Neural networks continue to face challenges in effectively extracting information from the high-dimensional and sparse range-azimuth-Doppler (RAD) tensor. While multi-view architectures using three-axis projections of the RAD tensor improve efficiency and maintain accuracy, existing designs suffer from inefficient inter-view information interaction. To address this issue, this letter proposes a new multi-view information fusion viewpoint: instead of directly blending feature maps, the orthogonal relationships among the RAD coordinate axes are leveraged to guide feature decomposition across views, thereby disentangling the mixed semantics introduced during view compression. Based on this idea, a new module, termed Cross-View Guided Disentangler (CVGD), is introduced to enable inter-view information interaction in multi-view architectures. Extensive experiments on the public CARRADA dataset demonstrate that networks incorporating the proposed module achieve performance comparable to state-of-the-art methods, while utilizing 50% fewer parameters and attaining a 6-fold increase in inference speed. Additionally, promising results are also observed on RADIal, achieving near-SOTA performance with higher efficiency.

Modeling of multiple-scattering channels in atmospheric turbulence is essential for the performance analysis of long-distance non-line-of-sight (NLOS) ultraviolet (UV) communications. Existing works on the turbulent channel modeling for NLOS UV communications either focused on single-scattering cases or estimate the turbulent fluctuation effect in an unreliable way based on Monte-Carlo simulation (MCS) approach. In this paper, we establish a comprehensive turbulent multiple-scattering channel model by using a more efficient Monte-Carlo integration (MCI) approach for NLOS UV communications, where both the scattering, absorption, and turbulence effects are considered. Compared with the MCS approach, the MCI approach is more interpretable for estimating the turbulent fluctuation. To achieve this, we first introduce the scattering, absorption, and turbulence effects for NLOS UV communications in turbulent channels. Then we propose the estimation methods based on MCI approach for estimating both the turbulent fluctuation and the distribution of turbulent fading coefficient. Numerical results demonstrate that the turbulence-induced scattering effect can always be ignored for typical UV communication scenarios. Besides, the turbulent fluctuation will increase as either the communication distance increases or the zenith angle decreases, which is compatible with existing experimental results and also with our experimental results. Moreover, we demonstrate numerically that the distribution of the turbulent fading coefficient for UV multiple-scattering channels under all turbulent conditions can be approximated as log-normal distribution; and we also demonstrate both numerically and experimentally that the turbulent fading can be approximated as a Gaussian distribution under weak turbulence.

Ultraviolet (UV) communication is widely known for its local confidentiality due to rapid signal attenuation over distance. However, the inherent low background interference in UV communication environments can make signal transmission more easily detectable by an eavesdropper. In this study, we introduce covert communication metrics based on overall photon counting and peak power to assess analytically the covert performance of UV non-line-of-sight (NLOS) communications on photon counting channels. By integrating the covert metrics with the UV omni-directional NLOS channel model, we demonstrate standoff boundaries for the first time. Our simulation results confirm the effectiveness of UV NLOS covert communication and offer vital insights into the design and operational strategies of UV NLOS covert communication systems.

In this paper, we focus on the orthogonal frequency division multiplexing (OFDM) waveform design for the joint multipleinput multiple-output radar and communications. An efficient method to simultaneously reduce the integrated sidelobe level (ISL) and peak-to-mean envelope power ratio (PMEPR) of OFDM waveforms is proposed from the radar side, which also guarantees high-quality information transmission for communications. Specifically, we exploit the spectral and phase randomness of waveforms to implement fast-time information embedding, based on which we formulate the design into a solvable nonconvex optimization problem. To solve it, we first rewrite its objective function into a quartic form by exploring the inherent algebraic structures and properties, which is then converted to a new quadratic form that is easy to be dealt with. Moreover, we obtain closed-form solutions at each iteration by means of a series of derivations involving majorization-minimization techniques. Simulation results verify the effectiveness of our method over existing works.

In the low-altitude urban background with heavy interference, especially in the face of corner interference with higher intensity than the target, infrared (IR) dim and small target is extremely lack of prior information (i.e., size, shape and contrast information). In such case, the existing detection methods usually suffer from high false alarm or even failure. To deal with this situation, we develop a novel spatial-temporal tensor model with tensor spectralk-support norm minimization (STTM-TSNM) for detecting IR dim and small target. Firstly, the spatial-temporal information of the original image sequence can be preserved completely by constructing the holistic STTM. Then, according to the spatial-temporal related prior knowledge of the target and background, the target detection task is customized as an optimization problem of low rank and sparse tensor recovery. To better preserve the internal structure and capture more global information, the tensor spectralk-support norm minimization is introduced as the regularization term of the constraint background. Finally, draw support from the framework of alternating direction method of multipliers (ADMM) algorithm, the precise separation of target and background is achieved. In addition, to promote the prosperity of sequential detection methods, we released to the scientific community a small IR target dataset containing six image sequences with urban background. The experimental results on six real IR sequences demonstrate that our method outputs the most outstanding detection performance compared with the latest sequential detection methods.

