All projects

Location-Based Android App

An indoor positioning Android app that locates the user from Wi-Fi RSSI fingerprints with k-nearest neighbors. Built with Room, Retrofit and Material 3.

Problem

GPS doesn’t work indoors. If you care about which room someone is in, you need positioning that runs off signals that are already in the air.

Approach

My app reads Wi-Fi signal strength (RSSI) from nearby access points, turns the readings into a fingerprint vector, and classifies it with k-nearest neighbors against a stored map of labeled fingerprints. Room stores the fingerprints on the device and Retrofit syncs training data with a backend. The UI is Material 3, kept calm and legible because you use it while moving through a space.

Result

It gives live room-level positioning without GPS. Classical ML on ordinary Wi-Fi signals turned out to be enough for a problem that hardware alone struggles with.

Get in touch

Have a research idea, a role, or a question about one of these projects?

There's also a contact form.