TY - JOUR
T1 - Smart care using a dnn-based approach for activities of daily living (ADL) recognition
AU - Su, Muchun
AU - Hayati, Diana Wahyu
AU - Tseng, Shaowu
AU - Chen, Jiehhaur
AU - Wei, Hsihsien
N1 - Publisher Copyright:
© 2020 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/1/1
Y1 - 2021/1/1
N2 - Health care for independently living elders is more important than ever. Automatic recognition of their Activities of Daily Living (ADL) is the first step to solving the health care issues faced by seniors in an efficient way. The paper describes a Deep Neural Network (DNN)-based recognition system aimed at facilitating smart care, which combines ADL recognition, image/video processing, movement calculation, and DNN. An algorithm is developed for processing skeletal data, filtering noise, and pattern recognition for identification of the 10 most common ADL including stand-ing, bending, squatting, sitting, eating, hand holding, hand raising, sitting plus drinking, standing plus drinking, and falling. The evaluation results show that this DNN-based system is suitable method for dealing with ADL recognition with an accuracy rate of over 95%. The findings support the feasibility of this system that is efficient enough for both practical and academic applications.
AB - Health care for independently living elders is more important than ever. Automatic recognition of their Activities of Daily Living (ADL) is the first step to solving the health care issues faced by seniors in an efficient way. The paper describes a Deep Neural Network (DNN)-based recognition system aimed at facilitating smart care, which combines ADL recognition, image/video processing, movement calculation, and DNN. An algorithm is developed for processing skeletal data, filtering noise, and pattern recognition for identification of the 10 most common ADL including stand-ing, bending, squatting, sitting, eating, hand holding, hand raising, sitting plus drinking, standing plus drinking, and falling. The evaluation results show that this DNN-based system is suitable method for dealing with ADL recognition with an accuracy rate of over 95%. The findings support the feasibility of this system that is efficient enough for both practical and academic applications.
KW - Activities of daily living (ADL)
KW - Deep neural network (DNN)
KW - Image processing
KW - Pattern recognition
KW - Skeletal data processing
UR - http://www.scopus.com/inward/record.url?scp=85098632670&partnerID=8YFLogxK
U2 - 10.3390/app11010010
DO - 10.3390/app11010010
M3 - 期刊論文
AN - SCOPUS:85098632670
SN - 2076-3417
VL - 11
SP - 1
EP - 12
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 1
M1 - 10
ER -