Radar, as one of the sensors for human activity recognition (HAR), has unique characteristics such as privacy protection and contactless sensing. Radar-based HAR has been applied in many fields such as human–computer interaction, smart surveillance and health assessment. Conventional machine learning approaches rely on heuristic hand-crafted feature extraction, and their generalization capability is limited. Additionally, extracting features manually is time–consuming and inefficient. Deep learning acts as a hierarchical approach to learn high-level features automatically and has achieved superior performance for HAR. This paper surveys deep learning based HAR in radar from three aspects: deep learning techniques, radar systems, and deep learning for radar-based HAR. Especially, we elaborate deep learning approaches designed for activity recognition in radar according to the dimension of radar returns (i.e., 1D, 2D and 3D echoes). Due to the difference of echo forms, corresponding deep learning approaches are different to fully exploit motion information. Experimental results have demonstrated the feasibility of applying deep learning for radar-based HAR in 1D, 2D and 3D echoes. Finally, we address some current research considerations and future opportunities.

Automatic modulation classification facilitates many important signal processing applications. Recently, deep learning models have been adopted in modulation recognition, which outperform traditional machine learning techniques based on hand-crafted features. However, automatic modulation classification is still challenging due to the following reasons. Existing deep learning methods are only applicable to the data of the same distribution. In practical scenarios, data distribution is varying with sampling frequency, thus domains with different sampling rates are formed. Besides, it is difficult to construct large-scale well-annotated datasets for all domains of interest. We define the domain with sufficient data as the source domain, while the domain with insufficient data as the target domain. Obviously, the classification model performs weakly in the target domain. To address these challenges, we propose an adversarial transfer learning architecture (ATLA), incorporating adversarial training and knowledge transfer in a unified way. Adversarial training performs an asymmetric mapping between domains and reduces the domain shift. Knowledge transfer is used to mine prior knowledge from the source domain. Experimental results demonstrate that the proposed ATLA substantially boosts the performance of the target model, which outperforms the existing parameter-transfer approach. With half of the training data reduced, the target model achieves competitive recognition accuracy to supervised learning. With one-tenth of training data, the promoted accuracy is up to 17.3% points.

Human activity recognition (HAR) plays a vital role in many applications, such as surveillance, in-home monitoring, and health care. Portable radar sensor has been increasingly used in HAR systems in combination with deep learning (DL). However, it is both difficult and time-consuming to obtain a large-scale radar dataset with reliable labels. Insufficient labeled data often limit the generalization of DL models. As a result, the performance of DL models will drop when being applied to a new scenario. In this sense, only labeling a small portion of data in the large-scale radar dataset is more feasible. In this article, we propose a semisupervised transfer learning (TL) algorithm, “ joint domain and semantic transfer learning ( JDS-TL ),” for radar-based HAR, which is composed of two modules: unsupervised domain adaptation (DA) and supervised semantic transfer. By employing a sparsely labeled dataset to train the HAR model, the proposed method alleviates the need of labeling a significantly large number of radar signals. We adopt a public radar micro-Doppler spectrogram dataset including six human activities to evaluate JDS-TL . Experiments show that the proposed JDS-TL is able to recognize the six activities with an average accuracy of 87.6% when there are only 10% instances labeled in the training dataset. Ablation analysis also demonstrates the efficiency of the DA and the semantic transfer modules.

In existing works of deep learning-based resource allocation, the scalability degrades heavily with the increase of network complexity, which is due to their limited learning ability of shallow neural networks and insufficient knowledge of network. Nowadays, to address the growth of cell density, cooperative beamforming in user-centric network (UCN) is emerged, where the additional degrees of freedom of multi-antenna and cell coordination aggravate the challenges. This paper proposes a deep residual learning framework, UcnBeamNet, to enhance the ability of approximating the iterative algorithm for sum rate maximization, where multi-branch subnets are connected in parallel to extract extra information. Specifically, a weighted minimum mean square error (WMMSE)-based algorithm is derived to determine the optimal clusters and beamforming matrices; then UcnBeamNet is trained to learn the input-output mapping and provide direct insight of UCN from association matrices in addition to plural inputs. Extensive experiments demonstrate UcnBeamNet still reaches 90.38% sum-rate relative to conventional algorithm even with a large network size, and achieves more than 50,000× speed up in computational efficiency.

As a typical task of passive biometrics, behavior-based person identification has been studied extensively in recent years. This letter proposes the use of the ultrawideband impulse radar for person identification based upon the micro-Doppler signatures of human motions. A new convolutional neural network (CNN) architecture is proposed for taking advantage of the hierarchical features. The experimental results show that, by utilizing the micro-Doppler signatures of the six selected human motions, the task of person identification can be accurately achieved. Both traditional algorithms and landmark CNN algorithms are chosen for comparison, and the proposed model performs better than the others. Especially when the motion of “running” is adopted to identify persons, the model achieves 95.21% accuracy on the identification of 15 people.

In remote sensing, micro-Doppler signatures are widely used in moving target detection and automatic target recognition. However, since Doppler signatures are easily affected by the moving direction of the target, prior information of aspect angle is essential for spectral analysis. Thus, a micro-Doppler-based classifier is considered to be ``angle-sensitive.'' In this article, we propose an angle-insensitive classifier for the omnidirectional classification problem using the monostatic radar through a proposed new convolutional neural network. We further provide a sensible definition of ``angle sensitivity,'' and perform experiments on two data sets obtained through simulations and measurements. The results demonstrate that the proposed algorithm outperforms both feature-based and existing deep-learning-based counterparts, and resolve the issue of angle sensitivity in micro-Doppler-based classification.