Maksim Isayenka/VE3EUN.

AI-assisted baby monitor on Raspberry Pi 5 / QNX: contactless heart rate and breathing via rPPG, IMU sleep-position and incline alerts, plus a live dashboard with AI wellness summaries.

Counter-UAS quadcopter with custom RTOS flight controller firmware, DShot motor signaling, and sub-millisecond sensor fusion — 500k+ views and venture interest.

High-frequency RF power monitor using the AD8318 log detector (1 MHz–8 GHz), conditioned for ESP32 ADC sampling and Wi-Fi data logging.

Discrete-component FM receiver using a superheterodyne chain: tuned RF front end, Si5351 LO, LC IF filtering, and MC3361 narrow-band demodulation to audio.

Industrial-style soil and environment node: STM32 Modbus RTU master over RS485 to a multi-parameter probe (TH, NPK, pH, salinity, TDS) with robust parsing and protection.

HF tracking and digital display add-on for a legacy Kenwood TS-520: buffers internal VFO signals, measures with the ESP32, and shows live operating frequency.

Vision models for gate detection and pose estimation coupled with MATLAB flight simulation and closed-loop control for autonomous racing-style quadcopter navigation.

Wrist-worn fall detector that fuses accelerometer and heart-rate data to confirm real falls, then alerts via haptic, audio, and LCD — fully offline, ~2 s latency.

Neighbourhood-matching web app: users set priorities via an AI chatbot or map controls; neighbourhoods are ranked from web-scraped data and shown on a Leaflet heatmap.

Personalized meal platform backed by a YOLOv8 food detector trained on a custom Roboflow dataset for fast, health-profile-aware recipe suggestions.

Accessibility reader that uses a device webcam with OpenCV and PyTesseract to scan printed text and speak it aloud for people with low vision.