Title :
Activity recognition system for watching over infant children
Author :
Goto, Jungo ; Kidokoro, Takuya ; Ogura, Tsuneo ; Suzuki, Satoshi
Author_Institution :
Dept. of Robot. & Mechatron., Tokyo Denki Univ., Tokyo, Japan
Abstract :
Infantile unhealthy lifestyle increases the risk of their adult diseases and cost of medical care in their future. If children life-log is measured and their physical condition can be analyzed, it is expected that such information can be utilized for prevention of adult diseases and for the health-promoting. Therefore, activity recognition for children is treated in the present paper. Feature points for activity recognition are computed from accelerations which are measured by a 3-axis acceleration sensor attached to child´s upper-arm. Two-phased classification was performed by using Self-Organizing Map. As a result, it was confirmed that the classification accuracy was 65.92[%].
Keywords :
acceleration; diseases; electric sensing devices; health care; risk analysis; self-organising feature maps; 3-axis acceleration sensor; activity recognition system; adult diseases; health promotion; infant children; infantile unhealthy lifestyle; medical care; physical condition; self-organizing map; two-phased classification; Acceleration; Accelerometers; Accuracy; Pediatrics; Robot sensing systems; Servers; Vectors;
Conference_Titel :
RO-MAN, 2013 IEEE
Conference_Location :
Gyeongju
DOI :
10.1109/ROMAN.2013.6628549
