{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T15:39:12Z","timestamp":1760369952879,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T00:00:00Z","timestamp":1698105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S036113\/1"],"award-info":[{"award-number":["EP\/S036113\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The assessment of food and industrial crops during harvesting is important to determine the quality and downstream processing requirements, which in turn affect their market value. While machine learning models have been developed for this purpose, their deployment is hindered by the high cost of labelling the crop images to provide data for model training. This study examines the capabilities of semi-supervised and active learning to minimise effort when labelling cotton lint samples while maintaining high classification accuracy. Random forest classification models were developed using supervised learning, semi-supervised learning, and active learning to determine Egyptian cotton grade. Compared to supervised learning (80.20\u201382.66%) and semi-supervised learning (81.39\u201385.26%), active learning models were able to achieve higher accuracy (82.85\u201385.33%) with up to 46.4% reduction in the volume of labelled data required. The primary obstacle when using machine learning for Egyptian cotton grading is the time required for labelling cotton lint samples. However, by applying active learning, this study successfully decreased the time needed from 422.5 to 177.5 min. The findings of this study demonstrate that active learning is a promising approach for developing accurate and efficient machine learning models for grading food and industrial crops.<\/jats:p>","DOI":"10.3390\/s23218671","type":"journal-article","created":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T11:39:04Z","timestamp":1698147544000},"page":"8671","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["AI-Assisted Cotton Grading: Active and Semi-Supervised Learning to Reduce the Image-Labelling Burden"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1158-6751","authenticated-orcid":false,"given":"Oliver J.","family":"Fisher","sequence":"first","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University of Nottingham, Nottingham NG7 2RD, UK"},{"name":"School of Chemistry and Chemical Engineering, University of Surrey, Guildford GU2 7XH, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4278-3165","authenticated-orcid":false,"given":"Ahmed","family":"Rady","sequence":"additional","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University of Nottingham, Nottingham NG7 2RD, UK"},{"name":"Teagasc Food Research Centre, Ashtown, D15 DY05 Dublin, Ireland"}]},{"given":"Aly A. A.","family":"El-Banna","sequence":"additional","affiliation":[{"name":"Department of Plant Production, Faculty of Agriculture, Saba Basha, Alexandria University, Alexandria 5424041, Egypt"}]},{"given":"Haitham H.","family":"Emaish","sequence":"additional","affiliation":[{"name":"Department of Soils and Agricultural Chemistry, Faculty of Agriculture, Saba Basha, Alexandria University, Alexandria 5424041, Egypt"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5216-4873","authenticated-orcid":false,"given":"Nicholas J.","family":"Watson","sequence":"additional","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University of Nottingham, Nottingham NG7 2RD, UK"},{"name":"School of Food Science and Nutrition, University of Leeds, Leeds LS2 9JT, UK"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.coche.2015.07.001","article-title":"Automatic discovery and optimization of chemical processes","volume":"9","author":"Houben","year":"2015","journal-title":"Curr. Opin. Chem. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2952","DOI":"10.2166\/wst.2017.162","article-title":"Gaussian process regression for monitoring and fault detection of wastewater treatment processes","volume":"75","author":"Samuelsson","year":"2017","journal-title":"Water Sci. Technol."},{"key":"ref_3","unstructured":"Mowbray, M., del Rio-Chanona, E., Harun, I., Hellgardt, K., and Zhang, D. (2020). Ensemble Learning for bioprocess dynamic modelling and prediction. Authorea Prepr."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.meatsci.2017.10.014","article-title":"Assessing different processed meats for adulterants using visible-near-infrared spectroscopy","volume":"136","author":"Rady","year":"2018","journal-title":"Meat Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"642786","DOI":"10.3389\/fsufs.2021.642786","article-title":"Intelligent sensors for sustainable food and drink manufacturing","volume":"5","author":"Watson","year":"2021","journal-title":"Front. Sustain. Food Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s12161-020-01886-1","article-title":"Near-infrared spectroscopy and hyperspectral imaging for sugar content evaluation in potatoes over multiple growing seasons","volume":"14","author":"Rady","year":"2021","journal-title":"Food Anal. Methods"},{"key":"ref_7","unstructured":"Sinclair, R. (2015). Woodhead Publishing Series in Textiles, Woodhead Publishing."