{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:41:47Z","timestamp":1777696907775,"version":"3.51.4"},"reference-count":55,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000},"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":["Intelligent Data Analysis: An International Journal"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>The activation functions are essential in neural networks because they are the ones responsible for gaining the abstract characteristics of the input through the use of nonlinear transformations. The paper presents a new activation function, which is referred to as Hybrid Discontinuous Activation Function (HDAF). It is continuously differentiable except at zero, unbounded above, bounded below, and non-monotonic. Our results demonstrate that HDAF outperforms ReLU on a number of challenging datasets and neural network models. In the beginning of the experiment, neural networks are trained and classified using benchmark data like Breast Cancer Wisconsin (Diagnostic) and Iris Flower datasets and HDAF achieved 92.98% and 95.56% accuracy, respectively. Secondly, experiments were conducted on VGG16 over the MNIST and CIFAR10 datasets. The HDAF obtained 99.21%, and 84.95% accuracy respectively. Statistical feature measurements demonstrate that HDAF has the best mean accuracy, lowest standard deviation, lowest Root Mean squared error, lowest variance, and lowest Mean squared error. The study indicated that HDAF has faster convergence compared to ReLU, making it a valuable factor in deep learning. The findings from the experiments indicate that HDAF can be a promising for ReLU, leading to better performance in neural network models.<\/jats:p>","DOI":"10.1177\/1088467x251337929","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T19:44:07Z","timestamp":1747251847000},"page":"58-75","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["HDAF: A novel activation function for image classification"],"prefix":"10.1177","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-9441","authenticated-orcid":false,"given":"Heena","family":"Kalim","sequence":"first","affiliation":[{"name":"University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New Delhi, 110078, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3139-4490","authenticated-orcid":false,"given":"Anuradha","family":"Chug","sequence":"additional","affiliation":[{"name":"University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New Delhi, 110078, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Prakash Singh","sequence":"additional","affiliation":[{"name":"University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New Delhi, 110078, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.096"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080920"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.095"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.093"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.10.015"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-022-09744-5"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.02.010"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058537"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120389"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116003"},{"key":"e_1_3_4_12_2","doi-asserted-by":"crossref","unstructured":"Kaliyar RK. Fake news detection using a deep neural network. In: 2018 4th International conference on computing communication and automation (ICCCA) 2018 pp.1\u20137.","DOI":"10.1109\/CCAA.2018.8777343"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7179-2"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.005"},{"key":"e_1_3_4_16_2","article-title":"Sentiment analysis using deep learning techniques: a review","volume":"8","author":"Ain QT","year":"2017","unstructured":"Ain QT, Ali M, Riaz A, et\u00a0al. Sentiment analysis using deep learning techniques: a review. Int J Adv Comput Sci Appl 2017; 8 .","journal-title":"Int J Adv Comput Sci Appl"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13198-020-00972-1"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00332918"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"e_1_3_4_23_2","unstructured":"Broomhead DS Lowe D. Radial basis functions multi-variable functional interpolation and adaptive networks. Technical report Royal Signals and Radar Establishment Malvern (United Kingdom) 1988."},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_4_25_2","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"Bengio Y","year":"2006","unstructured":"Bengio Y, Lamblin P, Popovici D, et\u00a0al. Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 2006; 19.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_26_2","unstructured":"Goodfellow Ian J Jean P-A Mehdi M et\u00a0al. Generative adversarial nets. In: Proceedings of the 27th international conference on neural information processing systems Vol. 2 2014 pp.2672\u20132680."},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955777"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.008"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.088"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.03.080"},{"key":"e_1_3_4_31_2","doi-asserted-by":"crossref","unstructured":"Srivastava Y Murali V Dubey SR. A performance evaluation of loss functions for deep face recognition. In: National conference on computer vision pattern recognition image processing and graphics 2019 pp.322\u2013332. Springer.","DOI":"10.1007\/978-981-15-8697-2_30"},{"key":"e_1_3_4_32_2","first-page":"163","article-title":"Survey of neural transfer functions","volume":"2","author":"Duch W","year":"1999","unstructured":"Duch W, Jankowski N. Survey of neural transfer functions. Neural Comput Surv 1999; 2: 163\u2013212.","journal-title":"Neural Comput Surv"},{"key":"e_1_3_4_33_2","unstructured":"Nair V Hinton GE. