List view
• Final undergraduate dissertation report. • Complete set of figures, tables, and appendices.
Due by April 19, 2026•0/3 issues closed• Comparison results between ML model and conventional indoor positioning methods. • Documented evaluation figures and comparison tables for the dissertations result section.
Due by April 5, 2026•0/3 issues closed• Trained ML model(s). • Documented training logs and performance trends. • Completed the outline of the final report including the title page, general structure, introduction and background.
Due by March 29, 2026•0/4 issues closed• Fully labelled training dataset. • Documented ML model design and training strategy.
Due by March 15, 2026•0/3 issues closed• Dataset of conventional indoor positioning estimations linked to ground-truth positions. • Documented performance comparison between RSSI, TOA, and AOA methods.
Due by March 8, 2026•0/3 issues closed• Synthetic dataset containing ground-truth positions and network/environment parameters. • Documented decision making for chosen parameters and constraints in the data generation stage.
Due by February 22, 2026•0/5 issues closed• Finished initial project plan. • Documented background and literature which summarises existing indoor positioning methods (RSSI, TOA, AOA), prior machine learning–based localisation approaches, and the key challenges introduced by noise, and LOS/NLOS conditions. This document will provide the theoretical and contextual foundation for the dissertation.
Due by February 8, 2026•2/5 issues closed