Giters

hwixley / Fall-Detection-App

Commercial iOS fall detection app. Connects to a Polar H10 device for triaxial acceleromter and ECG signals. These signals are passed to a trained ResNet152 model using Tensorflow background processes for live inference.

Home Page:https://arxiv.org/abs/2207.00008

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

fall-detectionmobile-machine-learningaccelerometerecgresnetresnet152swiftuitensorflow-litepolar-h10

Honours Project - Commercial Fall Detection System

Live fall detection inference with ResNet152 on a variety of ADLs. This app allows for create account functionality using Firebase, emergency local notifications (APNs), emergency text message notifications (Twilio), stats monitoring, and live sensor output visualizations.

This app connects to a PolarH10 chest strap via Bluetooth which is used to record a user's ECG and Accelerometer data for fall detection.

Home Page - Connected Home Page - Disconnected
IMG_3663 IMG_3674
Stats Page Menu
stats menu
Account Page Settings Page
account settings
Login Register
login register

About

Commercial iOS fall detection app. Connects to a Polar H10 device for triaxial acceleromter and ECG signals. These signals are passed to a trained ResNet152 model using Tensorflow background processes for live inference.

https://arxiv.org/abs/2207.00008

fall-detectionmobile-machine-learningaccelerometerecgresnetresnet152swiftuitensorflow-litepolar-h10

Languages

Language:Swift 99.6%Language:Ruby 0.4%