| DOI | Resolve DOI: https://doi.org/10.1109/LSENS.2023.3323903 |
|---|
| Author | Search for: Dey, AnkitaORCID identifier: https://orcid.org/0000-0002-5201-1081; Search for: Rajan, SreeramanORCID identifier: https://orcid.org/0000-0003-0153-6723; Search for: Xiao, Gaozhi1ORCID identifier: https://orcid.org/0000-0001-7717-1818; Search for: Lu, Jianping1ORCID identifier: https://orcid.org/0000-0003-3152-7510 |
|---|
| Affiliation | - National Research Council of Canada. Quantum and Nanotechnologies
|
|---|
| Format | Text, Article |
|---|
| Subject | sensor signal processing; census transform (CT); fall detection; histogram of oriented gradients (HOG); local binary pattern (LBP); radar; radar imaging; feature extraction; radar detection; event detection; histograms; transforms |
|---|
| Abstract | Existing deep learning techniques for radar-based fall event detection are computationally expensive and data hungry. This work proposes a novel methodology for radar-based fall event detection using computationally inexpensive traditional machine learning algorithms with the histogram of oriented gradients (HOG) of binary-encoded radar signatures. Radar signatures (binary) encoded using nonparametric local transforms, such as census transform (CT) and local binary pattern (LBP), contain enhanced gradient information and lead to distinguishable HOG features for better fall event detection. A comparative analysis of five different types of machine learning algorithms using HOG features from three different types of radar domain representations that are binary encoded in two different ways (CT and LBP) is presented. All evaluations are done on a publicly available dataset of human radar signatures. K-nearest neighbor algorithm using HOG features of binary-encoded spectrograms achieves an F1-score of 0.995. |
|---|
| Publication date | 2023-10-11 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | b86f8b65-eb91-4b80-87fb-e91af393e33e |
|---|
| Record created | 2024-10-28 |
|---|
| Record modified | 2024-10-28 |
|---|
