# US 12,181,598 B2 · Stable and accurate indoor localization based on predictive hyperbolic location fingerprinting

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,181,598 B2
- Document ID: US12181598B2
- Status: Granted
- Kind: B2
- Application number: 17/770,827
- Filed: 2020-10-21
- Published: 2023-01-05
- Granted: 2024-12-31
- Earliest claimed: 2019-10-21
- Assignees: Innerspace Technology Inc.
- Applicants: Innerspace Technology Inc.
- Inventors: Rafat Haque; Matthew Macgillivray; Sean Nyman
- Web page: https://patentgrep.com/patent/US12181598B2

## CPC

- G01S 5/0252: {Radio frequency fingerprinting}
- G01S 5/02525: {Gathering the radio frequency fingerprints}
- G01S 5/12: by co-ordinating position lines of different shape, e.g. hyperbolic, circular, elliptical or radial
- H04W 4/38: for collecting sensor information
- H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports}
- H04W 64/00: Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A computer-implemented method for precision hyperbolic location fingerprinting, the method comprising, at a computing system, the steps of: (a) receiving measured RSSI values associated with a plurality of fixedly-positioned sensor devices, wherein the plurality of fixedly-positioned sensor devices are stationary in known locations in a 2D environment and caused to transit radio signals to each other and measure characteristics of the received radio signals; (b) generating a raw RSSI fingerprint for each sensor device based on the measured RSSI values; (c) generating a log-ratio RSSI fingerprint between a pair of sensor devices; (d) normalizing the raw RSSI fingerprint and normalizing the log-ratio RSSI fingerprint; (e) combining the raw RSSI fingerprint and the log-ratio RSSI fingerprint to form a fusion RSSI fingerprint; and (f) repeating steps (a) to (e) at predetermined intervals to enhance prediction accuracy of regional fingerprints within the environment.

## Claims

### Claim 1

A computer-implemented method for precision hyperbolic location fingerprinting, the method comprising, at a computing system, the steps of:
(a) receiving measured RSSI values associated with a plurality of fixedly-positioned sensor devices, wherein the plurality of fixedly-positioned sensor devices are stationary in known locations in a 2D environment and caused to transit radio signals to each other and measure characteristics of the received radio signals;
(b) generating a raw RSSI fingerprint for each sensor device based on the measured RSSI values;
(c) generating a log-ratio RSSI fingerprint between a pair of sensor devices;
(d) normalizing the raw RSSI fingerprint and normalizing the log-ratio RSSI fingerprint;
(e) combining the normalized raw RSSI fingerprint and the normalized log-ratio RSSI fingerprint to form a fusion RSSI fingerprint; and
(f) repeating steps (a) to (e) at predetermined intervals to enhance prediction accuracy of regional fingerprints within the environment; and
wherein the computing system generates at least one Friis equation for each of the received radio signals, wherein the at least one Friis equation is defined as:
L=−10n log(d)+A
where A is a RSSI value at a 1-metre distance, n is a path-loss exponent, d is a distance in metres, and L is a distance between a transmitting sensor device and a receiving sensor device; to generate a raw RSSI fingerprint for each sensor device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the fusion RSSI fingerprint comprises a level of accuracy based on a number (N) of sensor devices within the environment.

### Claim 3 (depends on 1)

The method of claim 1, wherein the known locations in the environment comprise fixed geo-coordinates.

### Claim 4 (depends on 1)

The method of claim 1, wherein the known locations are fixed locations in a building.

### Claim 5 (depends on 1)

The method of claim 1, wherein the locations of the plurality of fixedly-positioned sensor devices remain unchanged with time.

### Claim 6 (depends on 5)

The method of claim 5, wherein the fusion RSSI fingerprint is generated using a single-dimensional vector to represent a location.

### Claim 7 (depends on 6)

The method of claim 6, wherein dimensions in the fusion RSSI fingerprint is represented by:
Dimensions=N+C(N,2)=N+N!/(2!(N−2)!)
where N is the number of sensor devices deployed within the environment and ! represents a factorial of a whole number.

### Claim 8 (depends on 7)

The method of claim 7, wherein the sensor devices are deployed at different altitudes, such that each sensor device is associated with geo-coordinates and altitude parameters.

### Claim 9 (depends on 8)

The method of claim 8, wherein the altitude parameters transform the 2D fusion fingerprint map into a 3D grid.

### Claim 10 (depends on 9)

The method of claim 9, wherein the sensor devices measure the RSSI values of their clients and forward these measurements to the computing system.

### Claim 11 (depends on 10)

The method of claim 10, wherein the computing system predicts locations values within unknown cells using estimation methods by considering measured values only.

### Claim 12 (depends on 10)

The method of claim 10, wherein the estimation methods comprise a model using classification based on at least one of a Support Vector Machine (SVM) and a machine learning (ML) algorithm for fingerprint-based indoor localization, based on the signal strength received from the sensor devices.

