This paper considers the problem of line of sight (LOS) and non-line-of-sight (NLOS) targets localization in an L-shaped corner. Specifically, first, the propagation paths of the electromagnetic waves in an L-shaped corner are analyzed by the ray tracing technology. Then, a sparsity-based multipath model is formulated by regularizing the LOS target with sparsity norm and the NLOS targets with jointly sparse across different paths, respectively. After that, a proximal gradient-based iterative algorithm is proposed to tackle this optimization problem. Finally, the feasibility of simultaneously localizing NLOS and LOS targets is demonstrated through simulations.

Localization of non-line-of-sight (NLOS) targets in the complex urban environment have attracted significant attention in recent years. However, the requirement for precise prior information about the environment is idealistic. It is challenging to know the environmental information in the blind area of vision in advance of practical applications. This paper proposes a joint estimation algorithm for building layout and target position in the L-shaped scene without any prior information. Specifically, a round-trip multipath propagation model is first developed for the cases of diffraction and multiple reflections. Then, the received echo signal is preprocessed with moving target identification (MTI), back-projection (BP) imaging, and image segmentation. In addition, the target points, which are screened by geometric association, are further matched and estimated by the multipath ghost’s hypothesis method, thus realizing the joint perceptual estimation of the building layout and the target position. Finally, electromagnetic (EM) simulations and experimental measurements are used to validate the effectiveness of the proposed algorithm.

Email threat is a serious issue for enterprise security. The threat can be in various malicious forms, such as phishing, fraud, blackmail and malvertisement. The traditional anti-spam gateway often maintains a greylist to filter out unexpected emails based on suspicious vocabularies present in the email’s subject and contents. However, this type of signature-based approach cannot effectively discover novel and unknown suspicious emails that utilize various evolving malicious payloads. To address the problem, in this paper, we present Holmes, an efficient and lightweight semantic based engine for anomalous email detection. Holmes can convert each email event log into a sentence through word embedding and then identify abnormalities that deviate from a historical baseline based on those translated sentences. We have evaluated the performance of Holmes in a real-world enterprise environment, where around 5,000 emails are sent/received each day. In our experiments, Holmes shows a high capability to detect email threats, especially those that cannot be handled by the enterprise anti-spam gateway. It is also demonstrated through our experiment that Holmes can discover more concealed malicious emails that are immune from several commercial detection tools.

Through-wall human motion recognition is suffered from the problems of too few samples and too large model parameters. In this letter, we propose a multi-domain fusion through-the-wall radar (TWR) human motion recognition model based on lightweight network and transfer learning. Specifically, in order to make full use of the target information, a multiple parallel feature pyramid network (FPN) is first proposed to extract the detailed feature information from the time–frequency map and range profile. After that, a lightweight network based on the MobileNetV3 network and transfer learning is proposed. The MobileNetV3 model is pre-trained on the public ImageNet database. To ensure the performance of transfer learning, a heterogeneous migration learning algorithm is used to cross-domain transform the obtained time–frequency map and range profile. Experimental results show that the proposed model has a better performance in accuracy, model size, training time, and robustness compared with the existing methods. It also has the potential to embed portable radar, which has important research value for the application of radar in real life.

This letter studies the problem of ultrawideband (UWB) tomographic imaging for unknown building layouts where the multipath-rich condition is considered. Specifically, first, the multiple propagation paths of the UWB signal are analyzed, and a delay estimation algorithm is proposed to estimate the direct path (DP) delay from the multipath signal. Then, a tomographic projection model is established by mapping the relationship between the delay of the DP and the relative permittivity of the unknown layout. Besides, a modified total variation method is developed to reconstruct the building layout, which shows significant performance in preserving the edges of the structure. Finally, the effectiveness of the proposed algorithm is verified using both simulated and real data.

Non-line-of-sight (NLOS) detection is an enduring topic as it provides a powerful tool to monitor visually blocked areas. Currently, the NLOS detection requires precise prior knowledge of building layout, which limits its further applications in practice. In this paper, we consider the problem of joint estimation of building layout and target location in the NLOS scenario by exploiting multipath returns. Specifically, first, the building layout is simplified into combined linear equations with unknown parameters. In this way, we establish a parametrized multipath propagation model in the multiple targets NLOS scenario for the multiple-input-multiple-output (MIMO) radar, which is used in the image reconstruction and layout estimation problem. Then, a shape-remodeling group sparse constraint algorithm is proposed and combined with the particle swarm optimization method to simultaneously reconstruct the unknown layout and targets. Compared to the conventional compressed sensing-based methods, the proposed method integrates the basic structural characteristics and sparsity prior of the NLOS image to improve the stability of the solution. Finally, the performance of the proposed method is verified with numerical and experimental results.

High false alarm rate and low detection rate are the major sticking points for unknown threat perception. To address the problems, in the paper, we present a densely connected residual network (Densely-ResNet) for attack recognition. Densely-ResNet is built with several basic residual units, where each of them consists of a series of Conv-GRU subnets by wide connections. Our evaluation shows that Densely-ResNet can accurately discover various unknown threats that appear in edge, fog and cloud layers and simultaneously maintain a much lower false alarm rate than existing algorithms.