Data Science Clinics

12 April 2021

Data Science Clinics

12 April 2020 - 12h15-14h00

Online - registration mandatory


12h15-12h40: Bart Vandereycken and Sylvain Sardy, Faculty of Sciences, Section of Mathematics. 

"The Consulting Platform in Applied Mathematics and Statistics"

The CAMAS is a Consulting Platform in Applied Mathematics and Statistics that includes faculty members from the Section of Mathematics and the Department of Computer Science at UNIGE. Its expertise includes areas of applied mathematics such as optimization, machine learning, probability, numerical analysis and scientific computing. 

We will present the CAMAS platform and give a broad overview of a few of its former projects, thereby answering questions like: How did CAMAS get involved in the project? What kind of help and expertise did CAMAS provide? Did the collaboration lead to new academic results and publications?


12h40-13h10: Nathan Hara, Faculty of Sciences, Department of Astronomy.

"Detecting exoplanets in radial velocity time-series"

When a star has planetary companions, it describes an epicyclic motion around the center of mass of the system. The component of the star velocity in the observer's direction, or radial velocity, can be estimated from spectroscopic measurements thanks to Doppler effect. In the radial velocity time series, one searches for periodic variations due to planets. Various phenomena complicate the task: the signals from several planets can be hard to disentangle, stellar noise might mimic planetary signals, correlated noise buries other signals etc. We review some tools to disentangle the planetary, stellar and instrumental signals and compare their merits. All new ideas are welcome. 


13h10-13h40: Igor Almeida Matias, Geneva School of Economics and Management, Information Science Institute.

"“Know you (self) better”: N-of-1 based self-examination using wearables and self-reported behaviors for an improved well-being"

N-of-1 randomized trials help better understand the effects of an intervention, e.g., behavioral changes in a specific person, allowing for the correlation and causation between, for example, duration of sleep and the level of physical exercise the following day.

By leveraging the data originating from affordable wearables like Fitbit and smartphones, it is now possible to view the individual’s daily behaviors and vital signs in a minimally intrusive way. Collecting and combining this data with an N-of-1 approach makes it possible to understand better the interventions that benefit or detriment the individual’s well-being on an hourly, daily, or monthly level.

We introduce an N-of-1 method leveraging wearable collected behavioral data from three participants for up to 4 years to assess the correlations between sleep duration, physical activity, walking performance, resting heart rate, self-reported stress levels, traveling, relationship status, and many more intervention-variables.
The study also aims to exemplify how wearable and self-reported data can help understand the changes most relevant to a specific individual, providing an alternative to the understanding based on an “in the lab” experiment, average population assessments; so far failing to provide personal insights into one's well-being.

Finally, in this study, we also reflect on the corroboration of personal beliefs driving individual behaviors. Furthermore, we discuss the N-of-1 approach in our upcoming population study, focusing on monitoring the decline of memory and cognitive performance in older adults.


13h40-14h00: Hugues Cazeaux, Division des Système et Technologies de l'Information et de la Communication.

"Search no further than e-research!"

Everything you need to know about the IT service's e-Research group:

       What is its mission?

       Why we can support you in your research endeavors

       Who are the team members?

       What services does it develop and offer?

       How can you reach us?

       And more...