### Claim 13 (depends on 12)

The method of claim 12, wherein the predictions are refreshed periodically at predetermined intervals.

### Claim 14 (depends on 1)

The method of claim 1, wherein the locations are represented as cells.

### Claim 15

A method for indoor location comprising the steps of:
(a) fixedly-positioning a first sensor device in a first known location in an environment and fixedly-positioning a second sensor device in a second known location in the environment;
(b) causing the first sensor device to transmit a first radio signal to the second sensor device, and causing the second sensor device to transmit a second radio signal to the first sensor device;
(c) at the first sensor device, measuring a received signal strength indicator (RSSI) value of the second radio signal, and at the second sensor device, measuring a received RSSI value of the first radio signal;
(d) generating at least one Friis equation for each of the first radio signal and the second radio signal;
(e) generating a fusion RSSI fingerprint based on a raw RSSI fingerprint and a log-ratio RSSI fingerprint, the fusion RSSI fingerprint comprising a level of accuracy based on a number (N) of sensor devices within the environment; and
(f) repeating steps (a) to (e) at predetermined intervals to enhance prediction accuracy of regional fingerprints within the environment; and
wherein the first known location and the second known location comprise permanent geo-coordinates.

### Claim 16 (depends on 15)

The method of claim 15, wherein the first known location and the second known location are fixed locations in a building.

### Claim 17 (depends on 15)

The method of claim 15, wherein the raw RSSI fingerprint is normalized.

### Claim 18 (depends on 15)

The method of claim 15, wherein the log-ratio RSSI fingerprint is normalized.

### Claim 19 (depends on 15)

The method of claim 15, wherein at least a 2D radio map is generated using the fusion RSSI fingerprint and a 3D radio map is generated using the fusion RSSI fingerprint and altitude parameters associated with the devices.

### Claim 20 (depends on 15)

The method of claim 15, wherein the at least one Friis equation is defined as:
L=−10nlog(d)+A
where A is a RSSI value at a 1-metre distance, n is a path-loss exponent, d is a distance in metres, and L is a distance between a transmitting device and a receiving device.

### Claim 21

A system for predicting cell fingerprints comprising:
a computing system comprising a processor and a memory storing instructions executable by the processor to cause the processor to at least:
receive measured RSSI values associated with a plurality of fixedly-positioned sensor devices, wherein the plurality of fixedly-positioned sensor devices are stationary in known locations in an environment and caused to transit radio signals to each other and measure characteristics of the received radio signals;
generate at least one Friis equation for each of the received radio signals, to generate a raw RSSI fingerprint for each sensor device;
generate a log-ratio RSSI fingerprint between a pair of sensor devices;
normalize the raw RSSI fingerprint and normalize the log-ratio RSSI fingerprint;
combine the normalized raw RSSI fingerprint and the normalized log-ratio RSSI fingerprint to form a fusion RSSI fingerprint comprising a level of accuracy based on a number (N) of sensor devices within the environment; and
receive updated measured RSSI values at predetermined intervals to enhance prediction accuracy of regional fingerprints within the environment;
wherein the plurality of fixedly-positioned sensor devices comprise fixed geo-coordinates.

### Claim 22 (depends on 21)

The system of claim 21, wherein the at least one Friis equation is defined as:
L=−10n log(d)+A
where A is a RSSI value at a 1-metre distance, n is a path-loss exponent, d is a distance in metres, and L is a distance between a transmitting device and a receiving device.

### Claim 23 (depends on 21)

The system of claim 21, wherein the known locations in the environment are fixed locations in a building.

### Claim 24 (depends on 21)

The system of claim 21, wherein the fusion RSSI fingerprint is generated using a single-dimensional vector to represent a location.

### Claim 25 (depends on 24)

The system of claim 24, wherein dimensions in the RSSI fusion fingerprint are represented by:
Dimensions=N+C(N,2)=N+N!/(2!(N−2)!)
where N is the number of sensor devices deployed within the environment and ! represents a factorial of a whole number.

### Claim 26 (depends on 25)

The system of claim 25, wherein the sensor devices are deployed at different altitudes, such that each sensor device is associated with geo-coordinates and altitude parameters.

### Claim 27 (depends on 26)

The system of claim 26, wherein the sensor devices measure the RSSI values of their client devices and forward these measurements to the computing system.

### Claim 28 (depends on 27)

The system of claim 27, wherein the locations are represented as cells, and the computing system predicts locations values within the remaining unknown cells using estimations methods by considering measured values only.

### Claim 29 (depends on 28)

The system of claim 28, wherein the estimation methods comprise a model using classification based on at least one of a Support Vector Machine (SVM) and a machine learning (ML) algorithm for fingerprint-based indoor localization, based on the signal strength received from the sensor devices.

### Claim 30 (depends on 29)

The system of claim 29, wherein the predictions are refreshed periodically at predetermined intervals.