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Khan, Z., Ali, Z., and Khan, A.A. (2022). Cotton Breeding and Biotechnology, Taylor & Francis Group.","DOI":"10.1201\/9781003096856"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"210","DOI":"10.56454\/ZELZ3209","article-title":"Engineering and ginning textile industry needs","volume":"21","author":"Delhom","year":"2017","journal-title":"J. Cotton Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2134\/cftm2017.07.0048","article-title":"Impact of cotton leaf and bract characteristics on cotton leaf grade","volume":"4","author":"Eder","year":"2018","journal-title":"Crop. Forage Turfgrass Manag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1016\/j.procs.2020.06.149","article-title":"Cotton appearance grade classification based on machine learning","volume":"174","author":"Lv","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wei, W., Zhang, C., and Deng, D. (2020). Content estimation of foreign fibers in cotton based on deep learning. Electronics, 9.","DOI":"10.3390\/electronics9111795"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1642","DOI":"10.1117\/12.164326","article-title":"Clustering and neural networks to categorize cotton trash","volume":"33","author":"Lieberman","year":"1994","journal-title":"Opt. Eng."},{"key":"ref_14","first-page":"17","article-title":"Important aspects of cotton colour measurement","volume":"18","author":"Matusiak","year":"2010","journal-title":"Fibres Text. East. Eur."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.13031\/2013.32584","article-title":"UV\/Visible\/Near-Infrared reflectance models for the rapid and non-destructive prediction and classification of cotton color and physical indices","volume":"53","author":"Liu","year":"2010","journal-title":"Trans. ASABE"},{"key":"ref_16","first-page":"191","article-title":"Relationship between fiber cotton grade and some related characteristics of long and extra-long staple Egyptian cotton varieties (Gossypium barbadense. L)","volume":"28","author":"Hussein","year":"2020","journal-title":"Arab Univ. J. Agric. Sci."},{"key":"ref_17","first-page":"88","article-title":"Current situation of Egyptian cotton: Econometrics study using ARDL model","volume":"11","author":"Ahmed","year":"2019","journal-title":"J. Agric. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1177\/004051759806800505","article-title":"Cotton color measurements by an imaging colorimeter","volume":"68","author":"Xu","year":"1998","journal-title":"Text. Res. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1177\/004051759806801101","article-title":"Investigating new factors in cotton color grading","volume":"68","author":"Xu","year":"2016","journal-title":"Text. Res. J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1177\/004051759906901202","article-title":"Color grading of cotton part II: Color grading with an expert system and neural networks","volume":"69","author":"Cheng","year":"1999","journal-title":"Text. Res. J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1177\/0040517513490055","article-title":"An investigation into the intra-sample variation in the color of cotton using image analysis","volume":"84","author":"Cui","year":"2014","journal-title":"Text. Res. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.compeleceng.2015.06.022","article-title":"A fast image segmentation algorithm for detection of pseudo-foreign fibers in lint cotton","volume":"46","author":"Wang","year":"2015","journal-title":"Comput. Electr. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"421","DOI":"10.13031\/2013.18307","article-title":"Image-processing solution to cotton color meaurement problems: Part I. instrument design and construction","volume":"48","author":"Thomasson","year":"2005","journal-title":"Trans. ASAE"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"75101","DOI":"10.1088\/2053-1591\/aba3e4","article-title":"Study on the measurement and evaluation of cotton color using image analysis","volume":"7","author":"Heng","year":"2020","journal-title":"Mater. Res. Express"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1177\/004051750207200905","article-title":"Objective evaluation of the trash and color of raw cotton by image processing and neural network","volume":"72","author":"Kang","year":"2016","journal-title":"Text. Res. J."},{"key":"ref_26","unstructured":"Chen, S., Ling, L.N., Yuan, R.C., and Sun, L.Q. (2012, January 27\u201329). Classification model of seed cotton grade based on least square support vector machine regression method. Proceedings of the Proceedings: 2012 IEEE 6th International Conference on Information and Automation for Sustainability, Beijing, China."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Mustafic, A., Li, C., and Haidekker, M. (2014). Blue and UV LED-induced fluorescence in cotton foreign matter. J. Biol. Eng., 8.","DOI":"10.1186\/1754-1611-8-29"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kuzy, J., and Li, C. (2017). A pulsed thermographic imaging system for detection and identification of cotton foreign matter. Sensors, 17.","DOI":"10.3390\/s17030518"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1177\/0040517513478481","article-title":"Potential of visible and near infrared spectroscopy in the determination of instrumental leaf grade in lint cottons","volume":"83","author":"Liu","year":"2013","journal-title":"Text. Res. J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.indcrop.2015.11.022","article-title":"Compositional features of cotton plant biomass fractions characterized by attenuated total reflection Fourier transform infrared spectroscopy","volume":"79","author":"Liu","year":"2016","journal-title":"Ind. Crops Prod."