The influence of non-learnable activation functions on the positioning performance of deep learning-based fingerprinting models trained with small CSI sample sizes

Simple item page
dc.contributor.authorLutakamale, Albert Selebea
dc.contributor.authorManyesela, Yona Zakaria
dc.date.accessioned2023-10-12T11:38:06Z
dc.date.available2023-10-12T11:38:06Z
dc.date.issued2022
dc.descriptionAbstract. Full text article available at https://doi.org/10.1007/s41403-022-00347-xen_US
dc.description.abstractActivation functions, being mathematical ‘gates’ in between the input feeding the current neuron and its output going to the next layer, is very crucial in the training of deep learning models. They play a big part in determining the output of a model, its accuracy, and computational efficiency. In some cases, activation functions have a major effect on the model’s ability to converge and the convergence speed. To be able to train deep learning based fingerprint positioning models using small CSI sample sizes and have satisfactory positioning results, the choice of appropriate activation functions is very important. In this paper we explore several non-learnable activation functions and conduct a comprehensive analysis to study the influence they have on the positioning performance of deep learning fingerprint-based positioning models using small CSI sample sizes. We then propose a better model training approach with a view of getting the best out of those activation functions.en_US
dc.identifier.citationLutakamale, A. S., & Manyesela, Y. Z. (2022). The Influence of Non-learnable Activation Functions on the Positioning Performance of Deep Learning-Based Fingerprinting Models Trained with Small CSI Sample Sizes. Transactions of the Indian National Academy of Engineering, 7(3), 1059-1067.en_US
dc.identifier.otherDOI: https://doi.org/10.1007/s41403-022-00347-x
dc.identifier.urihttp://hdl.handle.net/20.500.12661/4116
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.subjectDeep learningen_US
dc.subjectChannel state informationen_US
dc.subjectActivation functionsen_US
dc.subjectPositioning performanceen_US
dc.subjectSmall CSI sampleen_US
dc.titleThe influence of non-learnable activation functions on the positioning performance of deep learning-based fingerprinting models trained with small CSI sample sizesen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Lutakamale & Manyesela- The influence of non-learnable.pdf
Size:
90.2 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Journal Articles