{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:36:48Z","timestamp":1769830608952,"version":"3.49.0"},"reference-count":45,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T00:00:00Z","timestamp":1641427200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2022,3,31]]},"abstract":"<jats:p>The need to detect and classify objects correctly is a constant challenge, being able to recognize them at different scales and scenarios, sometimes cropped or badly lit is not an easy task. Convolutional neural networks (CNN) have become a widely applied technique since they are completely trainable and suitable to extract features. However, the growing number of convolutional neural networks applications constantly pushes their accuracy improvement. Initially, those improvements involved the use of large datasets, augmentation techniques, and complex algorithms. These methods may have a high computational cost. Nevertheless, feature extraction is known to be the heart of the problem. As a result, other approaches combine different technologies to extract better features to improve the accuracy without the need of more powerful hardware resources. In this paper, we propose a hybrid pooling method that incorporates multiresolution analysis within the CNN layers to reduce the feature map size without losing details. To prevent relevant information from losing during the downsampling process an existing pooling method is combined with wavelet transform technique, keeping those details \"alive\" and enriching other stages of the CNN. Achieving better quality characteristics improves CNN accuracy. To validate this study, ten pooling methods, including the proposed model, are tested using four benchmark datasets. The results are compared with four of the evaluated methods, which are also considered as the state-of-the-art.<\/jats:p>","DOI":"10.3233\/jifs-219223","type":"journal-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T11:46:41Z","timestamp":1641556001000},"page":"4327-4336","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":4,"title":["Hybrid pooling with wavelets for convolutional neural networks"],"prefix":"10.1177","volume":"42","author":[{"given":"Daniel","family":"Trevino-Sanchez","sequence":"first","affiliation":[{"name":"Department of Computing, Electronics and Mechatronics, Universidad de las Americas Puebla, Sta. Catarina Martir, San Andres Cholula, Puebla, Mexico"}]},{"given":"Vicente","family":"Alarcon-Aquino","sequence":"additional","affiliation":[{"name":"Department of Computing, Electronics and Mechatronics, Universidad de las Americas Puebla, Sta. Catarina Martir, San Andres Cholula, Puebla, Mexico"}]}],"member":"179","published-online":{"date-parts":[[2022,1,6]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.28.1.013012"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"StepanovA.B. Construction of activation functions for wavelet neural networks XX IEEE International Conference on Soft Computing and Measurements (2017) 397\u2013399.","DOI":"10.1109\/SCM.2017.7970597"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/s19092040"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Farah MalikA.E. BarinS. and YukselM.E. Accurate Classification of Heart Sound Signals for Cardiovascular Disease Diagnosis by Wavelet Analysis and Convolutional Neural Network: Preliminary Results 28th Signal Processing and Communications Applications Conference (2020) 1\u20134.","DOI":"10.1109\/SIU49456.2020.9302491"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_55"},{"key":"e_1_3_2_7_2","unstructured":"KrizhevskyA. Learning Multiple Layers of Features from Tiny Images Canadian Institute for Advanced Research (CIFAR) 2009."},{"key":"e_1_3_2_8_2","unstructured":"la Cour-HarboA. and JensenA. Wavelets and the lifting scheme Department of Mathematical Sciences Aalborg University (2007) 1\u201344."},{"key":"e_1_3_2_9_2","first-page":"84","article-title":"Improving Classification with CNNs using Wavelet Pooling with Nesterov-Accelerated Adam","volume":"60","author":"Rossetto A.M.","year":"2019","unstructured":"RossettoA.M. and ZhouW., Improving Classification with CNNs using Wavelet Pooling with Nesterov-Accelerated Adam, Proceedings of 11th International Conference on Bioinformatics and Computational Biology60 (2019), 84\u201393.","journal-title":"Proceedings of 11th International Conference on Bioinformatics and Computational Biology"},{"key":"e_1_3_2_10_2","unstructured":"AkansuA.N. and HaddadR.A. Multiresolution Signal Decomposition: Transforms Subbands and Wavelets Second Edition Academic Press San Diego USA (2001) 499."},{"key":"e_1_3_2_11_2","unstructured":"XuB. WangN. ChenT. and LiM. Empirical Evaluation of Rectified Activations in Convolutional Network Computing Research Repository (2015) 1505.00853."