Existing pharmaceutical information extraction research often focus on standalone entity or relationship identification tasks over drug instructions. There is a lack of a holistic solution for drug knowledge extraction. Moreover, current methods perform poorly in extracting fine-grained interaction relations from drug instructions. To solve these problems, this paper proposes an information extraction framework for drug instructions. The framework proposes deep learning models with fine-tuned pre-training models for entity recognition and relation extraction. In addition, it incorporates an novel entity pair calibration process to promote the performance for fine-grained relation extraction. The framework experiments on more than 60k Chinese drug description sentences from 4000 drug instructions. Empirical results show that the framework can successfully identify drug related entities (F1 3 0.95) and their relations (F1 3 0.83) from the realistic dataset, and the entity pair calibration plays an important role (~5% F1 score improvement) in extracting fine-grained relations.

The effective monitoring of low-altitude slow small (LSS) targets represented by unmanned aerial vehicle (UAV) is a great challenge in the field of security in recent years. Most of the existing infrared (IR) small target algorithms focus on high-altitude target detection. However, the low-altitude background is complex and changeable, and high-intensity suspected targets exist widely. Existing methods usually cause high false alarm or failure detection for LSS targets. In this letter, we propose a novel spatiotemporal saliency method for LSS IR targets in image sequences. First, spatial variance saliency mapping and temporal gray saliency mapping are calculated in spatial domain and temporal domain, respectively. Then, the fusion saliency map is obtained by fusing the spatial saliency map and temporal saliency map. Finally, the target is extracted by a simple adaptive threshold segmentation. The proposed method is verified in five low-altitude IR image sequences. Experimental results demonstrate that the proposed method can achieve better detection performance than the existing state-of-the-art methods for LSS targets.

Detecting small infrared (IR) targets against low-altitude complex background is always a challenge for IR search and tracking (IRST) system due to limited small target characteristics, the moving background caused by camera motion, and extremely cluttered backgrounds. The existing methods usually cause high false alarm or do not work against the chaotic low-altitude complex background. In this article, a novel spatial–temporal tensor model with saliency filter regularization (STTM-SFR) is developed to detect small IR targets. First, the small target detection task is transformed into a sparse and low-rank tensor optimization problem using the spatial–temporal prior knowledge of background and target. The construction of the holistic STTM can retain the complete spatial–temporal information of the original IR image sequence. Then, the SFR term limited between background and foreground aims to promote target saliency learning. That is to say, the SFR term can avoid the offset approximation of the low-rank tensor, so as to recover a clean target image from the original IR tensor. Finally, an effective alternating direction method of multipliers (ADMM) algorithm framework is designed to solve the proposed STTM-SFR model. The effectiveness and robustness of the STTM-SFR model are verified in six real IR scenes. Experimental results show that our method outperforms other baseline methods. Moreover, the proposed STTM-SFR method is more robust than the existing state-of-the-art STTMs against low-altitude moving backgrounds.

Infrared (IR) small target detection in the complex background is an important but challenging research hotspot in the field of target detection. The existing methods usually cause high false alarms in the complex background and fail to make full use of the complete information of the image. In this article, a novel IR small target detection model that combines facet derivative-based multidirectional edge awareness with spatial–temporal tensor (FDMDEA-STT) is presented. First, we construct an STT model (STTM) to transform the target detection problem into a low-rank and sparse tensor optimization problem based on the prior information of the target and background in the spatial–temporal domain. Then, based on the facet derivative, we define a multidirectional edge awareness mapping and fuse it into the STTM as sparse prior information. Finally, an effective algorithm based on the alternating direction method of multipliers (ADMM) is designed to solve the above model. The effectiveness of the proposed method is verified on eight real IR image sequences. Experimental results demonstrate that the proposed method has better detection performance than the existing state-of-the-art methods.

Human activity classification based on micro-Doppler (m-D) signatures finds applications in surveillance, search and rescue operations, and healthcare. In this article, we propose a new approach for human activity classification. This approach deals with the situations of reduced limb movements that could be due to the presence of injury or an individual carrying objects. It applies a preprocessing step to separate human m-D signals of the limbs from the Doppler signal corresponding to the torso. The separated m-D signal is input to a two-layer convolutional principal component analysis network (CPCAN) for feature extraction and motion classification. The CPCAN comprises a simple network architecture for efficient training and implementation, and it automatically learns the highly discriminative features. Experiments involving multiple human subjects performing different activities show a high classification accuracy associated with small arm motions.

