Our Goal

The goal of the VaVeL project is to radically advance our ability to use urban data in applications that can identify and address citizens’ needs and improve urban life by analyzing a very large number of diverse data streams. A large numbers of multimodal (text, video, relational) and multi-lingual (English, Polish) data streams is generated in a daily basis in smart cities environments. However, these data streams are quite complex since they are diverse and have many inherent challenges like noise, asynchronous information, different degrees of granularity and lack of labels. Consequently, it is critical to spend a conscious strong effort towards analyzing the voluminous and diverse urban data streams.

Our goal is to analyze diverse, multi-modal, multi-lingual Big Urban Data to significantly advance services provided to the citizens, the efficiency of city operators, and provide valuable insights into how people work, live and interact within a smart city. Thus we develop novel algorithms, methodologies, software architectures, language understanding technologies for managing and mining multiple heterogeneous urban data streams.  Emphasis will be given on improving data quality. Therefore, Prediction and Visualization techniques will be developed for large number of diverse structured and unstructured urban data streams. The developed techniques will be integrated under a common general purpose framework, for carrying out analysis on multiple, noisy, problematic, urban data streams. This  framework will allow the cities to become more efficient, productive and resilient, by taking advantage of the automatic analysis of the real-life urban data. Additionally, the framework will be able to solve major issues that arise with urban transportation related data and are currently not dealt by existing stream management technologies.

The project brings together two European cities that provide diverse large scale data of cross-country origin and real application needs, three major European companies in this space, and a strong group of researchers that have uniquely strong expertise in analyzing real-life urban data. VaVeL aims at making fundamental advances in addressing the most critical inefficiencies of current (big) data management systems and stream processing frameworks in order to cope with emerging urban sensor data. Major research problems will be addressed regarding the management and mining of multiple diverse urban data streams. More specifically the consortium will address scalability and responsiveness issues not only in terms of data volume and velocity, but, most importantly, in terms of variety, veracity and value. In VaVeL, we make European urban data more accessible and easy to use enhancing this way European industries that use big data management and analytics. In VaVeL two main European Open Data sources will be exploited. First, in Dublin City the Dublinked initiative (dublinked.ie) and in the City of Warsaw, the open APIs that are already available and provide access to City of Warsaw’s urban sensors.

In VaVeL, we have defined two use-cases, based in Dublin and Warsaw respectively. In each use case an experimental protocol has been defined in order to support the evaluation, the effectiveness, the efficiency, and the usability of the proposed systems. More specifically, Dublin City and City of Warsaw will provide employees for evaluating the efficiency, effectiveness and usability of the provided technologies and further pilot testing will include citizens. For each use case, we will also develop end-user driven concrete scenarios for validating the proposed methodologies. The two use cases are addressing real, important problems with the potential of enormous impact, and a large spectrum of technology requirements, thus enabling the realization of the fundamental capabilities required and the realistic evaluation of the success of our methods.