IP Library › Granted Patent US 12,413,868
Granted Patent B2
US 12,413,868 · App. 18/687,077 · Granted Sep 9, 2025

Pixelated monolithic photoplethysmographic sensor having spiking neural network structure and driving method therefor

Inventor: Dong Woo Jee (Suwon-si, KR)
Assignee: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
H04N25/10H04N25/77
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,413,868
App. No.
18/687,077
Granted
Sep 9, 2025
Kind
B2
Abstract

A pixelated monolithic photoplethysmographic (PPG) sensor with a spiking neural network structure and a driving method thereof are disclosed. The pixelated monolithic photoplethysmographic (PPG) sensor according to an exemplary embodiment of the present disclosure includes a plurality of input neurons which generates spike signals and is disposed in at least one of a row direction and a column direction, a plurality of output neurons which adds the spike signals applied from the plurality of input neurons based on the column direction or the row direction and generates an output spike signal when the added result is equal to or higher than a predetermined reference value, and a synchronizer which converts each of the output spike signals into a digital signal.

Claims (20)

1. A pixelated monolithic photoplethysmographic (PPG) sensor with a spiking neural network structure, comprising:

a plurality of input neurons which generates a spike signal and is disposed in at least one of a row direction and a column direction;

a plurality of output neurons which adds the spike signals applied from the plurality of input neurons based on the column direction or the row direction and generates output spike signals when the added result is equal to or higher than a predetermined reference value; and

a synchronizer which converts each of the output spike signals into a digital signal.

2. The PPG sensor according to claim 1 , wherein each of the plurality of input neurons includes:

a light-to-digital converter which generates the spike signal based on an intensity of received light;

a first transistor which outputs the spike signal to a column input node corresponding to the column direction; and

a second transistor which outputs the spike signal to a row input node corresponding to the row direction.

3. The PPG sensor according to claim 2 , wherein the light-to-digital converter generates the spike signal with a strength which is proportional to the intensity of the received light.

4. The PPG sensor according to claim 2 , wherein the plurality of input neurons is disposed to form an array including n×m pixels, the column input node includes n nodes to which the spike signal generated from m pixels corresponding to each column of the array is applied, and the row input node includes m nodes to which the spike signal generated from n pixels corresponding to each row of the array is applied.

5. The PPG sensor according to claim 4 , wherein the plurality of output neurons includes n output neurons each corresponding to any one of columns which form the array and m output neurons each corresponding to any one of rows which form the array.

6. The PPG sensor according to claim 1 , wherein the synchronizer converts the output spike signal into a one-bit digital signal which is synchronized with a clock signal.

7. The PPG sensor according to claim 1 , wherein relative spatial information of light which is applied to the plurality of input neurons with respect to the PPG sensor is derived based on magnitude information of the digital signal.

8. A driving method of a pixelated monolithic photoplethysmographic (PPG) sensor with a spiking neural network structure, comprising:

generating spike signals based on an intensity of light received by a plurality of input neurons;

adding the spike signals applied from the plurality of input neurons based on a column direction or a row direction;

generating output spike signals by a plurality of output neurons when the added result is equal to or higher than a predetermined reference value; and

converting each of the output spike signals into a digital signal.

9. The driving method of a PPG sensor according to claim 8 , wherein in the generating of spike signals, a light-to-digital converter generates the spike signal with a strength which is proportional to the intensity of the received light and outputs the spike signal to a column input node corresponding to the column direction and a row input node corresponding to the row direction.

10. The driving method of a PPG sensor according to claim 8 , wherein in the converting into a digital signal, the output spike signal is converted into a one-bit digital signal which is synchronized with a clock signal.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 27, 2024
From: JEE, DONG WOO
To: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
Reel/Frame 066576/0065 →
Priority Claims (1)
KR 10-2021-0172377 · Dec 3, 2021 · national
Continuity (1)
Related Publication 20240380991A1 · Nov 14, 2024
References Cited (8)
US 10579925B2 · Kasabov et al. · 2020 [cited by applicant]
US 20160283842A1 · Pescianschi · 2016 [cited by applicant]
US 20200202206A1 · Rummens et al. · 2020 [cited by applicant]
KR 101987399B1 · 2019 [cited by applicant]
KR 1020200133246A · 2020 [cited by applicant]
Geon-Myeong Lee, “Behavior of Spiking Neuron Models and Learning of Spiking Neural Networks”, Communications of the Korean Institute of Information Scientists and Engineers, Feb. 2020, pp. 8-19, vol. 38, No. 2. [cited by applicant]
Mostafa Rahimi Azghadi, et al., “Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications”, IEEE Transactions on Biomedical Circuits and Systems, Dec. 2020, pp. 1138-1159, vol.… [cited by applicant]
International Search Report for PCT/KR2022/015490 dated Jan. 26, 2023 (PCT/ISA/210). [cited by applicant]