State of the Art - Smartphone-Based Human Activity Recognition - page 38

3.2.2 Sensing and Data Collection
The definition of the experimental set up for data acquisition is also an important
aspect in HAR. Depending on how the subject is observed in its habitat with or with-
out any manipulation by the observer. Naturalistic environments are ideal for exper-
imentation but in many cases it is not feasible to exploit them. Therefore, controlled
experiments can be carried out in laboratory conditions aiming to simulate natural
settings ( semi-naturalistic environments ). Otherwise, fully controlled environments
are the last resource for data acquisition although the performance of the developed
method/system with this approach is uncertain until verified in real situations.
Failures in the design of HAR systems can be due to the lack of real life con-
siderations such as unaccounted activities or target users, noise, sensor calibration
and positioning, etc. This latter is for instance highly linked to the system perfor-
mance as presented in Atallah et al. ( 2010 ); Maurer et al. ( 2006 ) where different
sensor locations were evaluated for determining the ideal positions for performing
HAR through the use of wearable accelerometers. Another final consideration about
the experimentation process is the number of individuals selected as generally larger
number of people involving various age groups and physical conditions are preferred.
This is also directly related with the performance and generalization capability of
the system in the presence of new users.
3.2.3 Feature Selection and Extraction
In an ML problem, feature selection refers to the process of selecting a significant
set of features to largely impact the discrimination ability of a learning algorithm.
Feature extraction , on the other hand, is an approach to diminish the dimensionality
of an available set of features by performing inter-feature transformations in order to
obtain a new dimensionally reduced representation without largely sacrificing rele-
vant information from the original set. The curse of dimensionality , which describes
the difficulty in understanding and dealing with high-dimensional data, is certainly
linked with these two reduction mechanisms as they can alleviate the problems that
may arise when working in high-dimensional spaces.
Feature selection and extraction also allows to reduce the training times and
increase the generalization performance in ML problems. They, however, differ on
that the interpretability of models in which feature selection is employed is much
clearer. In this case, features are distinct between each other and not merged such as
in feature-extraction-based approaches.
Depending on the application, the features required for the extraction of relevant
information may vary. In the particular case of HAR, a reduced representation of the
sensor data can be used as the input of a recognition algorithm. This is attained by
estimating various measures from the sensor signals in different domains (e.g. in time
and frequency). Nonetheless, other time-frequency function representations such as