Satyanarayana Murthy T, Kuchipudi R. A comparative study on plant disease detection and classification using deep learning approaches. Int J Image Graph Signal Process. 2023;15(3):48\u201359. https:\/\/doi.org\/10.5815\/ijigsp.2023.03.04.","journal-title":"Int J Image Graph Signal Process"},{"issue":"1","key":"1027_CR5","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s12393-024-09386-2","volume":"17","author":"T Bidyalakshmi","year":"2025","unstructured":"Bidyalakshmi T, Jyoti B, Mansuri SM, Srivastava A, Mohapatra D, Kalnar YB, et al. Application of artificial intelligence in food processing: current status and future prospects. Food Eng Rev. 2025;17(1):27\u201354. https:\/\/doi.org\/10.1007\/s12393-024-09386-2.","journal-title":"Food Eng Rev"},{"issue":"1","key":"1027_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-025-09890-x","volume":"29","author":"BG Deepa","year":"2026","unstructured":"Deepa BG, Lokesh CK, Umamaheswari D, Ayshwarya B, Yethish PV, Suhaas KP. An enhanced deep learning framework for DeepFake detection using EfficientNet-B3 comparative evaluation of deep and machine learning techniques. Discov Comput. 2026;29(1):18.","journal-title":"Discov Comput"},{"key":"1027_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-34681-1","author":"D Devarajan","year":"2026","unstructured":"Devarajan D, Allafi R, Obayya M, Nemri N. AI based real time disease diagnosis in plants using deep learning driven CNNs. Sci Rep. 2026. https:\/\/doi.org\/10.1038\/s41598-025-34681-1.","journal-title":"Sci Rep"},{"issue":"1","key":"1027_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/ail2.70011","volume":"7","author":"MJ Hoque","year":"2026","unstructured":"Hoque MJ, Islam MS. An explainable and lightweight CNN framework for robust potato leaf disease classification using Grad\u2010CAM visualization. Appl AI Lett. 2026;7(1):e70011. https:\/\/doi.org\/10.1002\/ail2.70011.","journal-title":"Appl AI Lett"},{"key":"1027_CR9","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10020125","author":"QM Ilyas","year":"2023","unstructured":"Ilyas QM, Ahmad M, Mehmood A. Automated estimation of crop yield using artificial intelligence and remote sensing technologies. Bioengineering. 2023. https:\/\/doi.org\/10.3390\/bioengineering10020125.","journal-title":"Bioengineering"},{"key":"1027_CR10","doi-asserted-by":"publisher","unstructured":"Kunapuli G. Ensemble methods in machine learning. Simon and Schuster. In: Manning, vol. 1857. LNCS; 2023. https:\/\/doi.org\/10.1007\/3-540-45014-9_1.","DOI":"10.1007\/3-540-45014-9_1"},{"issue":"2023","key":"1027_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compag.2023.107721","volume":"207","author":"J Leukel","year":"2023","unstructured":"Leukel J, Zimpel T, Stumpe C. Machine learning technology for early prediction of grain yield at the field scale: a systematic review. Comput Electron Agric. 2023;207(2023):1\u201332. https:\/\/doi.org\/10.1016\/j.compag.2023.107721.","journal-title":"Comput Electron Agric"},{"issue":"2","key":"1027_CR12","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/s12403-022-00499-9","volume":"15","author":"JP Meneely","year":"2023","unstructured":"Meneely JP, Kolawole O, Haughey SA, Miller SJ, Krska R, Elliott CT. The challenge of global aflatoxins legislation with a focus on peanuts and peanut products: a systematic review. Exposure Health. 