AI-powered neuroprosthetic system

The brain never stopped
sending the signal.

After limb loss, the motor cortex still issues commands for the missing hand, and the sensory cortex still expects to hear back from it. This project decodes that intention with AI, drives a prosthetic hand, and sends real feedback the other way — closing a loop most prosthetics leave open.

Measured signal: residual-limb sEMG. No cortical recording, no clinical hardware — see what this project does and does not demonstrate.

How it works
System status Online
sEMG acquisitionLive
AI decoderReady
Prosthetic controlReady
Haptic feedbackReady
Adaptive calibrationReady
4-channel forearm sEMG Synthetic signal · simulated
CH1CH2CH3CH4
01 Signature demo

The closed loop

Select an intended gesture and watch it move through the complete control pipeline — sensing, decoding, actuation, and feedback — as one integrated sequence.

Intended gesture
Loop closed
t = 0ms · UI simulation timing, not measured system latency
USER INTENT RESIDUAL-LIMB sEMG AI DECODER RANDOM FOREST PROSTHETIC ACTION SIMULATED ACTUATOR EFFERENT → ← AFFERENT
Efferent · sEMG → AI decoder → actuator Afferent · pressure / slip → haptic feedback
Synthetic sEMG · 4 channel Simulated signal
Signal processing
Raw signal Filter Rectify Window
MAV RMS Waveform Length Zero Crossings Slope Sign Changes
AI intent classification Simulated confidence
Confidence derived deterministically from profile similarity to the five gestures' known activation signatures — a UI illustration, not a live model inference.
Sensor / feedback response Simulated
Pressure0%
Slip0%
No contact
02 Architecture

Five stages, one continuous loop

Each stage is a real, ordered step in the control pipeline. Select one to see what it does and what's actually implemented.

Sense

Surface electrodes on the residual limb pick up electrical activity from forearm muscles still associated with the missing hand's movements.

Implemented as: synthetic sEMG generator

03 Adaptation experiment

Signal drift & recalibration

Electrode shift and muscle fatigue change a signal's statistical properties after calibration. Drag the slider to introduce simulated drift, then recalibrate — using the real accuracy curves measured in research/emg_simulation.py.

Baseline Electrode shift / drift Confidence degrades Recalibration Recovered performance
Signal drift0%
Drift level
0.00
Classification accuracy
96.3%
not recalibrated at this drift level

Values interpolated from measured results: without recalibration, accuracy fell from 96.3% to 77.7% across drift 0–0.5. With a brief recalibration step, accuracy at drift 0.5 recovered to 89.4%.

04 Research

Validating the computational pipeline

These results come from a synthetic sEMG signal generator designed to reproduce relevant signal characteristics such as noise, crosstalk, and drift. They validate the computational signal-processing and classification pipeline. They are not human-subject or clinical results.

What this is, honestly: no real EMG hardware was available for this stage, so these results come from a synthetic sEMG signal generator built to match known real-signal characteristics — not a human subject. It validates that the signal-processing and classification pipeline works; it is a computational proof of concept, not a clinical result.
0%
Baseline test accuracy
0% ±1.2
5-fold cross-validation
0
Gesture classes (Rest · Open · Close · Pinch · Point)

Gesture classification — confusion matrix

Synthetic sEMG · 150 held-out test windows · rows = actual, columns = predicted

Accuracy under simulated signal drift

Electrode shift / fatigue simulation · with and without recalibration
No recalibration With recalibration
Signal
Synthetic sEMG
4 channels, 1000 Hz, 250 ms windows
Processing
Time-domain features
MAV · WL · ZC · SSC · RMS
Model
Random Forest
200 trees · 75/25 split · 5-fold CV
Control
Gesture → action
Classified intent maps to a simulated prosthetic pose
Feedback
Pressure / slip
Simulated sensor response per gesture, not measured hardware
Adaptation
Drift + recalibration
Parameterized electrode-shift experiment, 0.0–0.5
05 Limitations

What this establishes — and what it doesn't

Stated plainly, because scientific honesty matters more than looking finished.

What this project demonstrates

  • Computational sEMG signal-processing pipeline
  • Time-domain feature extraction & gesture classification
  • Prosthetic control simulation from classified intent
  • Closed-loop feedback simulation (pressure / slip)
  • Signal-drift experiment with measured accuracy loss
  • Recalibration concept with measured partial recovery

What it does not yet demonstrate

  • Human-subject validation
  • Real sEMG hardware acquisition
  • Physical prosthetic actuation
  • Clinical efficacy
  • Neural stimulation or cortical recording
Next experiment

Connect the computational pipeline to real sEMG hardware and evaluate gesture decoding under controlled human-subject testing.

06 Reproducibility

Run the pipeline yourself

The research pipeline is self-contained — no external dataset download needed.

Signal generation Feature extraction Model training Validation Robustness testing
Model
Random Forest
Features
MAV · RMS · WL · ZC · SSC
Signal
Synthetic sEMG
Validation
5 gesture classes
cd research # install deps pip install numpy scikit-learn matplotlib # regenerate results/confusion_matrix.png, results/drift_experiment.png, results/summary.txt python3 emg_simulation.py
Code on GitHub