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. For a building where you care about which room a user is in (a classroom, a warehouse aisle, a clinic ward), you need positioning that runs off ambient signals already in the air.
Approach
The app collects Wi-Fi signal strength readings (RSSI) from nearby access points, builds a fingerprint vector, and classifies it against a stored map of labeled fingerprints using k-nearest neighbors. Room persists the local fingerprint dataset; Retrofit talks to a backend for training data sync; Material 3 keeps the UI calm and legible while the user moves through a space.
Result
Live room-level positioning with no GPS dependency, demonstrating that classical ML on top of mundane signals can solve a problem that hardware-only solutions struggle with.
Correspondence
Research, data science work or a question about a project. Email, LinkedIn or the contact form all reach me.
There is also a contact form, and aresume (PDF).