A probabilistic approach to event log completeness

Ayo, Femi Emmanuel; Folorunso, Olusegun; Ibharalu, F. T.

doi:10.1016/j.eswa.2017.03.039

Cited by 8 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For potential rule a 0 b, three indicators are used for evaluating its effects, i.e. degree of support Suppða; bÞ, degree of confidence Conf ða; bÞ and degree of lift Liftða; bÞ (Ayo et al, 2017). In the rule, a can be either a single activity or the set of multiple activities.…”

Section: Extracting Association Rules With Bayesian Networkmentioning

confidence: 99%

“…the lack of some process activities may increase the uncertainties of determining activities' relationships). Hence, the process discovery based on those process models is often not convincing (Huang and Kumar, 2012;Ayo et al, 2017). Under such as situation, some studies proposed heuristic miner (HM) based on traditional Alpha miner.…”

Section: Introductionmentioning

confidence: 99%

“…HM defines the association relationships between activities as association rules and only selects the BPMJ 28,4 rules with high frequencies for process discovery, which can greatly help reduce noisy data (Weijters and van der Aalst, 2003;Broucke and De Weerdt, 2017). Other studies identify and supplement the missing activities from the association rules using probabilistic methods, which helps improve the performance of HM in dealing with process incompleteness (Ayo et al, 2017). In addition, some studies proposed some refined methods to identify complex and abstract associations contained in process samples, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A cross-domain knowledge transfer method for process discovery of urban community services with small datasets

Liu

Qiao³

2022

BPMJ

View full text Add to dashboard Cite

PurposeProcess mining tools can help discover and improve the business processes of urban community services from historical service event records. However, for the community service domains with small datasets, the effects of process mining are generally limited due to process incompleteness and data noise. In this paper, a cross-domain knowledge transfer method is proposed to help service process discovery with small datasets by making use of rich knowledge in similar domains with large datasets.Design/methodology/approachFirst, ontology modeling is used to reduce the effects of cross-domain semantic ambiguity on knowledge transfer. Second, association rules (of the activities in the service processes) are extracted with Bayesian network. Third, applicable association rules are retrieved using an applicability assignment function. Further, the retrieved association rules in domains with large datasets are mapped to those with a small dataset using a linear programming method, with a heuristic miner being adopted to generate the process model.FindingsThe proposed method is verified based on the empirical data of 10 service domains from Beidaihe, China. Results show that process discovery performance of all 10 domains were improved with the overall robustness score, precision, recall and F1 score increased by 13%, 13%, 17% and 15%, respectively. For the domains with only small datasets, the cross-domain knowledge transfer method outperforms popular state-of-the art methods.Originality/valueThe limitations of sample sizes are greatly reduced. This scheme can be followed to establish business process management systems of community services with reasonable performance and limited sample sizes.

show abstract

Section: Extracting Association Rules With Bayesian Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A cross-domain knowledge transfer method for process discovery of urban community services with small datasets

Liu

Qiao³

2022

BPMJ

View full text Add to dashboard Cite

show abstract

“…The second group is focused on technical improvements for process mining, that is, notations, development of new approaches, algorithms, etc. [6,7,15,38,49,52,53,55]. The second group of studies utilized process mining as a tool in order to overcome the business management problems without handling technical details [17,28,32,33,35,37,44].…”

Section: An Overview Of Process Mining Applications In Different Areasmentioning

confidence: 99%

Process mining based approach to performance evaluation in computer‐aided examinations

Baykasoğlu

Özbel

Dudaklı

et al. 2018

Comp Applic In Engineering

View full text Add to dashboard Cite

A considerable part of educational systems tends to be online and computer oriented. However, online examination may create some difficulties during the evaluation of student performance. Process mining which arises as a new concept presents various powerful techniques for processing and analyzing different types of data by making use of some advanced information technologies. This paper proposes a novel approach based on process mining for evaluating the performance of students that should follow certain tasks on the computer. The proposed approach is composed of two main phases which are process mining and similarity analysis. Automatic assessment is performed totally in six steps in order to obtain students’ final grades. In addition, cheat control is possible in the last step thanks to the similarity analysis. A real‐life application in an Enterprise Resource Planning (ERP) course is performed in order to present usefulness, validity and practicality of the proposed approach. Furthermore, to evaluate the performance of the assessment system, we compared the assessment mechanism against instructor. A total of 15 students’ answers belonging to computer‐aided exam are assessed by instructor and the results showed a very good agreement between the automatic assessment system and instructor.

show abstract

“…A different approach is a process analysis focusing on the time needed to complete each task and, in relation to it, the time needed to complete the entire order [ 15 ]. Despite the possibility to perform computer simulations at the production start-up or during production, it remains a difficult task to prepare a model based on the actual process [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Selection and Optimization of the Parameters of the Robotized Packaging Process of One Type of Product

Borys

Kaczmarek

Laskowski

2020

Sensors

View full text Add to dashboard Cite

The article presents the results of computer simulations related to the selection and optimization of the parameters of robotic packing process of one type of product. Taking the required performance of the robotic production line as a basis, we proposed its configuration using the RobotStudio environment for offline robot programming and virtual controller technology. Next, a methodology for the validation of the adopted assumptions was developed, based on a wide range of input data and a precise representation of the applicable conditions in the packaging process of one type of product. This methodology included test scenarios repeated an appropriate number of times in order to obtain the result data with the desired reliability and repeatability. The main element of the research was a computer simulation of the station based on the Picking PowerPac package. It was assumed that the products on the technological line are generated pseudo-randomly, thus reflecting the real working conditions. The result of the conducted works is the optimal operating speed of industrial robots and conveyors. The developed methodology allows for multifaceted analyses of the key parameters of the technological process (e.g., the number of active robots and their load, speed of conveyors, and station efficiency). We paid special attention to the occurrence of anomalies, i.e., emergency situations in the form of “halting” the operation of chosen robots and their impact on the obtained quality of the industrial process. As a result of the simulations, numerical values were obtained, maximum efficiency, with regard to maximum overflow of items of 5%, for LB algorithm was equal to 1188 completed containers per hour, with conveyors speeds of 270 mm/s and 165 mm/s. This efficiency was possible at robot speeds R1 = 6450 mm/s, R2 = 7500 mm/s, R3 = 6500 mm/s, R4 = 6375 mm/s, R5 = 5500 mm/s, R6 = 7200 mm/s. The ATC algorithm reached efficiency of 1332 containers per hour with less than 5% overflown items, with conveyor speeds of 310 mm/s and 185 mm/s. This efficiency was possible at robot speeds R1 = 7500 mm/s, R2 = 7500 mm/s, R3 = 7200 mm/s, R4 = 7000 mm/s, R5 = 6450 mm/s, R6 = 6300 mm/s. Tests carried out for emergency situations showed that the LB algorithm does not allow for automatic continuation of the process, while the ATC algorithm assured production efficiency of 94% to 98% of the maximum station efficiency.

show abstract

A probabilistic approach to event log completeness

Cited by 8 publications

References 29 publications

A cross-domain knowledge transfer method for process discovery of urban community services with small datasets

A cross-domain knowledge transfer method for process discovery of urban community services with small datasets

Process mining based approach to performance evaluation in computer‐aided examinations

Selection and Optimization of the Parameters of the Robotized Packaging Process of One Type of Product

Contact Info

Product

Resources

About