Novel activity classification and occupancy estimation methods for intelligent HVAC (heating, ventilation and air conditioning) systems
详细信息 查看全文
- 作者：Rajib Ranaa ; rajib.rana@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Brano Kusyb ; brano.kusy@csiro.au" class="auth_mail" title="E-mail the corresponding author ; Josh Wallc ; josh.wall@csiro.au" class="auth_mail" title="E-mail the corresponding author ; Wen Hub ; wen.hu@csiro.au" class="auth_mail" title="E-mail the corresponding author
- 关键词：HVAC (heating ; ventilation and air conditioning) ; Sparse random classifier ; Sensor fusion ; Smartphone ; Occupancy ; Physical activity
- 刊名：Energy
- 出版年：2015
- 出版时间：15 December 2015
- 年：2015
- 卷：93
- 期：part_P1
- 页码：245-255
- 全文大小：1265 K
文摘
- •
We propose activity and occupancy detection for efficient HVAC control.
- •
Activity classifier achieves 10% higher accuracy than SVM and kNN.
- •
For occupancy detection we propose a novel sensor fusion method.
- •
Using Weighted Majority Voting we fuse microphone and accelerometer data on phone.
- •
We achieve more than 90% accuracy in detecting occupancy.