This study starts from the physical perspective of electromagnetic wave propagation in ionosphere media, and the skywave OTH (over-the-horizon) ionosphere channel model is established for hypersonic vehicles based on the ray-tracing method, and this study identifies the key parameters influencing channel characteristics. Secondly, using the re-entry trajectory of the RAM C-II flight experiment as an example, dynamic multipath channel characteristic parameters—such as loss, delay, and Doppler shift—are analyzed in multiple seasons during the noon and midnight periods at a communication frequency of 14 MHz. The results indicate that the settling effect of the ionosphere at midnight makes the changes in the channel more complex, with the irregular sudden appearance and disappearance of multipath numbers. In addition, channel loss is greater in low-elevation propagation mode than in high-elevation propagation mode, indicating that the channel multipath exhibits high loss and low delay characteristics. The skywave communication channel model for hypersonic vehicles, and the dynamic multipath channel characteristic parameters presented in this study offer valuable support for the design, development, and evaluation of long-distance TT&C (Tracking, Telemetering, and Command) communication systems.
Traditional specific emitter identification (SEI) systems often suffer significant performance degradation when confronted with previously unseen signal sources, underscoring the critical need for accurate detection and rejection of novel-class instances. To address this limitation, we propose an Integrated Deep Feature Representation and Isolation Forest (IDFIF) method for identifying novel-class radiation emitters. IDFIF begins by employing a convolutional neural network (CNN) to extract embedding features from raw In-phase/Quadrature (IQ) signals, enhancing inter-class separability while suppressing intra-class variability. These deep features are then used to construct an unsupervised iForest that learns the statistical distribution of known classes, enabling the effective detection of anomalies via a threshold-based scoring mechanism. Experiments conducted on a real-world ADS-B dataset demonstrate that the proposed method achieves a novel-class detection accuracy of over 94%, significantly outperforming comparative methods. Furthermore, the method exhibits low sensitivity to known-class samples, thereby ensuring robustness and generalization under open-set conditions. The proposed IDFIF method is promising for deployment in challenging electromagnetic environments.