To solve the problem that Automatic Modulation Recognition (AMR) is limited by small-sample data and insufficient fusion of time-frequency multimodal information in practical applications, which in turn leads to low recognition accuracy, the limitations of existing technologies in the AMR field are analyzed and a cross-modal self-supervised learning framework integrating a diffusion model and a contrastive learning mechanism is proposed. By introducing the diffusion model, the framework leverages its generative capability to achieve high-quality data synthesis and augmentation of communication signals, effectively alleviating the constraints of small-sample data on model training. Meanwhile, combined with the cross-modal contrastive learning mechanism, it constructs an inter-modal association learning module to fully explore and utilize the inherent correlations and complementary information between different time-frequency modal representations, thus solving the problem of insufficient multimodal information fusion. Finally, based on the above design, a Diffusion-Contrastive Hybrid Network (DCHN) model is established. Experimental results show that the recognition accuracy of this model on the RML2016.10a dataset is significantly higher than that of other network models, indicating that it possesses excellent recognition capability.

Modulation recognition is a critical task in wireless communications. Although deep learning methods have achieved remarkable progress in this field, they still face the challenge of insufficient generalization ability in complex non-cooperative environments—particularly when confronted with varying channel conditions, which can obscure the subtle discriminative features between structurally similar modulation schemes (e. g. 16QAM and 64QAM) and thus degrade recognition performance. To address this unique challenge in the field of modulation recognition, an unsupervised adversarial domain adaptation method named Feature Alignment and Discrimination Domain Adaptation ( FADDA) is proposed. The core of FADDA is the introduction of a contrastive learning-based feature alignment loss on the basis of adversarial training. Adversarial training is responsible for learning domain-invariant features to adapt to channel variations, while the feature alignment. loss fundamentally enhances the model' s ability to distinguish between easily confused modulation types by explicitly reinforcing the compactness of intra-class features and the separability of inter-class features. Experimental results show that without target-domain labels, this method can significantly improve the model's cross-channel modulation recognition performance and demonstrate strong generalization ability.

To address the issues of insufficient low-frequency coverage and oversized antennas in radio monitoring systems，a miniaturized ultra-wideband receiving antenna based on improved dipole structure is proposed. The design employs meandering techniques to bend the dipole arms (dimensions: 38.6 mm×134.1 mm×0.8 mm)，integrating symmetrical parasitic elements and slotted structures to optimize current distribution and extend bandwidth. CST simulations and measurements demonstrate that the antenna achieves S₁₁＜-6 dB across 0.7～0.96 GHz and 1.3～5.3 GHz bands，covering standards such as GSM，DCS-1800，WLAN，WiMAX，and 5G NR n77/n78/n79.The radiation efficiency reaches 96.42% at 2.2 GHz and 95.63% at 4.4 GHz，with 85.4%±6.8% average efficiency in 5G Sub-6 GHz bands. The maximum gain of ( 4.23±0.54) dBi ( 3.3～5.0 GHz) surpasses conventional dipoles by 1.8 dBi. This structural innovation resolves the low-frequency coverage vs miniaturization trade-off，enabling multi-standard communication monitoring.

To solve the problem of stable information transmission for unmanned systems in complex electromagnetic environments, the information elastic adaptation method for unmanned systems based on communication quality assessment is proposed. Signal strength, bit error rate, and signal-to-noise ratio at the communication link layer are selected as characteristic parameters for communication quality assessment. Long Short-Term Memory ( LSTM) network is served as the signal prediction model to estimate future signal parameters, while a Support Vector Regression (SVR) model is employed to evaluate real-time communication quality. Based on the communication quality level evaluation model, the communication quality evaluation results are obtained; corresponding level of content is transmitted according to the communication quality level. Simulations using real-world data and field tests demonstrate that the proposed method ensures reliable information transmission for unmanned systems in highly dynamic and contested electromagnetic environments.

