A Dynamic multi-sensor data fusion approach based on evidence theory and WOWA operator

Chaotic Mapping-Based Anti-Sorting Radio Frequency Stealth Signals and Compressed Sensing-Based Echo Signal Processing Technology

Radio frequency (RF) stealth anti-sorting technology can improve the battlefield survival rate of radar and is one of the research hotspots in the radar field. In this study, the signal design principle of anti-sequential difference histogram (SDIF) sorting was explored for the main sorting algorithm of the SDIF. Furthermore, we designed a piecewise linear chaotic system with interval number parameterization based on random disturbance and proposed a method to modulate the repetition period of widely spaced signal pulses using a chaotic system. Then, considering the difficulty of the traditional signal processing method to measure the velocity of the highly random anti-sorting signals designed in this paper, we used compressed sensing (CS) technology to process the echoes of the signals to solve the velocity and distance of the detection targets. Finally, simulation verification was performed from the correctness of the signal design principle, the performance of the chaotic system, the anti-sorting performance of the designed signals and the recovery and reconstruction performance of the signals by CS. The results show that: (a) the signal design principle presented in this paper can guide the signal design correctly; (b) the performance of the piecewise linear chaotic system with interval number parameterization is better than that of the classical one-dimensional chaotic system; (c) the anti-sorting signal modulated by the chaotic system can achieve anti-SDIF sorting, and the anti-sorting signals designed in this paper can be processed to obtain the velocity and distance of the targets.

Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains

Multi-sensor fusion intends to boost the general reliability of a decision-making procedure or allow one sensor to compensate for others’ shortcomings. This field has been so prominent that authors have proposed many different fusion approaches, or “architectures” as we call them when they are structurally different, so it is now challenging to prescribe which one is better for a specific collection of sensors and a particular application environment, other than by trial and error. We propose an approach capable of predicting the best fusion architecture (from predefined options) for a given dataset. This method involves the construction of a meta-dataset where statistical characteristics from the original dataset are extracted. One challenge is that each dataset has a different number of variables (columns). Previous work took the principal component analysis’s first k components to make the meta-dataset columns coherent and trained machine learning classifiers to predict the best fusion architecture. In this paper, we take a new route to build the meta-dataset. We use the Sequential Forward Floating Selection algorithm and a T transform to reduce the features and match them to a given number, respectively. Our findings indicate that our proposed method could improve the accuracy in predicting the best sensor fusion architecture for multiple domains.