FHWS/IPIN2018
Archived
4
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

added novel contributions to conclusion and described the generality of the approach

Browse Source
This commit is contained in:
toni
2018-10-18 14:50:50 +02:00
parent 96d7b92683
commit 322678b715
2 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tex_review/chapters/conclusion.tex
View File

@@ -1,15 +1,24 @@
\section{Conclusion}
\commentByToni{Wie wirkt sich das jetzt auf ein generelles Gebäude aus?}
%what you have seen
Within this work we provided an extensive overview of our smartphone-based indoor localization system.
Within this work we provided an extensive overview of our smartphone-based indoor localization system, \add{providing both, previous advances and novel contributions.}
The thorough evaluation demonstrated the good performance under multiple scenarios within a complex environment.
The system is able to handle problems like sample impoverishment and multimodal densities, occurring through the use of a particle filtering scheme.
The main advantage of our approach is its suitability for practical use.
\add{Based on the good results in this challenging scenario, we believe that our solution can be adapted to many other public buildings and environments, resulting in a very generally usable solution for self-localization of pedestrians using smartphones.
Previous versions of the system have already proven themselves in other, more modern buildings, which supports this claim to general use.}
%novel stuff
\add{Thanks to the novel contributions presented, we have been able to further increase the robustness and accuracy of the system.
To a large extent, this was achieved by using the navigation mesh.
It allows to map continuous movements and enables to reduce the map sizes to only a few megabytes for a complete building.
The problem of sample impoverishment can be addressed easily by incorporating the here presented method onto the state transition of the particle filter.
In combination with the threshold-based activity recognition, both methods further enhance the robustness.}
Given the improvements above and those achieved in previous works, the main advantage of our approach is its suitability for practical use.
Compared to other state-of-the-art solutions, the setup time is only a few hours and does not require any expert knowledge or hardware.
\add{The system should require as little manual effort as possible.
This is mainly achieved by the optimization scheme, providing all necessary parameters for the Wi-Fi model.}
The localization runs solely an a commercial smartphone, thus no connection to a server or the Wi-Fi infrastructure is required.
By using navigation meshes we are able to reduce the map sizes to only a few megabytes for a complete building.
Nevertheless, there is still room for further improvements and future work.
Through the change from a graph to a mesh, we lost the ability to easily find the shortest path for navigation purposes as described in \cite{Ebner-16}.

4
tex_review/chapters/experiments.tex
View File

@@ -478,8 +478,4 @@ It does not provide a smooth estimated path, since it depends more on an accurat
At the end, in the here shown examples we only searched for a global maxima, even though the KDE approach opens a wide range of other possibilities for finding a best estimate.
\add{A detailed examination of the runtime performance of the used estimation methods in comparison to the state-of-the-art can be found in \cite{Bullmann-18}.}
\commentByToni{Diskussion, wie die Contributions uns jetzt geholfen haben. Nochmal zusammengefasst.}