Impulse radio ultrawideband (IR-UWB) radar has the advantages of low cost, high resolution, and independence of light and weather conditions. Its potential in human activity recognition (HAR) for IoT device sensing draws interest. One challenge in this domain is effectively representing spatial static and temporal dynamic information in echo sequences. Transformers, used extensively in NLP and CV, have powerful sequence long-range dependency modeling capabilities. However, in the field of radar HAR, the application research of transformers is still insufficient. In addition, there is currently a lack of publicly available IR-UWB radar human action data sets. To this end, we proposed various fine-grained feature image calculation methods and designed an IR-UWB Radar Human Activity data set (IURHA2023). This article presents a swin transformer encoder combining cosine similarity attention and patch overlap to obtain deep spatio-temporal features of human action feature images. Compared with other proposed transformer models or traditional CNNs and RNNs, the improved swin transformer encoder performs better. To further improve the feature learning capability of the backbone network and the robustness to echo variations, we propose a supervised contrastive learning-enhanced swin transformer (SCL-SwinT). It obtains distinctions and compact embeddings by comparing the similarities of positive and negative examples partitioned according to labels. Experimental results on the IURHA2023 data set show that SCL-SwinT achieves a recognition rate exceeding 90%, and the inference speed on IoT edge devices satisfies real-time applications. Ablation experiments demonstrate the effectiveness of the proposed components. In addition, SCL-SwinT exhibits good robustness to environmental factors like noise, multipath, and distance.

Carrier-free ultra-wideband sensors have high penetrability anti-jamming solid ability, which is not easily affected by the external environment, such as weather. Also, it has good performance in the complex jungle environment. In this paper, we propose a jungle vehicle identification system based on a carrier-free ultra-wideband sensor. Firstly, a composite jungle environment with the target vehicle is modeled. From this model, the simulation obtains time-domain echoes under the excitation of carrier-free ultra-wideband sensor signals in different orientations. Secondly, the time-domain signals are transformed into MTF images through the Markov transfer field to show the statistical characteristics of the time-domain echoes. At the same time, we propose an improved RepVGG network. The structure of the RepVGG network contains five stages, which consist of several RepVGG Blocks. Each RepVGG Block is created by combining convolutional kernels of different sizes using a weighted sum. We add the self-attention module to the output of stage 0 to improve the ability to extract the features of the MTF map and better capture the complex relationship between characteristics during training. In addition, a self-attention module is added before the linear layer classification output in stage 4 to improve the classification accuracy of the network. Moreover, a combined cross-entropy loss and sparsity penalty loss function helps enhance the performance and accuracy of the network. The experimental results show that the system can recognize jungle vehicle targets well.

Ultra-wideband (UWB) radio technique, due to its potential applications and great detection ability, is vulnerable to electromagnetic interference that cannot be ignored. With the improvement and maturity of digital radio frequency memory (DRFM) technology, a new type of active deception jamming, which has similar features in the time or frequency domain with transmitted signals, poses a greater risk to the UWB detectors compared with the conventional suppressive jamming. Therefore, antijamming has become a critical study, and how to recognize jamming signals becomes one of the vital steps. In this article, the geometric models of three ground vehicles are established first to obtain the echoes with multiple scattering centers model under the UWB system. Then, the wavelet scattering network (WSN) is used to extract the differentiable features of target echo and deception jamming. Multiple base classifiers are trained by the wavelet scattering features at different scales, and ensemble learning is adopted to improve the classification rate under the minor sample conditions. The WSN has better interpretability than deep neural networks and can effectively handle the environmental white noise. The proposed method proved efficient based on the results obtained from both measured and simulated data despite the low signal-to-noise ratio (SNR).

Electromagnetic threats the carrier-free ultrawideband (UWB) sensors face cannot be ignored. However, it is difficult to tackle various jamming signals well by using one type of jamming suppression algorithm with the development of jamming technology. To solve this issue, an anti-jamming model based on equivalent sampling and coupled chaotic oscillator is proposed in this letter. First, the echo data is collected by equivalent sampling, which can destroy the jamming features in the time domain. Therefore, it does not require extra attention to the initial jamming form during the signal process. Then an improved coupled chaotic model is used to detect the weak impulses after sampling. The advantage is that it reduces the sample rate and can destroy the original features of the jamming. Higher precision and outstanding robustness are proven according to our experiments.

In this letter, we propose a novel approach for vehicle object recognition based on a carrier-free wideband radar (UWBR) using 2D echo images and the Vision Transformer (ViT) model. The input image is generated by assembling 1D echo signals under multiple azimuth angles into 2D echo feature images. The performance of the proposed method is evaluated and compared with advanced Convolutional Neural Networks (CNNs) models such as LeNet, VGG16, and ResNet50. Experimental results demonstrate that the Vision Transformer model can achieve better performance in vehicle object recognition tasks, surpassing some advanced CNNs.

