conflict of elsart, lineno and amsmath

Hi people!

I would like to use lineno with elsevier class elsart. However, amsmath
makes some conflicts, namely the line number does not appear in all
lines. Please compile the code below with and without the line

Thans for some help,


RESULT OF \listfiles

*File List*
elsart.cls 2006/05/01, 2.19: Elsevier
latexsym.sty 1998/08/17 v2.2e Standard LaTeX package (lasy symbols)
ulasy.fd 1998/08/17 v2.2e LaTeX symbol font definitions
amsmath.sty 2000/07/18 v2.13 AMS math features
amstext.sty 2000/06/29 v2.01
amsgen.sty 1999/11/30 v2.0
amsbsy.sty 1999/11/29 v1.2d
amsopn.sty 1999/12/14 v2.01 operator names
lineno.sty 2005/01/10 line numbers on paragraphs v4.1c



In the following we will briefly discuss nonspecificity for finite
sets and for convex subsets of $R^d$. For details the
reader is referred to XXX.

\subsection{Nonspecificity for finite sets}
Consider the following problem: given a finite set $E$ of balls,
which contains a black ball, while the rest are white, we would like
to measure the amount of information $H$ required to find the
black ball. Suppose that the set of balls $E$ has $m \times n$
elements. If this set is partitioned into $n$ sets of $m$ balls or
into $m$ sets of $n$ balls, the measure of nonspecificity $H$
characterizing all those sets will be
H(m \times n) = H(m) + H(n) \label{eq:ax1ns}

Also, note that the larger the set of balls $E$, the less specific
the predictions are, and in consequence
H(n) \leq H(n+1) \label{eq:ax2ns}
where $n := \|E\|$.

xxx proposed the formula
H(n) := \log_2 n
where $n := \|E\|$, and XXX showed that this is
the unique expression that satisfies equations \ref{eq:ax1ns}
and \ref{eq:ax2ns} up to the normalization $H(2)=1$.

This function is known in the literature as the \emph{Hartley
measure} of uncertainty, and it measures the lack of specificity
of a finite set.