Kamalov, FiruzElnagar, Ashraf2022-05-182022-05-18© 20212021Kamalov, F., & Elnagar, A. (2021). Kernel density estimation-based sampling for neural network classification. 2021 International Symposium on Networks, Computers and Communications, ISNCC. https://doi.org/10.1109/ISNCC52172.2021.9615715978-073811316-6https://doi.org/10.1109/ISNCC52172.2021.9615715http://hdl.handle.net/20.500.12519/639This conference paper is not available at CUD collection. The version of scholarly record of this paper is published in 2021 International Symposium on Networks, Computers and Communications, ISNCC (2021), available online at: https://doi.org/10.1109/ISNCC52172.2021.9615715Imbalanced data occurs in a wide range of scenarios. The skewed distribution of the target variable elicits bias in machine learning algorithms. One of the popular methods to combat imbalanced data is to artificially balance the data through resampling. In this paper, we compare the efficacy of a recently proposed kernel density estimation (KDE) sampling technique in the context of artificial neural networks. We benchmark the KDE sampling method against two base sampling techniques and perform comparative experiments using 8 datasets and 3 neural networks architectures. The results show that KDE sampling produces the best performance on 6 out of 8 datasets. However, it must be used with caution on image datasets. We conclude that KDE sampling is capable of significantly improving the performance of neural networks. © 2021 IEEE.Permission to reuse abstract has been secured from Institute of Electrical and Electronics Engineers Inc.Deep learningImbalanced dataKDEKernel density estimationNeural networksSamplingConference PaperCopyright : © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.