IDEA (Innovation, Decision, Environment, Awareness) Research Transfer is a spin-off company of Technical University of Bari created to transfer technology and innovative tools for analysis and decision support from research to complex systems in civil engineering in order to raise awareness of management decisions in terms of effectiveness, efficiency and sustainability.
The technology transfer paradigm of IDEA Research Transfer is based on developing advanced tools in a high-level programming environment and deploying them as simple functions in software environments familiar to technicians (e.g. Excel of Microsoft Office®). This permits to quickly develop, update, test and customize analysis and decision support tools to be used in specific applications in close cooperation with end users. This realizes a dynamic and real-time transfer of the scientific research to the technical field.
IDEA Research Transfer provides:
- Scientific and technical advice for the analysis and decision support in civil engineering through innovative tools developed by the company, also integrated with other systems
- Training of users in developing and using innovative tools by organizing workshops, webinars and conferences oriented to researchers’ training or professional training
- Customized solutions and training of professionals on advanced tools for data analysis and decision support systems in civil engineering

 

WDNetXL 
WDNetGIS 
EPR MOGA-XL 
ANN MOGA-XL 

The availability of large and detailed databases together with the increased computational capabilities has motivated researchers to propose innovative techniques and methodologies to mine information from data. The Evolutionary Polynomial Regression (EPR) [Giustolisi and Savic (2006)] has been introduced in the hydroinformatics community as a hybrid data-driven technique, which combines the effectiveness of genetic algorithms with numerical regression for developing simple and easily interpretable mathematical model expressions. The multi-objective search paradigm has been introduced [Giustolisi and Savic (2009)] for developing multiple models by simultaneously optimizing fitness to training data and parsimony of resulting mathematical expressions. Such improvement allows for a sudden understanding of existing patterns in data

READ MORE