Instant Learning Sound Sensor for Ubiquitous Computing

We propose a smart sound sensor for ubiquitous computing that can learn and detect events from various sensor information with a time series signal. Using the smart sensor, a developer of a context-aware system and ubiquitous service can easily utilize a real world sound as a context information without a signal processing programming. The signal processing method can be extended for the other sensors such as accelerometer and directional sensor, pressure sensor, etc. By the experiment, we evaluate the feasibility of the instant learning sound sensor

[1]  Ning Liu,et al.  Bathroom Activity Monitoring Based on Sound , 2005, Pervasive.

[2]  Frank Vahid,et al.  eBlocks - an enabling technology for basic sensor based systems , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..