RESUMEN
Passive radars based on long-term evolution (LTE) signals suffer from sever interferences. The interferences are not only from the base station used as the illuminator of opportunity (BS-IoO), but also from the other co-channel base stations (CCBS) working at the same frequency with the BS-IoO. Because the reference signals of the co-channel interferences are difficult to obtain, cancellation performance degrades seriously when traditional interference suppression methods are applied in LTE-based passive radar. This paper proposes a cascaded cancellation method based on the spatial spectrum cognition of interference. It consists of several cancellation loops. In each loop, the spatial spectrum of strong interferences is first recognized by using the cyclostationary characteristic of LTE signal and the compressed sensing technique. A clean reference signal of each interference is then reconstructed according to the spatial spectrum previously obtained. With the reference signal, the interferences are cancelled. At the end of each loop, the energy of the interference residual is estimated. If the interference residual is still strong, then the cancellation loop continues; otherwise it terminates. The proposed method can get good cancellation performance with a small-sized antenna array. Theoretical and simulation results demonstrate the effectiveness of the proposed method.
RESUMEN
In recent years, wireless-based fingerprint positioning has attracted increasing research attention owing to its position-related features and applications in the Internet of Things (IoT). In this paper, by leveraging long-term evolution (LTE) signals, a novel deep-learning-based fingerprint positioning approach is proposed to solve the problem of outdoor positioning. Considering the outstanding performance of deep learning in image classification, LTE signal measurements are converted into location grayscale images to form a fingerprint database. In order to deal with the instability of LTE signals, prevent the gradient dispersion problem, and increase the robustness of the proposed deep neural network (DNN), the following methods are adopted: First, cross-entropy is used as the loss function of the DNN. Second, the learning rate of the proposed DNN is dynamically adjusted. Third, this paper adopted several data enhancement techniques. To find the best positioning fingerprint and method, three types of fingerprint and five positioning models are compared. Finally, by using a deep residual network (Resnet) and transfer learning, a hierarchical structure training method is proposed. The proposed Resnet is used to train with the united fingerprint image database to obtain a positioning model called a coarse localizer. By using the prior knowledge of the pretrained Resnet, feed-forward neural network (FFNN)-based transfer learning is used to train with the united fingerprint database to obtain a better positioning model, called a fine localizer. The experimental results convincingly show that the proposed DNN can automatically learn the location features of LTE signals and achieve satisfactory positioning accuracy in outdoor environments.