TY - GEN
T1 - Improving recognition accuracy for activities of daily living by adding time and area related features
AU - Arakawa, Yutaka
AU - Yasumoto, Keiichi
AU - Pattamasiriwat, Krita
AU - Mizumoto, Teruhiro
N1 - Publisher Copyright:
© 2017 IPSJ.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - Recognizing the activities of daily living (ADL) of residents in housing is indispensable for operating Daily Life Support Services such as Elderly Monitoring, Smart Home Automation, and Health Support. However, the existing methods have various problems: invasion of privacy, limited target activities, low recognition accuracy, initial installation cost, and long recognition time. As our prior work, we proposed a real-time ADL recognition method using indoor positioning sensor and power meters. We got a result that the method can recognize ten types of ADL with the average accuracy of 79%. However, the accuracy of some activities such as work/study and bathroom-related were not satisfactory. In this work, we aim to improve the accuracy of our prior method by newly adding several new time and are related features such as time slot when activity occurs, staying time in the same area, and previous position. As a result, we could achieve 82% of average recognition accuracy for 10 different activities.
AB - Recognizing the activities of daily living (ADL) of residents in housing is indispensable for operating Daily Life Support Services such as Elderly Monitoring, Smart Home Automation, and Health Support. However, the existing methods have various problems: invasion of privacy, limited target activities, low recognition accuracy, initial installation cost, and long recognition time. As our prior work, we proposed a real-time ADL recognition method using indoor positioning sensor and power meters. We got a result that the method can recognize ten types of ADL with the average accuracy of 79%. However, the accuracy of some activities such as work/study and bathroom-related were not satisfactory. In this work, we aim to improve the accuracy of our prior method by newly adding several new time and are related features such as time slot when activity occurs, staying time in the same area, and previous position. As a result, we could achieve 82% of average recognition accuracy for 10 different activities.
UR - http://www.scopus.com/inward/record.url?scp=85049563520&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85049563520&partnerID=8YFLogxK
U2 - 10.23919/ICMU.2017.8330104
DO - 10.23919/ICMU.2017.8330104
M3 - Conference contribution
AN - SCOPUS:85049563520
T3 - 2017 10th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2017
SP - 1
EP - 6
BT - 2017 10th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2017
Y2 - 3 October 2017 through 5 October 2017
ER -