MOTIVATION: Spatial clustering is a critical analytical task in spatial transcriptomics (ST) that aids in uncovering the spatial molecular mechanisms underlying biological phenotypes. Along with the numerous spatial clustering methods, there comes the imperative need for an effective metric to evaluate their performance. An ideal metric should consider three factors: label agreement, spatial organization, and error severity. However, existing evaluation metrics focus solely on either label agreement or spatial organization, leading to biased and misleading evaluations. RESULTS: To fill this gap, we propose CEMUSA, a novel graph-based metric that integrates these factors into a unified evaluation framework. Extensive testing on both simulated and real datasets demonstrate CEMUSA's superiority over conventional metrics in differentiating clustering results with subtle differences in topology and error severity, while maintaining computational efficiency. AVAILABILITY AND IMPLEMENTATION: The source code and data are freely available at https://github.com/YihDu/CEMUSA. CEMUSA is implemented as an R package at https://yihdu.github.io/CEMUSA.

In this letter, based on tensor modeling, we propose a novel panchromatic (Pan)-guided tensor low-rank (PGTLR) model for multispectral image (MSI) sharpening, which aims to fuse the low resolution (LR) MSI and Pan image to output the high resolution (HR) MSI. On one hand, we novelly exploit the tensor low-fibered-rank prior of HR MSI to model its global three-dimensional spatial-spectral correlations, which is constructed as the tensor nuclear norm (TNN) prior term. On the other hand, we further novelly exploit the Pan-guided tensor low-fibered-rank prior to model the spatial link between HR MSI and Pan, which is constructed as the novel Pan-guided TNN prior term. Furthermore, the proposed PGTLR model is optimized by an efficient alternative algorithm. Moreover, the experimental results on reduced-scale and full-scale datasets quantitatively and visually validate the superiority of PGTLR.

This letter proposes the Dynamic Margin Meta Metric Learning (DM-MML) framework to address unknown class interference and sample scarce challenges in few-shot open set specific emitter identification. In DM-MML, the dual-loop meta-training phase adopts a hierarchical margin strategy with triple-optimization, where in the inner loop, strong margins enhance feature separability for source domain emitters and the outer loop applies weak margins to calibrate target domain distributions. This strategy simultaneously preserves open decision boundaries for potential unknown class samples. During meta testing, a collaborative decision mechanism combines distance metrics and confidence scores, enabling precise known-class identification while maintaining open-space rejection capacity for unknown classes. Experiments on the WiSig dataset demonstrate superior performance over existing benchmarks under few-shot conditions.

Spatial labeling assigns labels to specific spatial locations to characterize their spatial properties and relationships, with broad applications in scientific research and practice. Measuring the similarity between two spatial labelings is essential for understanding their differences and the contributing factors, such as changes in location properties or labeling methods. An adequate and unbiased measurement of spatial labeling similarity should consider the number of matched labels (label agreement), the topology of spatial label distribution, and the heterogeneous impacts of mismatched labels. However, existing methods often fail to account for all these aspects. To address this gap, we propose a methodological framework to guide the development of methods that meet these requirements. Given two spatial labelings, the framework transforms them into graphs based on location organization, labels, and attributes (e.g., location significance). The distributions of their graph attributes are then extracted, enabling an efficient computation of distributional discrepancy to reflect the dissimilarity level between the two labelings. We further provide a concrete implementation of this framework, termed Spatial Labeling Analogy Metric (SLAM), along with an analysis of its theoretical foundation, for evaluating spatial labeling results in spatial transcriptomics (ST) as per their similarity with ground truth labeling. Through a series of carefully designed experimental cases involving both simulated and real ST data, we demonstrate that SLAM provides a comprehensive and accurate reflection of labeling quality compared to other well-established evaluation metrics. Our code is available at https://github.com/YihDu/ SLAM.

