1.
ABSTRACT
:
With the advent of ubiquitous
computing, we can easily collect large scale trajectory data, say, from moving
vehicles. This project studies pattern matching problems for trajectory data
over road networks, which complements existing efforts focusing on (a) a
spatio-temporal window query for location-based service or (b) Euclidean space
with no restriction. In contrast, we first identify some desirable properties
for pattern matching queries to the road network trajectories. As the existing
work does not fully satisfy these properties, we develop (1) trajectory
representation and (2) distance metric that satisfy all the desirable
properties we identified. Based on this representation and metric, we develop
efficient algorithms for three types of pattern matching queries– whole, sub
pattern, and reverse sub pattern matching. We analytically validate the
correctness of our algorithms and also empirically validate their scalability
over large-scale, real-life and synthetic trajectory data sets.
2.EXISTING SYSTEM :
The existing efforts focus on efficiently evaluating the spatio-temporal query, such as supporting range
and K nearest neighbor (KNN) queries, from the given query point, for
location-based services . Many index structures are surveyed for efficient
query processing on the spatio-temporal database.
3. PROPOSED SYSTEM :
The three pattern
matching queries (whole, sub pattern, and reverse sub pattern matching) to
search for similar trajectories to the given
query trajectory. Though
the notion of similarity
varies
across different types of queries, we proposed a unified framework efficiently
supporting range and KNN
queries for all three types
of matching based on M-tree and pruning rules. We validated the quality of
results by visualizing the results for different types of queries over
real-life road network trajectories.
R1: Road network. As we assume that the
moving object moves only along the road, the moving object should not be
located off the road, and such off road
locations should not affect
measuring the distance between trajectories.
R2: Spatial proximity. The distance measure
between trajectories should reflect the spatial proximity from the viewpoint of
the road network. For instance, the proximity between B and C shares more road segments than A and C, which has to be reflected to the
distance measure.
R3: Sampling rate / speed
invariant. Due to the difference in sampling rates or speeds, two objects
moving along the same route could be represented by two different trajectories
. Even when the two objects have the same sampling rates and move along the
same route, if the sampling is not synchronized,
their trajectories can
still differ . The distance measure should not be affected by when or how often
the locations are sampled.
R4: Robust to noise. Due to measurement errors
or communication failures, trajectories may contain noises. If a distance
measure is sensitive to noise, it cannot reflect the similarity between B and C, and may report A is closer to C. To avoid the problem, the distance
measure should be robust to noise, in order to identify an unusual movement as
noise and eliminate it in similarity computation.
R5: Metric. In general, it is desirable
for distance measures to be metric, because irrelevant
objects can be pruned out with no false dismissal leveraging existing index structures.
4.HARDWARE REQUIREMENTS:
•
System :
Pentium IV 2.4 GHz.
•
Hard Disk :
40 GB.
•
Floppy Drive : 1.44 MB.
•
Monitor :
15 VGA Colour.
•
Mouse :
Logitech.
•
Ram :
256 MB.
5.SOFTWARE REQUIREMENTS:
•
Operating
System : - Windows XP Professional.
•
Front
End :
- Asp .Net 2.0.
•
Coding
Language : - Visual C# .Net.
No comments:
Post a Comment