Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks

Mohammud J. Bocus; Xiaoyang Wang; Robert J. Piechocki

doi:10.48550/arXiv.2302.12636

Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks

Mohammud J. Bocus, Xiaoyang Wang, Robert J. Piechocki

Research output: Contribution to journal › Article (Academic Journal) › peer-review

86 Downloads (Pure)

Abstract

This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST-SVHN data and WiFi spectrogram data. Additionally, the multimodal VQVAE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources.

Original language	English
Number of pages	11
Journal	IEEE Transactions on Cognitive Communications and Networking
Early online date	10 Oct 2023
DOIs	https://doi.org/10.48550/arXiv.2302.12636 https://doi.org/10.1109/TCCN.2023.3322983
Publication status	E-pub ahead of print - 10 Oct 2023

Bibliographical note

Publisher Copyright: IEEE

Funding Information: This work was performed as a part of the OPERA Project, funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant EP/R018677/1. This work has also been funded in part by the Next-Generation Converged Digital Infrastructure (NG-CDI) Project, supported by BT and Engineering and Physical Sciences Research Council (EPSRC), Grant ref. EP/R004935/1.

Keywords

cs.LG
cs.AI
eess.SP

Access to Document

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/TCCN.2023.3322983. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 10.4 MBLicence: CC BY

Handle.net

Persistent link

Cite this

@article{bf1d9d4880534c6bbc9615037a577ca3,

title = "Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks",

abstract = "This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST-SVHN data and WiFi spectrogram data. Additionally, the multimodal VQVAE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources. ",

keywords = "cs.LG, cs.AI, eess.SP",

author = "Bocus, {Mohammud J.} and Xiaoyang Wang and Piechocki, {Robert J.}",

note = "Publisher Copyright: IEEE Funding Information: This work was performed as a part of the OPERA Project, funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant EP/R018677/1. This work has also been funded in part by the Next-Generation Converged Digital Infrastructure (NG-CDI) Project, supported by BT and Engineering and Physical Sciences Research Council (EPSRC), Grant ref. EP/R004935/1.",

year = "2023",

month = oct,

day = "10",

doi = "10.48550/arXiv.2302.12636",

language = "English",

journal = "IEEE Transactions on Cognitive Communications and Networking",

issn = "2332-7731",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - JOUR

T1 - Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks

AU - Bocus, Mohammud J.

AU - Wang, Xiaoyang

AU - Piechocki, Robert J.

N1 - Publisher Copyright: IEEE Funding Information: This work was performed as a part of the OPERA Project, funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant EP/R018677/1. This work has also been funded in part by the Next-Generation Converged Digital Infrastructure (NG-CDI) Project, supported by BT and Engineering and Physical Sciences Research Council (EPSRC), Grant ref. EP/R004935/1.

PY - 2023/10/10

Y1 - 2023/10/10

N2 - This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST-SVHN data and WiFi spectrogram data. Additionally, the multimodal VQVAE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources.

AB - This paper presents a novel approach for multimodal data fusion based on the Vector-Quantized Variational Autoencoder (VQVAE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST-SVHN data and WiFi spectrogram data. Additionally, the multimodal VQVAE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources.

KW - cs.LG

KW - cs.AI

KW - eess.SP

U2 - 10.48550/arXiv.2302.12636

DO - 10.48550/arXiv.2302.12636

M3 - Article (Academic Journal)

SN - 2332-7731

JO - IEEE Transactions on Cognitive Communications and Networking

JF - IEEE Transactions on Cognitive Communications and Networking

ER -

Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks

Abstract

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this