TY  - JOUR
T1  - Simultaneous Activity Segmentation and Recognition in Smart Homes
AU - Juboor, Saed Sa`deh AU - Chua, Sook-Ling AU - Foo, Lee Kien 
JO  - Journal of Engineering and Applied Sciences
VL  - 11
IS  - 8
SP  - 1851
EP  - 1854
PY  - 2016
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2016.1851.1854
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2016.1851.1854
KW  - Sensors readings
KW  -sensor stream
KW  -segmentation
KW  -recognition
KW  -viterbi algorithm
AB  - Activity recognition systems learn from sensors readings to recognise activities of the occupants in a smart home. In order to recognise activities, the sensor stream has to be segmented before any classification can be carried out. Many methods handle segmentation and recognition separately. In this study, we propose a method that can segment and recognise activity simultaneously by using a set of trained hidden Markov models and Viterbi algorithm. We evaluate our proposed method on two publicly available smart home datasets.
ER  -