PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
April 19, 2026SensorsOpen Access

FPGA Implementation of a Radar-Based Fall Detection System Using Binarized Convolutional Neural Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

HCHyeongwon ChoSKSoongyu KangYJYunho Jung

Discussion

Loading...

Member takes

Overview

This work implements a radar-based system for detecting falls in elderly individuals, demonstrating high accuracy and efficiency.

Key Points

  • The study aims to create an efficient and compact fall detection system using radar and machine learning.
  • Developed a lightweight system using continuous-wave radar and binarized convolutional neural networks (BCNN).
  • Preprocessed radar signals with short-time Fourier transform (STFT) to create binary spectrograms.
  • Integrated the preprocessing and classification modules into a system-on-chip (SoC) on an FPGA.
  • Achieved binary classification accuracy of 96.1% for five fall activities and seven non-fall activities.
  • Hardware implementation provided speedups of 387.5× for preprocessing and 86.7× for classification compared to software.
  • Overall system processing time was 2.58 ms, yielding an 89.5× speedup over the software baseline.

Cite This Study

Cho et al. (2026) studied this question.

synapsesocial.com/papers/69e471ef010ef96374d8e1f1https://doi.org/10.3390/s26082469
View Full Paper
Ask AI
Bookmark
Share