sEMG Gesture Wearable
Technical documentation for the surface Electromyography wearable system.
System Overview
The sEMG Gesture Wearable is designed to capture muscle activity from the forearm and translate it into digital commands via BLE. I'm also working on an IMU-only variant for gesture input without electrodes.
Hardware Architecture
Analog Front-End
The signal chain starts with the AD8232, which provides high-input impedance and excellent common-mode rejection.
- Electrodes: 316L Stainless Steel
- Filtering: Integrated high-pass and low-pass stages
- Gain: Configurable amplification for microvolt signals
Processing & Wireless
The nRF52840 handles both the ADC sampling and the BLE HID profile.
- Sampling Rate: 1kHz per channel
- Connectivity: BLE 5.0
- Power: LiPo 3.7V with LDO regulation
Firmware Logic
The firmware implements a sliding window buffer for EMG data and is being shaped around on-device gesture classification.
ML Direction
The model work is still in validation. I am collecting cleaner gesture data, comparing electrode placement, and using those results to decide what should run on-device.
- Tooling: Edge Impulse experiments
- Target: Small on-device classifier for gesture input
- Status: Data collection and testing in progress
- Accuracy: Not claimed yet