| Summary: | 碩士 === 清雲科技大學 === 電腦通訊與系統工程研究所 === 99 === According to the spirit of e-Home, e-Health, “offers the ubiquitous and adaptation service for the specified family”, the requirement is fixed. Now, a family activity identification technique with pressure-sensed floors can satisfy this requirement, which make families communicate with the serving systems at any place of home. This kind of communication doesn’t limited by the traditional input equipment, such as keyboards or mousses. In addition, this identification system also makes the serving system to understand the activity situation of the specified family, and to offer intelligence and conformable services further. So this thesis, a dual-model activity identification system is introduced for constructing the smart home-cared environments, which is empowered to understanding the family daily activities and the further to offer some intimate and conformable services appropriately. The dual-model activity identification system is composed by three major parts: activity signal processing, feature extraction, and activity recognition. The feature of this system is building both models of family activity and family identity simultaneously. And the operational procedure is to identify the family identity first, and then to find out the activity that the family just doing. This design makes the smart home-cared serving systems more accurate, and the stored family daily activity models can also embedded with the personal characteristic of some specified family simultaneously.
|
|---|
