
Arcle
IoT Healthcare and Fall Detection
Overview
The Problem
In elderly care facilities, the time between a fall and rescue is critical. Staff cannot continuously monitor every resident, and elderly people often can't call for help, or don't remember to. Existing solutions were either invasive (cameras with continuous recording) or unreliable (emergency buttons that get forgotten or can't be reached after a fall).
Arcle was an IoT healthcare startup project, with the goal of building a system that automatically detected falls without requiring any action from the elderly person, respected privacy, and worked even during internet outages.
The Solution
I built the prototype's software on hardware we already had. The wristbands use an ESP32 with an MPU-6050 3-axis accelerometer and gyroscope, and communicate over MQTT on the local network. The detection algorithm analyzes acceleration and rotation patterns in short time windows, to tell a fall from a normal abrupt movement.
The architecture is edge computing by choice: a Raspberry Pi 4 acts as the central hub and processes data locally, without depending on the internet. ESP32 modules handle environmental sensors such as temperature, humidity and air quality. If the connection drops, the local system keeps alerting staff over the LAN. A Flutter app on the staff's smartphones receives the notifications.
The Result
The prototype was built and tested with real devices. The project stayed at that level: the startup never launched.
Key Features
- Wristbands with ESP32, MPU-6050 3-axis accelerometer and gyroscope
- MQTT communication on the local network
- Edge computing with Raspberry Pi 4: local processing, works offline
- Flutter app for staff notifications