Minimum Description Feature Selection for Complexity Reduction in Machine Learning-based Wireless Positioning

TL;DR

This paper introduces a novel neural network for wireless positioning that uses minimal features to reduce computational complexity while maintaining high accuracy, especially in low SNR conditions.

Contribution

The work proposes a new feature selection strategy based on maximum power measurements and temporal locations, enhancing deep learning-based wireless positioning efficiency.

Findings

P-NN outperforms baseline models in performance-complexity tradeoff.

Significant improvements in low SNR scenarios.

Effective reduction in feature space without sacrificing accuracy.

Abstract

Recently, deep learning approaches have provided solutions to difficult problems in wireless positioning (WP). Although these WP algorithms have attained excellent and consistent performance against complex channel environments, the computational complexity coming from processing high-dimensional features can be prohibitive for mobile applications. In this work, we design a novel positioning neural network (P-NN) that utilizes the minimum description features to substantially reduce the complexity of deep learning-based WP. P-NN's feature selection strategy is based on maximum power measurements and their temporal locations to convey information needed to conduct WP. We improve P-NN's learning ability by intelligently processing two different types of inputs: sparse image and measurement matrices. Specifically, we implement a self-attention layer to reinforce the training ability of our network. We also develop a technique to adapt feature space size, optimizing over the expected information gain and the classification capability quantified with information-theoretic measures on signal bin selection. Numerical results show that P-NN achieves a significant advantage in performance-complexity tradeoff over deep learning baselines that leverage the full power delay profile (PDP). In particular, we find that P-NN achieves a large improvement in performance for low SNR, as unnecessary measurements are discarded in our minimum description features.