# US 12,113,829 B2 · Occupancy detection and people counting using passive wireless interfaces

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

- Number: US 12,113,829 B2
- Document ID: US12113829B2
- Status: Granted
- Kind: B2
- Application number: 17/071,912
- Filed: 2020-10-15
- Published: 2021-04-15
- Granted: 2024-10-08
- Earliest claimed: 2019-10-15
- Assignees: Syracuse University
- Applicants: Yuexin Jiang; Biao Chen
- Inventors: Yuexin Jiang; Biao Chen
- Web page: https://patentgrep.com/patent/US12113829B2

## CPC

- H04L 63/162: {at the data link layer}
- H04L 9/0643: {Hash functions, e.g. MD5, SHA, HMAC or f9 MAC}
- H04L 63/1433: {Vulnerability analysis}
- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- H04L 63/0407: {wherein the identity of one or more communicating identities is hidden (cryptographic mechanisms or cryptographic arrangements for anonymous credentials or for identity based cryptographic systems H04L9/00)}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method of detecting and quantifying human objects in a given environment by passively observing wireless signals in an interesting environment. Information pertaining to observed wireless signals, such as wireless physical layer data and metadata, encrypted or unencrypted data and metadata in the wireless media-access control layer, and channel state information are extracted from the observed wireless signals and used to detect and quantify human objects in a location. The signals that are observed can originate from a wireless object used by a target of interest, such as cellular phone or workstations, or from infrastructure devices, such as wireless access points, IoT devices, or other transceivers. The signals can also originate from other recognizable signal sources, such as electromagnetic interference introduced by equipment such as elevator motors or microwave ovens.

## Claims

### Claim 1

A system for determining occupancy, comprising:
a hardware receiver programmed to observe a signal emitting from at least one device positioned in an environment, wherein the receiver is programmed to extract a set of metadata about the signal that includes media access control layer information, to generate an artifact based on the set of metadata including media access control layer information, and to transmit the artifact including media access control layer information; and
a hardware controller in communication with and programmed to receive the artifact from the receiver and to process the artifact with a machine learning engine to determine any occupancy in the environment based on the artifact including media access control layer information.

### Claim 2 (depends on 1)

The system of claim 1, wherein controller is further programmed to aggregate the artifact with at least a second artifact received from a second receiver and to determine the occupancy in the environment based on the aggregated artifacts.

### Claim 3 (depends on 2)

The system of claim 2, wherein the machine learning engine comprises a first stage configured to process the aggregated artifacts to identify a series of events related to the occupancy within the environment.

### Claim 4 (depends on 3)

The system of claim 3, wherein the machine learning engine comprises a second stage configured to process the series of events identified by the first stage of the machine learning engine to determine the occupancy within the environment.

### Claim 5 (depends on 4)

The system of claim 4, wherein the first stage of the machine learning engine has been trained with a training set of metadata to determine when the extracted set of metadata indicates an occurrence of one of the series of events related to the occupancy within the environment.

### Claim 6 (depends on 5)

The system of claim 5, wherein the second stage of the machine learning engine has been trained with a training series of events to determine how the series of events identified by the first stage of the machine learning engine indicates the occupancy within the environment.

### Claim 7

A method of determining occupancy, comprising the steps of:
observing with a hardware receiver a signal emitting from at least one device positioned in an environment, wherein the receiver is programmed to extract a set of metadata from the signal that includes media access control layer information, to generate an artifact based on the set of metadata including media access control layer information, and to transmit the artifact including media access control layer information; and
receiving the artifact including media access control layer information from the receiver with a hardware controller that is in communication with the receiver; and
processing the artifact with a machine learning engine of the controller to determine any occupancy in the environment based on the artifact including media access control layer information.

### Claim 8 (depends on 7)

The method of claim 7, further comprising the step of aggregating the artifact with at least a second artifact received from the first or a second receiver and processing the aggregated artifacts to determine the occupancy in the environment based on the aggregated artifacts.

### Claim 9 (depends on 8)

The method of claim 8, wherein the step of processing the artifact with a machine learning engine comprises using a first stage of the machine learning engine to process the aggregated set of artifacts to identify a series of events related to the occupancy within the environment.

### Claim 10 (depends on 9)

The method of claim 9, wherein the step of processing the artifact with a machine learning engine comprises using a second stage to process the series of events identified by the first state of the machine learning image to determine the occupancy within the environment.

### Claim 11 (depends on 10)

The method of claim 10, further comprising the step of training the first stage of the machine learning engine with a training set of metadata to determine when the set of metadata extracted from the signal indicates an occurrence of one of the series of events related to the occupancy within the environment.

### Claim 12 (depends on 11)

The method of claim 11, further comprising the step of training the second stage of the machine learning engine with a training series of events to determine how the series of events identified by the first stage of the machine learning engine indicates the occupancy within the environment.