AGWORKF · 05
AHMEDABADIST
VOL. 032024
SCROLL
HOME / WORK / Air-Writing RecognitionWearable ML research · 2024
— CASE 05 / RESEARCH · IIT DELHI

AIR-WRITING
RECOGNITION.

A wearable air-writing system — 62 output classes from a single wrist-mounted IMU — and the discipline to evaluate it honestly.

62Output classes
12,400Labeled samples
1K+Configs swept
75/57User-dep / indep LOSO

— THE WORK

SWEEP
A THOUSAND
MODELS.
REPORT THE
HONEST DELTA.

ESP32 + MPU6050 wristband at 60 Hz over Wi-Fi (chose Wi-Fi over Bluetooth to escape Linux-only library lock-in). 20 participants × 62 classes × 10 repetitions = 12,400 labeled samples. Z-score normalized per channel.

Swept Dense / 1D-CNN / LSTM / BiLSTM / hybrids across 1,000+ configurations. Final: CNN-BiLSTM. Reported user-dependent and LOSO-CV user-independent numbers separately — the 18-point gap is the truth.

TENSORFLOWKERASESP32MPU6050I²CWI-FICNN-BiLSTM
— WANT THE FULL STORY?

LET’S
BUILD.