Mining Object Movement Patterns from Trajectory Data
-
Upload
nhathai-phan -
Category
Data & Analytics
-
view
141 -
download
0
Transcript of Mining Object Movement Patterns from Trajectory Data
![Page 1: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/1.jpg)
MINING OBJECT MOVEMENT PATTERNS
FROM TRAJECTORY DATA
Phan Nhat Hai
4th October, 2013
Supervisors Dr. Dino Ienco, Pr. Pascal Poncelet, Dr. Maguelonne Teisseire
![Page 2: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/2.jpg)
BACKGROUND AND MOTIVATION
Nowadays, many electronic devices are used for real world applications GPS, sensor networks, mobile phone, …
« interesting » patterns for: movement pattern analysis, animal behavior, route
planning and vehicle control, location prediction, …
2
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 3: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/3.jpg)
SOME EXAMPLES
3
Route Planning
Animal migration analysis
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
The world’s largest traffic jam in history (China)
![Page 4: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/4.jpg)
SPATIO-TEMPORAL DATA (ST)
Represented as a list of points, located in space and time T=(x1,y1, t1), …, (xn, yn, tn) position in space at time ti
was (xi, yi)
4
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 5: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/5.jpg)
MINING SPATIO-TEMPORAL PATTERNS FROM TRAJECTORY DATA (1)
Frequent Patterns:Frequent followed paths:
Group pattern [6], Tralus [7], …
5
Region (Cluster)[6] Y. Wang et. al. Data Knowl. Eng., June 2006.[7] J. G. Lee et. al. In ACM SIGMOD ’07.
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
o1
o2o3 o4
![Page 6: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/6.jpg)
[1] Z.Li et. al. PVLDB 10.[2] P. Kalnis et. al. SSTD’05.[3] J. Gudmundsson et. al. ACM GIS’06.[4] H. Jeung et. al. VLDB 08.[5] F. Verhein. SDM’09.
MINING SPATIO-TEMPORAL PATTERNS FROM TRAJECTORY DATA (2)
Clustering:Group together similar trajectoriesFor each group produce a summary
Flock [3], convoy [4], moving cluster [2], swarm & closed swarm [1], k-Star [5]
6
Region (Cluster)
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
o1
o2
o3o4
![Page 7: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/7.jpg)
SWARM – CLOSED SWARM [1]
Swarm - groups of objects (O, T ): At least objects move together timestamps
Closed Swarm Swarm which cannot be enlarged
Algorithm ObjectGrowth
7
[1] Z.Li et. al. Swarm: mining relaxed temporal moving object clusters. PVLDB 2010.
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 8: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/8.jpg)
CONVOY [4]
Convoy - groups of objects (O, T ): At least objects move together consecutive timestamps
Algorithm CuTS*
8
[4] H. Jeung et. al. Discovery of convoys in trajectory databases. PVLDB 2008.
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 9: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/9.jpg)
MOTIVATIONS (1)
Motivations: Complexity? Are they enough? Informative patterns?
9
dataInformative patterns
extract
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 10: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/10.jpg)
MOTIVATIONS (2)
Proposed solution
data
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
Unifying
10
![Page 11: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/11.jpg)
OUTLINE
Background and Motivations
Unifying Framework
Gradual Trajectory
Mining Representative Movement Patterns
Conclusions and Perspectives
11
![Page 12: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/12.jpg)
CLUSTER MATRIX
Objects: transactions Clusters: items
12
diaper
beer
diaperbeer
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 13: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/13.jpg)
FREQUENT CLOSED ITEMSET FROM CLUSTER MATRIX
13
Frequent Itemset
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 14: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/14.jpg)
THE MAIN INTUITION (FOLLOWING…)
We are now able to extract itemsets corresponding to a set of clusters occurring over time
Not movement patterns yet!
What about properties on Itemsets?
14
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 15: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/15.jpg)
SWARM
15
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 16: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/16.jpg)
PROPERTIES
In the same way it is possible to define properties for: Swarm, Closed Swarm, Convoy, Moving Cluster, Periodic Pattern, …
We are now able to extract different movement patterns!
