FPGA implementation of multi parameter deinterleaving

Electronic warfare (EW) is defined as military action involving the use of electromagnetic and directed energy to control the electromagnetic spectrum or to attack the enemy. One possible task of an EW system is to sort and classify received pulses from a dense environment of hostile radars so that the pulses can be processed. this process is known as pulse deinterleaving. The deinterleaving process needs to be completed with very low latency to support timely decision making required in modern EW environments. One method for deinterleaving streams of incoming radar pulses is incremental clustering. Clustering is the unsupervised partitioning of similar data samples into groups called clusters. The goal is to create clusters in which members of a particular cluster are as similar as possible to one another and as different as possible from members of other clusters. Many clustering algorithms require a complete data set to be present a priori and require multiple passes through the data in order to produce a result. Such algorithms are referred to as non-incremental. On the other hand an incremental clustering algorithm considers each input data point only once at which point it assigns it to a cluster. Such a technique allows streaming data such as radar pulse descriptor words (PDWs) to be clustered in real time.