Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks
Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks
复制标题
DOI：
10.1109/tccn.2023.3322983
复制
发表时间：
2023-02
影响因子：
8.6
通讯作者：
M. J. Bocus;Xiaoyang Wang;R. Piechocki
中科院分区：
文献类型：
--
作者：
M. J. Bocus;Xiaoyang Wang;R. Piechocki
提出了一种基于矢量量化变分自编码器（VQVAE）结构的多模态数据融合方法。所提出的方法是简单而有效的，在配对MNIST-SVHN数据和WiFi频谱数据上实现了良好的重建性能。此外，多模VQVAE模型被扩展到5G通信场景，其中端到端信道状态信息（CSI）反馈系统被实现以压缩在基站（eNodeB）和用户设备（UE）之间传输的数据，而没有显著的性能损失。所提出的模型为各种类型的输入数据（CSI，频谱图，自然图像等）学习一个有区别的压缩特征空间，使其成为计算资源有限的应用程序的合适解决方案。
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.