Indoor Localization Under Limited Measurements: A Cross-Environment Joint Semi-Supervised and Transfer Learning Approach
This addresses data scarcity in indoor localization for applications like navigation and tracking, though it is incremental as it builds on existing semi-supervised and transfer learning techniques.
The paper tackles the problem of insufficient labeled data for indoor localization by proposing a cross-environment approach that combines semi-supervised and transfer learning to transfer models from data-rich to data-limited environments, achieving up to 43% higher accuracy than conventional methods and matching performance with only 40% of the data compared to 75%.
The development of highly accurate deep learning methods for indoor localization is often hindered by the unavailability of sufficient data measurements in the desired environment to perform model training. To overcome the challenge of collecting costly measurements, this paper proposes a cross-environment approach that compensates for insufficient labelled measurements via a joint semi-supervised and transfer learning technique to transfer, in an appropriate manner, the model obtained from a rich-data environment to the desired environment for which data is limited. This is achieved via a sequence of operations that exploit the similarity across environments to enhance unlabelled data model training of the desired environment. Numerical experiments demonstrate that the proposed cross-environment approach outperforms the conventional method, convolutional neural network (CNN), with a significant increase in localization accuracy, up to 43%. Moreover, with only 40% data measurements, the proposed cross-environment approach compensates for data inadequacy and replicates the localization accuracy of the conventional method, CNN, which uses 75% data measurements.