US 2020/0348388 A1 · SYSTEMS AND METHODS TO DETERMINE ROOM OCCUPANCY

Abstract

Systems and methods determine occupancy of a mobile device in a room based on one or more wireless signals measured by the mobile device. The mobile device receives and processes one or more wireless signals detectable in the room to generate a feature vector that is inputted to a classifier. The wireless signals may originate either in the room or out of the room. The feature vector contains wireless-signal characteristics measured by the mobile device (e.g., time-averaged power, Fourier coefficients) that are essentially unique to a room. The classifier, which may be an artificial neural network, predicts the occupancy of the mobile device in the room from the feature vector. Alternatively, the location of the mobile device in the room may be verified, wherein the feature vector may form a training example to train the classifier.

Claims53

Dependent claims

A system that determines occupancy of a mobile device in a room, comprising:

a processor;
a memory communicatively coupled with the processor;
a classifier implemented as machine-readable instructions stored in the memory and configured to control the processor to calculate an occupancy probability from one or more wireless-signal characteristics measured by a mobile device from a wireless signal;
and
machine-readable instructions stored in the memory and configured to control the processor to:
receive the wireless-signal characteristics from the mobile device, and
predict the occupancy of the mobile device in the room by using the classifier to calculate the occupancy probability from the received wireless-signal characteristics.

4 more elements

Dependencies are inferred from the claim text.

Systems and methods to determine room occupancy

Life of this patent

Systems and methods to determine room occupancy

Life of this patent

Abstract

Claims53