The input data and their statistical characteristics are transformed into a multinomial vector and a set of multinomial parameters before designing an appropriate detection scheme. The Neyman-Pearson optimal detector and a likelihood ratio detector are derived and analyzed for the case where the multinomial parameters are available under the alternative and for the case where they are not. These detectors are simple, flexible and their performace can be quite good.
|Original language||English (US)|
|Number of pages||10|
|Journal||Proceedings - Annual Allerton Conference on Communication, Control, and Computing|
|State||Published - Jan 1 2017|
ASJC Scopus subject areas