A Data Driven Agent Elicitation Pipeline for Prediction Models

John Bruntse Larsen; Andrea Burattin; Christopher John Davis; Rasmus Hjardem-Hansen; Jørgen Villadsen

doi:10.1007/978-3-030-37453-2_46

A Data Driven Agent Elicitation Pipeline for Prediction Models

John Bruntse Larsen, Andrea Burattin, Christopher John Davis, Rasmus Hjardem-Hansen, Jørgen Villadsen

Department of Applied Mathematics and Computer Science

University of South Florida

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

80 Downloads (Orbit)

Abstract

Agent-based simulation is a method for simulating complex systems by breaking them down into autonomous interacting agents. However, to create an agent-based simulation for a real-world environment it is necessary to carefully design the agents. In this paper we demonstrate the elicitation of simulation agents from real-world event logs using process mining methods. Collection and processing of event data from a hospital emergency room setting enabled real-world event logs to be synthesized from observational and digital data and used to identify and delineate simulation agents.

Original language	English
Title of host publication	Business Process Management Workshops
Editors	C. Di Francescomarino , R. Dijkman , U. Zdun
Publisher	Springer
Publication date	2020
Pages	570-582
ISBN (Print)	978-3-030-37452-5
DOIs	https://doi.org/10.1007/978-3-030-37453-2_46
Publication status	Published - 2020
Event	17th Int. Conference on Business Process Management - Vienna University of Economics and Business, Vienna, Austria Duration: 1 Sept 2019 → 6 Sept 2019 Conference number: 17

Conference

Conference	17th Int. Conference on Business Process Management
Number	17
Location	Vienna University of Economics and Business
Country/Territory	Austria
City	Vienna
Period	01/09/2019 → 06/09/2019

Series	Lecture Notes in Business Information Processing
Volume	362
ISSN	1865-1348

Keywords

Agent-based simulation
Process mining
Emergency Rooms

Access to Document

10.1007/978-3-030-37453-2_46

fulltextAccepted author manuscript, 529 KB

OpenUrl availability

Full text

Cite this

@inproceedings{d264e2c6a5e24359b10c2afa6946fc3b,

title = "A Data Driven Agent Elicitation Pipeline for Prediction Models",

abstract = "Agent-based simulation is a method for simulating complex systems by breaking them down into autonomous interacting agents. However, to create an agent-based simulation for a real-world environment it is necessary to carefully design the agents. In this paper we demonstrate the elicitation of simulation agents from real-world event logs using process mining methods. Collection and processing of event data from a hospital emergency room setting enabled real-world event logs to be synthesized from observational and digital data and used to identify and delineate simulation agents.",

keywords = "Agent-based simulation, Process mining, Emergency Rooms",

author = "Larsen, {John Bruntse} and Andrea Burattin and Davis, {Christopher John} and Rasmus Hjardem-Hansen and J{\o}rgen Villadsen",

year = "2020",

doi = "10.1007/978-3-030-37453-2_46",

language = "English",

isbn = "978-3-030-37452-5",

series = "Lecture Notes in Business Information Processing",

publisher = "Springer",

pages = "570--582",

editor = "{Di Francescomarino }, C. and {Dijkman }, R. and {Zdun }, U.",

booktitle = "Business Process Management Workshops",

note = "17th Int. Conference on Business Process Management<br/>, BPM 2019 ; Conference date: 01-09-2019 Through 06-09-2019",

}

Larsen, JB, Burattin, A, Davis, CJ, Hjardem-Hansen, R & Villadsen, J 2020, A Data Driven Agent Elicitation Pipeline for Prediction Models. in C Di Francescomarino , R Dijkman & U Zdun (eds), Business Process Management Workshops. Springer, Lecture Notes in Business Information Processing, vol. 362, pp. 570-582, 17th Int. Conference on Business Process Management
, Vienna, Austria, 01/09/2019. https://doi.org/10.1007/978-3-030-37453-2_46

A Data Driven Agent Elicitation Pipeline for Prediction Models. / Larsen, John Bruntse; Burattin, Andrea; Davis, Christopher John et al.
Business Process Management Workshops. ed. / C. Di Francescomarino ; R. Dijkman ; U. Zdun . Springer, 2020. p. 570-582 (Lecture Notes in Business Information Processing, Vol. 362).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A Data Driven Agent Elicitation Pipeline for Prediction Models

AU - Larsen, John Bruntse

AU - Burattin, Andrea

AU - Davis, Christopher John

AU - Hjardem-Hansen, Rasmus

AU - Villadsen, Jørgen

N1 - Conference code: 17

PY - 2020

Y1 - 2020

N2 - Agent-based simulation is a method for simulating complex systems by breaking them down into autonomous interacting agents. However, to create an agent-based simulation for a real-world environment it is necessary to carefully design the agents. In this paper we demonstrate the elicitation of simulation agents from real-world event logs using process mining methods. Collection and processing of event data from a hospital emergency room setting enabled real-world event logs to be synthesized from observational and digital data and used to identify and delineate simulation agents.

AB - Agent-based simulation is a method for simulating complex systems by breaking them down into autonomous interacting agents. However, to create an agent-based simulation for a real-world environment it is necessary to carefully design the agents. In this paper we demonstrate the elicitation of simulation agents from real-world event logs using process mining methods. Collection and processing of event data from a hospital emergency room setting enabled real-world event logs to be synthesized from observational and digital data and used to identify and delineate simulation agents.

KW - Agent-based simulation

KW - Process mining

KW - Emergency Rooms

U2 - 10.1007/978-3-030-37453-2_46

DO - 10.1007/978-3-030-37453-2_46

M3 - Article in proceedings

SN - 978-3-030-37452-5

T3 - Lecture Notes in Business Information Processing

SP - 570

EP - 582

BT - Business Process Management Workshops

A2 - Di Francescomarino , C.

A2 - Dijkman , R.

A2 - Zdun , U.

PB - Springer

T2 - 17th Int. Conference on Business Process Management<br/>

Y2 - 1 September 2019 through 6 September 2019

ER -

A Data Driven Agent Elicitation Pipeline for Prediction Models

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this