Hierarchical classification of dynamically varying radar pulse repetition interval modulation patterns.

Tampere University of Technology, Department of Signal Processing, Tampere, Finland.
Neural networks: the official journal of the International Neural Network Society (Impact Factor: 1.88). 12/2010; 23(10):1226-37. DOI: 10.1016/j.neunet.2010.06.008
Source: PubMed

ABSTRACT The central purpose of passive signal intercept receivers is to perform automatic categorization of unknown radar signals. Currently, there is an urgent need to develop intelligent classification algorithms for these devices due to emerging complexity of radar waveforms. Especially multifunction radars (MFRs) capable of performing several simultaneous tasks by utilizing complex, dynamically varying scheduled waveforms are a major challenge for automatic pattern classification systems. To assist recognition of complex radar emissions in modern intercept receivers, we have developed a novel method to recognize dynamically varying pulse repetition interval (PRI) modulation patterns emitted by MFRs. We use robust feature extraction and classifier design techniques to assist recognition in unpredictable real-world signal environments. We classify received pulse trains hierarchically which allows unambiguous detection of the subpatterns using a sliding window. Accuracy, robustness and reliability of the technique are demonstrated with extensive simulations using both static and dynamically varying PRI modulation patterns.

1 Bookmark
  • [Show abstract] [Hide abstract]
    ABSTRACT: Electronic warfare (EW) receivers are passive receivers which receive emissions from other platforms, and do certain analysis on these emissions. Some EW receivers receive radar pulses, measure the parameter of each pulse received and group the pulses that belongs to the same emitter together to determine the radar parameters for each emitter. These parameters are then compared with values stored for known radar types, to identify the emitter type. Two parts are focused, emitters deinterleaving and PRF-type identification. The deinterleaving is done through parameters clustering. Two parameters are selected for clustering direction of arrival and radio frequency. A self-organising neural network called Fuzzy ART is proposed for clustering. This algorithm has a very good clustering quality and can run in real-time applications.The PRF-type identification is done through time-of-arrival (TOA) analysis. Three previously presented algorithms are combined in new scheme to do the TOA analysis (or PRF-type identification). These algorithms are difference TOA histogram, TOA folding histogram and sequence search algorithm. The complete proposed system has been tested using three different tests. These tests are simple PRI test, jittered PRI test and staggered PRI test. The proposed system identifies up to 90 simple emitters, 20 jittered emitters and 20 staggered emitters. In all tests, the data were simulated and generated using software.
    IET Radar Sonar ? Navigation 11/2007; · 0.92 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The authors present an improved method for the deinterleaving of radar signals, based on a time of arrival analysis and the use of the sequential difference histogram (SDIF) for determining the pulse repetition interval (PRI). The optimal detection threshold in the SDIF histogram is derived, which greatly contributes to the efficiency of the algorithm. The algorithm is applied to classic, frequency-agile and staggered PRI radar signals. It is shown that the new method is very successful in high-pulse-density radar environments and for complex signal types. Special attention is given to an application of this method to the multiple-parameter deinterleaving algorithm
    Radar and Signal Processing, IEE Proceedings F 03/1992;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Radar signals are generally characterised by repetitive patterns in time. An electronic support measures (ESM) receiver must intercept and identify several interleaved radar signals. Time-of-arrival (TOA) deinterleaving is employed in ESM processing to identify and extract the pulses of each radar signal. This task is extremely processor intensive and new techniques are required to operate on complex signals in high pulse densities. A new algorithm employing novel techniques is presented for fast, accurate deinterleaving of several repetitive signals. A cumulative TOA difference histogram gives an indication of probable pulse repetition intervals (PRIs) with a minimum number of computations. Validation and identification is given by searching for a sequence of these pulse intervals. The technique presented is less sensitive to interfering pulses and more robust to missed pulses than conventional published techniques. Weighting is used to enhance detection of sequences and three-pulse priming sequence dramatically reduces unsuccessful searches. By employing a learning process, the efficiency is increased still further. The application of this algorithm to agile PRI signals is shown.
    Radar and Signal Processing, IEE Proceedings F 09/1989;


Available from
May 19, 2014