Smartphone Sensor based Human Activity Recognition using Feature Fusion and Maximum Full A Posteriori

Smartphone Sensor based Human Activity Recognition using Feature Fusion and Maximum Full A Posteriori
Title:
Smartphone Sensor based Human Activity Recognition using Feature Fusion and Maximum Full A Posteriori
Other Titles:
IEEE Transactions on Instrumentation and Measurement
DOI:
10.1109/TIM.2019.2945467
Publication Date:
03 October 2019
Citation:
Z. Chen, C. Jiang, S. Xiang, J. Ding, M. Wu and X. Li, "Smartphone Sensor Based Human Activity Recognition Using Feature Fusion and Maximum Full A Posteriori," in IEEE Transactions on Instrumentation and Measurement. doi: 10.1109/TIM.2019.2945467
Abstract:
Human activity recognition (HAR) using smartphone sensors has attracted great attention, due to its wide range of applications. A standard solution for HAR is to firstly generate some features defined based on domain knowledge (handcrafted features), and then to train an activity classification model based on these features. Very recently, deep learning with automatic feature learning from raw sensory data has also achieved great performance for HAR task. We believe that both the handcrafted features and the learned features may convey some unique information which can complement each other for HAR. In this paper, we firstly propose a feature fusion framework to combine handcrafted features with automatically learned features by a deep algorithm for HAR. Then, taking the regular dynamics of human behaviour into consideration, we develop a maximum full a posterior (MFAP) algorithm to further enhance the performance of HAR. Our extensive experimental results show the proposed approach can achieve superior performance comparing with state-of-the-art methodologies across both a public dataset and a self-collected dataset.
License type:
PublisherCopyrights
Funding Info:
Description:
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
0018-9456
1557-9662
Files uploaded:
File Size Format Action
There are no attached files.