Advanced theory of signal detection. Weak signal detection in generalized observations. (Q1869933)

This book contains a number of interesting problems with signal detection theory. A generalized observation model for signal detection problems is presented. The model includes several interesting and common special cases such as those describing additive noise, multiplicative noise, and signal-dependent noise. This model can also describe composite signals in addition to the usual known signals and random signals. Locally optimum and locally optimum rank detectors for known and random signals in the model are discussed. Other approaches to detection of signals also are discussed. There are eight chapters in this book and problems are provided in the end of each chapter. Chapter 1 gives the preliminaries, where locally optimum detection, observation models, repara\-metrization of the generalized observation model, noise probability density functions, and rank statistics and score functions are described. Chapters 2--4 contain the application of statistical hypothesis testing to the problem of weak signal detection in a generalized observation model, where known signal cases are discussed in Chapter 2, random signal cases are studied in Chapter 3, and composite signal cases are investigated in Chapter 4. Asymptotic and finite sample-size performance characteristics of several detectors including the locally optimum detectors are considered for comparison. Chapters 5--6 deal with locally optimum rank detectors, where known signal cases are discussed in Chapter 5, and random signal cases are studied in Chapter 6. The locally optimum rank detectors are nonparametric signal detectors based on the sign and rank statistics of the observations. Detection of signals in weakly-dependent noise and a good approximation of high speed sampling communication systems are analyzed in Chapter 7, where the noise process is assumed to be dependent to a certain degree. The combination of fuzzy set theory and signal detection theory is considered in Chapter 8, where interesting results on the locally optimum fuzzy detection of known and random signals are included. Exercises are provided in the end of each chapter. This book is useful for practicing engineers and researchers as well as academics and students. It is more useful to those who have completed an introductory course on signal detection and have some background in mathematical statistics and random processes. Readers might also use this book as a handbook of locally optimum detection.