Discover Process Models Research Articles

EVENT DATA VISUALIZATION THROUGH PROCESS MINING: A CASE FOR EMERGENCY MEDICAL SERVICE SYSTEM IN ADANA

Increasing amount of data enables researchers the opportunity of applying new scientific methods to manage and visualize the systems and processes. Process mining is an emerging tool for discovering real processes using event data of complex systems such as communication, information, health care systems, transportation and etc. Emergency Medical Service (EMS) system is an integral part of health care systems and aims to respond cases on time in order to decrease mortality. Although the EMS system process is assumed to be known, related data may indicate some deviations from the real process. Aim of this study is to discover and visualize EMS system in Adana city, in Turkey. EMS system event logs are filtered and visualized by using plug-ins in ProM platform such as Simple Heuristic Filtering plug-in and Log visualizer, respectively. Other plug-ins such as Fuzzy Miner and Inductive Miner are used for discovering process model. The deviations are obtained in EMS system process model showing irregular or rare events that cannot be representable throughout the process. The results indicate that the process of transportation between hospitals should be investigated in order to improve the process of Adana EMS system.

Application of a Genetic Algorithm for Finding Edit Distances between Process Models

Finding graph edit distances (determining the similarity of graph models) is an important task in various areas of computer science, such as image analysis, machine learning, and chemoinformatics. In recent years, due to the development of process mining techniques, it has become necessary to adapt the existing graph matching methods to be applied to the analysis of process models (annotated graphs) discovered from event logs of information systems. In particular, methods for finding the minimum graph edit distance can be used to reveal patterns (subprocesses) and to compare discovered process models. As was shown experimentally and theoretically substantiated, exact methods for finding the minimum edit distance between the discovered process models (and graphs in the general case) have a great time complexity and can be applied only to small-sized process models. In this paper, we estimate the accuracy and time performance characteristics of a genetic algorithm applied to find distances between process models discovered from the event logs. In particular, we find distances between BPMN (Business Process Model and Notation) models discovered from the event logs by using different synthesis algorithms. It is shown that the genetic algorithm proposed in the paper allows us to significantly reduce the computation time and produces results close to the optimal solutions (the minimum edit distances).

Discovering process models for the analysis of application failures under uncertainty of event logs

Computer applications, such as servers, databases and middleware, ubiquitously emit execution traces stored in log files. The use of logs for the analysis of application failures is known since the early days of computers. Field data studies have shown that application logs are fraught with uncertainty, i.e., missing or noisy events in the logs. A body of research that has dealt successfully with uncertainty in event logs is process mining from the business process management community, specifically by discovering process models. The literature has shown the value of process mining across several domains, but as yet there is no study that quantifies possible improvements from using process models, and the impact of uncertainty in the context of application failures. This work addresses the use of process mining for detecting failures from application logs. First, process models are discovered from logs; then conformance checking is used to detect deviations from the models. We contribute to knowledge engineering research with a systematic measurement study that quantifies the failure detection capability of conformance checking in spite of missing events, and its accuracy with respect to process models obtained from noisy logs. Analysis is done with a dataset of 55,462 execution traces from three independent real-life applications. We obtain a mixed answer depending on the application under test; our measurements provide insights into the use of process mining for failure analysis.

Model Checking Based Approach for Compliance Checking


 
 
 Process mining is the set of techniques to retrieve a process model starting from available logging data. The discovered process model has to be analyzed to verify it respects the defined properties, i.e., the so-called compliance checking. Our aim is to use a model checking based approach to verify compliance. First, we propose an integrated-tool approach using existing tools as ProM (a framework supporting process mining techniques) and CADP (a formal verification environment). More precisely, the execution traces from a software system are extracted. Then, using the “Mine Transition System” plugin in ProM, we obtain a labelled transition system, that can be easily used to verify formal properties trough CADP. However, this choice presents the “state explosion” problem, i.e., models discovered through the classical process mining techniques tend to be large and complex. In order to solve this problem, another custom-made approach is shown, which accomplishes a pre- processing on the traces to obtain abstract traces, where abstraction is based on the set of temporal logic formulae specifying the system properties. Then, from the set of abstracted traces, we discover a system described in Lotos, a process algebra specification language; in this way we do not build an operational model for the system, but we produce only a language description from which a model checking environment will automatically obtain the reduced corresponding transition system. Real systems have been used as case studies to evaluate the proposed methodologies.
 
