THESIS
2014
xi, 97 pages : illustrations ; 30 cm
Abstract
Mobile crowdsourcing applications are becoming more and more prevalent in
recent years, as smartphones equipped with various built-in sensors are proliferating
rapidly. The large quantity of potential sensing data stimulates researchers
to probe into large-scale tasks that used to be costly or impossible, such as noise
pollution monitoring and traffic surveillance. Yet the efficient aggregation of the
crowdsourced data, which is of essential importance for such sensing tasks, has
not received sufficient attention. Specifically, we investigate the following crucial
challenges of data aggregation in this thesis: how to motivate normal users to
contribute sensing data and how to conduct robust inference from sensing data.
The low participation level of smartphone users due to vari...[
Read more ]
Mobile crowdsourcing applications are becoming more and more prevalent in
recent years, as smartphones equipped with various built-in sensors are proliferating
rapidly. The large quantity of potential sensing data stimulates researchers
to probe into large-scale tasks that used to be costly or impossible, such as noise
pollution monitoring and traffic surveillance. Yet the efficient aggregation of the
crowdsourced data, which is of essential importance for such sensing tasks, has
not received sufficient attention. Specifically, we investigate the following crucial
challenges of data aggregation in this thesis: how to motivate normal users to
contribute sensing data and how to conduct robust inference from sensing data.
The low participation level of smartphone users due to various resource consumptions,
such as time and power, remains a hurdle that prevents the enjoyment
brought by crowdsourcing applications. Recently, some researchers have done pioneer
works in motivating users to contribute their resources by designing incentive
mechanisms, which are able to provide certain rewards for participation. However,
none of these works considered smartphone users’ nature of opportunistically
occurring in the area of interest. Specifically, for a general smartphone sensing
application, the platform would distribute tasks to each user on her arrival and
has to make an immediate decision according to the user’s reply. To accommodate this general setting, we propose to design online incentive mechanisms based
on online reverse auction.
On the other hand, the low-quality crowdsourced data are prone to containing
outliers that may severely impair the mobile crowdsourcing applications. Thus in
this thesis, we conduct pioneer investigation considering crowdsourced data quality.
Specifically, we focus on estimating user motion trajectory information, which
plays an essential role in multiple crowdsourcing applications, such as indoor localization,
context recognition, indoor navigation, etc. We resort to the family
of robust statistics and design a robust trajectory estimation scheme, which is
capable of alleviating the negative influence of abnormal crowdsourced user trajectories,
differentiating normal users from abnormal users, and overcoming the
challenge brought by spatial imbalance of crowdsourced trajectories.
Most of mobile sensing applications, including crowd sensing applications,
rely on inference components heavily for detecting interesting activities or contexts.
Existing work implements inference components using traditional models
designed for balanced data sets, where the sizes of interesting (positive) and non-interesting
(negative) data are comparable. Practically, however, the positive
and negative sensing data are highly imbalanced. Therefore, we propose a new
inference framework SLIM based on several machine learning techniques in order
to accommodate the imbalanced nature of sensing data.
Theoretic properties of the designed methods are analyzed. Also, thorough
simulations and experiments are conducted to further verify the efficiency of these
methods in aggregating sensing data for mobile crowdsourcing applications.
Post a Comment