rafael oyamada

Postdoctoral Researcher @ KU Leuven | CS PhD @ University of Milan

[Paolo Ceravolo @paoloceravolo]

Tutorial:: Process Mining the Scikit-Learn Way: Introducing SkPM.
Sylvio Barbon Junior @raseidi
#ML4PM @icpm_conf

[Paolo Ceravolo @paoloceravolo]

Presenting CoSMo a Framework for Conditioned Process Simulation at @BPMConf

[rafael oyamada @raseidi]

codebase available as well: https://t.co/uAYxfSEXKe

[rafael oyamada @raseidi]

A step towards making deep learning more flexible for the simulation of processes! Very proud of this work. Paper available here https://t.co/18hpjYzbtT

[Paolo Ceravolo @paoloceravolo]

Next week, on Wednesday, at @BPMConf I will present CoSMo a #deeplearning framework to simulate #processes using user-defined conditions (expressed as DECLARE constraints)

Proud of this work by @raseidi @sbarbonjr @gmtavares_

[Paolo Ceravolo @paoloceravolo]

Well done @raseidi 🙂

[rafael oyamada @raseidi]

I'm really excited about this! Looking forward to working together and accomplishing great things :))

[Jochen De Weerdt @jochendw]

Great to host @raseidi in our research group for the next 5 months. Today, Rafael presented an overview of his research in #processmining and predictive process monitoring in particular. Special thanks to @paoloceravolo for making this possible!

[rafael oyamada @raseidi]

Our new paper has been published in the special issue on Artificial Intelligence for Process Mining in the Engineering Applications of Artificial Intelligence journal. Check it out!

[Sylvio Barbon Junior @sbarbonjr]

How might an encoding method contribute to a better comprehension of your initial problem within a new representation space? We extensively compared and discussed this matter in the context of trace data. https://t.co/tl7dZQsgF8 @MaleLabTs @paoloceravolo @gmtavares_ @raseidi

[rafael oyamada @raseidi]

We're always looking to improve and do even better. We value your feedback, so please don't hesitate to contact us!

[rafael oyamada @raseidi]

A new preprint is now available! Designing conditioned networks is the key to successful process simulation models. In this work, we propose CoSMo: a framework for implementing COnditioned process Simulation MOdels!

https://t.co/p2GMsrXGuN @gmtavares_ @paoloceravolo

[rafael oyamada @raseidi]

By biasing desired outputs, we can mitigate the natural stochasticity of deep neural nets. Our approach unlocks a range of powerful applications, such as synthetic log generation, what-if analysis, and outcome prediction.

[Sylvio Barbon Junior @sbarbonjr]

https://t.co/6JLfeIpeHA

#Metalearning meets Active Learning in Online Machine Learning. In this paper on Elsevier Pattern Recognition, we discuss when updating an online model reduces its performance!

@MaleLabTs

[Sylvio Barbon Junior @sbarbonjr]

Is one #encoding method better than another? We compared the expressiveness, scalability, correlation power, and domain agnosticism of 27 #traceencoding of #processmining methods to answer this question.

https://t.co/8nvtr4QAZA

@raseidi @gmtavares_ @paoloceravolo @MaleLabTs

[rafael oyamada @raseidi]

Any feedback and suggestions are welcomed. Feel free to get in touch :)

[rafael oyamada @raseidi]

Our survey about encoding methods in process mining is now available on arXiv: https://t.co/d4m17JZX4R

Here is a brief overview of what I, @sbarbonjr, @paoloceravolo, and @gmtavares_ found out:

[rafael oyamada @raseidi]

The benchmark focuses on the anomaly detection task and assesses 27 encoding methods through hundreds of event logs. We discuss future directions based on our findings. Therefore, we also expect the proposals and insights presented in our work can be leveraged for other PM tasks.