@article{4706,
  author = {Hongbin yuan, Chenyao yuan, Huiqun cao},
  title = {A Deep Learning Framework for Radar Signal Processing with a Multi-Target Analysis},
  journal = {Progress in Machines and Systems},
  year = {2026},
  volume = {15},
  number = {1},
  doi = {https://doi.org/10.6025/pms/2026/15/1/34-47},
  url = {https://www.dline.info/pms/fulltext/v15n1/pmsv15n1_3.pdf},
  abstract = {In recent years, biological radar systems have been increasingly utilized in diverse applications such as
safety monitoring, healthcare monitoring, environmental surveillance, and intelligent sensing systems.
Accurate extraction of human vital signs from radar signals remains challenging due to motion interference,
environmental noise, and multi-target conditions. In this study, a convolutional neural network (CNN)-
based approach for classifying biological radar signals is proposed for multi-target vital sign detection.
Principal Component Analysis (PCA) is applied to suppress motion noise and isolate meaningful physiological
signals. The GoogLeNet architecture is employed to predict the number of moving targets across different
environments, achieving improved accuracy. Furthermore, a novel Differential Cross-Multiplication and
State Space Method (DACM-SSM) is introduced to enhance human identity identification and signal
interpretation. Experimental results demonstrate that the proposed framework improves detection efficiency,
mitigates interference from respiratory harmonics, and reduces data loss caused by random variations in
breathing and heartbeat signals. Compared with traditional approaches, the proposed method reduces
algorithmic complexity and improves computational efficiency and signal-recognition accuracy. The results
confirm that CNN-based biological radar analysis can significantly enhance multi-target vital-sign monitoring
and provide reliable, real-time health-monitoring capabilities.},
}