Human lifespan is increasing in parallel with the development levels of societies. Consequently, the number of elderly individuals worldwide is also rising day by day. One of the most significant risks these individuals face is falling. In this study, fall and daily activity data were collected from different home environments using a continuous-wave (CW) radar. Micro-Doppler signatures were generated from 700 data samples obtained from 10 individuals. Furthermore, the dataset was expanded by doubling the number of spectrogram images through data augmentation. The YOLO architecture, generally used in vision-based studies for object detection and tracking, was preferred for radar-based fall and activity detection. Classifications were performed with different YOLO structures, and comparative results are presented. At this stage, binary (fall/non-fall) and multi-class (seven different classes) classifications were carried out, achieving 100% accuracy for binary classification and 88.02% for multi-class classification. Additionally, the generalizability of the proposed architecture is demonstrated using the Leave-One-Subject-Out (LOSO) approach on the collected data and through the analysis of a public dataset. These results demonstrate the applicability of YOLO architectures in radar-based fall detection studies.
Şeflek et al. (2026) studied this question.