Human motion classification using Impulse Radio Ultra Wide Band through-wall RADAR model

The detection of human motion is receiving more attention amongst researchers, and is important in several applications. However, the issue is to offer effective monitoring sensors amongst various platforms without diminishing privacy. The radar models are beneficial for detecting human motion due to their potential to detect targets from long ranges and work in all types of weather. This paper develops a technique for human motion classification using Impulse Radio Ultra Wide Band (IR-UWB) with a wall radar model. The goal is to devise a human motion classification framework using a Random Multimodal Deep Learning (RMDL), which is tuned by the proposed optimization algorithm. Here, the Ultra Wide Band (UWB) signals are employed in the gridding process to evaluate the grids. The grids are adapted for feature extraction wherein the Hilbert transform features and texture features, like Local Gradient Pattern (LGP) and Local Optimal Oriented Pattern (LOOP) are considered. These features are considered in RMDL for identifying human motion. The training of RMDL is done using the proposed Spotted Grey Wolf Optimizer (SGWO), which is obtained by combining Spotted Hyena Optimizer (SHO) and Grey Wolf optimizer (GWO). The developed SGWO-based RMDL offered effective performance with the highest accuracy of 0.956, smallest Mean square error (MSE) of 0.200, highest True negative rate (TNR) of 0.959, and highest true positive rate (TPR) of 0.956.

Automated summary

The detection of human motion is a focus of researchers and has various applications, but effective monitoring sensors are needed without compromising privacy. Radar models are beneficial for detecting human motion due to their long-range capabilities and ability to work in all weather conditions. This paper proposes a technique for human motion classification using Impulse Radio Ultra Wide Band (IR-UWB) with a wall radar model. The developed framework utilizes Random Multimodal Deep Learning (RMDL) optimized by the proposed Spotted Grey Wolf Optimizer (SGWO) for training. The results show that the SGWO-based RMDL achieved high accuracy, low mean square error (MSE), high true negative rate (TNR), and high true positive rate (TPR).