CoChat

Human Fall Detection with Ultra-Wideband Radar and Adaptive Weighted Fusion

Open access
Huang, Ling, Zhu, Anfu, Qian, Mengjie, An, Huifeng · 2024 · Sensors

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Abstract

To address the challenges in recognizing various types of falls, which often exhibit high similarity and are difficult to distinguish, this paper proposes a human fall classification system based on the SE-Residual Concatenate Network (SE-RCNet) with adaptive weighted fusion. First, we designed the innovative SE-RCNet network, incorporating SE modules after dense and residual connections to automatically recalibrate feature channel weights and suppress irrelevant features. Subsequently, this network was used to train and classify three types of radar images: time–distance images, time–distance images, and distance–distance images. By adaptively fusing the classification results of these three types of radar images, we achieved higher action recognition accuracy. Experimental results indicate that SE-RCNet achieved F1-scores of 94.0%, 94.3%, and 95.4% for the three radar image types on our self-built dataset. After applying the adaptive weighted fusion method, the F1-score further improved to 98.1%.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s24165294

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 PulsOn 440 radar module.
Figure 1 PulsOn 440 radar module.CC BY · PubMed Central
Figure 2 Diagram of Graph Generation.
Figure 2 Diagram of Graph Generation.CC BY · PubMed Central
Figure 3 Three Radar Spectrograms for Walking Away from the Radar. (a) Range-Time Diagram. (b) Time-Doppler Diagram. (c) Range-Doppler Diagram.
Figure 3 Three Radar Spectrograms for Walking Away from the Radar. (a) Range-Time Diagram. (b) Time-Doppler Diagram. (c) Range-Doppler Diagram.CC BY · PubMed Central
Figure 4 SE-RCNet Model Architecture Diagram.
Figure 4 SE-RCNet Model Architecture Diagram.CC BY · PubMed Central
Figure 5 Decision Fusion Diagram.
Figure 5 Decision Fusion Diagram.CC BY · PubMed Central
Figure 6 Adaptive Weighted Fusion Architecture Based on SE-RCNet.
Figure 6 Adaptive Weighted Fusion Architecture Based on SE-RCNet.CC BY · PubMed Central
Figure 7 The accuracy and Cross-Entropy Loss Curves of Single-Spectrogram Detection for 5-Fold Cross-Validation over the Number of Training Epochs. (a) Cross-entropy loss variation in the range–distance diagram. (b) Accuracy variation in the range–distance diagram. (c) Cross-entropy loss variation in the distance–time diagram. (d) Accuracy variation in the distance–time diagram. (e) Cross-entropy loss variation in the time–distance diagram. (f) Accuracy variation in the time–distance diagram.
Figure 7 The accuracy and Cross-Entropy Loss Curves of Single-Spectrogram Detection for 5-Fold Cross-Validation over the Number of Training Epochs. (a) Cross-entropy loss variation in the range–distance diagram. (b) Accuracy variation in the range–distance diagram. (c) Cross-entropy loss variation in the distance–time diagram. (d) Accuracy variation in the distance–time diagram. (e) Cross-entropy loss variation in the time–distance diagram. (f) Accuracy variation in the time–distance diagram.CC BY · PubMed Central
Figure 8 Boxplot of Model F1-Scores on Three Types of Spectrograms. (a) Boxplot based on time–doppler diagram. (b) Boxplot based on distance–time diagram. (c) Boxplot based on range–doppler diagram.
Figure 8 Boxplot of Model F1-Scores on Three Types of Spectrograms. (a) Boxplot based on time–doppler diagram. (b) Boxplot based on distance–time diagram. (c) Boxplot based on range–doppler diagram.CC BY · PubMed Central
Figure 9 Confusion Matrix of Fusion Methods in the Self-Built Dataset. (a) Decision Fusion Confusion Matrix Based on the Self-Built Dataset. (b) Adaptive Weighted Fusion Confusion Matrix Based on the Self-Built Dataset.
Figure 9 Confusion Matrix of Fusion Methods in the Self-Built Dataset. (a) Decision Fusion Confusion Matrix Based on the Self-Built Dataset. (b) Adaptive Weighted Fusion Confusion Matrix Based on the Self-Built Dataset.CC BY · PubMed Central
Figure 10 Confusion Matrix of Fusion Methods in the Public Datasets. (a) Decision Fusion Confusion Matrix Based on the Public Dataset. (b) Adaptive Weighted Fusion Confusion Matrix Based on the Public Dataset.
Figure 10 Confusion Matrix of Fusion Methods in the Public Datasets. (a) Decision Fusion Confusion Matrix Based on the Public Dataset. (b) Adaptive Weighted Fusion Confusion Matrix Based on the Public Dataset.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 22 references

Cited by

See all 11

Metadata

Authors
Huang, L., Zhu, A., Qian, M., & An, H.
Affiliations
Lanzhou University of Technology (CN)
Corresponding author
Huang, Ling
Venue
Sensors
Publisher
MDPI AG
Published
2024-08-15
Volume
24
Issue
16
Pages
5294
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4401613281
Cited by
11
References
22
Citations by year
2026: 4 · 2025: 5 · 2024: 2
FWCI
1.53
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • National Natural Science Foundation of China Special Program (62341311, 2022-RC-7)
  • Lanzhou Municipal Talent Innovation and Entrepreneurship Project (62341311, 2022-RC-7)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
  • Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
Keywords
fall detection, ultra-wideband radar, fall classification, squeeze-and-excitation module, adaptive weighted fusion, radar imagery, human action recognition
MeSH terms
Accidental Falls, Algorithms, Humans, Radar, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Human Fall Detection with Ultra-Wideband Radar and Adaptive Weighted Fusion. https://app.cochat.ai/papers/10.3390/s24165294
The paper
Huang, L., Zhu, A., Qian, M., & An, H. (2024). Human Fall Detection with Ultra-Wideband Radar and Adaptive Weighted Fusion. Sensors. https://doi.org/10.3390/s24165294

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.