Conclusions - Smartphone-Based Human Activity Recognition - page 126

￿

We presented a multiclass linear SVM algorithm (MC-L1-L2-SVM) to be applied
in smartphone-based HAR. Its advantages against non-linear approaches include
its faster prediction ability, memory-reduced learnedmodel, and distinctive embed-
ded mechanism of performing feature selection that discards irrelevant or noisy
features during the training process (Table 6.7 ) . Themethod also allows to trade-off
dimensionality reduction against classification accuracy. Moreover, we provided
along with this algorithm a novel and flexible training approach (EX-SMO) that
only requires any of the widely known QP solvers available such as SMO for its
implementation.

8.2 Future Work

There is still room for improvement in our work which can be addressed from two
different perspectives: (i) by solving current limitations of our proposed systems, and
(ii) by extending our achievements through complementary and novel applications.
In the first case, some issues have arisen such as the limited number of activities the
system can deal with, the fixed smartphone position on the waist, and the adoption
of novel approaches to deal users with distinct differences in their motion patterns
(e.g. people with walking difficulties) into the system. On the second case, new
ideas about how to exploit HAR information in order to provide new services can
be explored. These include the development of context-aware apps for health and
sports monitoring, elderly care and understanding interaction between users using
similar systems. In this section we focus on some of these aspects and propose them
as future research directions:

￿ For a new user, the performance of the proposed HAR system can be improved if

his motion data is integrated into the learned model. Although this can be done,
for instance, through retraining after following a controlled sequence of activities,
this process can be tedious for the user. But considering that during a normal day
it is possible to gather large amounts of data, we can explore semi-supervised
learning strategies which can allow to combine this unlabeled data with already
existing labeled trained data in order to produce considerable improvements in
the system learning accuracy. This can bring advantages to new users, specially
those with particular conditions such as very slow motion or physical disabilities
which are normally difficult to incorporate in the training and the ML algorithm
generalization capability is not sufficient to include them.

￿ The proposed HAR systems are specific to be used with waist-mounted smart-

phones. Although this position allows some degree of variability, it is important to
explore if it is also possible to place the device in different body parts such as shirt
or pants pockets and even worn around the arms (e.g. with armbands for running).
In the first case some problems may arise due to the free and continuous motion of
the devices with respect to the body position which can be hard to control (e.g. for
distinguishing between standing and sitting activities). Moreover, now that its is