English

Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition

Signal Processing 2019-08-20 v1 Machine Learning Machine Learning

Abstract

The lack of adequate training data is one of the major hurdles in WiFi-based activity recognition systems. In this paper, we propose Wi-Fringe, which is a WiFi CSI-based device-free human gesture recognition system that recognizes named gestures, i.e., activities and gestures that have a semantically meaningful name in English language, as opposed to arbitrary free-form gestures. Given a list of activities (only their names in English text), along with zero or more training examples (WiFi CSI values) per activity, Wi-Fringe is able to detect all activities at runtime. In other words, a subset of activities that Wi-Fringe detects do not require any training examples at all.

Cite

@article{arxiv.1908.06803,
  title  = {Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition},
  author = {Md Tamzeed Islam and Shahriar Nirjon},
  journal= {arXiv preprint arXiv:1908.06803},
  year   = {2019}
}

Comments

12 pages

R2 v1 2026-06-23T10:51:01.365Z