Radar-based human activity classification is crucial for applications such as healthcare monitoring, fall detection, and assisted living due to its superior sensing capabilities and privacy protection. Traditional classification methods generally retrieve features from the time-range domain or the time-frequency (TF) domain. Such 2-D representation neglects the underlying dependence between the three radar signal variables of time, range, and Doppler frequency, and cannot fully depict the dynamic human motion features. In this article, we propose a time-range-Doppler radar point clouds (RPCs)-based learning model for human activity classification using a frequency-modulated continuous waveform (FMCW) radar. The human echoes are first transformed into a series of 3-D point cloud cubes integrating the motion signatures in three domains, namely time-range, time-Doppler, and range-Doppler domains. The generated RPC cubes are then fed into a newly developed two-layer convolutional multilinear principal component analysis network (CMPCANet) for feature extraction and motion classification. The CMPCANet comprises a simple network architecture with small training parameters, and can be directly implemented on the 3-D tensor dataset to extract highly discriminative features. Experimental results demonstrate that proposed framework can achieve superior classification accuracy and noise robustness compared to other methods using multidomain information, even with small training samples.

Traditional micro-Doppler (m-D)-based human activity classification system using monostatic radar suffers from the drawback that classification performance is vulnerable to the variation of human motion aspect angle. This leads to a performance degradation if the human movements are not directly toward or away with respect to the radar line of sight. The multistatic radar system has been suggested as an effective solution to solve the problem, as it can observe the target from multiple views and achieve favorable aspect angles to the targets. In this article, a novel human activity classification method based on motion orientation determining using multistatic m-D signals is proposed. First, the aspect angles of target motion direction with respect to each radar nodes are inferred by using the proposed motion orientation estimation method. The multistatic m-D data are then divided into several intervals based on the measured angle, and the data in the same interval are fused at the data level. Finally, the classification results are obtained through the adaptive weighted decision-level fusion. Compared with the traditional multistatic classification method, due to the consideration of the time-varying human motion aspect angle, the proposed method is more reasonable in data fusion and has better classification performance.

In this article, multitask learning is applied to forward modeling of 2-D magnetotellurics (MT) to predict the apparent resistivity and impedance phase of MT data. Multitask learning can learn multiple objectives simultaneously based on the shared representation, thereby improving efficiency and accuracy. The loss function is carefully designed by weighing multiple objective functions based on homoscedastic uncertainty, and the structural similarity regularization term is applied to ensure the texture of the obtained apparent resistivity and impedance phase. The proposed convolutional neural network can make accurate predictions with an average relative error of apparent resistivity and impedance phase less than 1.2% and 0.2%, respectively. The generalization ability of the proposed network is verified by applying it to cases with more complex resistivity distributions than training samples. This article shows the potential for fast and accurate computation of two highly correlated physical quantities in electromagnetic fields.

Passive radar (PR) systems use the existing transmitters of opportunity in the environment to perform tasks such as detection, tracking, and imaging. The classical cross‐correlation based methods to obtain the range‐Doppler map have the problems of high sidelobe and limited resolution due to the influence of signal bandwidth. In this paper, we propose a novel range‐Doppler processing method based on compressed sensing (CS), which performs sparse reconstruction in range and Doppler dimensions to achieve high resolution and reduces sidelobe without excessive computational burden. Results from numerical simulations and experimental measurements recorded with the Chinese standard digital television terrestrial broadcasting (DTTB) based PR show that the proposed method successfully handles the range‐Doppler map formatting problem for PR and outperforms the existing CS‐based PR processing methods.

Target detection in hyperspectral images (HSI) is an important technique and many target detection algorithms have been developed in recent years. The most widely detection algorithms by the original spectral characteristics may lack the ability of target signal enhancement and background suppression. This paper presents an efficient algorithm for detecting hyperspectral targets based on fractional Fourier transform (FrFT). Firstly, fractional Fourier transform primary search is used as preprocessing to obtain the better intermediate domain features with complementary characteristics between the original reflection spectrum and the Fourier transform domain. Secondly, fractional Fourier transform secondary search and constrained energy minimization (FrFT-CEM) was adopted to find an optimal fractional order to distinguish the target from the background. The proposed method has been proved to be superior in two real hyperspectral data sets.

Fast and accurate detection of elderly falls can significantly reduce the rate of morbidity and mortality. In the past decade, extensive research has been performed to achieve real-time fall monitoring solutions. In this paper, we consider the radar-based modality and utilize the family of fractional Fourier transform to enhance the motion Doppler signature of falls. Compare with the conventional time-frequency analysis approaches, the proposed method achieves higher signal energy concentration and thus yields improved fall detection in low signal-to-noise ratio scenarios. Experimental results are used to validate the theoretical analysis and to demonstrate the feasibility of the proposed approach.

In passive bistatic radars, weak target echoes may often be masked by direct path interference, multipath components, and strong target echoes, making weak target detection a challenging problem. The conventional 1-D adaptive cancelation algorithms, such as the normalized least mean square (NLMS), cannot effectively suppress strong target echoes when their Doppler frequencies spread. In addition, the continuous distribution of the NLMS weight vector does not match the sparse characteristics of strong multipath components and target echoes, thus resulting in degraded cancelation performance. Motivated by this fact, a novel 2-D sparse-weight NLMS filtering scheme is proposed by extending the NLMS to a 2-D structure, in which the weight vector is sparsely distributed and adaptively adjusted based on the sparse strong multipath components and target echoes.