Detecting anomalies to improve classification performance in opportunistic sensor networks

@article{Sagha2011DetectingAT,
  title={Detecting anomalies to improve classification performance in opportunistic sensor networks},
  author={Hesam Sagha and Jos{\'e} del R. Mill{\'a}n and Ricardo Chavarriaga},
  journal={2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops)},
  year={2011},
  pages={154-159}
}
Anomalies and changes in sensor networks which are deployed for activity recognition may abate the classification performance. Detection of anomalies followed by compensatory reaction would ameliorate the performance. This paper introduces a novel approach to detect the faulty or degraded sensors in a multi-sensory environment and a way to compensate it. The approach considers the distance between each classifier output and the fusion output to decide whether a sensor (classifier) is degraded… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS