PACT-ART: Enrichment, Data Mining, and Complex Event Processing in the Internet of Cultural Things

Artwork transportation processes are generally agreed-upon, and long running propositions between multiple partners that are specified over service level agreements, performance, and complex quality constraints to be maintained. The complexity of the constraints is defined by the sensitivity, value, and significance of artworks, where any recorded damage would probably leave undesired marks on the long-term, and diminish the lifetime of art pieces. Due to the uncontrollable, and unpredictable nature of the context during transportation, the specified constraints are often violated in real scenarios. In this paper, we introduce the PACT-ART architecture to integrate advanced computing techniques with transportation activities. This integration counts on external and Internet of Things (IoT) services to draw and understand the context of activities, thus it paves a way to predict a future state of the ongoing process and point out any possible violation in advance. Moreover, PACT-ART combines Complex Event Processing (CEP) techniques and makes this technology available even to non-experts in the domain. Finally, we showcase some initial experiments on real-life transportation scenarios that testify to the efficiency of our proposal.

[1]  Nenad Stojanovic,et al.  An approach for iterative event pattern recommendation , 2010, DEBS '10.

[2]  D. Luckham.  Event Processing for Business: Organizing the Real-Time Enterprise , 2011 .

[3]  Andreas Meyer,et al.  Improving Process Monitoring and Progress Prediction with Data State Transition Events , 2013, ZEUS.

[4]  Michael Philippsen,et al.  Learning event detection rules with noise hidden Markov models , 2012, 2012 NASA/ESA Conference on Adaptive Hardware and Systems (AHS).

[5]  Jian Pei,et al.  Reliable Early Classification on Multivariate Time Series with Numerical and Categorical Attributes , 2015, PAKDD.

[6]  Fabrizio Maria Maggi,et al.  Predictive Monitoring of Business Processes , 2013, CAiSE.

[7]  Mohamed F. Ghalwash,et al.  Extraction of Interpretable Multivariate Patterns for Early Diagnostics , 2013, 2013 IEEE 13th International Conference on Data Mining.

[8]  Jan Mendling,et al.  Predictive Task Monitoring for Business Processes , 2014, BPM.

[9]  Philip S. Yu,et al.  Extracting Interpretable Features for Early Classification on Time Series , 2011, SDM.

[10]  Heiko Ludwig,et al.  The WSLA Framework: Specifying and Monitoring Service Level Agreements for Web Services , 2003, Journal of Network and Systems Management.

[11]  Andreas Meyer,et al.  Monitoring of Business Processes with Complex Event Processing , 2013, Business Process Management Workshops.

[12]  Giordano Tamburrelli,et al.  Learning from the past: automated rule generation for complex event processing , 2014, DEBS '14.

[13]  Mathias Weske,et al.  Enabling Semantic Complex Event Processing in the Domain of Logistics , 2013, ICSOC Workshops.

[14]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[15]  Eamonn J. Keogh,et al.  Time series shapelets: a new primitive for data mining , 2009, KDD.

[16]  Mathias Weske,et al.  Enriching Raw Events to Enable Process Intelligence – Research Challenges , 2013 .

[17]  Yehia Taher,et al.  The Butterfly: An Intelligent Framework for Violation Prediction within Business Processes , 2016, IDEAS.

[18]  Schahram Dustdar,et al.  Monitoring, Prediction and Prevention of SLA Violations in Composite Services , 2010, 2010 IEEE International Conference on Web Services.

[19]  Mohamed F. Ghalwash,et al.  Early classification of multivariate temporal observations by extraction of interpretable shapelets , 2012, BMC Bioinformatics.

[20]  Andreas Meyer,et al.  BPMN extension for business process monitoring , 2014, EMISA.

[21]  Remco M. Dijkman,et al.  GET Controller and UNICORN: Event-driven Process Execution and Monitoring in Logistics , 2015, BPM.

[22]  Xu Chen,et al.  Early prediction on imbalanced multivariate time series , 2013, CIKM.

[23]  Yehia Taher,et al.  autoCEP: Automatic Learning of Predictive Rules for Complex Event Processing , 2016, ICSOC.

[24]  Yehia Taher,et al.  Complex event processing for the non-expert with autoCEP: demo , 2016, DEBS.

[25]  Avigdor Gal,et al.  Tuning complex event processing rules using the prediction-correction paradigm , 2009, DEBS '09.

[26]  Jan Mendling,et al.  Towards the Enhancement of Business Process Monitoring for Complex Logistics Chains , 2013, Business Process Management Workshops.