Want to know a little bit more about how artificial intelligence can improve the energy sector? Or naturally curious to learn about network science?
Either way, this meetup is for you!
=== SCHEDULE ===
• 18:30-19:00: Welcome and get together
• 19:00-19:30: Data Science in Sustainable Energy Systems by Ricardo Bessa, INESC TEC
• 19:40-19:45: Group photo
• 19:45-20:15: Networking / Coffee Break
• 20:15-20:45: From Graph Theory to Modern Network Science: Why Networks are Ubiquitous by Miguel Lopes Martins, Critical TechWorks/INESC TEC Researcher
• 20:50: Closing
• 21:00: Dinner is optional but it might be an excellent opportunity for networking (register here: http://bit.ly/dspt73_dinner)
This meetup is sponsored by Bosch (https://www.bosch.pt) and the venue is provided by Porto Innovation Hub (https://portoinnovationhub.pt/en/home-page/). Thank you for your support!
Title: Data Science in Sustainable Energy Systems
Abstract: This talk will present different use cases in the energy sector for data science, such as load and renewable energy forecasting, energy optimization, electricity market behaviour prediction, alarm management, classification of events, etc. These use cases are supported with application examples from national and international projects.
Short bio: Ricardo Bessa has a background in Electrical and Computer Engineering (5-years degree), Data Analysis and Decision Support Systems (M.Sc.) and Sustainable Energy Systems (Ph.D.) from the University of Porto. He worked in several international and national projects about time-series forecasting, renewable energy and decision-aid under risk. Presently, he is assistant coordinator of the Center for Power and Energy Systems at INESC TEC, with a total of 80 that is internationally recognized for its expertise in the large-scale integration of renewable energy. He is co-author of 42 journal papers, 88 conference papers and 6 book chapters, namely about renewable energy forecasting and data-driven modelling of energy systems.
Title: From Graph Theory to Modern Network Science: Why Networks are Ubiquitous
Abstract: Since man first looked at the sky and found patterns of stars in the form of constellations, one can argue that He was subconsciously modelling a disconnected network where patterns emerged.
Later, Euler solved the famous problem of the Seven Bridges of Königsberg and many say this was the genesis of graph theory as we know it today. In 20th century, great scientists like Alfred Rényi and Paul Erdös also investigated this mathematical object and made arguably the first breakthrough which led to modern Network Science (Erdös-Rényi Networks). Just at the end of the century, we were gifted with the Barábasi-Albert model, which explained the emergence of scale-free distributions in a plethora of real-world phenomena modelled as graphs.
In this talk, I would address why Networks are ubiquitous, and the answer is quite simple: they make problem complex problems tractable. But why do these problems become tractable? Well, for that, you have to listen to the talk.
To encourage you a little bit further to hope on in on this journey, modern Network Science has many use-cases in social network analysis (Facebook, LinkedIn, Twitter, you name it), virus detection and repression, terrorism prevention and may even help us cure cancer (protein interaction networks). It all revolves, in one way or the other, in finding patterns.
Short bio: Data Scientist (NLP) at Critical TechWorks | BMW Group
Volunteer organizer at Kaggle Meetups in Lisbon. External Research collaborator in INESC&CRACS in Complex Networks. Ex-Research Collaborator in Computer Vision in FCUP: Generative Adversarial Networks and image super resolution. Written a paper accepted in CompleNet'2020 which encapsulates analytical and enumeration algorithms in a single framework. Prototype is state-of-the-art for many networks. Master of Computer Science from DCC-FCUP, Data science branch.