China Communications • October 2018
75
in which high-level features are the repre-
sentations of low-level features, the protocol
can be also regarded as composing of some
structural features. For bit-level, the protocol
is formed in the certain format, which consists
of pilot, transport format combination indica-
tor (TFCI), feedback information (FBI) and
transmit power control (TPC), et al. For sig-
nal-level, the radio signal is generated by the
radio interface technologies: coding, spreading
and modulation. From this point of view, the
protocol also can be regarded as a coalition of
a series of structured patterns, in signal-level.
Overall, the protocol can be described as a
series of structured features, both in signal-lev-
el and bit-level. Considering the advantages
on the characterization of structured features,
we introduce the deep learning algorithm, con-
volutional neural network, for the task of fea-
ture extraction. Here we mainly concern about
bit-level features.
1) Structure: Convolutional neural network
is a specialized kind of neural network for
processing data which has a known topology,
such as time-series data of 1D grid and image
marized as follows:
1) We propose a novel convolutional neural
network (CNN) based feature extractor to
extract the features from the traf c ow au-
tomatically.
2) We provide a support vector machine based
identi er to map the protocols into different
types.
3) We use real-world data of the most common
civil wireless communication system, WiFi
system, to evaluate the proposed method.
The results suggest that the proposed meth-
od outperforms the conventional protocol
identi cation methods.
The remainder of this paper is organized
as follows. Section II describes the scheme of
our method, which mainly consists of feature
extraction and protocol identi cation; Section
III shows the experimental results; Finally,
Section IV concludes the work.
PROTOCOL MODEL
The structure of our model is divided into two
parts: feature extraction and protocol classi-
cation. In our model, a deep learning based
method is developed for automatic feature ex-
traction, and a classification-based method is
used for identi cation. The framework of our
model is shown in Figure 1.
In order to demonstrate our method, the
used notations and their explanations are
shown in Table 1.
In wireless communication network, the way
for application identi cation is to identify and
determine the protocol type which used by the
application data. Among that, the quality of
selected features largely determines the result
of protocol identi cation. Thus, we rst intro-
duce our proposed feature extractor.
Considering the construction of data in
wireless communication system, the protocol
is rstly used to form the wireless radio frame
in some certain format, and then the frame
is used to generate the transmission signal.
Similar to the hierarchical structure of image,
Fig. 1. The framework of the proposed method, which consists of feature ex-
traction and protocol identi cation.
Table I. Notation and explanation.
Notation Explanation
S Dataset of protocols
N Number of protocol samples
L Length of protocol sample
x
i
Raw data of i-th protocol sample
y
i
Label of i-th protocol sample