Knowledge COMmunity for Efficient TrAining through Virtual Technologies

Kometa

A short description
Related publications
Deliverable on Process Mining in Kometa v. 1.0
Deliverable on Process Mining in Kometa v. 2.0
Deliverable on Results of the evaluation of process mining techniques in Kometa v. 1.0
The distribution package - PmKOMETA
The distribution package - VITE
Authors & Aknowledgement
Contact

A short description

The KDDE lab is the research partner of the project Kometa. In the project, KDDE researchers are aimed at the synthesis of advanced process mining techniques, in order to mine data collected in event logs and produced by tracking the training activities of a group of technicians involved in the aqueduct maintenance. The goal is the discovery of the hidden process models behind the training sessions. Discovered models can be employed to improve the plan of the training activities, as well as to check the conformance of new training sessions.

Project details (in Italian): Azione 1.4 “Promozione di nuovi mercati per l’innovazione” – Avviso pubblico INNOLABS- approvato con A.D. n. 13 del 08/02/2017, A.D. n. 37 del 28/03/2017 e A.D. n. 43 del 10/04/2017, tipologia “Knowledge Community”.

Intermediate Deliverable on "Process Mining in Kometa" v. 1.0 (in Italian)

Intermediate Deliverable on "Process Mining in Kometa" v. 2.0 (in Italian)

Final Deliverable on "Results of the evaluation of process mining techniques in Kometa" v. 1.0 (in Italian)

Software (in Italian)

PmKOMETA 1.0

PmKometa implements an accurate data-centric approach to predict business process behaviour. It resorts to shallow machine learning techniques, which are performed as a part of a holistic approach that combines feature construction, local and global learning, classification and regression algorithms. The empirical evaluation performed by Appice ed al (SCC 2019) shows that, despite the emerging attention towards deep learning also in predictive process mining, stacking feature construction and shallow machine learning algorithms can still outperform various process predictor competitors (included deep learning ones). It is implemented in Java and used WEKA toolkit.

jar	Description
PmKOMETA (ver 1.0)	This rar bundle contains : pmkometa.jar. (v 1.0) and the bat file to run the demo with the benchmark event log helpdesk log.
PmKOMETA (ver 2.0)	This rar bundle contains : pmkometa.jar (v 2.0) tailored to process data produced in Kometa. The results of the evaluation are described in Final Deliverable on "Results of the evaluation of process mining techniques in Kometa" v. 1.0 (in Italian)

VITE 1.0

VITE implements a process mining software to predict the score of an exam based on data collected during the training session of the student. It is implemented in Java and used WEKA toolkit.

VITE (ver 1.0)	This rar bundle contains: vite.jar. and the bat file to run a demo with artificial example data.
VITE (ver 2.0)	This rar bundle contains: vite.jar (ver 2.0) considered to process data produced in Kometa. The results of the evaluation are described in Final Deliverable on "Results of the evaluation of process mining techniques in Kometa" v. 1.0 (in Italian)

Data bridge

Data Bridge(ver 1.0)

This rar bundle contains: KometaData.jar. to extract the example data from the db/json sources. Details are reported in Final Deliverable on "Results of the evaluation of process mining techniques in Kometa" v. 1.0 (in Italian)

Warning: Both PmKometa and VITE are free for evaluation, research and teaching purposes, but not for commercial purposes.
Please Acknowledge

Top of this page

Related publications

A. Appice, N. Di Mauro, D. Malerba, Leveraging Shallow Machine Learning to Predict Business Process Behavior, IEEE World Congress on Services 2019, IEEE, July 2019.

P. Ardimento, N. Boffoli and C. Mele, A text-based regression approach to predict bug-fix time. Book chapter in Complex Pattern Mining: New Challenges, Methods and Applications Book in Studies in Computational Intelligence, 2020

S. Ferilli, S. Angelastro, Efficient Declarative-based Process Mining using an Enhanced Framework. Book chapter in Complex Pattern Mining: New Challenges, Methods and Applications, New Challenges, Methods and Applications Book in Studies in Computational Intelligence, 2020.

V. Pasquadibisceglie, A. Appice, G. Castellano, D. Malerba, Using Convolutional Neural Networks for Predictive Process Analytics, ICPM 2019, IEEE, 2019, pp 129-136

N. Di Mauro, A. Appice, T.M. Basile, Activity prediction of business process instances with inception based convolutional networks, AI*IA 2019, 2019, Springer-Verlag.

A. Appice, P. Ardimento, D. Malerba, G. Modugno, D. Marra, M. Mottola. Training in a Virtual Learning Environment: A Process Mining Approach. IEEE Conference on Evolving and Adaptive Intelligent Systems, 2020. Accepted for publication.

Top of this page

Project KDDE team

Donato MALERBA

Contact

Name	Email address	Tel. number	Fax
Annalisa Appice	annalisa.appice@uniba.it	+39 080 5443262	+39 080 5443262

Top of this page