{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T05:25:31Z","timestamp":1765862731802,"version":"3.48.0"},"reference-count":36,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T00:00:00Z","timestamp":1765584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100023652","name":"University of Rijeka","doi-asserted-by":"crossref","award":["uniri\u2014drustv\u201318\u2013122"],"award-info":[{"award-number":["uniri\u2014drustv\u201318\u2013122"]}],"id":[{"id":"10.13039\/501100023652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Peach maturity at harvest is a critical factor influencing fruit quality and postharvest life. Traditional destructive methods for maturity assessment, although effective, compromise fruit integrity and are unsuitable for practical implementation in modern production. This study presents a machine learning approach for non-destructive peach maturity prediction using tabular data collected from 701 \u2018Redhaven\u2019 peaches. Three neural network models suitable for small tabular datasets (TabNet, SAINT, and NODE) were applied and evaluated using classification metrics, including accuracy, F1-score, and AUC. The models demonstrated consistently strong performance across several feature configurations, with TabNet achieving the highest accuracy when all non-destructive measurements were available, while TabNet provided the most robust and practical performance on the comprehensive non-destructive subset and in optimized minimal-feature settings. These findings indicate that non-destructive sensing methods, particularly when combined with modern neural architectures, can reliably predict maturity and offer potential for real-time, automated fruit selection after harvest. The integration of such models into autonomous harvesting systems, for instance, through drone-based platforms equipped with appropriate sensors, could significantly improve efficiency and fruit quality management in horticultural peach production.<\/jats:p>","DOI":"10.3390\/computers14120554","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T15:52:59Z","timestamp":1765813979000},"page":"554","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative Analysis of Neural Network Models for Predicting Peach Maturity on Tabular Data"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9683-3204","authenticated-orcid":false,"given":"Dejan","family":"Ljubobratovi\u0107","sequence":"first","affiliation":[{"name":"Faculty of Informatics and Digital Technologies, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7889-6888","authenticated-orcid":false,"given":"Marko","family":"Vukovi\u0107","sequence":"additional","affiliation":[{"name":"Department of Pomology, Division of Horticulture and Landscape Architecture, University of Zagreb Faculty of Agriculture, Sveto\u0161imunska Cesta 25, 10000 Zagreb, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-4012","authenticated-orcid":false,"given":"Marija","family":"Brki\u0107 Bakari\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Informatics and Digital Technologies, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6672-1834","authenticated-orcid":false,"given":"Tomislav","family":"Jemri\u0107","sequence":"additional","affiliation":[{"name":"Department of Pomology, Division of Horticulture and Landscape Architecture, University of Zagreb Faculty of Agriculture, Sveto\u0161imunska Cesta 25, 10000 Zagreb, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4571-1546","authenticated-orcid":false,"given":"Maja","family":"Mateti\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Informatics and Digital Technologies, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,13]]},"reference":[{"key":"ref_1","unstructured":"Giannopoulos, O., Deltsidis, A., and Chavez, D. (2024). Peaches: Appropriate Harvest and Postharvest Handling. Bulletin 1555, University of Georgia Cooperative Extension."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhang, Y., Li, Y., Xu, L., Zhang, J., Ma, X., Zhang, W., and Jiang, H. (2017). Determination of fruit maturity and its prediction model based on the pericarp index of absorbance difference (IAD) for peaches. