These are some of my current interests. Browse them and feel free to drop me an email if you want to know more.

Smart cities for people

Smart City Sense is a P2020 project aiming at placing the citizen at the focus of the information gathering and sharing process. This concept places citizens as significant elements of the process of collecting / making available information about the city, and they become one of the active contributors, maybe the most relevant ones, due to their sensing capabilities.

The project proposes the conceptualization, design and implementation of a computer platform in which the wealth of data collected by citizens (volume, variety and detail) is aggregated with data collected by a multiplicity of other sensors in the city providing, in real time, a clearer and more vivid view of the city's global heartbeat. This platform will provide an environment (physical and virtual) suitable for cooperation between citizens and authorities enabling information flow between all interested parties.

This objective will be supported in a set of technologies and knowledge (Big Data and Data Mining, Statistical Reasoning, Social Sciences or Human Factors) that allow to cover from the process of information gathering and interface with the human sensors, analysis and evaluation of the quality of the collected data, aggregation and analysis of heterogeneous data, modeling of the city and its physical and functional relations, to the modes of presentation to citizens and authorities and mechanisms to encourage participation.

Check the project's website.

Patient / Doctor matching

It is known as a fact that the quality of the relationship between a family doctor and his patient is an important factor in avoiding morbidity. Nevertheless, The matching is currently done at random. There is a huge gap that may be bridged by what we call a 'mediation system’, that goes beyond a one-way recommendation to deliver the best match for both patient and doctor.

Our goal is to develop and deploy technology  —  an automated mediation system (a new type of “recommender system”)  —  for matching general practitioners with patients based on their characteristics and the micro-data of doctor/patient interactions.

This is a collaboration with Nova SBE and Data Science for Social Good Europe

Network localization

Networks of agents typically rely on known node positions even if the main goal of the network is not localization. A network of agents may comprise a large set of miniature, low cost, low power autonomous sensing nodes. In this scenario it is generally unsuitable to accurately deploy all nodes in a predefined location within the network operation area. GPS is also discarded as an option for indoor applications or due to cost and energy consumption constraints. The approaches pursuing distributed and scalable solutions develop approximations or tackle the maximum-likelihood nonconvex problem, sometimes combining both approaches. With the growing network sizes and constraints in energy expenditure and computation power, the need for simple, fast, and distributed algorithms for network localization spurred this line of work.

In collaboration with João Pedro Gomes, João Xavier, Beatriz Quintino, Pusheng Ji, António Pascoal, Miguel Vasques, all from ISR.

Scientific writing

I believe there is no research without good comunication. So I put my writing experience acquired in a past life to service, and try to broadcast as much as possible the easy handles for better scientific writing.