Abstract |
Wireless access, use and traffic demand are on a fast rise. The number of mobile
devices
and their capabilities, accessing potentially multiple wireless network interfaces, also increase dramatically. Wireless networks often experience “periods of severe
impairments”, causing severe degradation to the performance of the service running
on
wireless devices and to the respective user experience. The impact of the network
performance on the quality of experience (QoE) for various services is not well
-
understood. Assessing the impact of different network and channel conditions on the user
e
xperience is important for improving the telecommunication services. The QoE for
various wireless services including VoIP, video streaming, and web browsing, has been in
the epicenter of recent networking activities. The majority of such efforts aim to
cha
racterize the user experience, analyzing various types of measurements often in an
aggregate manner.
This thesis proposes the MLQoE, a modular algorithm for user
-
centric
QoE prediction. The
MLQoE employs multiple machine learning (ML) algorithms, namely,
the Artificial Neural
Networks, Support Vector Regression machines, Decision Trees, and Gaussian Naive
Bayes classifiers, and tunes their hyper
-
parameters. It uses the Nested Cross Validation
(nested CV) protocol for selecting the best classifier and the c
orresponding best hyper
-
parameter values and estimates the performance of the final model. The MLQoE is
modular, in that, it can be easily extended to include other ML algorithms. The MLQoE
selects the ML algorithm that exhibits the best performance and it
s parameters
automatically given the dataset used as input. It uses empirical measurements based on
network metrics (e.g., packet loss, delay, and packet interarrival) and subjective opinion
scores reported by actual users in the context of a service. This
thesis focuses on VoIP and
extensively evaluates the MLQoE using three unidirectional datasets containing VoIP calls
over wireless networks under various network conditions and feedback from subjects
(collected in field studies). The MLQoE has a very good
performance. For example, in our
experiments, a mean absolute error of less than 0.50 and median absolute error of less
than 0.30 (on the MOS scale) can be achieved.
|