# US 11,109,812 B2 · Electrocardiogram (ECG) signal based authentication apparatus and method

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

- Number: US 11,109,812 B2
- Document ID: US11109812B2
- Status: Granted
- Kind: B2
- Application number: 16/212,946
- Filed: 2018-12-07
- Published: 2019-04-11
- Granted: 2021-09-07
- Earliest claimed: 2016-02-01
- Assignees: Samsung Electronics Co., Ltd.; Korea Advanced Institute of Science and Technology
- Applicants: Samsung Electronics Co., Ltd.; Korea Advanced Institute of Science and Technology
- Inventors: Chisung Bae; Jin Woo Shin; Sung-Soo Ahn; Sang Joon Kim
- Web page: https://patentgrep.com/patent/US11109812B2

## CPC

- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 5/117: Identification of persons (methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00)
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- A61B 5/6898: {Portable consumer electronic devices, e.g. music players, telephones, tablet computers}
- G06V 40/15: {Biometric patterns based on physiological signals, e.g. heartbeat, blood flow}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

An authentication apparatus includes one or more processors configured to temporally implement a neural network, used to extract a feature value from hidden nodes, that is connected to input nodes to which an electrocardiogram (ECG) signal is input so as to share a weight set with the input nodes, and to match the ECG signal and the extracted feature value to a user for registration.

## Claims

### Claim 1

An authentication apparatus comprising:
a calculator configured to calculate a first output value corresponding to an input electrocardiogram (ECG) signal by applying the input ECG signal to a first neural network, and calculate second output values corresponding to reference ECG signals by applying the reference ECG signals to a second neural network,
wherein the first and second neural networks are at least temporally implemented by one or more processors, the first output value is provided as output from the first neural network, and the second output values are provided as outputs from the second neural network;
an extractor configured to extract a number of second output values from the second output values based on the first output value; and
a determiner configured to determine whether to authenticate a user associated with the input ECG signal based on a ratio of a number of the extracted second output values that are associated with a registered user to a total number of the extracted second output values.

### Claim 2 (depends on 1)

The authentication apparatus of claim 1, wherein the first and second neural networks share at least one of a connection relationship of nodes, the number of internal nodes, a size of weight, and a size of a parameter.

### Claim 3 (depends on 1)

The authentication apparatus of claim 1, wherein the reference ECG signals comprises an ECG signal associated with an unidentified user and an ECG signal associated with the registered user, and the calculator is further configured to calculate second output values corresponding to the unidentified user and the registered user.

### Claim 4 (depends on 1)

The authentication apparatus of claim 1, wherein the extractor is further configured to extract the number of second output values in a descending order of similarities with the first output value.

### Claim 5 (depends on 4)

The authentication apparatus of claim 4, wherein the extractor is further configured to repetitively extract second output values from the second output values, a number of the extracted second output values being different for each extraction, and repetitively calculate plural ratios from the repetitively extracting and
the determiner is further configured to determine whether to authenticate the user based on the plural ratios through the repetitive calculation.

### Claim 6 (depends on 1)

The authentication apparatus of claim 1, wherein the determiner is further configured to authenticate the user associated with the input ECG signal to be the registered user in response to the ratio of the number of the extracted second output values associated with the registered user to the total number of the extracted second output values having a highest value.

### Claim 7 (depends on 1)

The authentication apparatus of claim 1, wherein the determiner is further configured to authenticate the user associated with the input ECG signal to be the registered user in response to the ratio of the number of the extracted second output values associated with the registered user to the total number of the extracted second output values being higher than or equal to a threshold.

### Claim 8 (depends on 1)

The authentication apparatus of claim 1, further comprising:
a memory configured to store the reference ECG signals,
wherein, in response to the user being authenticated as the registered user, the determiner is further configured to store the input ECG signal in the memory as a part of the reference ECG signals in association with the registered user.

### Claim 9 (depends on 8)

The authentication apparatus of claim 8, wherein the memory is further configured to store ECG signals corresponding to different points in time as the reference ECG signals.

### Claim 10

A wearable device, comprising:
a sensor configured to acquire an input electrocardiogram (ECG) signal from a body of a user in contact with the wearable device;
a processor configured to:
calculate a first output value corresponding to the input ECG signal by applying the input ECG signal to a first neural network, and calculate second output values corresponding to reference ECG signals by applying the reference ECG signals to a second neural network, wherein the first output value is provided as output from the first neural network and the second output values are provided as outputs from the second neural network;
extract a number of second output values from the second output values based on the first output value; and
authenticate the user based on a ratio of a number of the extracted second output values that are associated with a registered user to a total number of the extracted second output values; and
a display configured to output an authentication result to the user.

### Claim 11 (depends on 10)

The wearable device of claim 10, wherein the processor is further configured to extract the number of second output values from the second output values in a descending order of similarities with the first output value.

### Claim 12 (depends on 10)

The wearable device of claim 10, wherein the processor is further configured to determine the user to be the registered user in response to the ratio of the extracted second output values associated with the registered user being higher than or equal to a threshold.