The satisfaction of various basic requirements of cognitive radar by ultra-wideband (UWB) signals makes UWB cognitive radar attract extensive attention. The variety and large dynamic range of jamming in the UWB spectrum range make jamming identification critical and challenging. However, the traditional method has low recognition accuracy, high computational complexity, and difficulty in multisignal recognition. In this article, we propose a multiscale attention network (MANet) for carrier-free UWB cognitive radar to identify target signals and nine types of jamming signals. MANet extracts different fine features by multiscale dilation convolution. The features are stitched together in the channel dimension. The subtle features that are beneficial for recognition are then substantially enhanced using channel attention blocks. The proposed method combines the time- and frequency-domain features to improve the recognition performance by using the powerful feature extraction ability and generalization ability of MANet. Simulation results show that the overall recognition accuracy of the method is 93.1%, with less storage space, shorter floating-point operations (FLOPs), and inference time than the five recognition methods, and better and more stable recognition performance is also achieved at low jamming-to-noise ratios (JNRs).

Suppressive interference is a common interference signal for synthetic aperture radar (SAR) that can seriously affect the target identification and imaging results of SAR. This article proposes a method for suppressing suppressive jamming using blind source separation (BSS) for singular value decomposition (SVD) and eigenvalue decomposition (EVD) based on information entropy. First, we developed an airborne SAR imaging geometry model and a suppressive interference signal mixing model. Next, we perform blind signal separation of the interfered mixed signal by means of BSS based on SVD and EVD. Then, we image the different signals we have extracted. Finally, we extract the features of the image domain for the separated signals and set the information entropy threshold by the difference of information entropy to identify the jamming signal and the source signal and obtain the source signal. This method uses EVD and SVD for BSS and extracts the image domain features of the signal after BSS by information entropy and identifies the source signal by information entropy thresholding. This method compensates for the uncertainty in the decomposition of the signal by means of BSS. The signal loss is minimal and the similarity of the separated signal and the original signal is very high. Simulated and measured data demonstrate the feasibility of this algorithm.

In this study, we introduce MobileViTX, an enhanced MobileViT architecture for human activity recognition (HAR) in impulse radio ultrawideband (IR-UWB) radar applications. MobileViT is a lightweight Vision Transformer mainly consisting of MobileViT blocks and MobileNetv2 blocks. Modifications to the MobileNetv2 block include adding a drop path and a squeeze-and-excitation (SE) module and altering activation functions to hard-sigmoid and hard-swish. Additionally, the self-attention in the MobileViT block is transformed to possess linear complexity. These adjustments aim to accelerate inference while preserving high accuracy. We experiment with a dataset from 20 individuals performing 20 distinct actions, using fivefold cross-validation to assess our model’s performance. Results show that MobileViTX outperforms the original MobileViT and other models in both recognition rate and efficiency.

The carrier-free ultra-wideband (UWB) radar (impulse radar) has seen a recent surge of interest. In this letter, a novel recognition system for vehicles based on the carrier-free UWB radar is proposed, in which the sparse representation is introduced as an effective feature extraction method. Based on the original K-SVD algorithm, we provide a new dictionary learning (DL) idea. Instead of only embedding discrimination criteria in the objective function, we expand and improve the optimization procedure of the K-SVD algorithm. Moreover, to alleviate the impact of the signal diversity on the recognition performance, we propose a hierarchical code constraint (HCC) and bind it to the improved K-SVD model. In this way, signals from the same class but with different distributions will be represented by the corresponding dictionary atoms. Extensive experiments prove the improved K-SVD with an HCC-IKSVD can effectively take both reconstruction capability and discriminative power of the dictionary into consideration.

Recently, target recognition based on the carrier-free ultrawideband (UWB) radar has attracted increasing attention, as compared with narrowband radars and other traditional UWB radars, short duration and extreme bandwidth guarantee that carrier-free UWB echoes carry richer knowledge concerning the target of interest. However, its widespread application to target recognition faces a challenge; that is, the target-aspect sensitivity issue. The target-aspect sensitivity refers to the phenomenon that carrier-free UWB echoes significantly vary as target-aspect changes, decreasing recognition accuracy. To address this problem, this article presents a novel multitask self-supervised learning model that can capture abundant semantic information relying on data itself instead of identity annotations. First, the model is formulated as a target-aspect-invariant task, which maximizes the mutual information between original data and transformed ones to learn insensitive representations. Then, given the impact of noise on recognition performance, a stacked convolutional denoising autoencoder (SCDAE) is combined with the proposed self-supervised learning framework to extract noise-robust and target-aspect-invariant features synchronously. Extensive experiments on the measured and synthetic data demonstrate that the proposed model can achieve excellent classification performance.

