# Exploring FMCW Radars and Feature Maps for Activity Recognition: A Benchmark Study

arXiv: https://arxiv.org/abs/2503.05629 · HTML: https://mlsanity.com/paper/2503.05629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 36 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Doppler Radar for the Extraction of Biomechanical Parameters in Gait Analysis](https://mlsanity.com/paper/2005.05280/) (2020)
- [Low-cost low-power in-vehicle occupant detection with mm-wave FMCW radar](https://mlsanity.com/paper/1908.04417/) (2019)
- [A Survey on Radar-Based Fall Detection](https://mlsanity.com/paper/2312.04037/) (2023)
- [AI-Powered Non-Contact In-Home Gait Monitoring and Activity Recognition System Based on mm-Wave FMCW Radar and Cloud Computing](https://mlsanity.com/paper/2208.05905/) (2022)

## Abstract (arXiv)

Human Activity Recognition has gained significant attention due to its diverse applications, including ambient assisted living and remote sensing. Wearable sensor-based solutions often suffer from user discomfort and reliability issues, while video-based methods raise privacy concerns and perform poorly in low-light conditions or long ranges. This study introduces a Frequency-Modulated Continuous Wave radar-based framework for human activity recognition, leveraging a 60 GHz radar and multi-dimensional feature maps. Unlike conventional approaches that process feature maps as images, this study feeds multi-dimensional feature maps -- Range-Doppler, Range-Azimuth, and Range-Elevation -- as data vectors directly into the machine learning (SVM, MLP) and deep learning (CNN, LSTM, ConvLSTM) models, preserving the spatial and temporal structures of the data. These features were extracted from a novel dataset with seven activity classes and validated using two different validation approaches. The ConvLSTM model outperformed conventional machine learning and deep learning models, achieving an accuracy of 90.51% and an F1-score of 87.31% on cross-scene validation and an accuracy of 89.56% and an F1-score of 87.15% on leave-one-person-out cross-validation. The results highlight the approach's potential for scalable, non-intrusive, and privacy-preserving activity monitoring in real-world scenarios.