Coupled Hidden Markov Model for Process Mining of Invisible Prime Tasks

Abstract

Process mining provides process improvement in a variety of application domains. A primary focus of process mining is transferring information from event logs into process model. One of the issues of process mining is dealing with invisible prime tasks. An invisible prime task is an additional task in the process model to assist in showing real processes. However, a few of algorithm solves the issue. This research proposes an algorithm for dealing with invisible prime tasks. The proposed algorithm contains rules and equations utilizing probability of state transition of Coupled Hidden Markov and double time-stamped in event logs. The rules and equations are used for determining invisible prime tasks and parallel control-flows patterns. In addition to dealing with invisible prime tasks, the experiment results also show that the proposed algorithm obtains right parallel control-flow patterns from non-complete event logs. This proposed algorithm also decreases usage of the invisible prime task in A# algorithm without reducing the quality of discovered process models. It has proven with the fitness of process models obtained by the proposed algorithm are relatively high as those obtained by A# algorithm.

Modified Alpha++ Algorithm for Discovering the Hybrid of Non-Free Choice and Invisible Task of Business Processes

“…That information can be used to build an improved system. The techniques of process mining are helpful to analysing the information since they collect information about the actual events in accordance with the event log of an organization [12].…”

“…Most activities in a business process are run in sequence. Thereafter, some activities are run in a parallel way [12]. During activities execution, there are several occurring problems, which are invisible tasks and a hybrid of non-free choice and invisible tasks.…”

“…During activities execution, there are several occurring problems, which are invisible tasks and a hybrid of non-free choice and invisible tasks. The primary task of invisible prime tasks is the main task that does not appear in the activity log, but it is added to illustrate the process clearly [12]. A hybrid of non-free choice and invisible tasks is a condition that needs invisible tasks to detect a nonfree choice relationship.…”

Graph-Based Algorithms for Discovering a Process Model Containing Invisible Tasks

“…One reason for adding invisible tasks is accommodating Split and Join relations in parallel processes. There are several algorithms that handle invisible tasks, such as Alpha# [9], Alpha$ [10], Coupled Hidden Markov Model-Nonfree Choice Invisible Task (CHMM-NCIT) [2] and Coupled Hidden Markov Model-Invisible Task (CHMM-IT) [5].…”

“…Those checking processes prolongs the processing time of Alpha#. Furthermore, both of Coupled Hidden Markov Model-Nonfree Choice Invisible Task (CHMM-NCIT) [2] and Coupled Hidden Markov Model-Invisible Task (CHMM-IT) [5] use Coupled Hidden Markov Model (CHMM) and utilize Baum-Welch algorithm to determine the weights of variables of CHMM. However, those algorithm check sequences of the event log and both of hidden variables and observed variables, so the time complexities of CHMM-NCIT and CHMM-IT are high.…”