Database Reference
In-Depth Information
immaturity of the research on mobile analysis, we will only introduce some recent
and representative analysis applications in this section.
With the growth of numbers of mobile users and the improved performance,
mobile phones are now useful for building and maintaining communities, such as
communities based on geographical locations and communities based on different
cultures and interests, e.g., the latest Wechat. Traditional network communities
or SNS communities are in short of online interaction among members, and the
communities are active only when members are sitting before computers. On
the contrary, mobile phones can support rich interaction any time and anywhere.
Wechat supports not only one-to-one communications, but also many-to-many
communication. Mobile communities are defined as that a group of individuals with
the same hobbies (i.e., health, safety, and entertainment, etc.) gather together on
networks, meet to make a common goal, decide measures through consultation
to achieve the goal, and start to implement their plan [
52
]. In [
53
], the authors
proposed a qualitative model of a mobile community. It is now widely believed
that mobile community applications will greatly promote the development of the
mobile industry.
RFID labels are used to identify, locate, track, and supervise physical objects
in a cost-effective manner. RFID is widely applied to inventory management and
logistics. However, RFID brings about many challenges to data analysis: (a) RFID
data is very noisy and redundant; (b) RFID data is instant and streaming data with a
huge volume and limited processing time. We can track objects and monitor system
status by deducing some original events through mining the semantics of RFID data,
including location, cluster, and time, etc. In addition, we may design the application
logic as complex events and then detect such complex events, so as to realize more
advanced business applications. In [
54
], the authors discussed a shoplifting case as
an advanced complex event.
Recently, the progress in wireless sensor, mobile communication technology,
and stream processing enable people to build a body area network to have real-
time monitoring of people's health. Generally, medical data from different sensors
has different characteristics, e.g., heterogeneous attribute sets, different time and
space relations, and different physiological relations, etc. In addition, such datasets
involve privacy and safety protection. In [
55
], Garg and others introduced a multi-
modal transport analysis mechanism of raw data for real-time monitoring of health.
Under the circumstance that only highly comprehensive characteristics related to
health are available, Park et al. in [
56
] examined approaches to better utilize such
comprehensive information to strength data at all levels. Comprehensive statistics
of some partitions is used to recognize clustering and input a characteristic value
with a more comprehensive degree. The input characteristics will be further used to
predict modeling so as to improve performance.
Researchers from Gjovik University College in Norway and Derawi Biometrics
united to develop an application for smart phones, which analyzes paces when
people walk and uses the paces for unlocking the safety system [
57
]. In the
meanwhile, Robert Delano and Brian Parise from Georgia Institute of Technology
developed an application called iTrem, which monitors human bodies' trembling
Search WWH ::
Custom Search