Corpus ID: 16424360

Context- and cost-aware feature selection in ultra-low-power sensor interfaces

@inproceedings{Lauwereins2014ContextAC,
  title={Context- and cost-aware feature selection in ultra-low-power sensor interfaces},
  author={Steven Lauwereins and Komail M. H. Badami and Wannes Meert and M. Verhelst},
  booktitle={ESANN},
  year={2014}
}
  • Steven Lauwereins, Komail M. H. Badami, +1 author M. Verhelst
  • Published in ESANN 2014
  • Computer Science
  • This paper introduces the use of machine learning to improve efficiency of ultra-low-power sensor interfaces. Adaptive feature extrac- tion circuits are assisted by hardware embedded learning to dynamically activate only most relevant features. This selection is done in a context and power cost-aware way, through modification of the C4.5 algorithm. Furthermore, context dependence of different feature sets is explained. As proof-of-principle, a Voice Activity Detector is expanded with the pro… CONTINUE READING
    10 Citations

    Figures, Tables, and Topics from this paper

    Ultra-low-power voice-activity-detector through context- and resource-cost-aware feature selection in decision trees
    • 8
    • PDF
    Low-power multichannel spectro-temporal feature extraction circuit for audio pattern wake-up
    • 10
    • PDF
    Dynamic Sensor-Frontend Tuning for Resource Efficient Embedded Classification
    • 4
    Where Analog Meets Digital
    Where Analog Meets Digital: Analog?to?Information Conversion and Beyond
    • 37
    Byte The Bullet: Learning on Real-World Computing Architectures
    • 6
    • PDF
    Online Budgeted Learning for Classifier Induction
    • PDF

    References

    SHOWING 1-10 OF 12 REFERENCES
    SenSay: a context-aware mobile phone
    • 362
    • PDF
    Body Sensor Networks: A Holistic Approach From Silicon to Users
    • 73
    • PDF
    A 48.6-to-105.2µW machine-learning assisted cardiac sensor SoC for mobile healthcare monitoring
    • 14
    A reconfigurable, 0.13µm CMOS 110pJ/pulse, fully integrated IR-UWB receiver for communication and sub-cm ranging
    • 49
    Cost-Sensitive Tree of Classifiers
    • 91
    • PDF
    User-Centric Indoor Air Quality Monitoring on Mobile Devices
    • 10
    • PDF
    Subjective comparison and evaluation of speech enhancement algorithms
    • 562
    • PDF
    Decision trees with minimal costs
    • 266
    • PDF
    ESANN 2014 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium)
    • ESANN 2014 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium)
    • 2014
    A reconfigurable 0.13um CMOS 110pJ/pulse, fully integrated IR-UWB receiver for communication and sub-cm ranging Solid-State Circuits Conference-Digest of Technical Papers
    • IEEE International. IEEE
    • 2009