CSE-HMM-RFN: A Method for Multifunctional Radar Pulse Deinterleaving

• Published in: IEEE sensors journal Vol. 25; no. 18; pp. 34956 - 34970
• Main Authors: Fu, Yuxin, Wang, Jiantao, Huang, Jie, Dang, Tongxin, Xie, Min
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.09.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Compressed state encoding; computational complexity; Encoding; hidden Markov chains; Hidden Markov models; Intelligent sensors; Markov chains; Modulation; Modules; multifunctional radar (MFR); Object detection; pulse deinterleaving; Radar; Robustness; Sensors; Target tracking; Viterbi; Viterbi algorithm; Viterbi algorithm detectors
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2025.3594372

Despite available prior knowledge, existing pulse deinterleaving algorithms for multifunctional radars (MFRs) suffer from limited robustness and high computational complexity. To address these limitations, we propose the CSE-hidden Markov model (HMM)-residual fence network (RFN), a novel hybrid pulse deinterleaving framework. To begin with, a two-layer hierarchical hidden Markov model (HHMM) is developed that maps operational tasks to pulse groups based on MFR radiation mechanisms. Then, the temporal dynamics within and between pulse groups are characterized by their temporal intervals, enabling a decomposed deinterleaving strategy, that is, pulse group extraction followed by temporal combination search. Accordingly, CSE-HMM-RFN implements two core modules. Each module constructs HMMs where nonzero states indicate target pulses or pulse groups, and employs a Viterbi algorithm guided by RFN path weights to backtrack optimal state transition paths. Experimental results demonstrate that CSE-HMM-RFN achieves enhanced robustness and reduced computational resources compared to baseline algorithms.