Projects — Marco Fasanella

Thesis author

A design guide and graphical tool for choosing AI deployment approaches on resource-constrained mobile and embedded devices.

Context: Master's thesis in Computer Science and Engineering at the Polytechnic University of Milan.
Contribution: Defined five design dimensions—resources, availability, accuracy, timeliness, and privacy—and developed a graphical tool to compare local, distributed, and hybrid deployment approaches. Applied the method to an OCR use case for credit-card registration in a banking app.
Outcome: The thesis reports a local OCR benchmark using TensorFlow Lite and concludes that local inference fits the use case's latency and privacy needs. Its dynamically quantized model pipeline measured 28.4 MB total model size and around 0.4 seconds of inference on a Redmi K20 Pro with four threads.

Co-author

A co-authored research and benchmark study of the architecture behind a decentralized-exchange arbitrage searcher on Ethereum.

Context: Research project at the Polytechnic University of Milan, co-authored with Elia Maggioni and Lucas Manini.
Contribution: Co-authored a model for cyclic arbitrage across decentralized exchanges and a two-stage architecture: startup-time market-graph construction followed by block-driven state synchronization and arbitrage-path evaluation.
Outcome: Built a benchmark implementation to examine graph-construction space and runtime costs, including synchronization and arbitrage checks. The report documents the architecture, complexity analysis, and benchmark results.