Benchmarking Learning Networks on Eat-Sleep Conditions
Victor Parque, Hammed Obasekore, Oladayo Solomon Ajani, Tomoyuki Miyashita · 2019 IEEE 1st Global Conference on Life Sciences and Technologies (LifeTech) · 2019
Human activity recognition technologies are key to promote healthy life styles, and potential to offer explanations to study the origin of complex diseases. In particular, it is well-known that the quick transition between eating and sleeping is known to trigger unfavorable conditions for healthy life style. In this paper we describe our observations and insights in the benchmarking of the state of the art classification models based on graph representations to classify activities comprising drinking, eating, walking, running and sleeping.