Mind the Gap: A SIG on Bridging the Gap in Research on Body Sensing, Body
Perception and Multisensory Feedback
SIG Meetings
/
Singh, Aneesha
/
Tajadura-Jimez, Ana
/
Bianchi-Berthouze, Nadia
/
Marquardt, Nic
/
Tentori, Monica
/
Bresin, Roberto
/
Kulic, Dana
Extended Abstracts of the ACM CHI'16 Conference on Human Factors in
Computing Systems
2016-05-07
v.2
p.1092-1095
© Copyright 2016 ACM
Summary: People's perceptions of their own body's appearance, capabilities and
position are constantly updated through sensory cues [10,14] that are naturally
produced by their actions. Increasingly cheap and ubiquitous sensing technology
is being used with multisensory feedback in multiple HCI areas of sports,
health, rehabilitation, psychology, neuroscience, arts and games to alter or
enhance sensory cues to achieve many ends such as enhanced body perception and
body awareness. However, the focus and aims differ between areas. Designing
more effective and efficient multisensory feedback requires an attempt to
bridge the gap between these worlds. This interactive SIG with minute madness
technology presentations, expert sessions, and multidisciplinary discussions
will: (i) bring together HCI researchers from different areas, (ii) discuss
tools, methods and frameworks, and (iii) form a multidisciplinary community to
build synergies for further collaboration.
Towards the detection of unusual temporal events during activities using
HMMs
Situation, Activity, and Goal Awareness (SAGAware 2012)
/
Khan, Shehroz S.
/
Karg, Michelle E.
/
Hoey, Jesse
/
Kulic, Dana
Proceedings of the 2012 International Conference on Ubiquitous Computing
2012-09-05
p.1075-1084
© Copyright 2012 ACM
Summary: Most of the systems for recognition of activities aim to identify a set of
normal human activities. Data is either recorded by computer vision or sensor
based networks. These systems may not work properly if an unusual event or
abnormal activity occurs, especially ones that have not been encountered in the
past. By definition, unusual events are mostly rare and unexpected, and
therefore very little or no data may be available for training. In this paper,
we focus on the challenging problem of detecting unusual temporal events in a
sensor network and present three Hidden Markov Models (HMM) based approaches to
tackle this problem. The first approach models each normal activity separately
as an HMM and the second approach models all the normal activities together as
one common HMM. If the likelihood is lower than a threshold, an unusual event
is identified. The third approach models all normal activities together in one
HMM and approximates an HMM for the the unusual events. All the methods train
HMM models on data of the usual events and do not require training data from
the unusual events. We perform our experiments on a Locomotion Analysis dataset
that contains gyroscope, force sensor, and accelerometer readings. To test the
performance of our approaches, we generate five types of unusual events that
represent random activity, extremely unusual events, unusual events similar to
specific normal activities, no or little motion and normal activity followed by
no or little motion. Our experiments suggest that for a moderately sized time
frame window, these approaches can identify all the five types of unusual
events with high confidence.
