Node Cardinality Estimation in the Internet of Things Using Privileged Feature Distillation

TL;DR

This paper introduces a novel neural network-based method using privileged feature distillation for accurate node cardinality estimation in IoT and RFID networks, outperforming existing protocols in accuracy without additional time overhead.

Contribution

It presents a new PFD-based neural network approach for node cardinality estimation applicable to both homogeneous and heterogeneous wireless networks, with improved accuracy.

Findings

Achieves significantly lower mean squared errors in estimates.

Works efficiently with the same time slots as existing protocols.

Effective for both homogeneous and heterogeneous networks.

Abstract

The Internet of Things (IoT) is emerging as a critical technology to connect resource-constrained devices such as sensors and actuators as well as appliances to the Internet. In this paper, we propose a novel methodology for node cardinality estimation in wireless networks such as the IoT and Radio-Frequency IDentification (RFID) systems, which uses the privileged feature distillation (PFD) technique and works using a neural network with a teacher-student model. The teacher is trained using both privileged and regular features, and the student is trained with predictions from the teacher and regular features. We propose node cardinality estimation algorithms based on the PFD technique for homogeneous as well as heterogeneous wireless networks. We show via extensive simulations that the proposed PFD based algorithms for homogeneous as well as heterogeneous networks achieve much lower mean squared errors in the computed node cardinality estimates than state-of-the-art protocols proposed in prior work, while taking the same number of time slots for executing the node cardinality estimation process as the latter protocols.