Download presentation
Presentation is loading. Please wait.
1
/faculteit technologie management Genetic Process Mining Ana Karla Medeiros Ton Weijters Wil van der Aalst Eindhoven University of Technology Department of Information Systems a.k.medeiros@tm.tue.nl
2
/faculteit technologie management Outline Process Mining Genetic Algorithms Genetic Process Mining –Internal Representation –Fitness measure –Genetic Operators Experiments and Results Conclusion and Future Work
3
/faculteit technologie management Outline Process Mining Genetic Algorithms Genetic Process Mining –Internal Representation –Fitness measure –Genetic Operators Experiments and Results Conclusion and Future Work
4
/faculteit technologie management Process Mining X = apply for license A = classes motobike B = classes car C = theoretical exam D = practical motorbike exam E = practical car exam Y = get result
5
/faculteit technologie management Process Mining (cont.) Most of the current techniques cannot handle –Structural constructs: non-free choice, duplicate tasks and invisible tasks –Noisy logs –Reason: local approach
6
/faculteit technologie management Outline Process Mining Genetic Algorithms Genetic Process Mining –Internal Representation –Fitness measure –Genetic Operators Experiments and Results Conclusion and Future Work
7
/faculteit technologie management Genetic Algorithms –Global approach local optimum global optimum
8
/faculteit technologie management Outline Process Mining Genetic Algorithms Genetic Process Mining –Internal Representation –Fitness measure –Genetic Operators Experiments and Results Conclusion and Future Work
9
/faculteit technologie management Genetic Process Mining (GPM) Aim: Use genetic algorithm to tackle non-free choice, invisible tasks, duplicate tasks and noise. Internal Representation Fitness Measure Genetic Operators
10
/faculteit technologie management GPM – Build the Initial Population Causal Matrix Input XABCDEY Output X A B C D E Y
11
/faculteit technologie management GPM – Build the Initial Population Causal Matrix InputXABCDEY Output X 0 11 0000 A 000 11 00 B 000 1 0 1 0 C 0000 11 0 D 000000 1 E 000000 1 Y 0000000
12
/faculteit technologie management GPM – Build the Initial Population Causal Matrix Input XABCDEY Output X 0 11 0000 A \/ B A 000 11 00 C /\ D B 000 1 0 1 0 C /\ E C 0000 11 0 D \/ E D 000000 1 Y E 000000 1 Y Y 0000000 True
13
/faculteit technologie management GPM – Build the Initial Population Causal Matrix Input TrueXXA \/ BA /\ CB /\ CD \/ E XABCDEY Output X 0 11 0000 A \/ B A 000 11 00 C /\ D B 000 1 0 1 0 C /\ E C 0000 11 0 D \/ E D 000000 1 Y E 000000 1 Y Y 0000000 True
14
/faculteit technologie management GPM – Build the Initial Population Every individual has the same amount of tasks (1) Log (2) Set of tasks (3) Randomly created individuals
15
/faculteit technologie management GPM – Calculate Fitness Main idea –Benefit the individuals that can parse more frequent material in the log Challenges –How to assess an individual’s fitness? –How to punish individuals that allow for undesired extra behavior?
16
/faculteit technologie management Fitness - How to assess an individual’s fitness? - Use continuous semantics parser and register problems L = log and CM = causal matrix
17
/faculteit technologie management Trace: X,A,C,D,Y For noise-free, fitness punishes: AND-join OR-joinOR-split AND-split AND-join OR-joinOR-split AND-split Original net Individual
18
/faculteit technologie management Trace: X,A,C,D,Y For noise-free, fitness punishes: AND-split OR-splitOR-join AND-join Original net Individual
19
/faculteit technologie management Fitness - How to assess an individual’s fitness?
20
/faculteit technologie management Fitness - How to punish individuals that allow for undesired extra behavior? Fitness = 1
21
/faculteit technologie management Fitness - How to punish individuals that allow for undesired extra behavior? - Count the amount of enabled tasks at every reachable marking
22
/faculteit technologie management GPM – Calculate Fitness where L = log and CM = causal matrix and CM[] = population
23
/faculteit technologie management GPM – Create next population Genetic operators –Crossover Recombines existing material in the population Crossover point = task Crossover probability Subsets are swapped –Mutation Introduce new material in the population Every task of a individual can be mutated Mutation probability
24
/faculteit technologie management GPM – Create next population Genetic operators - Crossover Parent 1Parent 2 Offspring 1Offspring 2
25
/faculteit technologie management Outline Process Mining Genetic Algorithms Genetic Process Mining –Internal Representation –Fitness measure –Genetic Operators Experiments and Results Conclusion and Future Work
26
/faculteit technologie management Experiments and Results Experiments –ProM framework Genetic Algorithm Plug-in http://www.processmining.org –Simulated data Results –The genetic algorihm found models that could parse all the traces in the log
27
/faculteit technologie management ProM framework – Genetic Algorithm Plug-in
28
/faculteit technologie management ProM framework – Genetic Algorithm Plug-in
29
/faculteit technologie management Outline Process Mining Genetic Algorithms Genetic Process Mining –Internal Representation –Fitness measure –Genetic Operators Experiments and Results Conclusion and Future Work
30
/faculteit technologie management Conclusion and Future Work Conclusion –Genetic algorithms can be used to mine process models Future Work –Tackle duplicate tasks How to detect the right level of abstraction? –Apply the genetic process mining to "real-life" logs How to deal with noise?
31
/faculteit technologie management http://www.processmining.org
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.