Machine Learning on Camera Images for Fast mmWave Beamforming

• URL: http://arxiv.org/abs/2102.07337v1
• Date: Mon, 15 Feb 2021 04:38:00 GMT
• Title: Machine Learning on Camera Images for Fast mmWave Beamforming
• Authors: Batool Salehi, Mauro Belgiovine, Sara Garcia Sanchez, Jennifer Dy, Stratis Ioannidis, Kaushik Chowdhury
• Abstract summary: Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector combinations to identify the beam pair with the highest SNR. We propose a machine learning (ML) approach with two sequential convolutional neural networks (CNN) that uses out-of-band information. We experimentally validate this intriguing concept for indoor settings using the NI 60GHz mmwave transceiver.
• Score: 7.89556780984955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands. Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector combinations to identify the beam pair with the highest SNR. In this paper, we propose a machine learning (ML) approach with two sequential convolutional neural networks (CNN) that uses out-of-band information, in the form of camera images, to (i) rapidly identify the locations of the transmitter and receiver nodes, and then (ii) return the optimal beam pair. We experimentally validate this intriguing concept for indoor settings using the NI 60GHz mmwave transceiver. Our results reveal that our ML approach reduces beamforming related exploration time by 93% under different ambient lighting conditions, with an error of less than 1% compared to the time-intensive deterministic method defined by the current standards.

Related papers

• bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction [57.199618102578576]
  We propose bit2bit, a new method for reconstructing high-quality image stacks at original resolution from sparse binary quantatemporal image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data. We present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions.
  arXiv  Detail & Related papers  (2024-10-30T17:30:35Z)
• Deep Learning and Image Super-Resolution-Guided Beam and Power Allocation for mmWave Networks [80.37827344656048]
  We develop a deep learning (DL)-guided hybrid beam and power allocation approach for millimeter-wave (mmWave) networks. We exploit the synergy of supervised learning and super-resolution technology to enable low-overhead beam- and power allocation.
  arXiv  Detail & Related papers  (2023-05-08T05:40:54Z)
• Fast Beam Alignment via Pure Exploration in Multi-armed Bandits [91.11360914335384]
  We develop a bandit-based fast BA algorithm to reduce BA latency for millimeter-wave (mmWave) communications. Our algorithm is named Two-Phase Heteroscedastic Track-and-Stop (2PHT&S)
  arXiv  Detail & Related papers  (2022-10-23T05:57:39Z)
• Deep Learning Based Hybrid Precoding in Dual-Band Communication Systems [34.03893373401685]
  We propose a deep learning-based method that uses spatial and temporal information extracted from the sub-6GHz band to predict/track beams in the millimeter-wave (mmWave) band. We consider a dual-band communication system operating in both the sub-6GHz and mmWave bands.
  arXiv  Detail & Related papers  (2021-07-16T12:10:32Z)
• Non-line-of-sight imaging with picosecond temporal resolution [13.81942907279106]
  Non-line-of-sight (NLOS) imaging enables monitoring around corners and is promising for diverse applications. We construct an up-conversion single-photon detector with a high temporal resolution of 1.4 ps and a low noise count rate of 5 counts per second (cps) Our system can provide a 180 mum axial resolution and a 2 mm lateral resolution, which is more than one order of magnitude better than that in previous experiments.
  arXiv  Detail & Related papers  (2021-06-30T03:55:45Z)
• A Novel Look at LIDAR-aided Data-driven mmWave Beam Selection [24.711393214172148]
  We propose a lightweight neural network (NN) architecture along with the corresponding LIDAR preprocessing. Our NN-based beam selection scheme can achieve 79.9% throughput without any beam search overhead and 95% by searching among as few as 6 beams.
  arXiv  Detail & Related papers  (2021-04-29T18:07:31Z)
• Deep Unfolded Recovery of Sub-Nyquist Sampled Ultrasound Image [94.42139459221784]
  We propose a reconstruction method from sub-Nyquist samples in the time and spatial domain, that is based on unfolding the ISTA algorithm. Our method allows reducing the number of array elements, sampling rate, and computational time while ensuring high quality imaging performance.
  arXiv  Detail & Related papers  (2021-03-01T19:19:38Z)
• Deep Learning for Fast and Reliable Initial Access in AI-Driven 6G mmWave Networks [6.097649192976533]
  We present DeepIA, a framework for enabling fast and reliable initial access for AI-driven beyond 5G and 6G millimeter (mmWave) networks. DeepIA reduces the beam sweep time compared to a conventional exhaustive search-based IA process by utilizing only a subset of the available beams. We show that the beam prediction accuracy of DeepIA saturates with the number of beams used for IA and depends on the particular selection of the beams.
  arXiv  Detail & Related papers  (2021-01-06T02:59:49Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)
• Fast Generation and Detection of Spatial Modes of Light using an Acousto-Optic Modulator [62.997667081978825]
  spatial modes of light provide a high-dimensional space that can be used to encode both classical and quantum information. Current approaches for dynamically generating and measuring these modes are slow, due to the need to reconfigure a high-resolution phase mask. We experimentally realize this approach, using a double-pass AOM to generate one of five orbital angular momentum states. We are able to reconstruct arbitrary states in under 1 ms with an average fidelity of 96.9%.
  arXiv  Detail & Related papers  (2020-07-31T14:58:30Z)
• Beamforming Learning for mmWave Communication: Theory and Experimental Validation [23.17604790640996]
  We propose a beam design technique that reduces the search time and does not require CSI while guaranteeing a minimum beamforming gain. We evaluate the efficacy of the proposed scheme in terms of building the codebook and assessing its performance through real-life measurements.
  arXiv  Detail & Related papers  (2019-12-28T05:46:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.