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0177511"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ljubobratovi\u0107, D., Vukovi\u0107, M., Brki\u0107 Bakari\u0107, M., Jemri\u0107, T., and Mateti\u0107, M. (2022). Assessment of various machine learning models for peach maturity prediction using non-destructive sensor data. Sensors, 22.","DOI":"10.3390\/s22155791"},{"key":"ref_4","first-page":"111","article-title":"Effect of yellow and Stop Drosophila Normal anti-insect photoselective nets on vegetative, generative and bioactive traits of peach (cv. Suncrest)","volume":"29","author":"Levaj","year":"2023","journal-title":"J. Agric. Sci."},{"key":"ref_5","unstructured":"Ljubobratovi\u0107, D., Zhang, G., Brki\u0107 Bakari\u0107, M., Jemri\u0107, T., and Mateti\u0107, M. (2020, January 21\u201324). Predicting peach fruit ripeness using explainable machine learning. Proceedings of the 31st International DAAAM Symposium, Virtually."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1016\/j.lwt.2009.01.015","article-title":"Non-destructive assessment of apricot fruit quality by portable visible-near infrared spectroscopy","volume":"42","author":"Camps","year":"2009","journal-title":"LWT-Food Sci. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"12345","DOI":"10.1038\/s41598-024-81694-3","article-title":"Incorporation of visible\/near-infrared spectroscopy and machine learning models for indirect assessment of grape ripening indicators","volume":"15","author":"Elsherbiny","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108369","DOI":"10.1016\/j.compag.2023.108369","article-title":"Peach ripeness classification based on a new one-stage instance segmentation model","volume":"214","author":"Zhao","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Aherwadi, N., Mittal, U., Singla, J., Jhanjhi, N.Z., Yassine, A., and Hossain, M.S. (2022). Prediction of fruit maturity, quality, and its life using deep learning algorithms. Electronics, 11.","DOI":"10.3390\/electronics11244100"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ropelewska, E., and Rutkowski, K.P. (2023). The classification of peaches at different ripening stages using machine learning models based on texture parameters of flesh images. Agriculture, 13.","DOI":"10.3390\/agriculture13020498"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"196783","DOI":"10.5586\/aa\/196387","article-title":"Predictions of oil volume in palm fruit and estimates of their ripeness: A comparative study of machine learning algorithms","volume":"77","author":"Shuaib","year":"2024","journal-title":"Acta Agrobot."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ljubobratovi\u0107, D., Vukovi\u0107, M., Brki\u0107 Bakari\u0107, M., Jemri\u0107, T., and Mateti\u0107, M. (2021). Utilization of Explainable Machine Learning Algorithms for Determination of Important Features in \u2018Suncrest\u2019 Peach Maturity Prediction. Electronics, 10.","DOI":"10.3390\/electronics10243115"},{"key":"ref_13","unstructured":"Somvanshi, S., Das, S., Javed, S.A., Antariksa, G., and Hossain, A. (2024). A survey on deep tabular learning. arXiv."},{"key":"ref_14","first-page":"215","article-title":"Recent deep learning methods for tabular data","volume":"30","author":"Hwang","year":"2023","journal-title":"Commun. Stat. Appl. Methods"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fan, Y., and Waldmann, P. (2024). Tabular deep learning: A comparative study applied to multi-task genome-wide prediction. BMC Bioinform., 25.","DOI":"10.1186\/s12859-024-05940-1"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6., and Pfister, T. (2021, January 2\u20139). Tabnet: Attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual Event.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref_17","unstructured":"Popov, S., Morozov, S., and Babenko, A. (2019). Neural oblivious decision ensembles for deep learning on tabular data. arXiv."},{"key":"ref_18","unstructured":"Somepalli, G., Goldblum, M., Schwarzschild, A., Bruss, C.B., and Goldstein, T. (2021). Saint: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Crisosto, C. (2001, January 8\u201311). How do we increase peach consumption?. Proceedings of the V International Peach Symposium 592, Davis, CA, USA.","DOI":"10.17660\/ActaHortic.2002.592.82"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.postharvbio.2008.01.017","article-title":"A new index based on vis spectroscopy to characterize the progression of ripening in peach fruit","volume":"49","author":"Ziosi","year":"2008","journal-title":"Postharvest Biol. