What shall we teach our pants?

Author

Van Laerhoven, K. ; Cakmakci, O.

Author_Institution

Starlab Res., Brussels, Belgium

fYear

2000

fDate

16-17 Oct. 2000

Firstpage

77

Lastpage

83

Abstract

If a wearable device can register what the wearer is currently doing, it can anticipate and adjust its behavior to avoid redundant interaction with the user. However, the relevance and properties of the activities that should be recognized depend on both the application and the user. This requires an adaptive recognition of the activities where the user, instead of the designer, can teach the device what he/she is doing. As a case study we connected a pair of pants with accelerometers to a laptop to interpret the raw sensor data. Using a combination of machine learning techniques such as Kohonen maps and probabilistic models, we build a system that is able to learn activities while requiring minimal user attention.

Keywords

laptop computers; learning (artificial intelligence); notebook computers; probability; self-organising feature maps; Kohonen maps; accelerometers; adaptive recognition; laptop; machine learning; minimal user attention; pants; probabilistic models; raw sensor data; wearable device; Accelerometers; Context awareness; Gas detectors; Infrared sensors; Machine learning algorithms; Sensor arrays; Sensor phenomena and characterization; Sensor systems; Tactile sensors; Temperature sensors;

fLanguage

English

Publisher

ieee

Conference_Titel

Wearable Computers, The Fourth International Symposium on

Conference_Location

Atlanta, GA, USA

Print_ISBN

0-7695-0795-6

Type

conf

DOI

10.1109/ISWC.2000.888468

Filename

888468