Hi all,<br>The talk on Friday will be about:<b> Frequent Trajectory Mining on GPS Data</b><br><b>Abstract:</b><br>In this paper we propose a new algorithm for finding the<br>frequent routes that a user has in his daily routine, in our<br>
method we build a grid in which we map each of the GPS<br>data points that belong to a certain sequence . (We consider<br>that each sequence conforms a route) we then carry out an<br>interpolation procedure that has a probabilistic basis and<br>
find a more precise description of the user’s trajectory. For<br>each trajectory we find the edges that were crossed, with the<br>crossed edges we create a histogram in which the bins denote<br>the crossed edges and the frequency value the number of<br>
times that edge was crossed for a certain user. We then select<br>the K most frequent edges and combine them to create a list<br>of the most frequent paths that a user has. We compared our<br>results with the algorithm that was proposed in Adaptive<br>
learning of semantic locations and routes [6] to find frequent<br>routes of a user, and found that our implementation on the<br>contrary of [6] can discriminate directions, ie routes that<br>go from A to B and routes that go from B to A are taken<br>
as different. Furthermore our implementation also permits<br>the analysis of subsections of the routes,something that to<br>our knowledge had not been carried out in previous related<br>work.<br><br clear="all">Thanks & Cheers!<br clear="all">
<br>-- <br>Norma Saiph Savage<br>