Research Projects

Citizen security

Citizen security is a fundamental determinant of the well-being of households and communities. Robberies, rapes, domestic violence, gender violence, kidnapping, among others, are examples of situations of insecurity having a negative effect on citizens and governments worldwide. This project deals with providing a surveillance technology based on speech recognition for citizen security without affecting the privacy of citizens. To this aim, a prototype software component for the automatic detection of situations of insecurity based on speech recognition, natural language processing, and pattern recognition is proposed. This component provides an automatic surveillance service that allows detecting in real time the occurrence of situations of insecurity, generate security alerts to help mitigating such situations, and report/record the occurred events. The software component minimizes the invasion of privacy of citizens, since speech recognition is performed entirely local, with no access to the Cloud. It also avoids the registration of any dialogue or conversation in which no situation of insecurity has been detected. A demo of the prototype can be accessed at https://youtu.be/dZr4QPhwu9Q. Preliminary results are presented in:

  • Roa, J., Jacob, G., Gallino, L., Hung, P.C.K.. Towards Smart Citizen Security Based on Speech Recognition. CACIDI 2018, Accepted. [PDF]

Cloud-based platform for Collaborative Business Process Management

With the wide adoption of the Internet, organizations establish collaborative networks to execute Collaborative Business Processes (CBPs). Current approaches to implement Process-Aware Information Systems (PAISs) for executing CBPs have shortcomings: high costs and complexity of IT infrastructure to deploy the PAISs; poor support for organization autonomy, decentralized execution, global view of message exchange, and peer-to-peer interactions; and rigid platforms for generating and deploying PAISs on-demand according to the CBPs agreed in collaborative networks. To overcome these issues, this project proposes a cloud-based platform for the execution of CBPs. The platform's architecture enables the generation and on-demand deployment of the PAIS required by each organization to implement and execute the agreed CBPs. The platform also provides approaches to deal with elasticity, privacy, and portability concerns.

Cocconi, D., Roa J., Villarreal P. eBPSim: A Simulation Tool for Testing Elasticity Strategies in Cloud-based Business Process Solutions. CIbSE 2019. Accepted.

Cocconi, D., Roa J., Villarreal P. Collaborative Business Process Management Through a Platform Based on Cloud Computing. CLEI Electronic Journal. Accepted.

Cocconi, D., Roa J., Villarreal P. Cloud-based Platform for Collaborative Business Process Management. Latin American Conference of Informatics (XLIII CLEI), 2017.

Business Process Intelligence

To maintain a competitive advantage in global markets and in government services, organizations are focusing on establishing collaboration networks or inter-organizational collaborations. These types of collaborations require new tools to improve the monitoring and evaluation of business processes. Current business intelligence technologies do not support this type of analysis. This project deals with the definition of new techniques and approaches for the mining of inter-organizational business processes. In the domain of business processes it is currently possible to exploit event logs to make predictions about the execution of cases. This project explores how Long Short-Term Memory (LSTM) neural networks can also be used in the context of process mining. LSTM neural networks and process logs can be valuable input for planning and resource allocation (either physical or virtual), since each trace associated with a case in a log indicates the sequential execution of activities in business processes.

Tello-Leal, E., Rubiolo, M., Roa, J., RamĂ­rez-Alcocer, U. Predicting Activities in Business Processes with LSTM Recurrent Neural Networks. Kaleidoscope 2018, Machine learning for a 5G future. Accepted.

Discovery and specification of business process anti-patterns

Business process languages allow different combinations of elements that could lead to problems in the behavior of business process models, such as deadlocks, lack of synchronizations, livelocks, or dead activities. Two types of verification methods have been used to detect these properties in process models: formal methods based on formal languages and informal methods based on heuristics (also known as anti-patterns). Existing verification methods have benefits and downsides with respect to these requirements. In general, formal methods are more reliable, since they have a total precision, whereas informal methods have partial precision. Both types of methods have a partial completeness, since in general they are not able to detect every possible error of process models. On the other hand, formal methods may have an exponential run-time due to the state space explosion problem and may have problems to provide a solution to fix detected errors. This is a key limitation for being adopted by industry. On the contrary, informal methods may have a short run-time and can provide predefined solutions to fix errors, which make them promising in comparison to formal methods. This project explores approaches for the discovery and specification of new heuristics for business process behavior and faces three challenges to make heuristics reliable: (1) discovery of new heuristics improving completeness; (2) specification of heuristics improving precision; and (3) use of heuristics for detection of errors in process models having a total precision.

Roa J., Reynares E., Caliusco M.L., Villarreal P. Formal Semantics for Modeling Collaborative Business Processes based on Interaction Protocols. In: Teniente E., Weidlich M. (eds) Business Process Management Workshops. BPM 2017. Lecture Notes in Business Information Processing, vol 308. Springer, Cham, 2017. [PDF]

Roa J., Reynares E., Caliusco M.L., Villarreal P. Ontology-Based Heuristics for Process Behavior: Formalizing False Positive Scenarios. In: Dumas M., Fantinato M. (eds) Business Process Management Workshops. BPM 2016. Lecture Notes in Business Information Processing, vol 281. Springer, Cham, 2017. [PDF]

Roa, J., Chiotti, O., Villarreal, P. Specification of Behavioral Anti-Patterns for the Verification of Block-Structured Collaborative Business Processes. Information and Software Technology 75, 148 - 170 (2016). [PDF]

Roa, J., Reynares, E., Caliusco, M.L., Villarreal, P. Towards Ontology-based Anti-Patterns for the Verification of Business Process Behavior. New Advances in Information Systems and Technologies, volume 2, pp. 665-673. Springer International Publishing (2016). [PDF]