16
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 17: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/17.jpg)
THE MAIN PROCESS (GET_MOVE)
17
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 18: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/18.jpg)
INCREMENTAL GET_MOVE
18
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 19: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/19.jpg)
THE MAIN PROCESS
19
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 20: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/20.jpg)
CMC CuTS* ObjectGrowth Vg-Growth Incremental GeT_Move
Convoys X X X
Closed Swarms X X
Group Patterns X X
Moving Cluster X
EXPERIMENTAL RESULTS
Datasets:
Competitive algorithms:
#objects #timestamps
Swainsoni 43 4,425
Buffalo 165 3,000
Synthetic* 500 10,000
Synthetic 2 50,000 10,000
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
* http://iapg.jade-hs.de/personen/brinkhoff/generator/
20
![Page 21: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/21.jpg)
SWAINSONI
21
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 22: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/22.jpg)
UNIFYING FRAMEWORK – CONCLUSIONS
GeT_Move: a unifying movement pattern mining approach
Properties adapted to specific movement patterns Proofs of properties Theorem providing that all the patterns are found
Incremental GeT_Move A new approach for identifying the size of blocks
Fully nested block partition
22
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 23: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/23.jpg)
OUTLINE
Background and Motivations
Unifying Framework
Gradual Trajectory
Mining Representative Movement Patterns
Conclusions and Perspectives
23
![Page 24: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/24.jpg)
ONE OF CLOSED SWARMS …
24
o1
o2
o3
o4
o6
o5
c1 c2
c3
c4
c5
t1 t2 t3 t4 t5 t6
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 25: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/25.jpg)
…GRADUAL TRAJECTORIES
25
o1
o2
o3
o4
o6
o5
c1 c2
c3
c4
c5
t1 t2 t3 t4 t5 t6
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 26: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/26.jpg)
26
A CONCRETE EXAMPLE
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 27: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/27.jpg)
PATTERN DEFINITION
The objects still remain in the next cluster The number of objects is equal-increasing (resp. equal-
decreasing) At least a number of certain timestamps
non-consecutive
27
- Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
27
![Page 28: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/28.jpg)
28
TIME RELAXED GRADUAL TRAJECTORIES
Timestamps can be: non-consecutive within a sliding time window
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
o1
o2
o3
o4
c1c2
t1 t2 t3 ………… t999 t1000
A
F
Sliding window
Too far away
![Page 29: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/29.jpg)
29
EXPERIMENTAL RESULTS
Synthetic data: 500 objects - 10,000 timestamps Reasonable scalability Low complexity
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 30: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/30.jpg)
30
GRADUAL TRAJECTORY - CONCLUSIONS
New kinds of trajectories: gradual trajectory
ClusterGrowth: an efficient algorithm to extract all gradual trajectories
Fuzzy closed swarm
Too many extracted patterns: DiCompoGP algorithm to directly extract the top-k gradual
trajectories
Convergent Divergent
![Page 31: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/31.jpg)
OUTLINE
Background and Motivations
Unifying Framework
Gradual Trajectory
Mining Representative Movement Patterns
Conclusions and Perspectives
31
![Page 32: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/32.jpg)
32
Methodology A set of movement patterns (closed swarms, convoys,
gradual trajectories, etc.) Employ MDL (Minimum Description Length) schema to
select the most informative and less redundant pattern set
Compo Algorithm Rank and select the most representative patterns Allow different types of pattern in the final results Characterize data by the selected patterns
CONTRIBUTIONS
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 33: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/33.jpg)
33
MOTIVATIONS
data
Patterns
1) One kind of patterns is not enough to describe the data!
2) Overlapping!
