Background - Smartphone-Based Human Activity Recognition - page 11

for obtaining activity information from the user bymeans of the analysis of their body
motion. In particular, through the use of the nowadays widely used smartphones.
The extraction of human activity information is only a small part of this large
process of developing AmI systems. Therefore, we aim to provide a technological
tool that can be employed as an input for applications in these two areas. This will
provide systems with opportunities for better decisionmaking not only to people with
limitations but also to any kind of people which need to improve their well-being,
health or comfort.
2.3 Sensing Activity
The right choice of sensors is one of the first elements to be taken into consideration
for the design of HAR systems. A number of sensors have already been explored
to extract activity-related information (Chen et al. 2012 ; Lara and Labrador 2012 ).
They measure several attributes including vital signs (e.g. heart rate, body tempera-
ture, blood pressure), environmental signals (e.g. light intensity, temperature, sound
levels), motion (e.g. acceleration, speed) and positioning (e.g. global and indoor
location).
Based on the sensor placement with respect to the user, the sensing mechanisms
are classified in: ambient , when sensors are in static locations of the environment and
wearable , when they are worn or attached to the user's body. These two categories
are detailed as follows. Besides, examples of sensors in these two categories are
depicted in Fig. 2.1 .
2.3.1 Ambient Sensors
Ambient sensors , also known as external or environmental sensors, are the collection
of devices found in the environment which measure physical properties regarding
Fig. 2.1 Examples of ambient and wearable devices