CM-LSTM Based Spectrum Sensing.

This paper presents spectrum sensing as a classification problem, and uses a spectrum-sensing algorithm based on a signal covariance matrix and long short-term memory network (CM-LSTM). We jointly exploited the spatial cross-correlation of multiple signals received by the antenna array and the temporal autocorrelation of single signals; we used the long short-term memory network (LSTM), which is good at extracting temporal correlation features, as the classification model; we then input the covariance matrix of the signals received by the array into the LSTM classification model to achieve the fusion learning of spatial correlation features and temporal correlation features of the signals, thus significantly improving the performance of spectrum sensing. Simulation analysis shows that the CM-LSTM-based spectrum-sensing algorithm shows better performance compared with support vector machine (SVM), gradient boosting machine (GBM), random forest (RF), and energy detection (ED) algorithm-based spectrum-sensing algorithms for different signal-to-noise ratios (SNRs) and different numbers of secondary users (SUs). Among them, SVM is a classical machine-learning algorithm, GBM and RF are two integrated learning methods with better generalization capability, and ED is a classical, traditional, and spectrum-sensing algorithm.

Polarization Domain Spectrum Sensing Algorithm Based on AlexNet.

In this paper, we propose a spectrum sensing algorithm based on the Jones vector covariance matrix (JCM) and AlexNet model, i.e., the JCM-AlexNet algorithm, by taking advantage of the different state characteristics of the signal and noise in the polarization domain. We use the AlexNet model, which is good at extracting matrix features, as the classification model and use the Jones vector, which characterizes the polarization state, to calculate its covariance matrix and convert it into an image and then use it as the input to the AlexNet model. Then, we calculate the likelihood ratio test statistic (AlexNet-LRT) based on the output of the model to achieve the classification of the signal and noise. The simulation analysis shows that the JCM-AlexNet algorithm performs better than the conventional polarization detection (PSD) algorithm and the other three (LeNet5, long short-term memory (LSTM), multilayer perceptron (MLP)) excellent deep-learning-based spectrum sensing algorithms for different signal-to-noise ratios and different false alarm probabilities.

A Low Complexity Sensing Algorithm for Non-Sparse Wideband Spectrum.

The vast majority of existing sub-Nyquist sampling wideband spectrum sensing (WSS) methods default to a sparse spectrum. However, research data suggests that in the near future, the wideband spectrum will no longer be sparse. This article proposes a sub-Nyquist sampling WSS algorithm that can adapt well to non-sparse spectrum scenarios. The algorithm continues to implement the idea of our previously proposed "no reconstruction (NoR) of spectrum" algorithm, thus having low computational complexity. The new one is actually an advanced version of the NoR algorithm, so it is called AdNoR. The key to its advancement lies in the establishment of a folded time-frequency (TF) spectrum model with the same special structure as in the fold spectrum model of the NoR algorithm. For this purpose, we have designed a comprehensive sampling technique which consists of multicoset sampling, digital fractional delay, and TF transform. It is verified by simulation that the AdNoR algorithm maintains a good sensing performance with low computational complexity in the non-sparse scenario.

Dynamic avoidance decision method for civil aircraft in a suborbital debris hazard zone.

Closing the static suborbital debris hazard zone method leads to low airspace resource utilization and long delays for civil aircraft, while the dynamic delineation of suborbital debris hazard zone method can solve the above phenomena. However, the existing research lacks the decision instruction for civil aircraft to avoid the dynamic suborbital debris hazard zone. To address the above problems, this paper creates probability ellipsoids of suborbital debris with different ballistic coefficients in the two-dimensional plane and use the divide-and-conquer algorithm for the dynamic delineation of the suborbital debris hazard zone. The suborbital debris hazard zone is extended outward by 10 km. Subsequently, the standard A* algorithm, the standard Lazy theta* algorithm, the improved Lazy theta* algorithm, and a flight path planning strategy are designed to avoid the suborbital debris hazard zone and provide safe dynamic avoidance commands for civil aircraft with fixed time intervals. The simulation results show that the average area of the dynamically delineated suborbital debris hazard zone is lower than the traditional static no-fly zone; the standard A* algorithm and improved Lazy theta* algorithm provides shorter flight path lengths and flight time and fewer waypoints in windless and windy conditions, respectively.

Modeling and probabilistic analysis of civil aircraft operational risk for suborbital disintegration accidents.

To reduce the collision risk to civil airliners caused by suborbital vehicle disintegration events, this paper uses a covariance propagation algorithm to model the debris landing point of suborbital disintegration accidents and gives a collision probability analysis method for civil airliners encountering debris during the cruise. Collision warning is performed for airborne risk targets to improve the emergency response capability of the ATC surveillance system to hazardous situations. The algorithm models the three-dimensional spatial motion target localization problem as a Gauss-Markov process, quantifying the location of debris landing points in the vicinity of nominal trajectories. By predicting the aircraft trajectory, the calculation of the inter-target collision probability is converted into an integration problem of a two-dimensional normally distributed probability density function in a circular domain. Compared with the traditional Monte Carlo method, the calculation speed of debris drop points is improved, which can meet the requirements of civil aviation for real-time response to unexpected situations.