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5121\/ijci.2016.5416"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"SzegedyC. VanhouckeV. IoffeS. ShlensJ. and WojnaZ. Rethinking the Inception Architecture for ComputerVision IEEE Conference on Computer Vision and Pattern Recognition (2016) 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"SzegedyC. LiuW. JiaY. SermanetP. ReedS. AnguelovD. ErhanD. VanhouckeV. and RabinovichA. Going deeper with convolutions IEEE Conference on Computer Vision and Pattern Recognition (2015) 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2703082"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11740-9_34"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1080\/02699930701626582"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"OyallonE. BelilovskyE. and ZagoruykoS. Scaling the scattering transform: Deep hybrid networks IEEE International Conference on Computer Vision (2017) 5619\u20135628.","DOI":"10.1109\/ICCV.2017.599"},{"issue":"59","key":"e_1_3_2_19_2","first-page":"1","article-title":"Feature extraction and classification of heart sound using 1D convolutional neural networks","volume":"2019","author":"Li F.","unstructured":"LiF., LiuM., ZhaoY., KongL., DongL., LiuX. and HuiM., Feature extraction and classification of heart sound using 1D convolutional neural networks, EURASIP Journal on Advances in Signal Processing2019(59), 1\u201311.","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"HuangH. HeR. SunZ. and TanT. Wavelet-SRNet: A Wavelet-BasedCNNfor Multi-scale Face Super Resolution IEEE International Conference on Computer Vision (2017) 1698\u20131706.","DOI":"10.1109\/ICCV.2017.187"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957990"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02476026"},{"key":"e_1_3_2_23_2","unstructured":"DaubechiesI. Ten Lectures onWavelets Society for Industrial and Applied Mathematics (1992) 350."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/18.57199"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.2307\/2272846"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2007.898348"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02015-5"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. and SunJ. Deep Residual Learning for Image Recognition IEEE Conference on Computer Vision and Pattern Recognition (2016) 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_29_2","unstructured":"NielsenM.A. Neural Networks and Deep Learning Determination Press 2015."},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"AzeemM.F. BanakarA. and KumarV. Comparative Study of Different Types ofWavelet Functions in Neural Network IEEE International Joint Conference on Neural Network Proceedings (2006) 1061\u20131066.","DOI":"10.1109\/IJCNN.2006.1716217"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"HaqueM.R. and MishuS.Z. Spectral-Spatial Feature Extraction Using PCA and Multi-Scale Deep Convolutional Neural Network for Hyperspectral Image Classification 22nd International Conference on Computer and Information Technology (2019) 1\u20136.","DOI":"10.1109\/ICCIT48885.2019.9038385"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Bastidas-RodriguezM.X. GrusonA. PolaniaL.F. FujiedaS. Prieto-OrtizF. TakayamaK. and HachisukaT. Deep AdaptiveWavelet Network IEEE Winter Conference on Applications of Computer Vision (2020) 3100\u20133108.","DOI":"10.1109\/WACV45572.2020.9093580"},{"key":"e_1_3_2_33_2","unstructured":"ZeilerM. and FergusR. Stochastic pooling for regularization of deep convolutional neural networks 1st International Conference on Learning Representations 2013."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"LiuP. ZhangH. ZhangK. LinL. and ZuoW. Multi-level Wavelet-CNN for Image Restoration IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2018) 886\u2013895.","DOI":"10.1109\/CVPRW.2018.00121"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2921451"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"SharanR.V. Spoken Digit Recognition Using Wavelet Scalogram and Convolutional Neural Networks IEEE Recent Advances in Intelligent Computational Systems (2020) 101\u2013105.","DOI":"10.1109\/RAICS51191.2020.9332505"},{"key":"e_1_3_2_37_2","unstructured":"FujiedaS. TakayamaK. and HachisukaT. Wavelet Convolutional Neural Networks Computing Research Repository (2018) 1805.08620."},{"key":"e_1_3_2_38_2","unstructured":"FujiedaS. TakayamaK. and HachisukaT. Wavelet Convolutional Neural Networks for Texture Classification Computing Research Repository (2017) 1707.07394."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.192463"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"WilliamsT. and LiR. Advanced Image Classification Using Wavelets and Convolutional Neural Networks 15th IEEE International Conference on Machine Learning and Applications (2016) 233\u2013239..","DOI":"10.1109\/ICMLA.2016.0046"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.4236\/jsea.2018.112004"},{"key":"e_1_3_2_42_2","unstructured":"WilliamsT. and LiR. Wavelet Pooling for Convolutional Neural Networks International Conference on Learning Representations 2018."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2885506"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141095289051"},{"key":"e_1_3_2_45_2","unstructured":"LeCunY. and CortesC. MNIST handwritten digit database 2010."},{"key":"e_1_3_2_46_2","unstructured":"NetzerY. WangT. CoatesA. BissaccoA. WuB. and NgA.Y. Reading Digits in Natural Images with Unsupervised Feature Learning (SVHN) NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-219223","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-219223","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-219223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T14:48:38Z","timestamp":1769784518000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-219223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,6]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,3,31]]}},"alternative-id":["10.3233\/JIFS-219223"],"URL":"https:\/\/doi.org\/10.3233\/jifs-219223","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,6]]}}}