2023;15(2):467\u201387. https:\/\/doi.org\/10.1007\/s12403-022-00499-9.","journal-title":"Exposure Health"},{"key":"1027_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2196\/66029","volume":"6","author":"A Mirugwe","year":"2024","unstructured":"Mirugwe A, Tamale L, Nyirenda J. Improving tuberculosis detection in chest X-ray images through transfer learning and deep learning: A comparative study of CNN architectures. JMIRx Med. 2024;6:1\u201315. https:\/\/doi.org\/10.2196\/66029.","journal-title":"JMIRx Med"},{"issue":"1","key":"1027_CR14","doi-asserted-by":"publisher","first-page":"090","DOI":"10.53771\/ijlsra.2023.5.1.0081","volume":"5","author":"S Mwesige","year":"2023","unstructured":"Mwesige S, Tushabe F, Okoth T, Kasamba I, Areu D. Levels of total aflatoxins in maize and groundnuts across food value chains, gender and agro-ecological zones of Uganda. Int J Life Sci Res Arch. 2023;5(1):090\u20137. https:\/\/doi.org\/10.53771\/ijlsra.2023.5.1.0081.","journal-title":"Int J Life Sci Res Arch"},{"issue":"4","key":"1027_CR15","doi-asserted-by":"publisher","first-page":"2435","DOI":"10.1007\/s00521-024-10758-2","volume":"37","author":"KG Panchbhai","year":"2025","unstructured":"Panchbhai KG, Lanjewar MG. Enhancement of tea leaf diseases identification using modified SOTA models. Neural Comput Appl. 2025;37(4):2435\u201353. https:\/\/doi.org\/10.1007\/s00521-024-10758-2.","journal-title":"Neural Comput Appl"},{"key":"1027_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.foodcont.2025.111234","volume":"174","author":"KG Panchbhai","year":"2025","unstructured":"Panchbhai KG, Lanjewar MG. Portable system for cocoa bean quality assessment using multi-output learning and augmentation. Food Control. 2025;174:111234.","journal-title":"Food Control"},{"issue":"42","key":"1027_CR17","doi-asserted-by":"publisher","first-page":"89871","DOI":"10.1007\/s11042-024-19042-w","volume":"83","author":"KG Panchbhai","year":"2024","unstructured":"Panchbhai KG, Lanjewar MG, Malik VV, Charanarur P. Small size CNN (CAS-CNN), and modified MobileNetV2 (CAS-MODMOBNET) to identify cashew nut and fruit diseases. Multimedia Tools Appl. 2024;83(42):89871\u201391. https:\/\/doi.org\/10.1007\/s11042-024-19042-w.","journal-title":"Multimedia Tools Appl"},{"issue":"1","key":"1027_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s12145-024-01521-1","volume":"18","author":"KG Panchbhai","year":"2024","unstructured":"Panchbhai KG, Lanjewar MG, Naik AV. Modified MobileNet with leaky ReLU and LSTM with balancing technique to classify the soil types. Earth Sci Inform. 2024;18(1):77. https:\/\/doi.org\/10.1007\/s12145-024-01521-1.","journal-title":"Earth Sci Inform"},{"key":"1027_CR19","unstructured":"Partnership for Aflatoxin Control in Africa (PACA). Strengthening aflatoxin control in Uganda: Policy recommendations. 2017, pp. 1\u20138."},{"key":"1027_CR20","doi-asserted-by":"publisher","DOI":"10.4018\/jdm.2013070101","author":"M Rossi","year":"2013","unstructured":"Rossi M, Henfridsson O, Lyytinen K, Siau K. Design science research. J Database Manag. 2013. https:\/\/doi.org\/10.4018\/jdm.2013070101.","journal-title":"J Database Manag"},{"issue":"1","key":"1027_CR21","doi-asserted-by":"publisher","first-page":"82","DOI":"10.18196\/jrc.v5i1.19081","volume":"5","author":"MS Sadimantara","year":"2024","unstructured":"Sadimantara MS, Argo BD, Sucipto S, Riza DFA, Hendrawan Y. The classification of aflatoxin contamination level in cocoa beans using fluorescence imaging and deep learning. J Robot Control JRC. 2024;5(1):82\u201391. https:\/\/doi.org\/10.18196\/jrc.v5i1.19081.","journal-title":"J Robot Control JRC"},{"issue":"June 2023","key":"1027_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jafr.2023.100923","volume":"15","author":"EN Salano","year":"2024","unstructured":"Salano EN, Mulwa RM, Obonyo MA. Peanut (Arachis hypogea) accessions