SIViP (2015) 9 (Suppl 1):S111–S120
DOI 10.1007/s11760-014-0666-z
ORIGINAL PAPER
Generalized compressive detection of stochastic signals using
Neyman–Pearson theorem
Ying-Gui Wang · Zheng Liu · Le Yang · Wen-Li Jiang
Received: 2 December 2013 / Revised: 7 June 2014 / Accepted: 26 June 2014 / Published online: 17 July 2014
© The Author(s) 2014. This article is published with open access at Springerlink.com
Abstract Compressive sensing (CS) enables reconstruct-
ing a sparse signal from fewer samples than those required
by the classic Nyquist sampling theorem. In general, CS sig-
nal recovery algorithms have high computational complexity.
However, several signal processing problems such as sig-
nal detection and classification can be tackled directly in the
compressive measurement domain. This makes recovering
the original signal from its compressive measurements not
necessary in these applications. We consider in this paper
detecting stochastic signals with known probability density
function from their compressive measurements. We refer to
it as the compressive detection problem to highlight that the
detection task can be achieved via directly exploring the com-
pressive measurements. The Neyman–Pearson (NP) theorem
is applied to derive the NP detectors for Gaussian and non-
Gaussian signals. Our work is more general over many exist-
ing literature in the sense that we do not require the ortho-
normality of the measurement matrix, and the compressive
detection problem for stochastic signals is generalized from
the case of Gaussian signals to the case of non-Gaussian
signals. Theoretical performance results of the proposed NP
detectors in terms of their detection probability and the false
Y. - G . Wa n g (
B
) · Z. Liu · W.-L. Ji ang
College of Electronic Science and Engineering, National
University of Defense Technology, Changsha 410073, Hunan,
People’s Republic of China
e-mail: wyinggui@gmail.com
Z. Liu
e-mail: liuzheng@nudt.edu.cn
W.-L. Jia ng
e-mail: jiangwenli@nudt.edu.cn
L. Yang
School of Internet of Things (IoT) Engineering, Jiangnan University,
Wuxi 214122, Jiangsu, People’s Republic of China
e-mail: le.yang.le@gmail.com
alarm rate averaged over the random measurement matrix are
established. They are verified via extensive computer simu-
lations.
Keywords Compressive detection · Stochastic signals ·
NP detector · False alarm rate · Detection probability
1 Introduction
Compressive sensing (CS) is an important innovation in the
field of signal processing. With CS, if the representation of a
signal in a particular linear basis is sparse, we can sample it
at a rate significantly smaller than that dictated by the classic
Nyquist sampling theorem. To ensure that the obtained com-
pressive measurements preserve sufficient information so
that signal reconstruction is feasible, the measurement matrix
needs to satisfy the well-known restricted isometry property
(RIP). Fortunately, measurement matrices whose elements
are independently drawn from the sub-Gaussian distribution
would meet this requirement with a high probability [1–6].
To reconstruct the original signal from its compres-
sive measurements, various algorithms were proposed in
literature. Roughly speaking, they belong to three differ-
ent categories, namely relaxation-based algorithms, pur-
suit algorithms, and Bayesian algorithms. Relaxation-based
algorithms use functions easier to tackle to approximate
the non-smooth and non-convex l
0
-norm employed in the
signal reconstruction-oriented optimization problem. The
relaxed problem is then solved via standard numerical tech-
niques. Well-known instances of relaxation-based algorithms
include the basis pursuit (BP) [7] and FOCUSS (focal under-
determined system solver) [8] that approximate the l
0
-norm
using the l
1
-norm and l
p
-norm with p < 1. Pursuit algo-
rithms search for a solution to the sparse signal recovery
problem by taking a sequence of greedy decisions on the
123