TY - GEN
T1 - A Multiscale Approach to Detect the Semantics of Locomotion without Positioning Information
AU - Qu, Chen
AU - Yang, Jinxin
AU - Si, Guangwen
AU - Zhao, Yufei
AU - Zhou, Yiren
AU - Yang, Wen Chi
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/14
Y1 - 2020/11/14
N2 - The detection of locomotion patterns and trajectory semantics has long relied on the positioning information. However, positioning information can be unavailable in specific scenarios. In addition, the position values are sensitive to rotation and hence a bias can exist during the training process in deep learning models. This paper introduces an alternative model that classifies trajectories based on accelerometers, instead of positioning systems. We built up a convolutional neural network that inputs the degree of velocity and turning angles at several time scales and converts this information into a semantic class. We examined the model in a simulated environment and also a benchmark task. This model has exhibited a competitive performance even compared with those models based on positioning information.
AB - The detection of locomotion patterns and trajectory semantics has long relied on the positioning information. However, positioning information can be unavailable in specific scenarios. In addition, the position values are sensitive to rotation and hence a bias can exist during the training process in deep learning models. This paper introduces an alternative model that classifies trajectories based on accelerometers, instead of positioning systems. We built up a convolutional neural network that inputs the degree of velocity and turning angles at several time scales and converts this information into a semantic class. We examined the model in a simulated environment and also a benchmark task. This model has exhibited a competitive performance even compared with those models based on positioning information.
KW - acceleration sensors
KW - deep learning
KW - locomotion semantics
KW - rotational invariance
KW - trajectory classification
UR - http://www.scopus.com/inward/record.url?scp=85100357437&partnerID=8YFLogxK
U2 - 10.1109/ISCMI51676.2020.9311556
DO - 10.1109/ISCMI51676.2020.9311556
M3 - Conference Proceeding
AN - SCOPUS:85100357437
T3 - 2020 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020
SP - 270
EP - 274
BT - 2020 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020
Y2 - 14 November 2020 through 15 November 2020
ER -