Imec Vzw

University of Minnesota

Katholieke Universiteit Leuven, Ku Leuven R&d

Stichting Imec Nederland

Christiaan Van Hoof

Walter De Raedt

Nick Van Helleputte

Mario Konijnenburg

Emmanuel Rios Velazquez

Luke Everson

Elena Smets

Giuseppina Schiavone

Dwaipayan Biswas

A method of generating a model for generating a synthetic electrocardiography (ECG) signal comprises: receiving subject-specific training data for machine learning, said training data comprising a photoplethysmography (PPG) signal acquired from the subject and an ECG signal acquired from the subject, wherein the ECG signal provides a ground truth of the subject for associating the ECG signal with the PPG signal; using associated pairs of a time-series of the PPG signal and a corresponding time-series of the ECG signal as input to a deep neural network, DNN; and determining, through the DNN, a subject-specific model relating the PPG signal of the subject to the ECG signal of the subject for converting the PPG signal to a synthetic ECG signal using the subject-specific model.

Method for generating a model for generating a synthetic ECG and a method and system for analysis of heart activity

Disclosed herein is a system for determining a subject's stress condition. The system includes a stress test unit configured for: receiving features defining the subject and physiological signals sensed from the subject when performing a relaxation and a stressful test task; extracting normalization parameters from the physiological signals; and identifying stress-responsive physiological features. The system also includes a storage unit configured for: storing a plurality of stress models; and storing the subject's features, normalization parameters, and the stress-responsive physiological features. The system also includes a stress detection unit configured for: selecting a stress model from the plurality of stress models based on the subject's features and the stress responsive physiological features; estimating a specific stress condition based on the stress model, stored subject's features, normalization parameters, and physiological signals that apply to the selected stress model; and providing a stress value representative of the subject's stress condition.

System and method for determining a subject's stress condition

Growing community of inventors

Heverlee, Belgium

Christiaan Van Hoof