A Radar Emitter Recognition Mechanism Based on IFS-Tri-Training Classification Processing

Abstract

Radar Warning Receiver (RWR) is one of the basic pieces of combat equipment necessary for the electromagnetic situational awareness of aircraft in modern operations and requires good rapid performance and accuracy. This paper proposes a data processing flow for radar warning devices based on a hierarchical processing mechanism to address the issue of existing algorithms’ inability to balance real-time and accuracy. In the front-level information processing module, multi-attribute decision-making under intuitionistic fuzzy information (IFS) is used to process radar signals with certain prior knowledge to achieve rapid performance. In the post-level information processing module, an improved tri-training method is used to ensure accurate recognition of signals with low pre-level recognition accuracy. To improve the performance of tri-training in identifying radar emitters, the original algorithm is combined with the modified Hyperbolic Tangent Weight (MHTW) to address the problem of data imbalance in the radar identification problem. Simultaneously, cross entropy is employed to enhance the sample selection mechanism, allowing the algorithm to converge rapidly.

Enhanced PRIM recognition using PRI sound and deep learning techniques

“…The Classical ELM methodology encompasses the utilization of randomly selected input biases and weights in conjunction with an activation function that possesses infinite differentiability [64]. The output weight (O) is obtained by maximizing the least-squares value in Eq (5), and the solution can be derived as shown in Eq (6) [21,69]:…”

“…PRIMs play a pivotal role in signal processing and serve as a fundamental point of reference for discerning the origin of radiation inside such systems [ 2 ]. Furthermore, radar warning receivers (RWR) and jammers employ pulse repetition interval (PRI) characteristics [ 5 , 6 ].…”

A Knowledge Graph-Driven CNN for Radar Emitter Identification

“…// Take the average of all measured values as the final value : e = f (e) // Use formula (8) to map the value of edges in the graph to We performed experiments based on the five test problems in Table 3 to verify the performance of the proposed algorithm in different situations, and we used 1D-CNN without KG (as in Figure 7) as the baseline method for the comparison.…”

“…This method identifies the target radar by comparing the parameters of the target signal to the data in the database. In the second stage, the identification method based on the expert database is the most prevalent [6][7][8][9]. Compared with the parameter matching method, the radar experts combine historical reconnaissance information and expert knowledge to form the expert database.…”