Corpus ID: 202727309

Uncovering Perpetual Patterns in Mobile App Use by Deep Visualization of Hand-Engineered Features

@inproceedings{Noor2019UncoveringPP,
  title={Uncovering Perpetual Patterns in Mobile App Use by Deep Visualization of Hand-Engineered Features},
  author={M. A. Noor and G. Kaptan and V. Cherukupally and Parush Gera},
  year={2019}
}
  • M. A. Noor, G. Kaptan, +1 author Parush Gera
  • Published 2019
  • This paper provides a discussion on the representation of mobile app usage activity as images to uncover perpetual patterns of behavior. Our goal is to provide a novel methodology in which consistent patterns of behavior are learned via convolutional neural networks (CNNs) by providing the networks with hand-engineered features in image format. Our hand-engineered features encode daily app usage behaviors in terms of frequency; in isolation, such hand-engineered features generally only allow… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 16 REFERENCES
    Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables
    • 427
    • PDF
    Continuous Authentication of Smartphones Based on Application Usage
    • 20
    • PDF
    Continuous authentication of smartphone users by fusing typing, swiping, and phone movement patterns
    • 41
    Active user authentication for smartphones: A challenge data set and benchmark results
    • 73
    • PDF
    Smart Phone User Behaviour Characterization Based on Autoencoders and Self Organizing Maps
    • 14
    • PDF
    Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition
    • 607
    • PDF
    Mobile Silent and Continuous Authentication using Apps Sequence
    • 3
    • PDF
    Deep Activity Recognition Models with Triaxial Accelerometers
    • 149
    • PDF