 

Stage-based discovery of business process models from event logs

An automated process discovery technique generates a process model from an event log recording the execution of a business process. For it to be useful, the generated process model should be as simple as possible, while accurately capturing the behavior recorded in, and implied by, the event log. Most existing automated process discovery techniques generate flat process models. When confronted to large event logs, these approaches lead to overly complex or inaccurate process models. An alternative is to apply a divide-and-conquer approach by decomposing the process into stages and discovering one model per stage. It turns out, however, that existing divide-and-conquer process discovery approaches often produce less accurate models than flat discovery techniques, when applied to real-life event logs. This article proposes an automated method to identify business process stages from an event log and an automated technique to discover process models based on a given stage-based process decomposition. An experimental evaluation shows that: (i) relative to existing automated process decomposition methods in the field of process mining, the proposed method leads to stage-based decompositions that are closer to decompositions derived by human experts; and (ii) the proposed stage-based process discovery technique outperforms existing flat and divide-and-conquer discovery techniques with respect to well-accepted measures of accuracy and achieves comparable results in terms of model complexity.

Getting There: Evidence-Based Decision-Making in Road Trauma Prehospital Transport and Care in Queensland

Introduction:Process mining, a branch of data science, aims at deriving an understanding of process behaviors from data collected during executions of the process. In this study, we apply process mining techniques to examine retrieval and transport of road trauma patients in Queensland. Specifically, we use multiple datasets collected from ground and air ambulance, emergency department, and hospital admissions to investigate the various patient pathways and transport modalities from accident to definitive care.Aim:The project aims to answer the question, “Are we providing the right level of care to patients?” We focus on (i) automatically discovering, from historical records, the different care and transport processes, and (ii) identifying and quantifying factors influencing deviance from standard processes, e.g. mechanisms of injury and geospatial (crash and trauma facility) considerations.Methods:We adapted the Cross-Industry Standard Process for Data Mining methodology to Queensland Ambulance Service, Retrieval Services Queensland (aero-medical), and Queensland Health (emergency department and hospital admissions) data. Data linkage and “case” definition emerged as particular challenges. We developed detailed data models, conduct a data quality assessment, and preliminary process mining analyses.Results:Preliminary results only with full results are presented at the conference. A collection of process models, which revealed multiple transport pathways, were automatically discovered from pilot data. Conformance checking showed some variations from expected processing. Systematic analysis of data quality allowed us to distinguish between systemic and occasional quality issues, and anticipate and explain certain observable features in process mining analyses. Results will be validated with domain experts to ensure insights are accurate and actionable.Discussion:Preliminary analysis unearthed challenging data quality issues that impact the use of historical retrieval data for secondary analysis. The automatically discovered process models will facilitate comparison of actual behavior with existing guidelines.

Decomposed and parallel process discovery: A framework and application

Abstract The rapid growth of event data motivates the developing of decomposed and parallel process discovery, which solves process discovery from a large event log by decomposing the log into multiple small event logs, discovering process models from these small logs in parallel, and merging discovered process models. As such, process discovery from a large event log can be solved in less time. Currently, the passage and maximal decomposition based techniques are successful in the activity partition by decomposing causal graph structure derived from a large event log. In this paper, we propose a five-step framework, based on which we can build various decomposed and parallel process discovery techniques by simply combining and adapting existing techniques. Then, we propose a technique, RPSTHD, based on the framework using the refined process structure tree (RPST), heuristic miner, process mining using integer linear programming (ILP), etc. An experimental evaluation shows that our technique significantly outperforms the state-of-the-art decomposed discovery techniques in both efficiency and effectiveness.

A Distributed Discovery of Communicating Resource Systems Models

In communicating resource systems (CRS), a set of independent, hierarchically composed resources communicate to realize a business process. Examples of CRSs include RESTful Web services, cloud computing platforms and hierarchical distributed systems. Unfortunately, their complexity, distributed nature, and usually long lifespan can lead to problems like livelocks, deadlock occurrences and invocation loops. This makes CRSs hard to maintain and manage; it also leads to a loss of QoS or system failures. Moreover, it is important to take into account, in system management, the exact way how the system gets to some desired or undesired state. Therefore, it is crucial to analyze processes, executed in a system to find and fix the above problems. Unfortunately, CRS process models are hardly ever available. Therefore, we present a new distributed algorithm, dRMA, discovering process models from CRS event logs. In order to reduce the representational bias between the discovered process model and the real process, we have defined a Communication Net, which can express features of CRSs: directed communication channels, hierarchy, and a resource perspective. Finally, we have evaluated dRMA on a cluster, and have showed that distributing jobs can significantly reduce the time of process model discovery.

