Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > Couch Potato or Gym Addict? Se...

Couch Potato or Gym Addict? Semantic Lifestyle Profiling with Wearables and Fuzzy Knowledge Graphs

Natalia Díaz Rodríguez, Aki Harma, Ignacio Huitzil, Fernando Bobillo, Rim Helaoui, Umberto Straccia, Couch Potato or Gym Addict? Semantic Lifestyle Profiling with Wearables and Fuzzy Knowledge Graphs. In: Jay Pujara, Danqi Chen, Bhavana Dalvi, Tim Rocktäschel (Eds.), 6th Workshop on Automated Knowledge Base Construction (AKBC) 2017, 1–8, NIPS, 2017.

Abstract:

Automatic lifestyle profiling to categorize users according to their daily routinebased lifestyles is an unexplored area. Despite the current trends on having wearable devices that generate large amounts of heterogeneous data, figuring out the lifestyle patterns of people is not a trivial task. We present Lifestyles-KG, a knowledge graph (fuzzy ontology) for semantic reasoning from wearable sensors. It can serve
as a pre-processing taxonomical step that can be integrated into further prediction techniques for intuitively categorizing fuzzy lifestyle concepts, treats or profiles.
The ultimate aim is to help tasks such as long-term human behavior classification and consequently, improve virtual coaching or customize lifestyle recommendation and intervention programs from free form non-labelled sensor data.

Files:

Full publication in PDF-format

BibTeX entry:

@INPROCEEDINGS{inpDxHaHuBoHeSt17a,
  title = {Couch Potato or Gym Addict? Semantic Lifestyle Profiling with Wearables and Fuzzy Knowledge Graphs},
  booktitle = {6th Workshop on Automated Knowledge Base Construction (AKBC) 2017},
  author = {Díaz Rodríguez, Natalia and Harma, Aki and Huitzil, Ignacio and Bobillo, Fernando and Helaoui, Rim and Straccia, Umberto},
  editor = {Pujara, Jay and Chen, Danqi and Dalvi, Bhavana and Rocktäschel, Tim},
  publisher = {NIPS},
  pages = {1–8},
  year = {2017},
  keywords = {fuzzy ontologies, knowledge graphs, lifestyle profiling, wearable sensors, ambient intelligence},
}

Belongs to TUCS Research Unit(s): Embedded Systems Laboratory (ESLAB)

Edit publication