Fraunhofer AICOS presented a session on its Machine Learning work entitled “Transfer learning approach for fall detection with the FARSEEING real-world dataset and simulated falls” at the Priberam Machine Learning Lunch Seminars, held on March 21 at IST – Instituto Superior Técnico, in Lisbon.
AICOS’ Researcher, Joana Silva, showcased the centre’ vast knowledge in the field, resulting from the use of Machine Learning techniques in the work developed in R&D projects, master theses and research papers, with a special focus within the application areas of: Fall and Activity Monitoring; Chronic Diseases and Well-Being Management; and Assistive Environments.
Falls are very rare and extremely difficult to acquire in free living conditions. Due to this, most of prior work on fall detection has focused on simulated datasets acquired in scenarios that mimic the real-world context, however, the validation of systems trained with simulated falls remains unclear.
The work demonstrated by Joana Silva, presents a transfer learning approach for combining a dataset of simulated falls and non-falls, obtained from young volunteers, with the real-world FARSEEING dataset, in order to train a set of supervised classifiers for discriminating between falls and non-falls events. The objective is to analyse if a combination of simulated and real falls could enrich the model.
The Priberam Machine Learning Lunch Seminars are a series of informal meetings which occur every two weeks at Instituto Superior Técnico, in Lisbon. It works as a discussion forum involving different research groups, interested in areas such as: statistical machine learning, signal processing, pattern recognition, computer vision, natural language processing, computational biology, neural networks, control systems, reinforcement learning, among others.