Resources of our survey paper "Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System Strategies"

MINERVA - Minimal Inference Engine for Robust, Verifiable, and Authenticated ML. Encrypted, integrity-verified neural network inference for MCUs down to ATmega328P.

[ICLR2022] Efficient Split-Mix federated learning for in-situ model customization during both training and testing time

Benchmarking machine learning inferencing on embedded hardware.

Source code of “Agile Reinforcement Learning for Real-Time Task Scheduling in Edge Computing” (CAIAC 2025)

Epsilon is a library with functions for machine learning and statistics written in plain C. It is intended to run on microcontrollers.

This project focuses on the implementation of optimized Linear and DNN regression models for inter-vehicle distance prediction in a Cooperative Adaptive Cruise Control (CACC) application. It leverages Tensorflow Lite to create optimized models through quantization and pruning for realtime inferencing on Raspberry Pi and On-board Unit (OBU) of Co…

Implementación de un clasificador de vocales basado en SVMs y features MFCC.

Real-time wildfire detection on microcontrollers with TinyML + Edge Impulse + Wokwi

A new communication paradigm proposal for restricted bandwidth and fragile channel conditions in NTN.

Experimental pipeline for evaluating motion-related decisions in TinyML-based inertial systems under embedded constraints. The project focuses on understanding how IMU-only models behave, fail, and degrade when deployed on resource-limited hardware, using controlled datasets and reproducible engineering workflows.

Ultra-low-latency Ternary Neural Network inference engine for HFT alpha generation, optimized for an ultra-budget 1,120-LUT Renesas FPGA. Features a fully unrolled combinatorial popcount tree achieving 2-cycle deterministic execution without hardware multipliers, paired with an ESP32-S3 hardware-software co-design.

A Smart Mask Enforcement System using Multitenant Cascading Architecture in TinyML

Tiny CNN cat/dog classifier for RISC-V edge AI, with PyTorch training, quantized firmware export, and Renode simulation benchmarks.

Ingenuity is an optimized inference engine and benchmarking tool for TinyML models on embedded IoT devices.

Edge-optimized wildlife detection for crop protection

IoT-based smart medication adherence system using TinyML, BLE, wearable sensing, and React dashboard monitoring.

Practical work developed for the subject internet of things/embedded systems. My Replenisher is a complete end-to-end application, ranging from TinyMl with arduino nano 33 ble, communication with ESP32 to a mobile application that embodies the entire final scope.

Embedded Software: Running machine learning models on Raspberry Pi

Tiny implementation of kernel passive-aggressive regression on a budget in C.