Algorithm Unrolling-based Denoising of Multimodal Graph Signals
Authors:
- Hayate KojimaHKHayate Kojima
- Keigo TakanamiKTKeigo Takanami
- Junya HaraJHJunya Hara
- Yukihiro BandohYBYukihiro Bandoh
- Seishi TakamuraSTSeishi Takamura
- Hiroshi HigashiHHHiroshi Higashi
- Yuichi TanakaYTYuichi Tanaka
Preprint
Abstract
We propose a denoising method of multimodal graph signals by iteratively solving signal restoration and graph learning problems. Many complex-structured data, i.e., those on sensor networks, can capture multiple modalities at each measurement point, referred to as modalities. They are also assumed to have an underlying structure or correlations in modality as well as space. Such multimodal data are regarded as graph signals on a twofold graph and they are often corrupted by noise. Furthermore, their spatial/modality relationships are not always given a priori: We need to estimate twofold graphs during a denoising algorithm. In this paper, we consider a signal denoising method on twofold graphs, where graphs are learned simultaneously. We formulate an optimization problem for that and parameters in an iterative algorithm are learned from training data by unrolling the iteration with deep algorithm unrolling. Experimental results on synthetic and real-world data demonstrate that the proposed method outperforms existing model- and deep learning-based graph signal denoising methods.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Graph-Based Denoising for Respiration and Heart Rate Estimation During Sleep in Thermal VideoIEEE Internet of Things Journal, 2022
- Sensor network data denoising via recursive graph median filtersSignal Processing, 2021
- Learning Graphs From Data: A Signal Representation PerspectiveIEEE Signal Processing Magazine, 2019
- Connecting the Dots: Identifying Network Structure via Graph Signal ProcessingIEEE Signal Processing Magazine, 2019
- Playing with Duality: An overview of recent primal?dual approaches for solving large-scale optimization problemsIEEE Signal Processing Magazine, 2015
- The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domainsIEEE Signal Processing Magazine, 2013
- Wireless sensor networks for healthcare: A surveyComputer Networks, 2010
- Graph spectral image smoothing using the heat kernelPattern Recognition, 2008
- Sensor networks: an overviewIEEE Potentials, 2003
- A survey on sensor networksIEEE Communications Magazine, 2002