Application of Genetic Algorithms for Finding Edit Distance between Process Models

Finding graph-edit distance (graph similarity) is an important task in many computer science areas, such as image analysis, machine learning, chemicalinformatics. Recently, with the development of process mining techniques, it became important to adapt and apply existing graph analysis methods to examine process models (annotated graphs) discovered from event data. In particular, finding graph-edit distance techniques can be used to reveal patterns (subprocesses), compare discovered process models. As it was shown experimentally and theoretically justified, exact methods for finding graph-edit distances between discovered process models (and graphs in general) are computationally expensive and can be applied to small models only. In this paper, we present and assess accuracy and performance characteristics of an inexact genetic algorithm applied to find distances between process models discovered from event logs. In particular, we find distances between BPMN (Business Process Model and Notation) models discovered from event logs by using different process discovery algorithms. We show that the genetic algorithm allows us to dramatically reduce the time of comparison and produces results which are close to the optimal solutions (minimal graph edit distances calculated by the exact search algorithm).

Predictive Monitoring of Business Processes: A Survey

Nowadays, process mining is becoming a growing area of interest in business process management (BPM). Process mining consists in the extraction of information from the event logs of a business process. From this information, we can discover process models, monitor and improve our processes. One of the applications of process mining, is the predictive monitoring of business process. The aim of these techniques is the prediction of quantifiable metrics of a running process instance with the generation of predictive models. The most representative approaches for the runtime prediction of business process are summarized in this paper. The different types of computational predictive methods, such as statistical techniques or machine learning approaches, and certain aspects as the type of predicted values and quality evaluation metrics, have been considered for the categorization of these methods. This paper also includes a summary of the basic concepts, as well as a global overview of the process predictive monitoring area, that can be used to support future efforts of researchers and practitioners in this research field.

Discovering high-level BPMN process models from event data

PurposeThe purpose of this paper is to demonstrate that process mining techniques can help to discover process models from event logs, using conventional high-level process modeling languages, such as Business Process Model and Notation (BPMN), leveraging their representational bias.Design/methodology/approachThe integrated discovery approach presented in this work is aimed to mine: control, data and resource perspectives within one process diagram, and, if possible, construct a hierarchy of subprocesses improving the model readability. The proposed approach is defined as a sequence of steps, performed to discover a model, containing various perspectives and presenting a holistic view of a process. This approach was implemented within an open-source process mining framework called ProM and proved its applicability for the analysis of real-life event logs.FindingsThis paper shows that the proposed integrated approach can be applied to real-life event logs of information systems from different domains. The multi-perspective process diagrams obtained within the approach are of good quality and better than models discovered using a technique that does not consider hierarchy. Moreover, due to the decomposition methods applied, the proposed approach can deal with large event logs, which cannot be handled by methods that do not use decomposition.Originality/valueThe paper consolidates various process mining techniques, which were never integrated before and presents a novel approach for the discovery of multi-perspective hierarchical BPMN models. This approach bridges the gap between well-known process mining techniques and a wide range of BPMN-complaint tools.

ICMA: a new efficient algorithm for process model discovery

Nowadays, Business processes in organizations are supported by information systems. These systems record organizational processes outputs in the form of event logs, which contain valuable information about processes and their performance. Process mining extract knowledge from event logs. One of the most important tasks in process mining is process model discovery that uses an algorithm to build a process model from a given event log. In this research, a new model which named ICMA proposed for discovering process models. This model has three steps, pre-processing phase, body of model and post-processing phase. Imperialist Competitive Algorithm (ICA) was used for the first time as body of proposed model. Nine hundred nineteen event logs were used, those are balanced event logs, unbalanced event logs, and real-life event logs. Moreover, those event logs were studied at the 0%, 1%, 5%, 10% and 20% noise levels and the results have compared to the recent Vazquise algorithm. The research findings revealed that precision and completeness of our model is better than Vazquez model. In this paper has been shown that the ICMA model compared to the other approaches in literature method drastically improved the precision and completeness of the model. In addition, the noise problem was satisfactorily solved through data pre-processing and post-processing operations.