differentially accumulate aflatoxins upon challenge by Aspergillus flavus: implications for aflatoxin mitigation. J Agric Food Res. 2024;15(June 2023):100923. https:\/\/doi.org\/10.1016\/j.jafr.2023.100923.","journal-title":"J Agric Food Res"},{"key":"1027_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI conference on artificial intelligence, vol. 31(1), 2017. http:\/\/arxiv.org\/abs\/1512.00567.","DOI":"10.1609\/aaai.v31i1.11231"},{"issue":"2","key":"1027_CR24","first-page":"141","volume":"10","author":"L Tamale","year":"2025","unstructured":"Tamale L, Ssebuggwawo D, Mirembe DP, Mirugwe A, Lubega JT. Optimizing deep learning models for aflatoxin detection in agricultural products: a case study of groundnuts. Afr J Rural Dev. 2025;10(2):141\u201356.","journal-title":"Afr J Rural Dev"},{"key":"1027_CR25","doi-asserted-by":"publisher","unstructured":"Villamar-Torres RO, Factos-Lai\u00f1o KN, Y\u00e1nez-Cajo D, Mayorga-Morejon KR, Jazayeri SM. An overview to the new era in efficient crop management: artificial intelligence, machine learning, big data, bioinformatics, metagenomics and precision agriculture. 2025. https:\/\/doi.org\/10.36899\/JAPS.2025.3.0054.","DOI":"10.36899\/JAPS.2025.3.0054"},{"key":"1027_CR26","doi-asserted-by":"publisher","unstructured":"Yacouby R, Axman D. Probabilistic extension of precision, recall, and F1 score for more thorough evaluation of classification models. 2020, pp. 79\u201391. https:\/\/doi.org\/10.18653\/v1\/2020.eval4nlp-1.9.","DOI":"10.18653\/v1\/2020.eval4nlp-1.9"},{"issue":"August 2018","key":"1027_CR27","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.fcr.2019.02.022","volume":"235","author":"Q Yang","year":"2019","unstructured":"Yang Q, Shi L, Han J, Zha Y, Zhu P. Deep convolutional neural networks for rice grain yield estimation at the ripening stage using UAV-based remotely sensed images. Field Crops Res. 2019;235(August 2018):142\u201353. https:\/\/doi.org\/10.1016\/j.fcr.2019.02.022.","journal-title":"Field Crops Res"},{"key":"1027_CR28","doi-asserted-by":"publisher","unstructured":"Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design science in information systems research. MIS quarterly, 28(1), 75-106. https:\/\/doi.org\/10.2307\/25148625","DOI":"10.2307\/25148625"},{"key":"1027_CR29","doi-asserted-by":"publisher","unstructured":"Kaminiaris, M. D., Camardo Leggieri, M., Tsitsigiannis, D. I., & Battilani, P. (2020). AFLA-pistachio: Development of a mechanistic model to predict the aflatoxin contamination of pistachio nuts. Toxins, 12(7), 445. https:\/\/doi.org\/10.3390\/toxins12070445","DOI":"10.3390\/toxins12070445"},{"key":"1027_CR30","doi-asserted-by":"publisher","unstructured":"Maharana, K., Mondal, S., & Nemade, B. (2022). A review: Data pre-processing and data augmentation techniques. Global Transitions Proceedings, 3(1), 91-99. https:\/\/doi.org\/10.1016\/j.gltp.2022.04.020","DOI":"10.1016\/j.gltp.2022.04.020"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-026-01027-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-026-01027-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-026-01027-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:07:24Z","timestamp":1781636844000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-026-01027-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1027"],"URL":"https:\/\/doi.org\/10.1007\/s44163-026-01027-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7890269\/v1","asserted-by":"object"}]},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,1]]},"assertion":[{"value":"18 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"291"}}