Human activity recognition from accelerometer data using Convolutional Neural Network

We propose a one-dimensional (1D) Convolutional Neural Network (CNN)-based method for recognizing human activity using triaxial accelerometer data collected from users' smartphones. The three human activity data, walking, running, and staying still, are gathered using smartphone accelerometer s...

Full description

Saved in:
Bibliographic Details
Published inInternational Conference on Big Data and Smart Computing pp. 131 - 134
Main Authors Song-Mi Lee, Sang Min Yoon, Heeryon Cho
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.02.2017
Subjects
3D accelerometer data
Accelerometers
Activity recognition
convolutional neural network
Hidden Markov models
human activity recognition
Intelligent sensors
random forest
Smart phones
Time series analysis
Online AccessGet full text
ISSN2375-9356
DOI10.1109/BIGCOMP.2017.7881728

Cover

More Information
Summary:We propose a one-dimensional (1D) Convolutional Neural Network (CNN)-based method for recognizing human activity using triaxial accelerometer data collected from users' smartphones. The three human activity data, walking, running, and staying still, are gathered using smartphone accelerometer sensor. The x, y, and z acceleration data are transformed into a vector magnitude data and used as the input for learning the 1D CNN. The ternary activity recognition performance of our 1D CNN-based method which showed 92.71% accuracy outperformed the baseline random forest approach of 89.10%.
ISSN:2375-9356
DOI:10.1109/BIGCOMP.2017.7881728