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 34: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/34.jpg)
34
PROBLEM STATEMENT
Given a spatio-temporal DB Odb and a set of patterns F (extracted from Odb)
Discover the optimal dictionary P (subset of F) compresses the data best w.r.t. the given encoding schema
L(p): number of bits to encode the pattern p + extra bit to encode the type of pattern
L(Odb|P): number of bits to encode the dataset Odb given P
MDL approach: LP(Odb) = L(P) + L(Odb|P)
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 35: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/35.jpg)
ENCODING EXAMPLE (I)
35
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 36: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/36.jpg)
36
ENCODING EXAMPLE (II)
L(ODB|P) = 4 + 6 + 2 + 1 + 1 = 14 L(P) = 4 + 5 + 3 + 4 = 16LP(ODB) = 30
L(ODB|P) = 4 + 5 + 2 + 1 + 1 = 13L(P) = 4 + 5 = 9LP(ODB) = 22
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 37: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/37.jpg)
37
NAÏVE COMPO VS SMART COMPO
We design two different approaches:
Naive Compo (baseline) Work in a greedy way Given the actual P, for each candidate p’ recompress the data
with P U p’ Select the p’ that obtain the best performance
Smart Compo Compute the gain incrementally Avoid to recompress the whole data Directly compute Gain(p’,P) = L(Odb|P) - L(Odb|P U p’) without
compute L(Odb|P U p’)
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 38: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/38.jpg)
38
EXPERIMENTAL RESULTS
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 39: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/39.jpg)
39
REPRESENTATIVE PATTERN - CONCLUSIONS
Propose an encoding scheme allowing multi-overlapping movement patterns
Propose two algorithms Naïve Compo (greedy approach) Smart Compo (compute gain incrementally)
Experimental results show that the top-k representative patterns are well adapted to the data
![Page 40: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/40.jpg)
OUTLINE
Background and Motivations
Unifying Framework
Gradual Trajectory
Mining Representative Movement Patterns
Conclusions and Perspectives
40
![Page 41: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/41.jpg)
41
OVERALL CONCLUSIONS (1)
Three step framework GeT_Move: a unifying movement pattern mining
approach Discovering novel patterns: Gradual trajectory + Fuzzy
closed swarm Mining representative movement patterns
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
data
![Page 42: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/42.jpg)
42
OVERALL CONCLUSIONS (2) DEMONSTRATION SYSTEM
Link: http://www.lirmm.fr/~phan/multimove.jsp
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 43: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/43.jpg)
43
OVERALL CONCLUSIONS (3) – OTHER APPLICATIONS
Mining trajectories on genes
Mining trajectories on tweets
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 44: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/44.jpg)
44
PERSPECTIVES (1)
Streaming GeT_Move Mining representative movement patterns from streaming
trajectory data
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 45: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/45.jpg)
45
PERSPECTIVES (2)
Trajectory mining on remote sensing, spatial information on satellite image processing
![Page 46: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/46.jpg)
46
EXTRA WORK Mining multi-relational gradual patterns (with Prof. Donato
Malerba) Kendal’s tau Gradual support
Communication graph summarization (with Dr. Francesco Bonchi)
-Background and Motivations - Unifying Framework - Gradual Trajectory - Mining Representative Movement Patterns - Conclusions & Perspectives
![Page 47: Mining Object Movement Patterns from Trajectory Data](https://reader038.fdocuments.us/reader038/viewer/2022110318/55d26a5ebb61eb91268b4636/html5/thumbnails/47.jpg)
47
PUBLICATIONS[1] P. N. Hai, D. Ienco, P. Poncelet, M. Teisseire. "Mining Representative Movement Patterns
through Compression". PAKDD 2013.
[2] A.Z.E. Aabidine, A. Sallaberry, S. Bringay, M. Fabregue, C. Lecellier, P. N. Hai, P. Poncelet. “Co2Vis: A Visual Analytics Tool for Mining Co-expressed And Co-regulated Genes Implied in HIV Infections”. IEEE BioVis 2013.
[3] P. N. Hai, D. Ienco, P. Poncelet, M. Teisseire. "Mining Fuzzy Moving Object Clusters". ADMA 2012.
[4] P. N. Hai, D. Ienco, P. Poncelet, M. Teisseire. "Mining Time Relaxed Gradual Moving Object Clusters". ACM GIS 2012.
[5] F. Bouillot, P. N. Hai, N. Béchet, S. Bringay, D. Ienco, S. Matwin, P. Poncelet, M. Roche, and M. Teisseire. "How to Extract Relevant Knowledge from Tweets?". ISIP 2012.
[6] P. N. Hai, P. Poncelet, M. Teisseire. "GET_MOVE: An Efficient and Unifying Spatio-Temporal Pattern Mining Algorithm for Moving Objects". IDA 2012.
[7] P. N. Hai, P. Poncelet, M. Teisseire. "An Efficient Spatio-Temporal Mining Approach to Really Know Who Travels with Whom!". BDA 2012. (selected as Best papers)
[8] P. N. Hai, D. Ienco, P. Poncelet, M. Teisseire. "Extracting Trajectories through an Efficient and Unifying Spatio-Temporal Patten Mining System". ECML-PKDD 2012.
[9] P. N. Hai, P. Poncelet, M. Teisseire. "MovingObjects: Combining Gradual Rules and Spatio-Temporal Patterns". IEEE ICSDM 2011.
[10] P. N. Hai, P. Poncelet, M. Teisseire. "An Efficient Spatio-Temporal Mining Approach to Really Know Who Travels with Whom!". ISI special issue, selected papers from BDA’12, 2013, to appear.