Guided Process Discovery – A pattern-based approach

Process mining techniques analyze processes based on events stored in event logs. Yet, low-level events recorded by information systems may not directly match high-level activities that make sense to process stakeholders. This results in discovered process models that cannot be easily understood. To prevent such situations from happening, low-level events need to be translated into high-level activities that are recognizable by stakeholders. This paper proposes the Guided Process Discovery method (GPD). Low-level events are grouped based on behavioral activity patterns, which capture domain knowledge on the relation between high-level activities and low-level events. Events in the resulting abstracted event log correspond to instantiations of high-level activities. We validate process models discovered on the abstracted event log by checking conformance between the low-level event log and an expanded model in which the high-level activities are replaced by activity patterns. The method was tested using two real-life event logs. We show that the process models discovered with the GPD method are more comprehensible and can be used to answer process questions, whereas process models discovered using standard process discovery techniques do not provide the insights needed.

Analysis of production planning in a global manufacturing company with process mining

PurposeThe purpose of this paper is to present the result of using process mining to model the production planning (PP) process of a manufacturing company that is supported by enterprise resource planning (ERP) systems.Design/methodology/approachThis paper uses event logs obtained from the case company’s ERP database. The steps for this research are planning process mining implementation, extraction and construction of event log, discovering process model with Heuristic Miner and analysis.FindingsProcess model obtained from process mining shows how the PP is actually conducted. It shows the loop in materials requirement planning and create plan order process. Furthermore, the occurrences of changing plan order date and production line indicate the schedule instability in the case company. Further analysis of the material management (MM) event log shows the implication of production plan changes on MM. Continuous change in the plan affects material allocation priority and may result in a mismatch between production needs and the materials available.Research limitations/implicationsThe study is only conducted in a single and specific case. Therefore, even though the findings provide good insight, the use of solitary case study does not imply a general result applied to other cases. Hence, there is a need to conduct similar studies on various cases so that a more generic conclusion can be drawn.Practical implicationsThe result provides insights into how the current company’s policy of adjusting the production plan to accommodate changing demand impacts their operation. It can help the company to consider a better balance between flexibility and efficiency to improve their process.Originality/valueThe paper demonstrates the use of process mining to capture the real progression of PP based on the data stored in the company’s ERP database, which give an insight into how a real company conducts their PP process, the implication of schedule instability on MM and production. The novelty of this research lies in the use of process mining to attest to the schedule nervousness issue at a process level.

Learning From the Past: Uncovering Design Process Models Using an Enriched Process Mining

Design documents and design project footprints accumulated by corporate information technology systems have increasingly become valuable sources of evidence for design information and knowledge management. Identification and extraction of such embedded information and knowledge into a clear and usable format will greatly accelerate continuous learning from past design efforts for competitive product innovation and efficient design process management in future design projects. Most of the existing design information extraction systems focus on either organizing design documents for efficient retrieval or extracting relevant product information for product optimization. Different from traditional systems, this paper proposes a methodology of learning and extracting useful knowledge using past design project documents from design process perspective based on process mining techniques. Particularly different from conventional techniques that deal with timestamps or event logs only, a new process mining approach that is able to directly process textual data is proposed at the first stage of the proposed methodology. The outcome is a hierarchical process model that reveals the actual design process hidden behind a large amount of design documents and enables the connection of various design information from different perspectives. At the second stage, the discovered process model is analyzed to extract multifaceted knowledge patterns by applying a number of statistical analysis methods. The outcomes range from task dependency study from workflow analysis, identification of irregular task execution from performance analysis, cooperation pattern discovery from social net analysis to evaluation of personal contribution based on role analysis. Relying on the knowledge patterns extracted, lessons and best practices can be uncovered which offer great support to decision makers in managing any future design initiatives. The proposed methodology was tested using an email dataset from a university-hosted multiyear multidisciplinary design project.

Semantic fuzzy mining: Enhancement of process models and event logs analysis from syntactic to conceptual level

Semantic-based process mining is a useful technique towards improving information values of process models and analysis by means of conceptualization. The conceptual system of analysis allows the meaning of process elements to be enhanced through the use of property characteristics and classificati on of discoverable entities, to generate inference knowledge that can be used to determine useful patterns and predict future outcomes. The work in this paper presents a Semantic-Fuzzy mining approach that makes use of labels within event log about real-time process to provide a method which allows for mining and improved process analysis of the resulting process models through semantic – annotation, representation and reasoning. Qualitatively, the study shows by using a case study of Learning Process – how data from various process domains can be extracted, semantically prepared, and transformed into mining executable formats to support the discovery, monitoring and enhancement of real-time domain processes through further semantic analysis of the discovered models. Also, the paper quantitatively assess the level of accuracy of the classification results to predict behaviours of unobserved instances within the process knowledge-base by determing which traces are fitting or not fitting the discovered model by using a training set and test log for the cross-validation experiment. Accordingly, the work looks at the sophistication of the proposed semantic-based approach and the discovered models, validation of the classification results and their influence compared to other existing benchmark techniques and algorithms for process mining. The experimental results and data validation ends with the supposition that a system which is formally encoded with semantic labelling (annotation), semantic representation (ontology) and semantic reasoning (reasoner) has the capability to lift process mining analysis and outcomes from the syntactic level to a much more conceptual level, resulting in a mining approach that is able to induce new knowledge based on previously unobserved behaviours and a more intuitive and easy way to envisage the relationships between the process instances found within the available event data logs and the discovered process models.

