Built a low-cost bionic arm with 93% real-time accuracy and published it at IEEE
Raeyaan built a complete system from scratch: a low-cost bionic robotic arm that reads EMG muscle signals from the forearm, classifies gestures with AI and drives servos in real time. MyoWare sensors feed an ESP32 that transmits over MQTT to a Raspberry Pi 4 running inference. He compared KNN, Random Forest, MLP and SVM across three feature pipelines, and Random Forest on raw EMG envelopes reached 93% real-time accuracy.
AI & Robotics
Published and presented at IEEE WcCST-2026
IEEE WcCST-2026, 2026
Raeyaan Muppaneni, YRI Fellow
An 11th grader at Irvington High School interested in AI and robotics, with Python and Java experience but no prior research or publication experience.
Built a working bionic arm and published at an IEEE conference with 93% real-time ML accuracy on edge hardware.
Published and presented at IEEE WcCST-2026, Chandigarh University, March 26 to 27, 2026
DOI 10.1109/WcCST67302.2026.11496321, co-sponsored by the IEEE Computational Intelligence Society
93% real-time classification accuracy running on a $35 Raspberry Pi
Built the full hardware stack: MyoWare EMG sensors, ESP32 and Raspberry Pi 4
Arm recognizes four gestures with proportional servo movement
Real-Time Control of a Low-Cost Robotic Arm Using EMG Signal Classification by AI-Based Machine Learning on Raspberry PiSuriya Dev Saravanakumar, Accepted at IEEE EMBC 2026 in Toronto