TY - GEN
T1 - Human activity recognition with smart watch based on H-SVM
AU - Tang, Tao
AU - Zheng, Lingxiang
AU - Weng, Shaolin
AU - Peng, Ao
AU - Zheng, Huiru
PY - 2017/9/27
Y1 - 2017/9/27
N2 - Activity recognition allows ubiquitous wearable device like smart watch to simplify the study and experiment. It is very convenient and extensibility that we do study with the accelerometer sensor of a smart watch. In this paper, we use Samsung GEAR smart watch to collect data, then extract features, classify with H-SVM (Hierarchical Support Vector Machine) classifier and identify human activities classification. Experiment results show great effect at low sampling rate, such as 10 and 5 Hz, which will give us the energy saving. In most cases, the accuracies of activity recognition experiment are above 99%.
AB - Activity recognition allows ubiquitous wearable device like smart watch to simplify the study and experiment. It is very convenient and extensibility that we do study with the accelerometer sensor of a smart watch. In this paper, we use Samsung GEAR smart watch to collect data, then extract features, classify with H-SVM (Hierarchical Support Vector Machine) classifier and identify human activities classification. Experiment results show great effect at low sampling rate, such as 10 and 5 Hz, which will give us the energy saving. In most cases, the accuracies of activity recognition experiment are above 99%.
KW - H-SVM
KW - Human activity recognition
KW - Smart watch
UR - http://www.scopus.com/inward/record.url?scp=85031412123&partnerID=8YFLogxK
U2 - 10.1007/978-981-10-3187-8_19
DO - 10.1007/978-981-10-3187-8_19
M3 - Conference contribution
AN - SCOPUS:85031412123
SN - 9789811031861
VL - 422
T3 - Lecture Notes in Electrical Engineering
SP - 179
EP - 186
BT - Frontier Computing - Theory, Technologies and Applications, FC 2016
PB - Springer
T2 - 5th International Conference on Frontier Computing, FC 2016
Y2 - 13 July 2016 through 15 July 2016
ER -