Owlet has patented a system using artificial neural networks to predict heart rates from photoplethysmogram (PPG) data. The technology involves training the network to decode PPG frequency representations into heart rate predictions, providing accurate and efficient monitoring capabilities. GlobalData’s report on Owlet gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Owlet, Treatment progress monitoring was a key innovation area identified from patents. Owlet's grant share as of January 2024 was 55%. Grant share is based on the ratio of number of grants to total number of patents.
Predicting heart rate from photoplethysmogram (ppg) signal using neural network
A recently granted patent (Publication Number: US11826129B2) discloses a system for predicting heart rate from photoplethysmogram (PPG) data using an artificial neural network model. The system includes a series of convolutional layers to identify the PPG signal, a fast Fourier transform (FFT) layer to convert the signal to frequency representations, and a dense layer to decode the frequency representations into heart rate predictions. The system preprocesses the PPG data by accentuating high-frequency components, removing outliers, and normalizing the waveform. Additionally, the neural network model is trained using categorical cross entropy and an Adam optimizer to update weights.
Furthermore, the system can identify and process red and infrared light signals in the PPG data, generate heart rate distributions, and compare current predictions with previous ones to ensure accuracy. The system also includes instructions for discarding inaccurate predictions based on evaluation of previous predictions. A computer-implemented method and a non-transitory machine-readable storage medium are also disclosed, detailing the steps for obtaining and storing heart rate predictions, preprocessing PPG data, comparing predictions, and training the neural network model. The method also involves sending predictions over a network and deploying the model in a production environment for real-time heart rate prediction. The storage medium includes instructions for calculating Fourier transforms of prior predictions and updating weights using categorical cross entropy and an Adam optimizer during training.
To know more about GlobalData’s detailed insights on Owlet, buy the report here.
Premium Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
