Detection and Classification on Amateur Drones Based on Cepstrum of Radio Frequency Signal

As a prospective component of the future air transportation system,unmanned aerial vehicles(UAVs)have attracted enormous interest in both academia and industry.However,small UAVs are barely supervised in the current situation.Crash accidents or illegal airspace invading caused by these small drones affect public security negatively.To solve this security problem,we use the back-propagation neural network(BPNN),the support-vector machine(SVM),and the k-nearest neighbors(KNN)method to detect and classify the non-cooperative drones at the edge of the flight restriction zone based on the cepstrum of the radio frequency(RF)signal of the drone’s downlink.The signal from five various amateur drones and ambient wireless devices are sampled in an electromagnetic clean environment.The detection and classification algorithm based on the cepstrum properties is conducted.Results of the outdoor experiments suggest the proposed workflow and methods are sufficient to detect non-cooperative drones with an average accuracy of around 90%.The mainstream downlink protocols of amateur drones can be classified effectively as well.

Efficient and Effective 4D Trajectory Data Cleansing

As the rapid development of aviation industry and newly emerging crowd-sourcing projects such as Flightradar24 and FlightAware,large amount of air traffic data,particularly four-dimension(4D)trajectory data,have become available for the public.In order to guarantee the accuracy and reliability of results,data cleansing is the first step in analyzing 4D trajectory data,including error identification and mitigation.Data cleansing techniques for the 4D trajectory data are investigated.Back propagation(BP)neural network algorithm is applied to repair errors.Newton interpolation method is used to obtain even-spaced trajectory samples over a uniform distribution of each flight’s 4D trajectory data.Furthermore,a new method is proposed to compress data while maintaining the intrinsic characteristics of the trajectories.Density-based spatial clustering of applications with noise(DBSCAN)is applied to identify remaining outliers of sample points.Experiments are performed on a data set of one-day 4D trajectory data over Europe.The results show that the proposed method can achieve more efficient and effective results than the existing approaches.The work contributes to the first step of data preprocessing and lays foundation for further downstream 4D trajectory analysis.