Detecting location within a network

Patent metadata

Field	Value
Publication number	US-2019297459-A1
Application number	US-201916435783-A
Country	US
Kind code	A1
Filing date	Jun 10, 2019
Priority date	Sep 16, 2015
Publication date	Sep 26, 2019
Grant date	—

Abstract

Systems and methods for detecting the presence of a body in a network without fiducial elements, using signal absorption, and signal forward and reflected backscatter of RF waves caused by the presence of a biological mass in a communications network.

First claim

1 . A presence detection method comprising:
obtaining, at a machine learning computer server, multiple sets of input training data, each set of input training data based on a statistical analysis of characteristics of wireless signals transmitted through a detection area over a respective time period, each set of the input training data indicating whether a human was detected in the detection area over the respective time period, wherein the input training data comprises machine learning data, and the statistical analysis includes:
obtaining frequencies and power levels of the wireless signals;
computing statistical parameter values based on the frequencies and power levels of the wireless signals;
populating the statistical parameter values into an initial signal characteristic profile; and
generating the machine learning data based on the initial signal characteristic profile; and
by operation of the machine learning computer server, processing the sets of input training data to parameterize nodes of a machine learning system; and detecting presence of a human in the detection area, using the machine learning system comprising the parameterized nodes, based on a newly obtained set of input data.

2 . The method of claim 1 , wherein the statistical parameters comprise a mean and a standard deviation.

3 . The method of claim 1 , wherein the input training data indicates a category of motion, and parameterizing the nodes configures the machine learning system to detect a category of motion based on the newly obtained set of input data.

4 . The method of claim 1 , comprising:
obtaining, at the machine learning computer server, additional sets of input training data, each additional set of input training data indicating whether interference was present in the detection area over the respective time period; and by operation of the machine learning computer server, processing the additional sets of input training data to parameterize nodes of the machine learning system, wherein parameterizing the nodes configures the machine learning system to detect interference based on the newly obtained set of input data.

5 . The method of claim 1 , wherein the machine learning system comprises a neural network.

6 . A machine learning training system comprising:
a data processing apparatus; and memory comprising instructions that are operable when executed by the data processing apparatus to perform operations comprising:
obtaining multiple sets of input training data, each set of input training data based on a statistical analysis of wireless signals transmitted through a detection area over a respective time period, each set of the input training data indicating whether a human was detected in the detection area over the respective time period;
wherein the input training data comprises machine learning data, and the statistical analysis comprises:
obtaining frequencies and power levels of the wireless signals;
computing statistical parameter values based on the frequencies and power levels of the wireless signals;
populating the statistical parameter values into an initial signal characteristic profile;
generating the machine learning data based on the initial signal characteristic profile;
processing the input training data to parameterize nodes of a machine learning system; and
detecting presence of a human in the detection area, using the machine learning system comprising the parameterized nodes, based on a newly obtained set of input data.

7 . The machine learning training system of claim 6 , wherein the statistical parameters comprise a mean and a standard deviation.

8 . The machine learning training system of claim 6 , wherein the input training data indicates a category of motion, and parameterizing the nodes configures the machine learning system to detect a category of motion based on the newly obtained set of input data.

9 . The machine learning training system of claim 6 , wherein the operations comprise:
obtaining additional sets of input training data, each additional set of input training data indicating whether interference was present in the detection area over the respective time period; and processing the additional sets of input training data to parameterize nodes of the machine learning system, wherein parameterizing the nodes configures the machine learning system to detect interference based on the newly obtained set of input data.

10 . The machine learning training system of claim 6 , wherein the machine learning system comprises a neural network.

11 . A motion detection method, comprising:
obtaining, at a machine learning system, multiple sets of input training data, each set of input training data based on a statistical analysis of a series of wireless signals transmitted through a detection area over a respective time period, wherein the input training data comprises machine learning data, and the statistical analysis comprises:
obtaining frequencies and power levels of the wireless signals;
computing statistical parameter values based on the frequencies and power levels of the wireless signals;
populating the statistical parameter values into an initial signal profile; and
generating the machine learning data based on the initial signal profile, and
by operation of the machine learning system, processing the sets of input training data through a plurality of programmed machine learning nodes; and determining whether motion occurred in the detection area during the respective time period.

12 . The method of claim 11 , wherein the statistical parameters comprise a mean and a standard deviation.

13 . The method of claim 11 , wherein determining whether motion occurred in the detection area comprises generating an indication of motion by an object in the detection area, a category of motion that occurred in the detection area, interference present in the detection area, or an absence of motion in the detection area.

14 . The method of claim 11 , wherein the machine learning system comprises a neural network.

15 . A machine learning system comprising:
a data processing apparatus; and memory comprising instructions that are operable when executed by the data processing apparatus to perform operations comprising:
obtaining multiple sets of input training data, each set of input training data based on a statistical analysis of a series of wireless signals transmitted through a detection area over a respective time period,
wherein the input training data comprises machine learning data, and the statistical analysis comprises:
obtaining frequencies and power levels of the wireless signals;
computing statistical parameter values based on the frequencies and power levels of the wireless signals;
populating the statistical parameter values into an initial signal profile; and
generating the machine learning data based on the initial signal profile; and
processing the sets of input training data through a plurality of programmed machine learning nodes; and
determining whether motion occurred in the detected area during the respective time period.

16 . The machine learning system of claim 15 , wherein the statistical parameters comprise a mean and a standard deviation.

17 . The machine learning system of claim 15 , wherein determining whether motion occurred in the detection area comprises generating an indication of motion by an object in the detection area, a category of motion that occurred in the detection area, interference present in the detection area, or an absence of motion in the detection area.

Assignees

• Ivani Llc

Inventors

• Wootton John
• Wootton Matthew
• Nissman Chris
• Preston Victoria
• Clark Jonathan
• Mckinney Justin
• Barnes Claire

Classifications

• H04B17/373

  Predicting channel quality {or other radio frequency [RF]} parameters · CPC title

• H04B17/27

  for locating or positioning the transmitter · CPC title

• G11C11/2297

  Power supply circuits · CPC title

• G11C11/2293

  Timing circuits or methods · CPC title

• G11C11/2273

  Reading or sensing circuits or methods · CPC title