{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:42:50Z","timestamp":1773002570759,"version":"3.50.1"},"reference-count":33,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"vor","delay-in-days":54,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Leveraging batch normalization (BN) is crucial for deep learning for quick and precise identification of objects. It is a commonly used approach to reduce the variation of input distribution using BN. However, the complex parameters computed at the classifier layer of convolutional neural network (CNN) are the reason for model overfitting and consumption of long training time. This study is proposed to make a comparative analysis of models\u2019 performances on multiclass and multilabel classifiers with and without BN at dense layers of CNN. Consequently, for both classifications, BN layers are incorporated at the fully connected layer of CNN. To build a model, we used datasets of medical plant leaves, potato leaves, and fashion images. The pretrained models such as Mobile Net, VGG16, and Inception Net are customized (tuned) using the transfer learning technique. We made adjustments to training and model hyperparameters, including batch size, number of layers, learning rate, number of epochs, and optimizers. After several experiments on the three models, we observed that the best way to improve the model\u2019s accuracy is by applying BN at the CNN\u2019s dense layer. BN improved the performances of the models on both multiclass and multilabel classifications. This improvement has more significant change in the multilabel classification. Hence, using medicinal plant dataset, the model achieved accuracy of 93% and 83% for multilabel with and without BN, respectively, while achieving 99.2% and 99% for multiclass classification. The experiment also proved that the effectiveness of BN is affected on type datasets, depth of CNN, and batch sizes.<\/jats:p>","DOI":"10.1155\/int\/1466655","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T04:09:35Z","timestamp":1740542975000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Batch Normalization\u2019s Impact on Dense Layers of Multiclass and Multilabel Classifiers"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1102-4414","authenticated-orcid":false,"given":"Misganaw Aguate","family":"Widneh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6455-1838","authenticated-orcid":false,"given":"Amlakie Aschale","family":"Alemu","sequence":"additional","affiliation":[]},{"given":"Dereje Derib","family":"Getie","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,2,24]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"crossref","unstructured":"KimP. Matlab Deep Learning 2017 https:\/\/doi.org\/10.1007\/978-1-4842-2845-6.","DOI":"10.1007\/978-1-4842-2845-6"},{"key":"e_1_2_11_2_2","article-title":"Multi-Label Classification Methods: A Comparative Study","author":"Mayurisingh Nareshpalsingh J.","year":"2017","journal-title":"International Research Journal of Engineering and Technology"},{"key":"e_1_2_11_3_2","unstructured":"ZhangJ.andTungA. Multiple Label Classification for Amazon Rainforest Images 2017."},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929394"},{"key":"e_1_2_11_5_2","article-title":"Medicinal Plant Part Identification and Classification Using Deep Learning Based on Multi Label Categories","volume":"8","author":"Misganaw Aguate A. A.","year":"2021","journal-title":"Ethiopian Journal of Science and Sustainable Development"},{"key":"e_1_2_11_6_2","first-page":"1952","article-title":"A Comparative Analysis of Supervised Multi-Label Text Classification Methods","volume":"1","author":"Dharmadhikari S. C.","year":"1961","journal-title":"International Journal of Engineering Research and Applications"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"e_1_2_11_8_2","doi-asserted-by":"crossref","unstructured":"MohammedH. H. DogduE. G\u00f6r\u00fcrA. K. andChoupaniR. Multi-Label Classification of Text Documents Using Deep Learning 2020 IEEE International Conference on Big Data (Big Data) 2020 IEEE 4681\u20134689.","DOI":"10.1109\/BigData50022.2020.9378266"},{"key":"e_1_2_11_9_2","volume-title":"Multi-Label Classification of Text Documents Using Deep Learning a Thesis Submitted to the Graduate School of Natural and Applied Sciences of C","author":"Haruna Mohammed H.","year":"2020"},{"key":"e_1_2_11_10_2","first-page":"448","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","volume":"1","author":"Ioffe S.","year":"2015","journal-title":"The 32nd International Conference on Machine Learning"},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0378-3758(00)00115-4"},{"key":"e_1_2_11_12_2","first-page":"1946","article-title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models","volume":"2017","author":"Ioffe S.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_13_2","unstructured":"SchillingF. The Effect of Batch Normalization on Deep Convolutional Neural Networks 2016."},{"key":"e_1_2_11_14_2","unstructured":"BaJ. L. KirosJ. R. andHintonG. E. Layer Normalization 2016 https:\/\/arxiv.org\/abs\/1607.06450."},{"key":"e_1_2_11_15_2","first-page":"7694","volume-title":"Advances in Neural Information Processing Systems","author":"Bjorck J.","year":"2018"},{"key":"e_1_2_11_16_2","first-page":"2483","article-title":"How Does Batch Normalization Help Optimization?","volume":"2018","author":"Santurkar S.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2895781"},{"key":"e_1_2_11_18_2","unstructured":"WangZ. SheQ. ZhangP. andZhangJ. Correct Normalization Matters: Understanding the Effect of Normalization on Deep Neural Network Models for Click-Through Rate Prediction 2020 https:\/\/arxiv.org\/abs\/2006.12753."},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.10.049"},{"key":"e_1_2_11_20_2","unstructured":"MichalskiV. An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation 2019 1\u201312 https:\/\/arxiv.org\/abs\/1908.00061."},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v10i2.pp2045-2053"},{"key":"e_1_2_11_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/EAIT.2018.8470438"},{"key":"e_1_2_11_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/APP10082950"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-18402-6"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.30630\/joiv.6.2-2.921"},{"key":"e_1_2_11_26_2","unstructured":"ZhouM. WangQ. ShuJ. ZhaoQ. andMengD. Diagnosing Batch Normalization in Class Incremental Learning 2022 https:\/\/arxiv.org\/abs\/2202.08025."},{"key":"e_1_2_11_27_2","doi-asserted-by":"publisher","DOI":"10.30880\/ijie.2019.11.04.006"},{"key":"e_1_2_11_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412907"},{"key":"e_1_2_11_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01198-w"},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.008"},{"key":"e_1_2_11_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"e_1_2_11_32_2","volume-title":"Transfer Learning-A Comparative Analysis","author":"Saha R.","year":"2018"},{"key":"e_1_2_11_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/1466655","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/1466655","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/1466655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:15:48Z","timestamp":1772993748000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/1466655"}},"subtitle":[],"editor":[{"given":"Riccardo","family":"Ortale","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/1466655"],"URL":"https:\/\/doi.org\/10.1155\/int\/1466655","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-04-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"1466655"}}