Project Diya is a wearable AI device that sees obstacles, faces, and currency for its user, while guiding them with voice and haptic cues.
An experimental language model I trained from scratch, running offline on ESP32-S3 with a touchscreen chat interface.
A chest X-ray goes in, a written report comes out, on one Jetson Orin Nano Super. Two models share 8 GB, and nothing leaves the board.
A Bluetooth bearing monitor that relates vibration to shaft speed and shows evidence for inspection using sensors I already own.
A camera-based RC car using a PilotNet-style CNN and LiteRT on Raspberry Pi to predict steering, with gamepad-controlled throttle.
A bike tag that feels the road, classifies the surface with on-device AI, and maps cycle paths that are wearing out before potholes form.
Open RTL, ISA, simulator and compiler, running LFM2.5 and Qwen3 on a repurposed Kintex-7 PCIe card.
A robotic arm that uses Google's Coral Edge TPU USB Accelerator to run object detection and recognition of different recycling materials.
Adding a much cheaper alternative to the Carter and Kaya designs reference using a Lego EV3 set.
An Alexa enabled door lock with face recognition and remote control.
The image extraction is based on a novel algorithm which effectively works with the encoding system of the robot movement.
Robot that drives around autonomously in greenhouse environment and identifies diseases.
Assistant for efficient beekeeping!
Telemetry system of my Ducati Monster based on Arduino, UWP, Azure features and Machine Learning. Enterprise IoT Cloud Solution.
Using the TensorFlow Lite library, we can flash tiny machine learning models on an Arduino to detect humans from a camera.
A TinyML based Medical device powered by Edge Impulse to predict Atrial fibrillation, AV Block 1 and Normal ECG with >90%.
Redesigned approach with Implementation of Decision Tree for better parameter analysis with alert and control provided by 3rd party app.
Help the hearing and speech impaired children learn and communicate normally by means of sign-language.
Jrobot Self Drive (episode 3 of Jrobot series) is a self-driving footpath traveler based on machine learning (Keras and TensorFlow Lite).
Spectrino - Arduino devices that can be implemented on a wide spectrum of touch-free tinyML based housing and society systems.
This project shows how you can bring the Wizarding of Harry Potter to reality with computer vision and machine learning!
An intelligent device for seniors which detects falls and sends emergency alert messages with location information using a cellular network
Combine the power of autonomous flight and computer vision in a UAV that can detect people in search and rescue operations.
They took our jobs, they will take our fun!
