Pervasive informatics and persistent actimetric information in health smart homes : From Language Model to Location Model

Yannick Fouquet (1) , Jacques Demongeot (2) , Nicolas Vuillerme (1)

1 AFIRM
2 TIMB

This paper presents an approach of location model deriving from language models existing in speech recognition research. The purpose is to applicate existing model in speech recognition to predict location of an elderly person. Using statistics, the model offers up to 98.03% of good prediction location, considering only the last second of location but distinguishing days of week. Simpler than Polya's urns derived approach, this approach seems to be a good way of location modelling.

Mots clés: smart flats for elderly people; pervasive watching systems; actimetry; localization sensors; n-grams; Polya's urns; Markov chain; Mobile and pervasive sensing; Biostatistics and time series of long recording at home; Elderly people watching

Domaines: Modélisation et simulation; Apprentissage [cs.LG]; Probabilités [math.PR]; Statistiques [math.ST]; Théorie [stat.TH]; Informatique et langage [cs.CL]; Informatique ubiquitaire; Autres [stat.ML]; Machine Learning [stat.ML]; Ingénierie biomédicale

Yannick Fouquet, Jacques Demongeot, Nicolas Vuillerme. Pervasive informatics and persistent actimetric information in health smart homes : From Language Model to Location Model. International Conference on Complex, Intelligent and Software Intensive Systems, Mar 2009, Fukuoka, Japan. pp.935-942, ⟨10.1109/CISIS.2009.81⟩. ⟨hal-00379459⟩