Positional encoding is essential for supplementing transformer with positional information of tokens. Existing positional encoding methods demand predefined token/feature order, rendering them unsuitable for real-world data with non-sequential yet causally-related features. To address this limitation, we propose CAPE, a novel method that identifies underlying causal structure over non-sequential features as a weighted directed acyclic graph (DAG) using generalized structural equation modeling. The DAG is then embedded in hyperbolic space where its geometric structure is well-preserved using a hyperboloid model-based approach that effectively captures two important causal graph properties (causal strength & causal specificity). This step yields causality-aware positional encodings for the features, which are converted into their rotary form for integrating with transformer's self-attention mechanism. Theoretical analysis reveals that CAPE-generated rotary positional encodings possess three valuable properties for enhanced self-attention, including causal distance-induced attenuation, causal generality-induced attenuation, and robustness to positional disturbances. We evaluate CAPE over both synthetic and real-word datasets, empirically demonstrating its theoretical properties and effectiveness in enhancing transformer for data with non-sequential features. Our code is available at https://github.com/Catchxu/CAPE.

Abstract Specific emitter identification (SEI) plays an important role in enhancing physical layer transmission security. However, with the promotion of wireless technology, the environment is filled with a large number of unknown wireless signals. SEI will face a more challenging scenario referred to as “open set.” To cope with the above difficulties, an open‐set recognition (OSR) model based on complex‐valued convolutional neural network (CVCNN) is proposed. The CVCNN can adapt to IQ signal input and extract complex domain features. Furthermore, a novel inter‐class loss is proposed to effectively improve the classification performance. Finally, the classifier is designed based on the incremental approach. It can continuously learn new classes to achieve the recognition of multiple unknown emitters. The experiments show that compared with the real‐valued convolutional neural network and the single loss function, the accuracy is improved by 3.8% and 10%, respectively.

Natural disasters often destroy critical infrastructure, such as terrestrial communication networks and transportation routes, thereby severely disrupting post-disaster rescue operations. To rapidly re-establish communication links and provide flexible computational support in disaster rescue scenarios, the integration of unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) has emerged as a promising solution. Nevertheless, the highly complex and resource-constrained characteristics of disaster environments pose significant challenges for UAV-assisted computation task offloading. In this paper, we investigate the joint task offloading and resource allocation (JTORA) problem to minimize the energy consumption associated with communication and computation during task offloading. Specifically, we develop a twin-delayed deep deterministic policy gradient (TD3)-based JTORA (JTORA-TD3) algorithm, which enables the UAV to optimize decisions of task offloading and resource allocation intelligently. To further enhance the training efficiency of the JTORA-TD3 algorithm in a complex disaster rescue environment, we integrate a large AI model (LAM) into the TD3 framework. Based on the textual interaction, we propose an LAM-enabled TD3-based JTORA (JTORA-LAM4TD3) algorithm. Simulation results demonstrate that the proposed JTORA-LAM4TD3 algorithm significantly outperforms baselines. These findings confirm the effectiveness of integrating LAMs with deep reinforcement learning (DRL) for solving the decision optimization problem.

Specific Emitter Identification (SEI) is crucial for ensuring the security of physical layer communication. However, signal characteristics can be affected by various factors such as environmental and equipment variations. An effective SEI system must continuously learn and adapt to these changes to maintain accurate signal recognition. This study proposes an advanced domain incremental learning (DIL) framework for SEI, named Adaptive Domain-Incremental Learning with Knowledge Replay and Domain Alignment (ADIRA). ADIRA employs knowledge replay and distillation strategies, along with adaptive coefficients, to balance the model’s performance in recognizing signals across both new and old domains. To address the variations in signal data feature distributions across different domains, we introduce a domain alignment strategy based on adversarial training. This approach integrates embedding distillation loss with supervised contrastive loss, significantly enhancing the model’s adaptability to domain changes. Experimental results on two benchmark datasets demonstrate that ADIRA achieves performance only 0.42% and 1.71% lower than joint training, with replay samples constituting just 1.1% and 1.5% of the training set, effectively mitigating catastrophic forgetting.

Abstract Reactive jammers select jamming strategies according to the users’ responses; thus, conventional anti‐jamming methods such as frequency hopping are inadequate to defeat the jamming attack. In this article, the authors propose a novel uncoupled deception scheme to trap the reactive jammer into attacking a decoy channel in distributed networks. Specifically, the authors design a multi‐functional network utility for every user to mislead the jammer with a minimum energy consumption while achieving the highest network throughput. Based on the network utility, the anti‐jamming problem is formulated as an exact potential game such that the existence of Nash equilibrium can be guaranteed theoretically. The authors further propose a back‐to‐back coordination‐based learning algorithm to reach the optimal channel selection and power adaption in a non‐cooperative way. To alleviate the lack of mutual information exchange, the back‐to‐back coordination mechanism derives all users to deceive the jammer by inferring others’ strategies based on a shared belief. Simulation results show that the proposed algorithm yields higher network throughput and efficiency‐cost ratio compared to the state‐of‐the‐art cooperative schemes.

