Deep Learning-Based Channel Estimation

By Mehran Soltani, V. Pourahmadi, A. Mirzaei, H. Sheikhzadeh. IEEE Communications Letters, 2018

711 citations recorded by the source corpus.

In this letter, we present a deep learning algorithm for channel estimation in communication systems. We consider the time–frequency response of a fast fading communication channel as a 2D image. The aim is to find the unknown values of the channel response using some known values at the pilot locations. To this end, a general pipeline using deep image processing techniques, image super-resolution (SR), and image restoration (IR) is proposed. This scheme considers the pilot values, altogether, as a low-resolution image and uses an SR network cascaded with a denoising IR network to estimate the channel. Moreover, the implementation of the proposed pipeline is presented. The estimation error shows that the presented algorithm is comparable to the minimum mean square error (MMSE) with full knowledge of the channel statistics, and it is better than an approximation to linear MMSE. The results confirm that this pipeline can be used efficiently in channel estimation.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0045afe2628902c17300982266798af7b2a3c440

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. David Gesbert
2. Paul de Kerret
3. Chandra Ramabhadra Murthy
4. Mihaela van der Schaar
5. N. Sidiropoulos
6. Deniz Gündüz
7. Ahmed M. Alaa
8. Ioana Bica

In Computational Mechanics

1. Deniz Gündüz
2. Mihaela van der Schaar
3. N. Sidiropoulos
4. Lieven De Lathauwer
5. Alwin Stegeman
6. Pierre Comon
7. Andrzej S. Cichocki
8. Anh Huy Phan

In Computer Vision and Pattern Recognition

1. Deniz Gündüz
2. Mihaela van der Schaar
3. Shu Sun
4. N. Sidiropoulos

Citations in the corpus

• Massive MIMO Systems for 5G and beyond Networks—Overview, Recent Trends, Challenges, and Future Research Direction (2020, neutral): “The authors of Reference [153] considered a massive MIMO channel as an image and applied a deep learning image super-position and denoising method.”
• Machine Learning in the Air (2019, background): “In the context of wideband channels, [28] models the channel time-frequency response as an image, and the pilot based samples as a low-resolution sampled version of the image.”
• 5G-Advanced Toward 6G: Past, Present, and Future (2023, methodology): “Channel estimation was treated as a super-resolution problem in [29] and [30], where ChannelNet [29] and ReEsNet [30] have shown their capability”