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on international conference on machine learning ICML\u201910 2010 pp.807\u2013814 Madison WI USA. Omnipress."},{"key":"e_1_3_4_34_2","unstructured":"Glorot X Bordes A Bengio Y. Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics 2011 pp.315\u2013323. JMLR Workshop and Conference Proceedings."},{"key":"e_1_3_4_35_2","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"Clevert D-A","year":"2015","unstructured":"Clevert D-A, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 2015.","journal-title":"arXiv preprint arXiv:1511.07289"},{"key":"e_1_3_4_36_2","unstructured":"Maas AL Hannun AY Ng AY et\u00a0al. Rectifier nonlinearities improve neural network acoustic models. In: Proc. icml Vol 30 2013 p.3. Citeseer."},{"key":"e_1_3_4_37_2","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S et\u00a0al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision 2015 pp.1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_4_38_2","article-title":"Self-normalizing neural networks","volume":"30","author":"Klambauer G","year":"2017","unstructured":"Klambauer G, Unterthiner T, Mayr A, et\u00a0al. Self-normalizing neural networks. Adv Neural Inf Process Syst 2017; 30.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_39_2","unstructured":"Xu B Wang N Chen T et\u00a0al. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 2015."},{"key":"e_1_3_4_40_2","first-page":"1","article-title":"Advancing brain tumor detection with neurofusion: an innovative cnn-lstm model featuring a novel activation function","author":"Rawat U","year":"2024","unstructured":"Rawat U, Rai C. Advancing brain tumor detection with neurofusion: an innovative cnn-lstm model featuring a novel activation function. Serv Orient Comput Appl 2024; 1\u201319.","journal-title":"Serv Orient Comput Appl"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-024-00908-9"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.3103\/S1060992X24700152"},{"key":"e_1_3_4_43_2","first-page":"10","article-title":"MISH: a self regularized non-monotonic neural activation function","volume":"4","author":"Misra D","year":"2019","unstructured":"Misra D. MISH: a self regularized non-monotonic neural activation function. arXiv preprint arXiv:1908.08681 2019; 4: 10\u201348550.","journal-title":"arXiv preprint arXiv:1908.08681"},{"key":"e_1_3_4_44_2","unstructured":"Ramachandran P Zoph B Le QV. Searching for activation functions. arXiv preprint arXiv:1710.05941 2017."},{"key":"e_1_3_4_45_2","article-title":"Incorporating second-order functional knowledge for better option pricing","volume":"13","author":"Dugas C","year":"2000","unstructured":"Dugas C, Bengio Y, B\u00e9lisle F, et\u00a0al. Incorporating second-order functional knowledge for better option pricing. Adv Neural Inf Process Syst 2000; 13.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_46_2","volume-title":"A better activation function for artificial neural networks","author":"Elliott DL","year":"1993","unstructured":"Elliott DL. A better activation function for artificial neural networks. University of Maryland. Systems Research Center, 1993."},{"key":"e_1_3_4_47_2","doi-asserted-by":"crossref","unstructured":"Adriana Mercioni M Holban S. Telu: a new activation function for deep learning. In: 2020 International symposium on electronics and telecommunications (ISETC) 2020 pp. 1\u20134.","DOI":"10.1109\/ISETC50328.2020.9301084"},{"key":"e_1_3_4_48_2","unstructured":"Vagerwal A. Deeper learning with colu activation. arXiv preprint arXiv:2112.12078 2021."},{"key":"e_1_3_4_49_2","unstructured":"Mithra Noel M Trivedi A Dutta P et\u00a0al. Growing cosine unit: a novel oscillatory activation function that can speedup training and reduce parameters in convolutional neural networks. arXiv e-prints 2021 pages arXiv\u20132108."},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12020"},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11040540"},{"key":"e_1_3_4_52_2","doi-asserted-by":"crossref","unstructured":"Nag S Bhattacharyya M Mukherjee A et\u00a0al. Serf: towards better training of deep neural networks using log-softplus error activation function. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision 2023 pp.5324\u20135333.","DOI":"10.1109\/WACV56688.2023.00529"},{"key":"e_1_3_4_53_2","unstructured":"Fisher R. Iris. UCI Machine Learning Repository 1988."},{"key":"e_1_3_4_54_2","unstructured":"LeCun Y Cortes C Burges C. Mnist handwritten digit database. ATT Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist 2 2010."},{"key":"e_1_3_4_55_2","unstructured":"Kingma DP Ba J. ADAM: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 2014."},{"key":"e_1_3_4_56_2","unstructured":"Ruder S. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 2016."}],"container-title":["Intelligent Data Analysis: An International Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251337929","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1088467X251337929","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251337929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:17Z","timestamp":1777454477000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1088467X251337929"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,14]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1177\/1088467X251337929"],"URL":"https:\/\/doi.org\/10.1177\/1088467x251337929","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,14]]}}}