{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T06:28:10Z","timestamp":1787120890801,"version":"build-2736575974"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Accurate classification of unsound wheat kernels is important for automated grain quality assessment, but improved recognition performance often comes at the cost of increased model complexity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study presents ECA-ModNet, a parameter-efficient convolutional network derived from EfficientNetV2-S. The architecture replaces two early-stage Fused-MBConv blocks with Mod-FusedMBConv blocks to introduce input-dependent local contextual modulation and replaces the squeeze-and-excitation modules in later stages with efficient channel attention to model local cross-channel interactions using fewer attention-related parameters. Experiments were conducted on the seven-class G600 wheat subset of the GrainSpace dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across three independent runs, ECA-ModNet achieved an accuracy of 90.17 \u00b1 0.21% and a macro-F1 score of 90.23 \u00b1 0.21%, improving upon EfficientNetV2-S by 3.80 and 3.84 percentage points, respectively. The parameter count decreased from 20.19M to 16.49M, while FLOPs increased marginally from 2.90G to 2.95G. ECA-ModNet achieved accuracy statistically comparable to that of ConvNeXt-Tiny and InceptionNeXt-T while using substantially fewer parameters, and obtained 3.03\u20134.55 percentage points higher mean accuracy than six lightweight baselines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Ablation experiments identified two Stage 1 Mod-FusedMBConv blocks with a 3\u00d73 context kernel as the configuration with the highest mean accuracy among those evaluated. These results indicate that ECA-ModNet offers a favorable accuracy\u2013parameter trade-off for image-based classification of unsound wheat kernels.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1902739","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T05:48:56Z","timestamp":1787118536000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ECA-ModNet: a parameter-efficient network for unsound wheat kernel classification"],"prefix":"10.3389","volume":"17","author":[{"given":"Ming","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Tongling University","place":["Tongling, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Ning","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Software Engineering, Zhengzhou University of Light Industry","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Tongling University","place":["Tongling, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengtao","family":"Lv","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zelong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Food and Health, Beijing Technology and Business University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxin","family":"Cai","sequence":"additional","affiliation":[{"name":"Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s12571-013-0248-x","article-title":"The importance for food security of maintaining rust resistance in wheat","volume":"5","author":"Chaves","year":"2013","journal-title":"Food Secur."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1111\/j.1365-2621.2012.02970.x","article-title":"Unsound kernel identification using linear colour charge\u2010coupled device","volume":"47","author":"Chen","year":"2012","journal-title":"Int. J. Food Sci. Technol."},{"key":"B3","first-page":"172","article-title":"Image recognition of unsound wheat using artificial neural network","author":"Cheng","year":"2010"},{"key":"B4","doi-asserted-by":"publisher","first-page":"771","DOI":"10.28979\/jarnas.1512352","article-title":"Classifying sunn pest damaged and healthy wheat grains across different species with YOLOV8 and vision transformers","volume":"10","author":"\u00c7olak","year":"2024","journal-title":"J. Adv. Res. Nat. Appl. Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1111\/aab.12108","article-title":"Food security: The challenge of increasing wheat yield and the importance of not compromising food safety","volume":"164","author":"Curtis","year":"2014","journal-title":"Ann. Appl. Biol."},{"key":"B6","first-page":"13728","article-title":"RepVGG: Making VGG-style ConvNets great again","author":"Ding","year":"2021"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2010.11929","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"B8","first-page":"21084","article-title":"GrainSpace: A large-scale dataset for fine-grained and domain-adaptive recognition of cereal grains","author":"Fan","year":"2022"},{"key":"B9","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.fcr.2007.04.002","article-title":"The importance of grain or kernel number in wheat: A reply to sinclair and jamieson","volume":"105","author":"Fischer","year":"2008","journal-title":"Field Crops Res."},{"key":"B10","doi-asserted-by":"publisher","first-page":"20092","DOI":"10.1109\/ACCESS.2022.3147838","article-title":"Detection of wheat unsound kernels based on improved ResNet","volume":"10","author":"Gao","year":"2022","journal-title":"IEEE Access"},{"key":"B11","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","article-title":"Visual attention network","volume":"9","author":"Guo","year":"2023","journal-title":"Comput. Vis. Media"},{"key":"B12","first-page":"1577","article-title":"GhostNet: More features from cheap operations","author":"Han","year":"2020"},{"key":"B13","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1503.02531","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"B15","first-page":"1314","article-title":"Searching for mobileNetV3","author":"Howard","year":"2019"},{"key":"B16","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"B17","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"B18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-030-34163-3_1","article-title":"The importance of wheat","volume-title":"Wheat Quality for Improving Processing and Human Health","author":"Igrejas","year":"2020"},{"key":"B19","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"B20","first-page":"11966","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2403.19963","article-title":"Efficient modulation for vision networks","author":"Ma","year":"2024"},{"key":"B22","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","volume-title":"Computer Vision \u2013 ECCV 2018, Lecture Notes in Computer Science","author":"Ma","year":"2018"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2110.02178","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"B24","doi-asserted-by":"publisher","first-page":"6105","DOI":"10.48550\/ARXIV.1905.11946","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"97","author":"Tan","year":"2019"},{"key":"B25","doi-asserted-by":"publisher","first-page":"10096","DOI":"10.48550\/ARXIV.2104.00298","article-title":"EfficientNetV2: Smaller models and faster training","volume":"139","author":"Tan","year":"2021"},{"key":"B26","first-page":"15909","article-title":"Rep ViT: Revisiting mobile CNN from ViT perspective","author":"Wang","year":"2024"},{"key":"B27","first-page":"11531","article-title":"ECA-net: Efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"B28","first-page":"4203","article-title":"Focal modulation networks","author":"Yang","year":"2022"},{"key":"B29","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.foodchem.2003.08.037","article-title":"Comparison of wheat flours grown at different locations for their antioxidant properties","volume":"86","author":"Yu","year":"2004","journal-title":"Food Chem."},{"key":"B30","first-page":"5672","article-title":"InceptionNeXt: When inception meets ConvNeXt","author":"Yu","year":"2024"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2023.104843","article-title":"Rapid and nondestructive THz inspection of unsound kernel of sunflower seed based on SMOTE algorithm","volume":"133","author":"Yuan","year":"2023","journal-title":"Infrared Phys. Technol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"5833","DOI":"10.3233\/JIFS-213195","article-title":"Unsound wheat kernel recognition based on deep convolutional neural network transfer learning and feature fusion","volume":"43","author":"Zhang","year":"2022","journal-title":"J.\u00a0Intell. Fuzzy Syst. Appl. Eng. Technol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"474","DOI":"10.20965\/jaciii.2023.p0474","article-title":"Real-time wheat unsound kernel classification detection based on improved YOLOv5","volume":"27","author":"Zhang","year":"2023","journal-title":"J. Adv. Comput. Intell. Intell. Inform."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1902739\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T05:48:58Z","timestamp":1787118538000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1902739\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":33,"alternative-id":["10.3389\/fpls.2026.1902739"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1902739","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"article-number":"1902739"}}