Abstract Radio frequency fingerprint identification (RFFI) is a widely used technique for authenticating equipment. It identifies transmitters by extracting hardware defects found in the RF front end. Recent research has focused on the impact of transmitters and wireless channels on radio frequency fingerprint (RFF). Most work is based on the same receiver assumption, while the influence of the receiver on RFF remains unresolved. This paper focuses on the impact of receiver hardware characteristics on RFF and proposes a few‐shot cross‐receiver RFFI method based on feature separation. Data augmentation with noise addition and simulated channels addresses sparse sample issues and enhances the model's robustness to channel variations. Simultaneously, feature separation is realized by reducing the correlation between transmitter and receiver features through classification loss and similarity loss. We evaluate the proposed approaches using a large‐scale WiFi dataset. It is shown that when a trained transmitter classifier is deployed on new receivers with only 30 samples per trained transmitter, the average identification accuracy of the proposed method is 83.6%. This accuracy is 9.45% higher than the baseline method without considering transmitter hardware influence. After fine‐tuning, the average identification accuracy can reach 98.25%.

Abstract In this paper, the problem of mission planning and spectrum resource allocation for cooperative reconnaissance of ground targets with multiple unmanned aerial vehicles (UAVs) is studied. A joint mission planning and spectrum resource optimization algorithm for multi‐UAVs is proposed to improve the information transmission rate by reusing the spectrum of existing users. The joint optimization problem is formulated as mixed‐integer non‐linear programming. The block coordinate descent (BCD) method is further applied to achieve the optimal strategies of mission planning, channel allocation, and power control. Specifically, an improved genetic algorithm (GA) combined with the successive convex approximation (SCA) is used to solve the sub‐problem of mission planning. For the channel allocation sub‐problem, an iterative convergence channel allocation algorithm is proposed. Numerical results show that the proposed algorithm can achieve a higher UAV transmission rate and better robustness than existing algorithms.

Abstract Aiming at the issues of low individual identification accuracy of radiation sources under the condition of little samples, this paper proposes a way of individual identification of radiation source based on strengthening global deep convolutional generative adversarial network (SGDCGAN) and deep convolutional neural network (DCNN) to achieve data augmentation. The method first performs IQ map feature splicing processing on the input signal, and then uses DCNN to automatically obtain the deep essential features of the data. Besides, an adaptive improvement is created to the deep convolutional generative adversarial network, and a self‐attention mechanism is introduced into the discriminator and the generator to reinforce the integrity and authenticity of the generated samples. For the common gradient disappearance during model training, the gradient penalty mechanism and spectral normalization are added to make the training process more stable. Through comparison experiments on the collected ADS‐B signals, the experimental results have demonstrated that when the signal‐to‐noise ratio is 0 dB and the number of original samples in each class is 40, the recognition accuracy is improved by 23.6% after doubling the data. Compared with the DCGAN‐DCNN and GAN‐DCNN methods, the recognition accuracy is improved by 3.5% and 4%.

Complexity of emergency procedures have direct impacts on the accomplishment of tasks in metro system. In order to ensure the efficient operation of automated metro in emergency scenarios, it is necessary to understand the potential relationship between system change and emergency procedures. To solve this problem, an evaluation method for emergency procedures is proposed. Firstly, on the basis of investigation, interview and empirical analysis of different types of automated metro lines, combined with Team-Cognitive Work Analysis(CWA) method and network theory, the team emergency task network is established. Then four characteristic indexes, i.e. degree, average shortest path length, agglomeration coefficient and overall network efficiency, are selected as the analysis metrics of emergency task network complexity. The complexity of different emergency procedures under grades of automation(GOA) 4 and same emergency procedure under GOA1-GOA4 are comprehensively analyzed. The research results reveal that no matter what level of automation system, the more nodes and communication between nodes, the larger network scale is, which will lead to the emergency procedures more complicated, and vice versa. The driver's behavior plays a decisive role in the variation of communicating frequencies.