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, D., Wang, Q., and Arandjelovi\u2019c, O.A. (2021). Edge detecting method for microscopic image of cotton fiber cross-section using RCF deep neural network. Information, 12.","DOI":"10.3390\/info12050196"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1177\/00405175221145571","article-title":"An image processing and machine learning solution to automate Egyptian cotton lint grading","volume":"93","author":"Fisher","year":"2022","journal-title":"Text. Res. J."},{"key":"ref_33","unstructured":"(2023, August 15). Cotton the Stages of Trading and Ginning and the Factors Affecting the Determination of Grades. Available online: https:\/\/misrelzraea.com\/43153-2\/."},{"key":"ref_34","unstructured":"(2023, August 15). Cotton Arbitration and Testing General Organization. Available online: https:\/\/www.egyptcotton-catgo.org\/HomePageEN.aspx."},{"key":"ref_35","unstructured":"Gourlot, J.-P., Drieling, A., Qaud, M., Gordon, S., Knowlton, J., Matusiak, M., van der Sluijs, R., Martin, V., Froese, K., and Delhom, C. (2020). Interpretation and Use of Instrument Measured Cotto Characteristics, International Cotton Advisory Committee (ICAC). Available online: https:\/\/ica-bremen.org\/cotton-information\/cotton-quality-information\/the-cotton-testing-guideline\/."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"105240","DOI":"10.1016\/j.compag.2020.105240","article-title":"Few-shot cotton pest recognition and terminal realization","volume":"169","author":"Li","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s13007-022-00866-2","article-title":"A survey of few-shot learning in smart agriculture: Developments, applications, and challenges","volume":"18","author":"Yang","year":"2022","journal-title":"Plant Methods"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1007\/s11704-019-8452-2","article-title":"Safe semi-supervised learning: A brief introduction","volume":"13","author":"Li","year":"2019","journal-title":"Front. Comput. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Bao, X.M., Peng, X., Wang, Y.M., and Cao, Z.B. (2009, January 7\u20138). Textile image segmentation based on semi-supervised clustering and Bayes decision. Proceedings of the 2009 International Conference on Artificial Intelligence and Computational Intelligence, Shanghai, China.","DOI":"10.1109\/AICI.2009.174"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1177\/0040517520966733","article-title":"Semi-supervised fabric defect detection based on image reconstruction and density estimation","volume":"91","author":"Zhou","year":"2020","journal-title":"Text. Res. J."},{"key":"ref_41","unstructured":"Chapelle, O., Sch\u00f6lkopf, B., and Zien, A. (2010). Semi-Supervised Learning, The MIT Press."},{"key":"ref_42","first-page":"129","article-title":"Active learning with statistical models","volume":"4","author":"Cohncohn","year":"1996","journal-title":"J. Articial Intell. Res."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/LLS.2016.2615086","article-title":"A Multimetric Evaluation of Stratified Random Sampling for Classification: A Case Study","volume":"2","author":"Thakur","year":"2016","journal-title":"IEEE Life Sci. Lett."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/1758-2946-6-10","article-title":"Cross-validation pitfalls when selecting and assessing regression and classification models","volume":"6","author":"Krstajic","year":"2014","journal-title":"J. Cheminform."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.compchemeng.2017.02.008","article-title":"Comparative analysis of data mining and response surface methodology predictive models for enzymatic hydrolysis of pretreated olive tree biomass","volume":"11","author":"Charte","year":"2017","journal-title":"Comput. Chem. Eng."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.enbuild.2017.04.038","article-title":"Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption","volume":"147","author":"Ahmad","year":"2017","journal-title":"Energy Build."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s13755-017-0023-z","article-title":"Progressive sampling-based Bayesian optimization for efficient and automatic machine learning model selection","volume":"5","author":"Zeng","year":"2017","journal-title":"Health Inf. Sci. Syst."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Varma, S., and Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinform., 7.","DOI":"10.1186\/1471-2105-7-91"},{"key":"ref_49","first-page":"52","article-title":"Exploration of the validity of utilizing different aspects of color attributes to signalize and signify the lint grade of Egyptian cottons","volume":"3","author":"Hussein","year":"2013","journal-title":"Indian J. Fibre Text. Res."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Commun. ACM"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","article-title":"A survey on semi-supervised learning","volume":"109","author":"Hoos","year":"2020","journal-title":"Mach. Learn."},{"key":"ref_53","unstructured":"Selvaraj, H., Zydek, D., and Chmaj, G. (2015). Active Learning based on Random Forest and Its Application to Terrain Classification BT\u2014Progress in Systems Engineering, Springer International Publishing."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8671\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:10:56Z","timestamp":1760130656000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8671"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,24]]},"references-count":53,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23218671"],"URL":"https:\/\/doi.org\/10.3390\/s23218671","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,10,24]]}}}