A multi-task learning model for super resolution of wireless channel characteristics

Simple item page
dc.contributor.authorWang, Xiping
dc.contributor.authorZhang, Zhao
dc.contributor.authorHe, Danping
dc.contributor.authorGuan, Ke
dc.contributor.authorLiu, Dongliang
dc.contributor.authorDou, Jianwu
dc.contributor.authorMumtaz, Shahid
dc.contributor.authorAl-Rubaye, Saba
dc.date.accessioned2023-01-23T15:04:35Z
dc.date.available2023-01-23T15:04:35Z
dc.date.issued2023-01-11
dc.description.abstractChannel modeling has always been the core part in communication system design and development, especially in 5G and 6G era. Traditional approaches like stochastic channel modeling and ray-tracing (RT) based channel modeling depend heavily on measurement data or simulation, which are usually expensive and time consuming. In this paper, we propose a novel super resolution (SR) model for generating channel character-istics data. The model is based on multi-task learning (MTL) convolutional neural networks (CNN) with residual connection. Experiments demonstrate that the proposed SR model could achieve excellent performances in mean absolute error and standard deviation of error. Advantages of the proposed model are demonstrated in comparisons with other state-of-the-art deep learning models. Ablation study also proved the necessity of multi-task learning and techniques in model design. The contribution in this paper could be helpful in channel modeling, network optimization, positioning and other wireless channel characteristics related work by largely reducing workload of simulation or measurement.en_UK
dc.identifier.citationWang X, Zhang Z, He D, et al., (2023) A multi-task learning model for super resolution of wireless channel characteristics. In: 2022 IEEE Globecom Workshops (GC Wkshps), 4-8 December 2022, Rio de Janeiro, Brazil, pp. 952-957en_UK
dc.identifier.eisbn978-1-6654-3540-6
dc.identifier.isbn978-1-6654-3541-3
dc.identifier.urihttps://doi.org/10.1109/GLOBECOM48099.2022.10001700
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/19005
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectWireless channel modelingen_UK
dc.subjectray-tracing (RT)en_UK
dc.subjectsuper resolution (SR)en_UK
dc.subjectmulti-task learning (MTL)en_UK
dc.subjectconvolutional neural network (CNN)en_UK
dc.titleA multi-task learning model for super resolution of wireless channel characteristicsen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Super_resolution_of_wireless_channel_characteristics-2022.pdf
Size:
9.56 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)