• Home
  • Search
  • Near-channel classifier: symbiotic communication and classification in high-dimensional space
  • Cite Icon11
  • https://doi.org/10.1186/s40708-021-00138-0Copy DOI Icon

Near-channel classifier: symbiotic communication and classification in high-dimensional space

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Brain-inspired high-dimensional (HD) computing represents and manipulates data using very long, random vectors with dimensionality in the thousands. This representation provides great robustness for various classification tasks where classifiers operate at low signal-to-noise ratio (SNR) conditions. Similarly, hyperdimensional modulation (HDM) leverages the robustness of complex-valued HD representations to reliably transmit information over a wireless channel, achieving a similar SNR gain compared to state-of-the-art codes. Here, we first propose methods to improve HDM in two ways: (1) reducing the complexity of encoding and decoding operations by generating, manipulating, and transmitting bipolar or integer vectors instead of complex vectors; (2) increasing the SNR gain by 0.2 dB using a new soft-feedback decoder; it can also increase the additive superposition capacity of HD vectors up to 1.7times in noise-free cases. Secondly, we propose to combine encoding/decoding aspects of communication with classification into a single framework by relying on multifaceted HD representations. This leads to a near-channel classification (NCC) approach that avoids transformations between different representations and the overhead of multiple layers of encoding/decoding, hence reducing latency and complexity of a wireless smart distributed system while providing robustness against noise and interference from other nodes. We provide a use-case for wearable hand gesture recognition with 5 classes from 64 EMG sensors, where the encoded vectors are transmitted to a remote node for either performing NCC, or reconstruction of the encoded data. In NCC mode, the original classification accuracy of 94% is maintained, even in the channel at SNR of 0 dB, by transmitting 10,000-bit vectors. We remove the redundancy by reducing the vector dimensionality to 2048-bit that still exhibits a graceful degradation: less than 6% accuracy loss is occurred in the channel at − 5 dB, and with the interference from 6 nodes that simultaneously transmit their encoded vectors. In the reconstruction mode, it improves the mean-squared error by up to 20 dB, compared to standard decoding, when transmitting 2048-dimensional vectors.

Loading PDF

Similar Papers
  • Supplementary Content

Fibrose systémique néphrogénique

  • Mar 09, 2009
  • Annales de dermatologie et de venereologie
  • P Senet
  • Research Article
  • Citations68

Abdominal Magnetic Resonance Imaging at 3.0 T: What Is the Ultimate Gain in Signal-to-Noise Ratio?

  • Sep 13, 2006
  • Academic Radiology
  • Sebastian T Schindera +4
  • Research Article
  • Citations7

Comparison of SNR gain between quantum illumination radar and classical radar.

  • Sep 19, 2022
  • Optics Express
  • Rongyu Wei +5
  • Research Article
  • Citations2

Utility of respiratory‐navigator‐rejected k‐space lines for improved signal‐to‐noise ratio in three‐dimensional cardiac MR

  • Dec 11, 2012
  • Magnetic Resonance in Medicine
  • Mehmet Akçakaya +3
  • Conference Article
  • Citations5

Comparison of image Signal-to-Noise Ratio and Noise Equivalent Counts in Time-of-Flight PET

  • Oct 01, 2010
  • E Clementel +3
  • Research Article
  • Citations33

MRI of the carotid artery at 7 Tesla: Quantitative comparison with 3 Tesla

  • Feb 27, 2014
  • Journal of Magnetic Resonance Imaging
  • Wouter Koning +6
  • Research Article
  • Citations16

The Effect of Otoacoustic Emission Stimulus Level on the Strength and Detectability of the Medial Olivocochlear Reflex.

  • Jan 01, 2019
  • Ear & Hearing
  • James D Lewis
  • Research Article
  • Citations3

Bit error rate analysis of the scheduled TAS with MRC for CR-MIMO systems

  • Nov 11, 2016
  • Physical Communication
  • Donghun Lee
  • Research Article
  • Citations2

Outage Probability of Zero Forcing Precoded Scheduling System for Multiple Input Multiple Output Broadcast Transmission

  • Dec 01, 2011
  • IEEE Communications Letters
  • Donghun Lee +2
  • Research Article
  • Citations10

Fourier decomposition pulmonary MRI using a variable flip angle balanced steady-state free precession technique.

  • May 20, 2014
  • Magnetic Resonance in Medicine
  • D M R Corteville +4
  • PDF
  • Research Article
  • Citations3

Feasibility and Robustness of 3T Magnetic Resonance Angiography Using Modified Dixon Fat Suppression in Patients With Known or Suspected Peripheral Artery Disease.

  • Oct 30, 2020
  • Frontiers in Cardiovascular Medicine
  • Karl Jakob Weiss +8
  • Research Article
  • Citations5

A Near‐Field Coupling Array Enables Parallel Imaging and SNR Gain in MRI

  • Jul 22, 2025
  • Advanced Science
  • Zhiguang Mo +11
  • Research Article
  • Citations4

Perturbative corrections to stochastic resonant quantizers

  • Jun 09, 2006
  • Signal Processing
  • Aditya A Saha
  • Research Article

A compact Fourier transform spectrometer with no moving parts for laser induced breakdown spectroscopy

  • Jul 01, 2019
  • Journal of Physics: Conference Series
  • S J Davitt +2
  • Research Article
  • Citations6

Signal-to-Noise Ratio Improvement of MAMR on CoX/Pt Media

  • Nov 01, 2015
  • IEEE Transactions on Magnetics
  • Zhen Zhao +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.