Aiming to solve the problems of false detection, missed detection, and insufficient detection ability of infrared vehicle images, an infrared vehicle target detection algorithm based on the improved YOLOv5 is proposed. The article analyzes the image characteristics of infrared vehicle detection, and then discusses the improved YOLOv5 algorithm in detail. The algorithm uses the DenseBlock module to increase the ability of shallow feature extraction. The Ghost convolution layer is used to replace the ordinary convolution layer, which increases the redundant feature graph based on linear calculation, improves the network feature extraction ability, and increases the amount of information from the original image. The detection accuracy of the whole network is enhanced by adding a channel attention mechanism and modifying loss function. Finally, the improved performance and comprehensive improved performance of each module are compared with common algorithms. Experimental results show that the detection accuracy of the DenseBlock and EIOU module added alone are improved by 2.5% and 3% compared with the original YOLOv5 algorithm, respectively, and the addition of the Ghost convolution module and SE module alone does not increase significantly. By using the EIOU module as the loss function, the three modules of DenseBlock, Ghost convolution and SE Layer are added to the YOLOv5 algorithm for comparative analysis, of which the combination of DenseBlock and Ghost convolution has the best effect. When adding three modules at the same time, the mAP fluctuation is smaller, which can reach 73.1%, which is 4.6% higher than the original YOLOv5 algorithm.

Automatic modulation recognition (AMR) plays an essential role in modern communication systems. In recent years, various modulation recognition algorithms based on deep learning have been emerging, but the problem of low recognition accuracy has not been solved well. To solve this problem, based on the existing MCLDNN algorithm, in this paper, we proposed an improved spatiotemporal multi-channel network (IQ-related features Multi-channel Convolutional Bi-LSTM with Gaussian noise, IQGMCL). Firstly, dividing the input IQ signals into three channels, time sequence feature extraction is carried out for route I, route Q, and route IQ, respectively. For route IQ, convolution kernel (2,1) is first used to extract relevant features. Two layers of the small convolution kernel (1,3) are used to extract time sequence features further, and the three channels are used to extract features further. Then, a two-layer short-length memory network is used to extract features from time and space more effectively. Through comparison experiments, Bi-LSTM is introduced to replace one layer of LSTM, and a fully connected layer is removed to prevent overfitting. Finally, multiplicative Gaussian noise is introduced to naturally corrode the feature parameters, further improving the robustness and accuracy of the model. Experiments are carried out on three public datasets RML2016.10a, RML2016.10b, and RML2016.04C. The experiments show that the IQGMCL network has higher recognition accuracies on all datasets, especially on the RML2016.10a dataset. When the SNR is 4 dB, the recognition accuracy reaches 93.52%. When the SNR is greater than 0 dB, the average recognition accuracy reaches 92.3%, 1.31%, and 1.2% higher than the original MCLDNN network, respectively.

Automatic modulation recognition (AMR) is a critical technology in spatial cognitive radio (SCR), and building high-performance AMR model can achieve high classification accuracy of signals. AMR is a classification problem essentially, and deep learning has achieved excellent performance in various classification tasks. In recent years, joint recognition of multiple networks has become increasingly popular. In complex wireless environments, there are multiple signal types and diversity of characteristics between different signals. Also, the existence of multiple interference in wireless environment makes the signal characteristics more complex. It is difficult for a single network to accurately extract the unique features of all signals and achieve accurate classification. So, this article proposes a time–frequency domain joint recognition model that combines two deep learning networks (DLNs), to achieve higher accuracy AMR. A DLN named MCLDNN (multi-channel convolutional long short-term deep neural network) is trained on samples composed of in-phase and quadrature component (IQ) signals, to distinguish modulation modes that are relatively easy to identify. This paper proposes a BiGRU3 (three-layer bidirectional gated recurrent unit) network based on FFT as the second DLN. For signals with significant similarity in the time domain and significant differences in the frequency domain that are difficult to distinguish by the former DLN, such as AM-DSB and WBFM, FFT (Fast Fourier Transform) is used to obtain frequency domain amplitude and phase (FDAP) information. Experiments have shown that the BiGUR3 network has superior extraction performance for amplitude spectrum and phase spectrum features. Experiments are conducted on two publicly available datasets, the RML2016.10a and RML2016.10b, and the results show that the overall recognition accuracy of the proposed joint model reaches 94.94% and 96.69%, respectively. Compared to a single network, the recognition accuracy is significantly improved. At the same time, the recognition accuracy of AM-DSB and WBFM signals has been improved by 17% and 18.2%, respectively.

With the rapid development of communication technology, due to the advantages of high flexibility, good compatibility, wide openness and other advantages of software radio, and it is easy to upgrade and expand the system in the later stage, software radio technology has been applied in many radio engineering occasions, showing broad application prospects. This paper applies the GNU Radio experimental platform, and selects eight modulation methods of AM, DSB, SSB, 2ASK, MASK, 2FSK, 2PSK, MPSK, etc., through the setting of basic parameters such as frequency, phase, FFT points, window function and the setting of channel parameters such as additive white Gaussian noise, frequency offset, epsilon and signal-to-noise ratio range, to obtain different simulated time domain charts, frequency domain charts, waterfall charts, constellation charts, and compare and analyze different signal modulation techniques, understand and master the modulation principles and modulation methods of signals. At the same time, modeled on a number of open source datasets such as RML2016.10A and RML2018.01A, a small sample electromagnetic dataset is formed in the GNU Radio software platform, providing a reliable data set for technical research in the field of electromagnetic space and providing more general options for researchers who design related systems.

No abstract