Radar-based Human Activities Classification with Complex-valued Neural Networks

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review


Human activities classification in assisted living is one of the emerging applications of radar. The conventional analysis considers micro-Doppler signatures as the chosen input for feature extraction or deep learning classification algorithms, or, less frequently, other radar data formats such as the range-time, the range-Doppler, or the Cadence Velocity Diagram. However, these data are typically used as real-valued images, whereas they are actually complex-valued data structures. In this paper, neural networks processing radar data as complex data structures are investigated, with a focus on spectrograms, range-time, and range-Doppler plots as the data formats of choice. Different network architectures are explored both in terms of complex numbers' representations and the depth/complexity of the architecture itself. Experimental data with 9 activities and 15 volunteers collected using an UWB radar are used to test the networks' performances. It is shown that for certain data formats and network architectures, there is an advantage in using complex-valued networks compared to their real-valued counterparts.
Original languageEnglish
Title of host publication2022 IEEE Radar Conference (RadarConf22) Proceedings
Place of PublicationPiscataway
Number of pages6
ISBN (Electronic)978-1-7281-5368-1
ISBN (Print)978-1-7281-5369-8
Publication statusPublished - 2022
Event2022 IEEE Radar Conference
- New York City, United States
Duration: 21 Mar 202225 Mar 2022


Conference2022 IEEE Radar Conference
Abbreviated titleRadarConf22
Country/TerritoryUnited States
CityNew York City

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • Micro-Doppler Classification
  • Deep learning
  • Human Activity Recognition
  • Complex-valued Networks


Dive into the research topics of 'Radar-based Human Activities Classification with Complex-valued Neural Networks'. Together they form a unique fingerprint.

Cite this