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ramina, A., Tonutti, P., and McGlasson, W. (2008). Ripening, nutrition and postharvest physiology. The Peach: Botany, Production and Uses, CABI.","DOI":"10.1079\/9781845933869.0550"},{"key":"ref_22","unstructured":"Neri, F., and Brigati, S. (1994). Sensory and objective evaluation of peaches. COST 94. The Post-Harvest Treatment of Fruit and Vegetables: Quality Criteria, COST."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Vukovi\u0107, M., Ljubobratovi\u0107, D., Mateti\u0107, M., Brki\u0107 Bakari\u0107, M., Juri\u0107, S., and Jemri\u0107, T. (2025). Evolution of Non-Destructive and Destructive Peach \u2018Redhaven\u2019Quality Traits During Maturation. Agronomy, 15.","DOI":"10.3390\/agronomy15061476"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, G., Fu, Q., Fu, Z., Li, X., Mateti\u0107, M., Brkic Bakaric, M., and Jemri\u0107, T. (2020). A comprehensive peach fruit quality evaluation method for grading and consumption. Appl. Sci., 10.","DOI":"10.3390\/app10041348"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer Science & Business Media.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abdel-Sattar, M., Al-Obeed, R.S., Aboukarima, A.M., and Eshra, D.H. (2021). Development of an artificial neural network as a tool for predicting the chemical attributes of fresh peach fruits. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0251185"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kangune, K., Kulkarni, V., and Kosamkar, P. (2019, January 18\u201320). Grapes Ripeness Estimation using Convolutional Neural network and Support Vector Machine. Proceedings of the 2019 Global Conference for Advancement in Technology (GCAT), Bangalore, India.","DOI":"10.1109\/GCAT47503.2019.8978341"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Scalisi, A., Pelliccia, D., and O\u2019Connell, M.G. (2020). Maturity Prediction in Yellow Peach (Prunus persica L.) Cultivars Using a Fluorescence Spectrometer. Sensors, 20.","DOI":"10.3390\/s20226555"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Saragih, R.E., and Emanuel, A.W.R. (2021, January 9\u201311). Banana Ripeness Classification Based on Deep Learning using Convolutional Neural Network. Proceedings of the 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), Virtually.","DOI":"10.1109\/EIConCIT50028.2021.9431928"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Miragaia, R., Ch\u00e1vez, F., D\u00edaz, J., Vivas, A., Prieto, M.H., and Mo\u00f1ino, M.J. (2021). Plum Ripeness Analysis in Real Environments Using Deep Learning with Convolutional Neural Networks. Agronomy, 11.","DOI":"10.3390\/agronomy11112353"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1088\/0957-0233\/10\/6\/320","article-title":"Non-destructive banana ripeness determination using a neural network-based electronic nose","volume":"10","author":"Llobet","year":"1999","journal-title":"Meas. Sci. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1756","DOI":"10.1002\/fsn3.2794","article-title":"Fruit quality prediction based on soil mineral element content in peach orchard","volume":"10","author":"Sun","year":"2022","journal-title":"Food Sci. Nutr."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Betemps, D.L., de Paula, B.V., Parent, S.\u00c9., Galar\u00e7a, S.P., Mayer, N.A., Marodin, G.A.B., Rozane, D.E., Natale, W., Melo, G.W.B., and Parent, L.E. (2020). Humboldtian Diagnosis of Peach Tree (Prunus persica) Nutrition Using Machine-Learning and Compositional Methods. Agronomy, 10.","DOI":"10.3390\/agronomy10060900"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Jin, Y., Chen, B., and Brown, P. (2019). California Almond Yield Prediction at the Orchard Level with a Machine Learning Approach. Front. Plant Sci., 10.","DOI":"10.3389\/fpls.2019.00809"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"6901","DOI":"10.1007\/s13369-018-03695-5","article-title":"Ripeness Classification of Bananas Using an Artificial Neural Network","volume":"44","author":"Mazen","year":"2019","journal-title":"Arab. J. Sci. Eng."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/554\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T05:21:06Z","timestamp":1765862466000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,13]]},"references-count":36,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["computers14120554"],"URL":"https:\/\/doi.org\/10.3390\/computers14120554","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,12,13]]}}}