Efficient Mining of Recurrent Rules
from a Sequence Database
David Lo
Siau-Cheng Khoo
Chao Liu
DASFAA 2008
1
Outline
 Introduction
 Preliminaries
 Generation of Recurrent Rules
 Algorithm
 Performance Evaluation
 Conclusion
2
Introduction
 Mining for knowledge from data has been shown useful for
many purposes ranging from finance, advertising, bioinformatics and recently software engineering.
“Whenever a series of precedent events occurs,
eventually another series of consequent events occurs”
3
Introduction
1. Resource Locking Protocol: Whenever a lock is acquired,
eventually it is released.
2. Internet Banking: Whenever a connection to a bank server is
made and an authentication is completed and money transfer
command is issued, eventually money is transferred and a
receipt is displayed.
3. Network Protocol: Whenever an HDLC connection is made
and an acknowledgement is received, eventually a
disconnection message is sent and an acknowledgement is
received.
4
Preliminaries
 Linear-time Temporal Logic (LTL)
‘G’ specifies that globally at every point in time a certain property
holds.
‘F’ specifies that a property holds either at that point in time or
finally (eventually) it holds.
‘X’ specifies that a property holds at the next event.
5
Preliminaries
6
Preliminaries
 Checking/Verifying LTL Expressions.
(main, lock) → (unlock, end)
(main, lock, use) → (unlock, end)
7
Generation of Recurrent Rules
Concepts and Definitions
8
Generation of Recurrent Rules
Concepts and Definitions
9
Generation of Recurrent Rules
Concepts and Definitions
10
Generation of Recurrent Rules
Concepts and Definitions
11
Generation of Recurrent Rules
Concepts and Definitions
12
Generation of Recurrent Rules
Concepts and Definitions
s-support:2
i-support:2
confidence:1
13
Generation of Recurrent Rules
Concepts and Definitions
14
Generation of Recurrent Rules
Concepts and Definitions
s-support:2
i-support:2
confidence:1
15
Generation of Recurrent Rules
Apriori Properties and Non-redundancy
16
Generation of Recurrent Rules
Apriori Properties and Non-redundancy
17
Generation of Recurrent Rules
Apriori Properties and Non-redundancy
18
Algorithm
19
Performance Evaluation
20
Conclusion
21