In traffic surveillance systems, radar-camera devices are used to collaboratively perceive and monitor the roadside environment. Due to the principles of perspective imaging, the greater the distance to a target, the smaller its corresponding pixel area in the image. Furthermore, the bounding boxes generated by visual detection exhibit significant jitter. If calibration errors or visual occlusion exist, or if the detection boxes shake, a significant error will be introduced when the target' s position is mapped from the image coordinate system to the radar coordinate system, affecting tracking accuracy. This is especially true for collaborative target sensing and tracking with multiple sensors, which further increases the difficulty. To address these challenges, a multi-sensor, multi-target collaborative perception and tracking method is proposed, leveraging a two-stage matching strategy and an adaptive Kalman filter. This method improves association precision by adding a secondary matching strategy of Perspective View (PV) plane after the Bird's Eye View (BEV) plane is associated with the data of frame before and after. This effectively solves the problem of low tracking accuracy for distant targets caused by significant mapping errors. Based on the relationship model between image points and range-position jitter, an adaptive multi-sensor multi-target tracking method is proposed. By using the relationship model to update the parameters of the Kalman filter, and adaptively selecting the appropriate observation matrix and measurement covariance matrix according to the target sensor data source, the position and velocity parameters of the target are estimated. This effectively improves the real-time prediction accuracy of the target' s spatial position and velocity, and further enhances the accuracy of target association in the BEV plane. Experimental results show that the proposed method improves the Multiple Object Tracking Accuracy ( MOTA) index by 16.3% compared to the method without the two-stage matching strategy and only using the ordinary Kalman filter, significantly improving the accuracy of target perception and tracking in traffic scenes using millimeter-wave radar and vision integrated systems.

To meet the requirements of half/full duplex communication systems, a dual-frequency omnidirectional dual-circularly-polarized Multiple Input Multiple Output (MIMO) antenna based on magnetic-electric dipole is proposed. It consists of four identical antenna elements symmetrically arranged to form a 2×2 MIMO array, and each antenna element is composed of circular planar waveguide, four folded electric dipoles, and eight parasitic electric dipoles. The slits on the circular planar waveguide and short-circuit cylinders are employed to form four magnetic dipoles on the opening side of the circular planar waveguide, and their radiated E-field is orthogonal to the E-field of the electric dipole. When a 90° phase difference between the magnetic dipole and the electric dipole is realized due to their spatial distance, a left-handed or right-handed circularly polarized wave with 360° coverage can be produced. The results demonstrate that each antenna element can radiate right-handed circularly polarized wave in low bands (2.42～2.47 GHz) and left-handed circularly polarize wave in high band (5.76～5.85 GHz), its Axial Ratio (AR) is less than 3 dB, and the gain fluctuation is less than 2.1 dB and 7.3 dB, respectively. Moreover, the isolation is lower than -30 dB in low band and -50 dB in high band respectively owing to symmetrical distributions between adjacent elements.

Target detection in autonomous driving scenarios faces challenges such as complex environmental interference, multi-scale target distribution and target occlusion, and existing algorithms are still deficient in feature fusion capability, detail characterization accuracy and localization regression performance. To this end, an improved YOLOv8 detection algorithm, DMP-YOLO, is proposed. The original neck structure is optimized using Multi-Branch Auxiliary Feature Pyramid Network (MAFPN) to enhance the multi-scale feature fusion capability in complex traffic scenarios; C2f_DEConv is proposed in backbone network module, which replaces the standard convolution with Detail-Enhanced Convolution (DEConv) to significantly improve the detail capturing ability of small-scale vehicles and occluded targets through high-frequency feature preservation and local texture enhancement; the Powerful Intersection over Union version 2 (PIoUv2) loss function is introduced to optimize the improved bounding-box loss, which improves the regression accuracy of the target bounding-box through the optimization of dynamic scale-sensitive factors and geometric constraints. Experiments on the KITTI dataset demonstrate that DMP-YOLO achieves significant improvements across all key performance metrics, with mAP@0.5 reaching 89.0% (2.6% improvement compared with the baseline YOLOv8) as well as 2.9% improvement for mAP@0.5: 0.95, which provides an effective solution for high-precision real-time detection in autonomous driving scenarios.

