Dr. Julian Theis

Dr. Julian Theis

Uniting Process Mining and Deep Learning | PhD in Industrial Engineering and Operations Research from the University of Illinois Chicago

Talks and Workshops

Masking Neural Networks Using Reachability Graphs to Predict Process Events

December 20, 2021

Talk, 2021 International Conference on Cyber-physical Social Intelligence, Beijing, China

Decay Replay Mining is a deep learning method that utilizes process model notations to predict the next event. However, this method does not intertwine the neural network with the structure of the process model to its full extent. This paper proposes an approach to further interlock the process model of Decay Replay Mining with its neural network for next event prediction. The approach uses a masking layer which is initialized based on the reachability graph of the process model. Additionally, modifications to the neural network architecture are proposed to increase the predictive performance. Experimental results demonstrate the value of the approach and underscore the importance of discovering precise and generalized process models.

On the Performance Analysis of the Adversarial System Variant Approximation Method to Quantify Process Model Generalization

November 01, 2021

Talk, 6th International Workshop on Process Querying, Manipulation, and Intelligence held in conjunction with the 3rd International Conference on Process Mining, Eindhoven, Netherlands

Process mining algorithms discover a process model from an event log. The resulting process model is supposed to describe all possible event sequences of the underlying system. Generalization is a process model quality dimension of interest. A generalization metric should quantify the extent to which a process model represents the observed event sequences contained in the event log and the unobserved event sequences of the system. Most of the available metrics in the literature cannot properly quantify the generalization of a process model. A recently published method called Adversarial System Variant Approximation leverages Generative Adversarial Networks to approximate the underlying event sequence distribution of a system from an event log. While this method demonstrated performance gains over existing methods in measuring the generalization of process models, its experimental evaluations have been performed under ideal conditions. This paper experimentally investigates the performance of Adversarial System Variant Approximation under non-ideal conditions such as biased and limited event logs. Moreover, experiments are performed to investigate the originally proposed sampling hyperparameter value of the method on its performance to measure the generalization. The results confirm the need to raise awareness about the working conditions of the Adversarial System Variant Approximation method. The outcomes of this paper also serve to initiate future research directions.

Introduction to Entrepreneurship

October 15, 2019

Talk, Engineering Success Initiative of the University of Illinois at Chicago, Chicago, USA

Introduction to Entrepreneurship seminar at the University of Illinois at Chicago.

Process Mining of Programmable Logic Controllers: Input/Output Event Logs

August 23, 2019

Talk, 2019 IEEE 15th International Conference on Automation Science and Engineering, Vancouver, Canada

We present an approach to model an unknown Ladder Logic based Programmable Logic Controller (PLC) program consisting of Boolean logic and counters using Process Mining techniques. First, we tap the inputs and outputs of a PLC to create a data flow log. Second, we propose a method to translate the obtained data flow log to an event log suitable for Process Mining. In a third step, we propose a hybrid Petri net (PN) and neural network approach to approximate the logic of the actual underlying PLC program. We demonstrate the applicability of our proposed approach on a case study with three simulated scenarios.

Hands-On: Artificial Intelligence

July 18, 2019

Workshop, University of Illinois at Chicago Summer Bridge Program for NSF S-STEM Scholars, Chicago, Illinois

Introduction of basic Artificial Intelligence fundamentals with real world examples to 13 incoming freshmen engineering students as part of the Summer Bridge Program organized by the UIC College of Engineering. This workshop included three hands-on parts on building a machine learning classifier, training deep neural networks, and buidling a Generative Adversarial Network (GAN).

Behavioral Petri Net Mining and Automated Analysis for Human Computer Interaction Recommendations in Multi-Application Environments

June 20, 2019

Talk, 11th ACM SIGCHI Symposium on Engineering Interactive Computing Systems, Valencia, Spain

Process Mining is a famous technique which is frequently applied to Software Development Processes, while being neglected in Human-Computer Interaction (HCI) recommendation applications. Organizations usually train employees to interact with required IT systems. Often, employees, or users in general, develop their own strategies for solving repetitive tasks and processes. However, organizations find it hard to detect whether employees interact efficiently with IT systems or not. Hence, we have developed a method which detects inefficient behavior assuming that at least one optimal HCI strategy is known. This method provides recommendations to gradually adapt users’ behavior towards the optimal way of interaction considering satisfaction of users. Based on users’ behavior logs tracked by a Java application suitable for multi-application and multi-instance environments, we demonstrate the applicability for a specific task in a common Windows environment utilizing realistic simulated behaviors of users.

PyData Meetup - Process Mining

May 06, 2019

Talk, PyData Chicago, Chicago, Illinois

Process Mining describes a set of data-driven techniques to discover process models from event logs, to check conformance and monitor processes, and to enhance and improve models. During the last ten years, these techniques have developed into a mature research field with many use cases, resulting in a strong industry uptake. Its main applications can be found in business process management to create actionable insights leveraging existing data from IT systems. However, recent research shows a broader range of Process Mining applications such as in Software Engineering, Human-Computer Interaction, and control of manufacturing processes. In this presentation, Julian Theis will introduce the fundamentals of Process Mining based on real-world examples. He will also talk about recent research projects in atypical fields and will discuss future directions.

Neural Networks and Deep Learning

April 03, 2019

Seminar, University of Illinois at Chicago - School of Public Health, Chicago, Illinois

Neural Network and Deep Learning introduction seminar at the School of Public Health at the University of Illinois at Chicago.

Artificial Intelligence Around Us

March 12, 2019

Seminar, Institute of Industrial and Systems Engineers, Chicago, Illinois

An Artificial Intelligence workshop and demonstration hosted by the University of Illinois at Chicago Institute of Industrial and Systems Engineers.

Hands-On: Artificial Intelligence

July 19, 2018

Workshop, University of Illinois at Chicago Summer Bridge Program for NSF S-STEM Scholars, Chicago, Illinois

Introduction on Deep Learning and Artificial Intelligence for 30 incoming freshmen engineering students as part of the Summer Bridge Program organized by the UIC College of Engineering.

Regression and Classification Algorithms

November 28, 2017

Workshop, Data Science I (IE594), University of Illinois, Chicago, Illinois

Python workshop on regression and classification algorithms as part of the graduate course Data Science I (IE594) in the Mechanical and Industrial Engineering department at UIC.

Machine Learning Using Tensorflow

November 21, 2017

Workshop, Data Science I (IE594), University of Illinois, Chicago, Illinois

Guest lecture on Machine Learning using Tensorflow as part of the graduate course Data Science I (IE594) in the Mechanical and Industrial Engineering department at UIC.

Secure Socket Layer Virtual Private Networks

June 18, 2015

Talk, Secure Networking, RheinMain University of Applied Sciences, Rüsselsheim, Germany

Guest lecture on Secure Socket Layer Virtual Private Networks as part of the graduate course Secure Networking at RheinMain University of Applied Sciences.

Software-defined Networking

November 05, 2014

Talk, Multimedia Networking, RheinMain University of Applied Sciences, Wiesbaden, Germany

Guest lecture on Software-defined Networking as part of the graduate course Multimedia Networking at RheinMain University of Applied Sciences.