Corpus ID: 201070630

Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback

@article{Yamagata2019OnlineFS,
  title={Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback},
  author={Taku Yamagata and Ra{\'u}l Santos-Rodr{\'i}guez and Ryan McConville and A. Elsts},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.06134}
}
Recent advances in both machine learning and Internet-of-Things have attracted attention to automatic Activity Recognition, where users wear a device with sensors and their outputs are mapped to a predefined set of activities. However, few studies have considered the balance between wearable power consumption and activity recognition accuracy. This is particularly important when part of the computational load happens on the wearable device. In this paper, we present a new methodology to perform… Expand
1 Citations
A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review
  • 5
  • PDF

References

SHOWING 1-10 OF 13 REFERENCES
Egocentric Activity Recognition on a Budget
  • 14
  • PDF
A Survey on Human Activity Recognition using Wearable Sensors
  • 1,630
  • PDF
A Comprehensive Study of Activity Recognition Using Accelerometers
  • 61
  • PDF
Online Heart Rate Prediction using Acceleration from a Wrist Worn Wearable
  • 5
  • PDF
The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data
  • 44
  • Highly Influential
  • PDF
Classification with Costly Features using Deep Reinforcement Learning
  • 42
  • PDF
On-Board Feature Extraction from Acceleration Data for Activity Recognition
  • 17
  • PDF
Person Identification and Discovery With Wrist Worn Accelerometer Data
  • 5
  • PDF
Large Scale Population Assessment of Physical Activity Using Wrist Worn Accelerometers: The UK Biobank Study
  • 337
  • PDF
Policy Shaping: Integrating Human Feedback with Reinforcement Learning
  • 221
  • Highly Influential
  • PDF
...
1
2
...