An algorithm for weed recognition in beet fields based on improved YOLOv11 model is proposed to address the problems of low efficiency, low accuracy, and missed detection of small targets in complex real-world scenarios. The PoolFormer module and AKConv module are introduced into the backbone network to enhance the model's ability to capture global semantic information to improve detection accuracy, enhancing the detection performance in low resolution images and small objects. The AKConv module improves the feature extraction ability of the model for beets and weeds with irregular growth patterns by dynamically adjusting the convolution kernel parameters and shapes, while the PoolFormer module can effectively segment the edge features of beets and weeds that cover each other. Secondly, the High-level Screening Feature Pyramid Network (HS-FPN) module is added to the head network to enhance the efficiency of multi-scale fusion and improve the feature extraction efficiency and speed of beets and weeds during the seedling stage. Through experiments, it is found that the improved YOLOv11 model achieves increases of 6.9%, 7.8%, 7.9%, and 7.8% in precision, recall, mAP@0.5 and mAP@0.5: 0.95, respectively, compared to the original model. The results show that this algorithm has achieved significant improvement in weed recognition in beet fields, providing a more feasible solution for detecting weeds in beet fields in complex scenarios.

The application value of Brain-Computer Interface (BCI) and human-machine integration technology in the fields of UAV control and countermeasure equipment operation is explored, the problems faced by these technologies are analyzed, and targeted solutions are proposed to promote their rational application in the development of the low-altitude economy and security protection. By analyzing the role of BCI technology in improving UAV control efficiency and enhancing the accuracy of countermeasure equipment operation, and combining the new application scenarios that BCI technology shapes for the low-altitude economy and the new form of low-altitude security protection it creates, the problems faced by these technologies are sorted out, such as inherent defects of human-machine integration technology, information security risks, and their impacts on low-altitude security, and corresponding countermeasures are further put forward. BCI technology plays a significant role in the fields of UAV control and countermeasure equipment operation: it can improve UAV control efficiency and enhance the accuracy of countermeasure equipment operation. Based on BCI and human-machine integration technology, new application scenarios for the low-altitude economy have been shaped, and a new form of low-altitude security protection has been created.

Beidou Satellite Navigation System (BDS) navigation receiver has the functions of Positioning, Navigation, and Timing (PNT) and message communication, and has been widely used in various industries. Under the background of the smooth transition from BDS-2 regional system to BDS-3 global system, its influence on the service performance of the navigation receiver and countermeasures are studied. The differences between BDS-2 and BDS-3 in signal type, signal system, constellation scale and service performance are compared, and the specific manifestations and state change trends of BDS smooth transition are expounded. The impact of the smooth transition of BDS on the service performance of navigation receiver is analyzed emphatically, including navigation and positioning, message communication and anti-suppression-jamming ability. The simulation results show that the RDSS message communication service can still be used normally during the smooth transition period of BDS-2 receiver ( PRN01～37). With the progressive retirement of BDS-2 satellite, the number of satellites available in space will gradually decrease from 33 to 18, the average number of satellites visible worldwide will decrease from 11.62 to 6.31, the average Geometric Dilution Precision (GDOP) value will increase from 2.00 to 3.15, and the continuous availability of services will decrease from 93% to 46.46%, which will affect the positioning accuracy and service range. When the power of BDS-3 satellite is enhanced, the navigation receiver can obtain 7～15 dB improvement in anti-suppression-jamming ability. According to the different application scenarios of the navigation receiver, the corresponding countermeasures are given to weaken or eliminate the impact, so that the navigation receiver can continuously provide reliable services for users during the smooth transition of the BDS. The research results can provide reference for the design, development and application of BDS navigation receivers.