Hierarchy Process Mining from Multi-Source Logs

Nowadays, large-scale business processes is growing rapidly; in this regards process mining is required to discover and enhance business processes in different departments of an organization. A process mining algorithm can generally discover the process model of an organization without considering the detailed process models of the departments, and the relationship among departments. The exchange of messages among departments can produce asynchronous activities among department process models. The event logs from departments can be considered as multi-source logs, which cause difficulties in mining the process model. Discovering process models from multi-source logs is still in the state of the art, therefore this paper proposes a hierarchy high-to-low process mining approach to discover the process model from a complex multi-source and heterogeneous event logs collected from distributed departments. The proposed method involves three steps; i.e. firstly a high level process model is developed; secondly a separate low level process model is discovered from multi-source logs; finally the Petri net refinement operation is used to integrate the discovered process models. The refinement operation replaced the abctract transitions of a high level process model with the corresponding low level process models. Multi-source event logs from several departments of a yarn manufacturing were used in the computational study, and the results showed that the proposed method combined with the modified time-based heuristics miner could discover a correct parallel process business model containing XOR, AND, and OR relations.

Discovering workflow nets using integer linear programming

Process mining is concerned with the analysis, understanding and improvement of business processes. Process discovery, i.e. discovering a process model based on an event log, is considered the most challenging process mining task. State-of-the-art process discovery algorithms only discover local control flow patterns and are unable to discover complex, non-local patterns. Region theory based techniques, i.e. an established class of process discovery techniques, do allow for discovering such patterns. However, applying region theory directly results in complex, overfitting models, which is less desirable. Moreover, region theory does not cope with guarantees provided by state-of-the-art process discovery algorithms, both w.r.t. structural and behavioural properties of the discovered process models. In this paper we present an ILP-based process discovery approach, based on region theory, that guarantees to discover relaxed sound workflow nets. Moreover, we devise a filtering algorithm, based on the internal working of the ILP-formulation, that is able to cope with the presence of infrequent, exceptional behaviour. We have extensively evaluated the technique using different event logs with different levels of exceptional behaviour. Our experiments show that the presented approach allows us to leverage the inherent shortcomings of existing region-based approaches. The techniques presented are implemented and readily available in the HybridILPMiner package in the open-source process mining tool-kits ProM (http://promtools.org) and RapidProM (http://rapidprom.org).

Discovering Process Model from Event Logs by Considering Overlapping Rules

Process Mining is a technique to automatically discover and analyze business processes from event logs. Discovering concurrent activities often uses process mining since there are many of them contained in business processes. Since researchers and practitioners are giving attention to the process discovery (one of process mining techniques), then the best result of the discovered process models is a must. Nowadays, using process execution data in the past, process models with rules underlying decisions in processes can be enriched, called decision mining. Rules defined over process data specify choices between multiple activities. One out of multiple activities is allowed to be executed in existing decision mining methods or it is known as mutually-exclusive rules. Not only mutually-exclusive rules, but also fully deterministic because all factors which influence decisions are recorded. However, because of non-determinism or incomplete information, there are some cases that are overlapping in process model. Moreover, the rules which are generated from existing method are not suitable with the recorded data. In this paper, a discovery technique for process model with data by considering the overlapping rules from event logs is presented. Discovering overlapping rules uses decision tree learning techniques, which fit the recorded data better than the existing method. Process model discovery from event logs is generated using Modified Time-Based Heuristics Miner Algorithm. Last, online book store management process model is presented in High-level BPMN Process Model.

A Combination of the Evolutionary Tree Miner and Simulated Annealing

In recent years, process mining is important to discover process model from event logs; however the existing methods have not achieved good in overall fitness. In this context, this paper proposes a combination of the Evolutionary Tree Miner (ETM) and Simulated Annealing (SA). The ETM aims to reduce randomness of population so that it can improved the quality of individuals. SA aims to increase overall fitness in the population. The results of the proposed method which was compared to other approaches show that the proposes method had better in overall fitness and better quality of individuals.