Zhenghui Li

Micro-Doppler signatures are a widely used technique for human activity recognition (HAR) in assisted living using radar systems. However, traditional methods such as the Short-Time Fourier Transform (STFT) encounter significant issues, including a compromise between temporal and spectral resolution, susceptibility to noise, and the necessity for precise parameter adjustments. To address these problems, we propose a novel method employing the Iterative Adaptive Approach (IAA) to extract high-resolution micro-Doppler signatures. The proposed method improves temporal resolution by achieving super-resolution in Doppler estimation with fewer samples in the spectral domain. This results in spectrograms with enhanced resolution, thereby improving the accuracy of micro-Doppler classification techniques. The effectiveness of the proposed method is evaluated using a challenging dataset of real-world human activities, which includes six distinct types of activities. Our findings reveal that the proposed IAA-based approach achieves up to a 3.4% improvement in classification accuracy compared to traditional STFT-based methods. This improvement is significant for the research community focused on radar-based HAR and for indoor human activity monitoring in the context of assisted living, offering a more robust and accurate technique for identifying human activities.

Building on previous radar‐based human activity recognition (HAR), we expand the micro‐Doppler signature to 6 domains and exploit each domain with a set of handcrafted features derived from the literature and our patents. An adaptive thresholding method to isolate the region of interest is employed, which is then applied in other domains. To reduce the computational burden and accelerate the convergence to an optimal solution for classification accuracy, a holistic approach to HAR optimisation is proposed using a surrogate model‐assisted differential evolutionary algorithm (SADEA‐I) to jointly optimise signal processing, adaptive thresholding and classification parameters for HAR. Two distinct classification models are evaluated with holistic optimisation: SADEA‐I with support vector machine classifiers (SVM) and SADEA‐I with AlexNet. They achieve an accuracy of 89.41% and 93.54%, respectively. This is an improvement of ∼11.3% for SVM and ∼2.7% for AlexNet when compared to the performance without SADEA‐I. The effectiveness of our holistic approach is validated using the University of Glasgow human radar signatures dataset. This proof of concept is significant for dimensionality reduction and computational efficiency when facing a multiplication of radar representation domains/feature spaces and transmitting/receiving channels that could be individually tuned in modern radar systems.