TY - GEN
T1 - Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor
AU - Ishikawa, Takahiro
AU - Hayami, Hitoshi
AU - Murakami, Toshiyuki
N1 - Funding Information:
VIII. ACKNOWLEDGMENT This research presentation is supported in part by a research assistantship of a Grant-in-Aid to the Program for Leading Graduate School for “ Science for Development of Super Mature Society ” from the Ministry of Education, Culture, Sport, Science, and Technology in Japan.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/14
Y1 - 2017/12/14
N2 - This paper focuses on accuracy improvement of human activities detection and classification by using single Inertia Measurement Unit sensor (IMU sensor: an acceleration sensor, a gyro sensor, a magnetometer, and an air pressure sensor) which is a type of the wearable sensors. Generally, performance of classification model is determined by these methodologies; number and type of sensors, coordinate transformation, time window, time-frequency domain analysis, and machine learning algorithms. The contributions of this paper are summarized in the following three points. Firstly, a pressure sensor is additionally utilized to improve the accuracy of human activities estimation. This information is effective to estimate up/down motion by stair and elevator. Secondly, comprehensive evaluation of the combinations using different methodologies is conducted to find an optimal classification model. Thirdly, ensemble learning is performed to improve estimation accuracy. It shows superior performance with over 95 % accuracy of human activity estimation.
AB - This paper focuses on accuracy improvement of human activities detection and classification by using single Inertia Measurement Unit sensor (IMU sensor: an acceleration sensor, a gyro sensor, a magnetometer, and an air pressure sensor) which is a type of the wearable sensors. Generally, performance of classification model is determined by these methodologies; number and type of sensors, coordinate transformation, time window, time-frequency domain analysis, and machine learning algorithms. The contributions of this paper are summarized in the following three points. Firstly, a pressure sensor is additionally utilized to improve the accuracy of human activities estimation. This information is effective to estimate up/down motion by stair and elevator. Secondly, comprehensive evaluation of the combinations using different methodologies is conducted to find an optimal classification model. Thirdly, ensemble learning is performed to improve estimation accuracy. It shows superior performance with over 95 % accuracy of human activity estimation.
KW - Activity Classification
KW - Feature Selection
KW - Inertia Measurement Unit
KW - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85048496701&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048496701&partnerID=8YFLogxK
U2 - 10.1109/M2VIP.2017.8211471
DO - 10.1109/M2VIP.2017.8211471
M3 - Conference contribution
AN - SCOPUS:85048496701
T3 - 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017
SP - 1
EP - 6
BT - 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017
Y2 - 21 November 2017 through 23 November 2017
ER -