Impulse radio ultrawideband (IR-UWB) radar has high range resolution, strong anti-jamming ability, and low power consumption and has been widely used in target detection and recognition. Currently, existing studies always extract artificial features of echo signals, such as time–frequency images, Doppler features, or time-domain features, and then distinguish these features through well-designed deep networks. However, these manual features are difficult to achieve task-invariant and disentangled representations. The target echo received by UWB radar also has amplitude, time-shift, and target-aspect sensitivity problems. To address the above problems, we propose a novel supervised contrastive learning (SupCon) framework to recognize different vehicles. Under label constraints, deep invariant representations are obtained through contrastive learning of echo signals, improving classification accuracy. First, a 1-D deep residual network (ResNet) is designed as the backbone, and the self-attention (SA) layer is added to extract long-range features of echo signals. Second, well-designed data augmentation methods can improve the performance of contrastive learning. Due to the integration of multiple data transformations, the model can learn invariant features by maximizing the mutual information between different signal transformations. Finally, we modify the SupCon loss function. It alleviates the conflict problem of simultaneously shrinking and expanding the distance between the positive samples in the feature space and improves the recognition performance of the model. Ablation experiments on the measured dataset show that the designed components of the method are effective. Comparative experiments on ultrawideband radar public datasets [Air Force Research Laboratory’s (AFRL) high-resolution range profile (HRRP), moving and stationary target acquisition and recognition (MSTAR)] also demonstrate the excellent classification performance of the proposed algorithm.

The carrier-free UWB sensor features high distance resolution and high interference immunity. It is not easily affected by weather and lighting conditions, and its received echoes contain detailed structural information of the target. This paper proposes a small sample terrain recognition framework based on the carrier-free UWB sensor. The time-frequency feature maps of terrain echo signals are used for classification. However, insufficient samples make the classifier prone to overfitting, so we propose an Improved Auxiliary Classifier Generative Adversarial Network (IACGAN) for data enhancement in this paper. Firstly, attention mechanism and multi-scale convolution are added to the network structure of ACGAN to improve the feature extraction capability of time-feature images of echo signals. Secondly, the discriminator's true/false judgment criterion changes from Jensen-Shannon divergence to Wasserstein distance with gradient penalty, improving training stability. Finally, label classification of the generated samples by the discriminator is eliminated, which further enhances the quality of the generated images. Experiments show that the IACGAN improves the quality of generated images with IS and FID as the generation quality evaluation criteria. Furthermore, k-fold cross-validation shows that data augmentation by IACGAN improves the recognition rate of the CNN classifier. Finally, the experiment also found that directly using the discriminator in the trained IACGAN as the classifier can achieve more than 97% accuracy. That does not require additional training of the classifier on the expanded training set, which is an efficient and low-cost alternative.

无载波超宽带引信由于具有定距精度高、抗截获能力强、穿透性好、有一定反隐身能力等特点,在多个弹药平台上得到应用.在对地面目标作用时,不同地形会影响引信炸高,从而影响毁伤效果.首次提出将无载波超宽带引信用于地形识别,为引信自适应确定最佳炸高提供先决条件.地形回波的采集周期长、成本高,获取回波的数量往往较少,这会影响识别精度.为扩充数据集,提出一种改进的条件生成对抗网络,将生成器和判别器的全连接层替换为一维卷积同时增加批标准化,在实现信号生成的同时减小模式崩溃问题发生的概率,提升了小样本条件下的序列生成效果.将扩充回波信号的小波能量特征作为输入特征,利用粒子群优化的反向传播(PSO-BP)神经网络实现地形智能分类.实验结果表明:相比在原始训练集上训练,扩充训练集上训练的PSO-BP神经网络在测试集上取得了4％以上的准确率提升.

The carrier-free ultra-wideband (UWB) sensor characterizes high distance resolution and high interference immunity. It is not easily affected by weather and lighting conditions, and its received echoes contain detailed structural information of the target. In this paper, we propose a terrain recognition framework based on the carrier-free UWB sensor. For the purpose of extracting noise-robustness features, a deep network named stacked denoising autoencoder (SDAE) is developed. Given that the convolutional neural network (CNN) is insensitive to translation to some extent, we combine several CNNs as middle structures of the proposed model. Experimental results demonstrate that the proposed algorithm can effectively learn essential representation and improve classification accuracy in the presence of low signal-to-noise ratios (SNRs), making it very suitable for use in a classification scheme.

This paper proposes a scheme for ground-target recognition based on the carrier-free ultra-wideband (UWB) radar sensor for the first time. Carrier-free UWB system emits an extremely short pulse, which can provide potential advantages over other UWB systems, such as high range resolution, short blind range, enhanced anti-multipath jamming ability. These characteristics above guarantee that UWB echoes contain more comprehensive and detailed information with respect to the target of interest. Feature extraction is fundamental and crucial for target recognition. In this paper a deep network named semi-supervised stacked convolutional denoising autoencoder (SCDAE) is developed to extract discriminative features. As an extension of stacked denoising autoencoders (SDAE), SCDAE replaces fully-connected layers with one-dimensional convolutional layers as middle structures. In order to capture essential signatures exactly and improve classification accuracy, we build up a semi-supervised learning mechanism via binding a label regularization term with SCDAE. Moreover, given that echoes observed at different angles belonging to the same target are different, a new multi-level label coding method is proposed and embedded in SCDAE. Experimental results demonstrate that the proposed algorithm can effectively learn essential representation and improve classification accuracy in the presence of low signal-to-noise ratios (SNRs), making it very suitable for use in a classification scheme.