Optimising Tea Fermentation with Internet of Things and Data Science

Abstract

Tea (Camellia sinensis) is among the mostly used drinks across the world, with black tea being the most popular. In this talk, we explore the use of Internet of Things (IoT), deep convolutional neural networks, and image processing with majority voting techniques in detecting the optimum fermentation state of black tea. We have deployed a prototype in a tea factory in Kenya for training, validation and evaluation, and have also gathered an extensive dataset of images and environmental data. In the talk, we will shortly explore the design and implementation of the prototype, and will discuss its limitations and applicability to other fields.


About the Speaker

Anna Förster obtained her MSc degree in computer science and aerospace engineering from the Free University of Berlin, Germany, in 2004 and her PhD degree in self-organising sensor networks from the University of Lugano, Switzerland, in 2009. She also worked as a junior business consultant for McKinsey&Company, Berlin, between 2004 and 2005. From 2010 to 2014, she was a researcher and lecturer at SUPSI (the University of Applied Sciences of Southern Switzerland). Since 2015, she leads the Sustainable Communication Networks group at the University of Bremen.

Her main research interests lie in self-organising and autonomous sensor, opportunistic and vehicular networks. She applies various artificial intelligence techniques, like machine learning and swarm intelligence, to various aspects of wireless communication protocols and applications. Furthermore, she is active in designing and developing simulation models and benchmarks for wireless networks. Her research group is especially focused to how to achieve better sustainability of communication networks on one side and how to boost everyday sustainability by innovative applications.

Speaker:
Prof. Dr. Anna Förster

---

The Data Science Center is funded by: