In this work, a novel double-covertness framework is developed for integrated sensing and communication (ISAC) systems, where both the radar and communication signals are protected from being maliciously detected by adversaries. Specifically, a new measurement named joint intercept probability (JIP) is proposed for characterizing the double-covertness performance. Next, an optimal power allocation strategy is designed to minimize the JIP, subject to certain quality-of-service (QoS) requirements for communication and sensing. Simulation results verify the effectiveness of our proposed solution and demonstrate the intrinsic relationship among power allocation, JIP and different QoS requirements.

In this paper, we consider the physical layer security (PLS) problem for integrated sensing and communication (ISAC) systems in the presence of hybrid-colluding eavesdroppers, where an active eavesdropper (AE) and a passive eavesdropper (PE) collude to intercept the confidential information. To ensure the accuracy of sensing while preventing the eavesdropping, a base station transmits a signal consisting of information symbols and sensing waveform, in which the sensing waveform can be also used as artificial noise to interfere with eavesdroppers. Under this setup, we propose an alternating optimization-based two stage scheme (AO-TSS) for improving the sensing and communication performance. In the first stage, based on the assumptions that the perfect channel state information (CSI) of the AE and statistical CSI of the PE are known, the communication and sensing beamforming problem is formulated with the objective of minimizing the weighted sum of the beampattern matching mean squared error (MSE) and cross-correlation, subject to the secure transmission constraint. To tackle the non-convexity, we propose a semi-definite relaxation (SDR) algorithm and a reduced-complexity zero-forcing (ZF) algorithm. Then, the scenarios are further extended to more general cases with imperfect AE CSI and unknown PE CSI. To further improve the communication performance, the second-stage problem is developed to optimize the secrecy rate threshold under the radar performance constraint. Finally, numerical results demonstrate the superiority of the proposed scheme in terms of sensing and secure communication.

In this paper, aimed to protect the transmitted waveform from being intercepted by advanced electronic support measure systems, a low probability of intercept (LPI) signal design, taking into account the transmitted waveform and precoder of communication users, is developed for multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) systems. The considered system simultaneously senses multiple targets and communicates with multiple users in the presence of various interferences. Specifically, based on the analysis of cyclic spectrum, the desired LPI performance is achieved by minimizing the cyclic frequency sidelobe level. Moreover, sensing and communication requirements are satisfied by respectively maximizing the minimum signal-to-interference-plus-noise ratio (SINR) of targets and constraining the received SINR lower bound of each user. Energy budget and peak-to-average power ratio constraints are introduced to meet the practical resources limits, while similarity constraint is constructed to further ensure the target sensing. Next, in order to solve the formulated nonconvex problem, an efficient iterative algorithm is proposed based on the idea of successive convex approximation (SCA). Finally, simulation results demonstrate the effectiveness of our proposed scheme and display the trade-off among LPI, sensing and communication performance.

Fetal cerebellum landmark detection is crucial for assessing fetal brain development. Although deep learning has become the standard for automatic landmark detection, most previous methods have focused on using 2D ultrasound or thick Magnetic Resonance Imaging (MRI). To improve accuracy, landmarks should be located on thin 3D MRIs. However, abnormal development, high noise, and fuzzy boundaries in 3D fetal brain images make traditional methods less effective for cerebellum landmark detection. To address this, we introduce the Anatomical Pseudo-label Guided Attention (APGA) network alongside a 3D MRI-based benchmark for fetal cerebellum landmark detection. During training, we use a shared encoder to extract image features and two decoders for landmark regression and anatomical pseudo-label segmentation. We design a Feature Decoupling Transformer (FDT) and embed it into the encoder to better calibrate the features for the two tasks. We only need the encoder, the FDT, and the landmark decoder during the inference phase. Extensive experiments on our proposed benchmark and out-of-domain test set have shown the effectiveness of our method. Our simulations also demonstrated that 3D biometrics are better than 2D biometrics.

With the explosive growth of spectrum demand for various wireless devices and applications, it is more and more difficult to allocate contiguous spectral bands for radar and communication nowadays. In this paper, the problem of dual-functional radar-communication (DFRC) multiple-input multiple-output (MIMO)-orthogonal frequency division multiplexing (OFDM) waveform design under non-contiguous spectrum bands is studied. We consider a flexible spectrum structure where a large number of non-contiguous bands are used for communication and some idle bands which are complementary to the communication bands are exploited for radar detection. The symbols transmitted on the communication bands are first designed by minimizing the multi-user interference (MUI) to enhance the performance of communication. Meanwhile, the radar performance is improved by designing the waveform of idle bands. We formulate the radar beampattern design as a rank-1 approximation problem, which can be solved with a closed-form solution. Numerical results show that we can achieve omnidirectional strict beampattern design and data transmission with zero MUI.

Genetic Programming (GP) is reputable for its power in finding creative solutions for complex problems. However the downside of it is also well known: the evolved solutions are often difficult to understand. This interpretability issue hinders GP to gain acceptance from many application areas. To address this issue in the context of motion detection, GP programs evolved for various detection tasks are analyzed in this study. Previous work has shown the capabilities of these evolved motion detectors such as ignoring uninteresting motions, differentiating fast motions from slow motions, identifying genuine motions from a moving background, and handling noises. This study aims to reveal the behavior of these GP individuals by introducing simplified motion detection tasks. The investigation on these GP motion detectors shows that their good performance is not random. There are contributing characteristics captured by these detectors, of which the behaviors are more or less explainable. This study validates GP as a good approach for motion detection.

Motion detection is a vital part of vision systems, either biological or computerized. Conventional motion detection methods in machine vision can differentiate moving objects from background, but cannot directly handle different types of motions. In this paper, we present Genetic Programming (GP) as a method which not only removes relatively stationary background, but also can be selective on what kind of motions to capture. Programs can be evolved to select a certain type of moving objects and ignore other motions. That is to select fast moving target and ignore slowing moving ones. Furthermore programs can be evolved to handle these tasks even when the camera itself is in relatively arbitrary motion. This general GP method does not require additional process to differentiate various types of motions.