Blood pressure prediction based on the heart rate measurements
A solution to predict patient's blood pressure basing on previously measured and logged heart rate data.
Our developers have made evaluation of parameters of the model for predicting systolic and diastolic blood pressure based on the values of current pulse transit time and heart rate parameters.
Data gathering according to the measurement protocol provided by the customer was step #1.
Part of the data was selected to teach the model by least square method.
For the selected parameters we have calculated confidence intervals and residuals distribution. The resulting model successfully passed testing on a sample data set.
The final model was integrated into the application that is used to estimate the patient's stress level and the state of his cardiovascular system.
Virtual try-on tool for makeup products
The system consists of a face detection and segmentation model and an algorithm that allows recoloring objects without losing their original texture.
Online sign language interpreter
AI algorithm that converts video of a person using sign language into a text transcript
Cardiac coherence training app
Mobile application with a set of exercises to practice breathing techniques.